Skip to main content

2018 | Buch

Information Systems Design and Intelligent Applications

Proceedings of Fourth International Conference INDIA 2017

herausgegeben von: Prof. Dr. Vikrant Bhateja, Dr. Bao Le Nguyen, Dr. Nhu Gia Nguyen, Dr. Suresh Chandra Satapathy, Dr. Dac-Nhuong Le

Verlag: Springer Singapore

Buchreihe : Advances in Intelligent Systems and Computing

insite
SUCHEN

Über dieses Buch

The book is a collection of high-quality peer-reviewed research papers presented at International Conference on Information System Design and Intelligent Applications (INDIA 2017) held at Duy Tan University, Da Nang, Vietnam during 15-17 June 2017. The book covers a wide range of topics of computer science and information technology discipline ranging from image processing, database application, data mining, grid and cloud computing, bioinformatics and many others. The various intelligent tools like swarm intelligence, artificial intelligence, evolutionary algorithms, bio-inspired algorithms have been well applied in different domains for solving various challenging problems.

Inhaltsverzeichnis

Frontmatter
Pharmacophore Modeling and Docking Studies of SNCA Receptor with Some Active Phytocompounds from Selected Ayurvedic Medicinal Plants Known for their CNS Activity

Neurodegeneration is an alarming problem all over the globe. The significant role of SNCA receptor has been well established in several neurodegenerative disorders including various types of progressive dementia—most commonly in Parkinson’s disorder (PD) and Lewy body dementia. Phytocompounds selected from ayurvedic medicinal plants are thoroughly screened against the SNCA receptor (in silico). The gene receptor responsible for Parkinson’s disorder (PD), SNCA, was taken for this work. Mutated mammalian SNCA implicated as one of the factors responsible for PD was taken from NCBI; templates as retrieved from BLAST were downloaded from PDB. The 3D structure of SNCA was modeled; the 3D structures of phytocompounds (unknown ligands) were taken from various online databases; phytocompounds were virtually screened against the SNCA receptor, and the best ligand was selected.

Preenon Bagchi, M. Anuradha, Ajit Kar
Sociopsycho-Economic Knowledge-Based System in E-Commerce Using Soft Set Theory Technique

Fast creating of the present territory, a few of the wonders are broadly seen to flourishing the significant fulfillment to the behavior of the information to the punter. The prerequisite from client satisfaction is made as a design to achieve sociopsycho-economic knowledge. The substance structure approach gathers the informational collection to accomplish the objective of consumer necessity. The system contains the client fulfillment to online market conduct to watch the customer request on every single tick of client, based on every single arrangement of snap and hunt information, thereby constructing the model. The representation supports the sociopsycho behavior to watch the request limits of the customers with few ways to achieve the state of a client. Earlier frameworks do not thoroughly investigate the human sociopsycho based Web-based promoting. The designed structure provides investigating the human sociopsycho completely with the assistance of soft set theoretic hypothesis technique. The strategy assesses every single substance of the client request and investigates it.

P. Vijayaragavan, R. Ponnusamy, M. Arramuthan
RSSI-Based ZIGBEE Independent Monitoring System in Prison for Prisoners

Law-breakers around the world are put behind the bars, whereby various chances of escaping from the prison are available. Several secure technologies are available in and around the world, but none of them helps to reduce the chances of escaping from the prison. So a system was created to protect the prisoners from escaping the prison by using the method of received signal strength indicator (RSSI) which monitors the distance between a pair of nodes in a network. Another method called Electron-ICS enables the development of microsensor which manages the wireless communication network.

P. Vijayaragavan, R. Ponnusamy, M. Arramuthan, T. Vijila
Automatic Target Acquisition and Discreet Close Surveillance Using Quad Copter with Raspberry Pi Support

The paper is about making a micro modular drone (MMD) which can be used by armed forces to automatically acquire targets in a wide environment and can maintain discreet close surveillance. A simple quad copter is used to maintain contact with the hostiles. To acquire targets, we use a PI sensor camera which is programmed by Raspberry Pi to automatically acquire targets. For real-time tracking and surveillance, we use a cloud to store coordinates which are continuously sent by the quad copter. A simple application (RM7) is used to acquire data from cloud which can be used by the quick reaction force (QRF) to effectively neutralize threats without taking too much risks and damages. The application is made in a way so that it is compatible with any handheld device and can be used anywhere. Thus, we make a drone which is modular, does not require air eld and much knowledge to operate, and can be used in border with fewer resources.

P. Vijayaragavan, R. Ponnusamy, M. Arramuthan
Mining Frequent Fuzzy Itemsets Using Node-List

Data mining plays an important in knowledge discovery in databases; many types of knowledge and technology have been proposed for data mining. Among them, association rule mining is the problem important not only in data mining task but also in many practical applications in different areas of life. These previous studies mostly focused on showing the transaction data with binary values. However, in real-world applications, transactions also contain uncertain and imprecise data. To solve the above-mentioned problem, fuzzy association rule mining algorithms are developed to handle quantitative data using fuzzy set. In this paper, we present proposed algorithm NFFP, an improved fuzzy version of PPV algorithm for discovering frequent fuzzy itemsets using Node-List structure.

Trinh T. T. Tran, Giang L. Nguyen, Chau N. Truong, Thuan T. Nguyen
A New Approach for Query Processing and Optimization in Fuzzy Object-Oriented Database

For enhancing the efficiency of processing users’ queries, all database management systems (DBMSs) must conduct query preprocessing, or query optimizing. This paper proposes a new model for the Fuzzy Object-Oriented DBMS (FOO-DBMS), which optimizes the query statements and processes the data before returning back to users based on fuzzy object algebra and equivalent transformation rules. Discussions on this model are also presented with computation and analysis.

Thuan T. Nguyen, Ban V. Doan, Chau N. Truong, Trinh T. T. Tran
A Hybrid Threshold Group Signature Scheme with Distinguished Signing Authority

This paper proposes a new hybrid threshold group signature scheme with distinguished signing authority to provide all proof of member signing processes in case of dispute internally and internal integrity of multisignature generation process. In practical, the proposed scheme has more controls to an organization by using the threshold mechanism and allowing a limited number of members who can authorize transactions while allowing the group to grow. Moreover, the risk of losing group secret either by an APT attack or by any subset of corrupt members can be eliminated. The proposed scheme is secure based on the hardness of elliptic curve discrete logarithm problem (ECDLP).

Dao Tuan Hung, Nguyen Hieu Minh, Nguyen Nam Hai
Implementation and Analysis of BBO Algorithm for Better Damping of Rotor Oscillations of a Synchronous Machine

In this paper, a new evolutionary algorithm, namely the biogeography-based optimization (BBO) algorithm, is proposed to tune the Proportional Integral Derivative (PID) controller and power system stabilizer (PSS) parameters. The efficiency of BBO algorithm is verified on the single-machine infinite-bus (SMIB) system for various operating conditions. The proposed method suppresses the (0.1–2.5 Hz) low-frequency electromechanical oscillations and increases the power system stability via minimizing the objective function such as integral square error (ISE). Simulations of BBO-based PID, BBO-based PSS, BBO-based PID-PSS and conventional PSS are performed by using MATLAB/Simulink. The results show that BBO-based PID-PSS method improves the system performance and provides better dynamic performance.

Gowrishankar Kasilingam, Jagadeesh Pasupuleti, Nithiyananthan Kannan
Eye Blink Artefact Cancellation in EEG Signal Using Sign-Based Nonlinear Adaptive Filtering Techniques

This paper presents the filtering of the noise from the Electroencephalogram (EEG) using an adaptive filtering approach known as Nonlinear LMS algorithm. The noise presence in the signals makes it difficult to analyze the EEG as well as to get the correct representation of the signal. It, therefore, becomes important to design the signal filters to minimize the noise in such EEG signals. Nonlinear adaptive filter is implemented to minimize the ocular artefact/eye blink from the EEG in which the parameters can be adjusted to maintain the input–output relationship. Further, within Nonlinear adaptive filter approach, different sign-based versions such as Nonlinear sign Least Mean Square (NSSLMS), Nonlinear sign Least Mean Square (NSLMS), Nonlinear sign regressor Least Mean Square (NSRLMS) are developed to minimize the eye blink noise along with reducing the computational complexity. After this, a comparison of the filtered output signal is done with the output from the conventional LMS filter. Based on the parameters such as signal-to-noise ratio (SNR), misadjustment ratio (Madj) and excess mean square error (EMSE), we noticed that the filtered output from the Nonlinear adaptive filter is considerably more efficient. The main benefit of preferring NLMS in our analysis is its superior computational speed with multiplier free weight update loops. Also, it eliminates the need to make assumptions regarding data distribution and its size. Finally, to test the performance of the proposed algorithm, the same is applied on EEG signals extracted from CHB-MIT database. On comparing the results of the proposed algorithms with the conventional LMS, we noticed that NSRLMS outperforms the current realizations in reducing the noise.

Sruthi Sudha Nallamothu, Rama Kotireddy Dodda, Kanthi Sudha Dasara
No-Key Protocol for Deniable Encryption

There is proposed a new method for deniable encryption based on commutative transformations. The method has been used to design the deniable encryption protocol resistant to the passive coercive attacks, which uses no pre-shared secret keys and no pre-exchanged public keys. The protocol begins with the stage at which the sender and receiver exchange their single-use public keys and compute the single-use shared secret key. Then, it is performed pseudo-probabilistic three-pass protocol with simultaneous commutative encryption of the fake and secret messages. Resistance of the proposed protocol to coercive attacks is provided by its computational indistinguishability from probabilistic no-key three-pass protocol used to send securely the fake message. To perform commutative encryption, it used exponentiation cipher. To provide security against active coercer, the protocol is to be complemented with procedure for authenticating the sent messages.

Nam Hai Nguyen, Nikolay Andreevich Moldovyan, Alexei Victorovich Shcherbacov, Hieu Minh Nguyen, Duc Tam Nguyen
JCIA: A Tool for Change Impact Analysis of Java EE Applications

This paper presents a novel tool for change impact analysis of Java EE applications named JCIA. Analyzing the source code of the Java EE applications is a big challenge because of the complexity and large scale of the applications. Moreover, components in Java EE applications are not only in Java language but also in different languages such as XHTML, XML, JSP. This tool analyzes source code of Java EE applications for building the dependency graphs (called JDG). The main idea for generating JDG is based on developing the source code analyzers for the typical technologies of Java EE such as JavaServer Faces, Context and Dependency Injection, Web services. Based on the obtained JDG and the given change sets, JCIA calculates the corresponding impact sets by applying the change impact analysis (CIA) based on change types and Wave-CIA method. The calculated impact sets help managers in planning and estimating changes, developers in implementing changes, and testers with regression testing.

Le Ba Cuong, Van Son Nguyen, Duc Anh Nguyen, Pham Ngoc Hung, Dinh Hieu Vo
On the Robustness of Cry Detection Methods in Real Neonatal Intensive Care Units

The detection of cry is crucial in intelligent computerized systems that aim at assessing the well-being of neonates during their hospitalization periods. Moreover, a precise characterization of cry allows its classification (e.g., hunger, pain, tiredness…). Although several cry detection and characterization techniques can be found in the literature, there is no testing of such techniques in real-life environments such as hospital intensive care units. In this article, we first summarize the problem of background noise in intensive care units that may prevent the operation of cry detection algorithms from succeeding. Second, we implement a specific cry detection technique that is based on some of the relevant cry detection proposals that have been found in the literature. Finally, we test this method using audio samples recorded in a real neonatal intensive care unit.

Manh Chinh Dang, Antoni Martínez-Ballesté, Ngoc Minh Pham, Thanh Trung Dang
Energy-Efficient Resource Allocation for Virtual Service in Cloud Computing Environment

For the past severalNguyen Minh Nhut PhamVan Son LeHa Huy Cuong Nguyen years, using cloud computing technology has become popular. With the cloud computing service providers, reducing the physical machine number providing resources for virtual service in cloud computing is one of the efficient ways to decrease the energy consumption amount which in turn enhance the performance of data centers. In this study, we propose the resource allocation problem to reduce the energy consumption. $$ECRA-SA$$ algorithm was designed to solve and evaluate through CloudSim simulation tool compared with an FFD algorithm. The experimental results indicate that the proposed $$ECRA-SA$$ algorithm yields a higher performance in comparison with an FFD algorithm.

Nguyen Minh Nhut Pham, Van Son Le, Ha Huy Cuong Nguyen
Novel Adaptive Neural Sliding Mode Control for Uncertain Nonlinear System with Disturbance Estimation

The paper deals with the problem of tracking control for a class of nonlinear systems in presence of the disturbances. The developed formation for the tracking control is taken into account as an adaptive neural sliding mode. A chattering phenomenon will be eliminated by reducing a norm of disturbance based on disturbance estimation and feed-forward correction. The set of controller’s parameter, which is a satisfy Hurwitz polynomial, is then updated by adaptive laws via a model reference system. In addition, the unknown nonlinear functions are estimated by radial basis functions neural network. The adaptive updated law based on radial basis functions neural network and a feed-forward correction is proposed to estimate both estimation errors of nonlinear functions and external disturbances, which is called lumped disturbances. An asymptotic stability of a closed loop system is illustrated by Lyapunov theory. And lastly, to demonstrate an efficiency of our approach, an illustrative example, a coupled-tank liquid system, is shown.

Thiem V. Pham, Du Dao Huy
A Modification of Solution Optimization in Support Vector Machine Simplification for Classification

The efficient classification ability of support vector machine (SVM) has been shown in many practical applications, but currently it is significantly slower in testing phase than other classification approaches due to large number of support vectors included in the solution. Among different approaches, simplification of support vector machine (SimpSVM) accelerates the test phase by replacing original SVM with a simplified SVM that uses significantly fewer support vectors. Nevertheless, the final aim of the simplification is to try keeping the simplified solution as similar as possible to the original one. To ameliorate this similarity, in this paper, we present a modification of solution optimization in SimpSVM. The proposed approach is based on stochastic optimization. Experiments on benchmark and sign language datasets show improved results by our modification.

Pham Quoc Thang, Nguyen Thanh Thuy, Hoang Thi Lam
A Two-Stage Detection Approach for Car Counting in Day and Nighttime

We developed a car counting system using car detection methods for both daytime and nighttime traffic scenes. The detection methods comprise two stages: car hypothesis generation and hypothesis verification. For daytime traffic scenes, we proposed a new car hypothesis generation by rapidly locating car windshield regions, which are used to estimate car positions in occlusion situations. For car hypothesis at nighttime, we proposed an approach using k-means clustering-based segmentation to find headlight candidates to facilitate the later pairing process. Counting decision is made from Kalman filter-based tracking, followed by rule-based verification. The results evaluated on real-world traffic videos show that our system can work well in different conditions of lighting and occlusion.

Van-Huy Pham, Duc-Hau Le
An Effective FP-Tree-Based Movie Recommender System

Movie recommender systems play an important role in introducing users to the most interesting movies efficiently. It is useful for users to find what they want in a large numerous of various movies on the Web quickly. The performance of movie recommendation is influenced by many factors, such as user behavior, user ratings. Therefore, the aim of this study is to mine datasets of user ratings and user behaviors in order to recommend the most suitable movies to active users. User behaviors are sequences of users’ movie viewing activities which can be discovered by a frequent-pattern tree (FP-Tree). The FP-tree is then modified with rating data and an effective recommendation strategy can improve the recommendation performance of the FP-tree. A MovieLens dataset which is public and popular for evaluating movie recommender systems is observed and examined for assessing the proposed method.

Sam Quoc Tuan, Nguyen Thi Thanh Sang, Dao Tran Hoang Chau
Metadata-Based Semantic Query in Relational Databases

The retrieval of data from various semantically equivalent databases having different schemas is long been an important issue. In this context, the proposed WordNet-based model demonstrates the semantic data retrieval capabilities from different databases using metadata available with them and publishes the results.

Ch. V. S. Satyamurty, J. V. R. Murthy, M. Raghava
Performance Analysis of Information Transmission Systems Over Indoor LED Lighting Based Visible Light Communication Channels

This paper presents performance analysis of full-duplex indoor Visible Light Communication (VLC) system for text and image information transmission over Light Emitting Diode (LED) lighting. The system and channel models are firstly studied. The designed system consists of transmitters and receivers then investigated that can achieve information data rate of 161.2 Kbps with error free at the distance of 92 cm between for real-time text and image transmission over indoor environment. Experiment results have shown that the transmission delays for text and image transmission at different distances of 0.8 and 2.4 m are almost constant. In addition, symbol error rate (SER) do not vary data rate at some transmission distances. The bit error rate (BER) confirms that the longest transmission distance is achieved at distance of 107.5 cm with bit rate of 57.6 kbps for the forward channel and 38.4 kbps for the reverse channel without any symbol error.

Trung Ha Duyen, Tuan Do Trong
Collective Signature Protocols for Signing Groups

To extend practical applicability of the group signature protocols, there are introduced signature schemes of two novel types: (i) collective signature shared by a set of signing groups and (ii) combined collective signature shared by several signing groups and several individual signers. The protocol of the first type is constructed and described in detail. It is also shown a possible modification of the described protocol which allows transforming the protocol of the first type into the protocol of the second type. The proposed collective signature protocols have significant merits, one of which is connected with possibility of their practical using on the base of the existing public key infrastructures.

N. K. Tuan, V. L. Van, D. N. Moldovyan, H. N. Duy, A. A. Moldovyan
Deniability of Symmetric Encryption Based on Computational Indistinguishability from Probabilistic Ciphering

It is proposed as a novel interpretation of the notion of the shared-key deniable encryption, extended model of the coercive adversary, set of the design criteria, and a new practical approach to designing the shared-key deniable encryption algorithms, which is characterized using computational indistinguishability from probabilistic ciphering. The approach is implemented in several described algorithms relating to the plan-ahead shared-key deniable encryption schemes. The algorithms encrypt simultaneously secret and fake messages and produce the single cryptogram that is computationally indistinguishable from the ciphertext produced by some probabilistic cipher, while encrypting the fake message. The proposed algorithms are based on block conversion functions (hash-functions and block ciphers) and satisfy criterion of complete coincidence of the algorithms for recovering the fake and secret messages. Due to possibility to perform the inverse transformation the block ciphers used as the base block conversion function provide higher speed of the deniable encryption. It is also proposed as a general design of fast block deniable encryption algorithms satisfying the proposed design criteria.

Nikolay Andreevich Moldovyan, Ahmed Al-Majmar Nashwan, Duc Tam Nguyen, Nam Hai Nguyen, Hieu Minh Nguyen
Opinion Extraction from Quora Using User-Biased Sentiment Analysis

Opinion extraction is a field of computer science which deals with understanding the context of textual data and further forming an opinion on behalf of the user. In this paper, we present an opinion extraction model based on user’s profile. The opinion formulation algorithm is governed by factors that vary among users. A user-biased sentimental analysis technique is introduced, which mines the answers written on various topics on the popular Web site Quora and provides an opinion based on user’s preferences. The generics work independently. For implementation, a personal assistant to assist students in selecting a university for graduate studies based on their preferences, of course, the return of investment expectations, importance to university ranks, etc., was created. The algorithm achieved optimal performance and hence can be used as a reliable method to form opinions on behalf of the user.

Akshi Kumar, Satyarth Praveen, Nalin Goel, Karan Sanwal
Smart Surveillance Robot for Real-Time Monitoring and Control System in Environment and Industrial Applications

The current ongoing revolution of Internet of Things (IoT), is now integrated with Robotics in various diverse fields of everyday life is making up new era i.e. Internet of Robotics (IoR). Internet of Robotics is on the mature stage of development and is currently surrounded by various challenges to be solved for more implementations, i.e., design, security, sensors, and long-range communication systems. The main objective of this paper is to propose an Internet-of-Things-based Internet of Robot, i.e., InterBot 1.0. InterBot 1.0 is efficient in terms of real-time environmental monitoring in terms of temperature, humidity, and gas sensing and is equipped with long-range communication system via 2.4 GHz 6-channel remote and also short range via HC-05 (Bluetooth module). InterBot 1.0 is IoT-based via ESP8266, and all the data can be viewed in live graphs via ThingSpeak.com. The Results state the efficiency of Interbot 1.0 in monitoring real-time environments.

Anand Nayyar, Vikram Puri, Nhu Gia Nguyen, Dac Nhuong Le
Agile Team Assembling Supporting High Cooperative Performance

Modern organizations are repeatedly immersed in rapidly changing situations requiring a large variety of skills and expertise which more often than not implies bringing together new teams. In this paper, we present an approach that can significantly speed up team assembling processes where each required skill is possessed by more than one team member. Another important feature is providing automated information about members of other teams who possess specific currently requested skills when there is a need for it.

Sylvia Encheva
Accelerating Establishment of a Balanced Structure in New Organizations

When several organizations agree upon establishment of a new larger one, they have to solve a number of organizational problems. Several of them are related to assembling administrative and academic units across campuses. Some difficulties, arising while aiming at a flexible structure ready to support tomorrow’s needs, can be avoided by providing visual representation of employees’ skills and expertise.

Sylvia Encheva
Interpretations of Relationships Among Knowledge Assessment Tests Outcomes

Recently developed knowledge assessment tests provide students and educators with information about degrees to which certain skills are mastered, terms and concepts are understood, and to which extend abilities to solve predefined problems efficiently and in a timely fashion without difficulty are demonstrated. In case of partially correct or incorrect answers, students are suggested appropriate theory, examples, and possibilities to take new tests addressing those specific issues. Provided help is primarily related to a problem a student has not solved, a question not being answered correctly, or an answer has been omitted. In this work, we attempt to unveil hidden correlations among correct and wrong answers from students in a test.

Sylvia Encheva
Implementing Complex Radio System in Short Time Using Cognitive Radio

Usually, the frequency use of wireless system is characterized by static spectrum allocation. In order to cope with high data rate and high quality service, new wireless communication cognitive radio is emerged. The major issue in communication is declared by FCC is that the licensed band remains unused. These problems are addressed by the Mitola (Software radio, wireless architecture for twenty-first century [1]), and as a result, the cognitive radio technology has been proposed to improve the efficiency in spectrum utilization, by exploiting frequencies that are not been used by licensed users at a given time and location. Modulation determines the performance of communication system. The primary purpose of this paper is to experiment various modulation techniques of the wireless channel using software-defined radio. The paper emphasizes the cognitive radio and its significance compared with conventional wireless communication and also provides a comprehensive literature review of modulation techniques and its implementation using the universal software radio peripheral (USRP) device which acts as a transmitter, a receiver, and a relay.

Madhuri Gummineni, P. Trinatha Rao
Communication in Internet of Things

Internet of Things (IoT) is merging all things together and make this world better and makeDac-Nhuong, LeVivek Hareshbhai PuarChintan M. BhattDuong Minh Hoang it easy to live, actually with the help of IoT we can achieve those goals which do not till now. IoT will create a very big network of huge numbers of “Things” that will communicate with each other. Use of IoT tools is the simple way to make things smart. Contiki OS is one of the simulator on which one can run programs and simulate them. One of the examples given here which is border router using InstantContiki simulator. In this paper, we look forward to research how we can connect the border router to internet and how it is connected to other motes.

Vivek Hareshbhai Puar, Chintan M. Bhatt, Duong Minh Hoang, Dac-Nhuong Le
A Proposed Model to Integrate Business Intelligence System in Cloud Environment to Improve Business Function

Business intelligence system (BIS) has gained a high momentum and played a significant role in enhancing the business environment especially with the help of cloud. The BIS with cloud computing is the solution to overcome complex problems where large amounts of data (market analysis, customer’s view, feedback and organization response time) are required to be processed. The objective of this paper is to show the realistic perspective of the possibilities for maximizing benefits and minimizing risks in Indian business. The authors have highlighted the importance of cloud computing in business and tried to develop a framework for integrating BIS with cloud computing, and an attempt has also been made to analyse the efficiency of the proposed model which improves performance over the cloud. Some of the challenging issues as well as the future research directions have also been discussed.

Manas Kumar Sanyal, Biswajit Biswas, Subhranshu Roy, Sajal Bhadra
Combined Center-Symmetric Local Patterns for Image Recognition

Local feature description is gaining a lot of attention in the fields of texture classification, image recognition, and face recognition. In this paper, we propose Center-Symmetric Local Derivative Mapped Patterns (CS-LDMP) and eXtended Center-Symmetric Local Mapped Patterns (XCS-LMP) for local description of images. Strengths from Center-Symmetric Local Derivative Pattern (CS-LDP) which is gaining more texture information and Center-Symmetric Local Mapped Pattern (CS-LMP) which is capturing nuances between images were combined to make the CS-LDMP, and similarly, we combined CS-LMP and eXtended Center-Symmetric Local Binary Pattern (XCS-LBP), which is tolerant to illumination changes and noise were combined to form XCS-LMP. The experiments were conducted on the CIFAR10 dataset and hence proved that CS-LDMP and XCS-LMP perform better than its direct competitors.

Bhargav Parsi, Kunal Tyagi, Shweta R. Malwe
A Laguerre Model-Based Model Predictive Control Law for Permanent Magnet Linear Synchronous Motor

Linear motors have many advantages in comparison with rotary motors due to directly creating linear motion without gears or belts. The difficulties of designing the controller are that we need not only the tracking of position and velocity but guarantee that the voltage control and its variation are small enough as well. Model predictive control (MPC) is an advanced method of control that needs the corresponding predictive model. In this work, we propose the model predictive control based on Laguerre function with the constraints of voltage control and its variation. The numerical simulation generated by MATLAB–Simulink validates the performance of the proposed controller.

Nguyen Trung Ty, Nguyen Manh Hung, Dao Phuong Nam, Nguyen Hong Quang
Hybrid Model of Self-Organized Map and Integrated Fuzzy Rules with Support Vector Machine: Application to Stock Price Analysis

Prediction of stock price is always an interesting task. However, it is not easy to make this prediction with high accuracy. Recently, plenty of combinations of statistical methods have been proposed. The main direction of these methods is that combination of regression learner (e.g., SVM) and a clustering of data (e.g., SOM). While these methods make relative success, their extensibility is still under discussion. In this paper, we propose an hybrid model of self-organized map and integrated fuzzy rules with support vector machine. The proposition method is evaluated to be a good approach to apply to stock price analysis. Moreover, this method provides interpretable rules which can be understood, calibrated, and modified by experts in order to direct the learning phase.

Duc-Hien Nguyen, Van-Minh Le
Translation of UNL Expression into Vietnamese Compound Sentence Based on DeConverter Tool

DeConverter is one of the core software of the Universal Networking Language (UNL) translation system. Automatic translation system based on UNL consists of two components: EnConverter and DeConverter. EnConverter is used to translate a sentence from natural language into an equivalent UNL expression, and DeConverter is used to create a sentence on natural language from an UNL expression. The UNL system has supported over 48 different languages, but not much as certain research has been done for Vietnamese. In this paper, we describe the process of the translation from UNL expressions with scope into Vietnamese sentences by analyzing Vietnamese grammar and the semantic relationships in UNL expressions with scope node and how rules of translation from UNL expressions to equivalent Vietnamese sentences are built. We tested the UNL–Vietnamese–English translation on 500 different expressions alternatively by the DeCoVie tool and the English server, which was then compared to the manual translations. The results showed that the two machine translations are synonymous and 90% are identical in terms of grammar.

Thuyen Thi Le Phan, Hung Trung Vo
Filling Hole on the Surface of 3D Point Clouds Based on Reverse Computation of Bezier Curves

Reconstructing the surface of a 3D object is an important step in geometric modeling. This paper presents a proposed method for filling the holes on a surface of 3D point clouds based on reverse computation of Bezier curves. The novelty of the method is processed directly on the 3D point clouds consisting of three steps. In the first step, we extract the exterior boundary of the surface. In the second step, we detect the hole boundary and its extended boundary. In the third step, we fill the holes based on the reverse computation of Bezier curves and surface patch to find and insert missing points into the holes. Our method could process very fast comparing to the existing methods, fill all holes on the surface, and obtain a reconstructed surface that is watertight and close to the initial shape of the input surface.

Van Sinh Nguyen, Khai Minh Tran, Manh Ha Tran
Keyword Extraction from Hindi Documents Using Document Statistics and Fuzzy Modelling

In this paper, we put forward a novel unsupervised, domain independent and corpus independent approach for automatic keyword extraction. Our approach combines the document statistics of frequency and spatial distribution of a word in order to extract the keywords. We have extracted keywords from Hindi documents using document statistics and utilized the power of fuzzy logic to combine those document statistics effectively for better results. Further, we use this information to frame fuzzy rules for keyword extraction. Main advantages of our approach are that it uses the fuzzy membership for the variables instead of dealing with crisp thresholds and corpus independent setting of fuzzy membership boundaries. Our work is especially significant in the light that it has been implemented and tested on Hindi which is a resource poor and underrepresented language.

Sifatullah Siddiqi, Aditi Sharan
Improving Data Hiding Capacity Using Bit-Plane Slicing of Color Image Through (7, 4) Hamming Code

Achievement of high-capacity data hiding with good visual quality is an important research issue in the field of steganography. In this paper, we have introduced RGB color image and bit-plane slicing for data hiding through Hamming code using shared secret key. We partitioned the color image into (3 × 3) pixel blocks and then decomposed into three basic color blocks. Again each color blocks are sliced up to four bit-plane starting from LSB plane. Now, a segment of three bits secret data is embedded within each bit-plane depending on a syndrome calculated using hamming code. As a result, 36 bits secret data can be embedded within (3 × 3) pixel block and achieve a high payload capacity with good visual quality compared with existing schemes.

Ananya Banerjee, Biswapati Jana
Optimization of Fuzzy C-Means Algorithm Using Feature Selection Strategies

In the era of Digital World, everything has a cost whether the cost is in terms of money, time, space, or data. Big data is a term used to define very large volume of data which possesses a lot of varieties in it. In the following paper, we are presenting feature selection strategy to optimize fuzzy-based clustering over very large data. By using selective features method, we can reduce number of features used to classify the following dataset; thus, the reduction of dimensions/features can help in optimizing iteration count, space, time as well as minimize objective function for the following dataset. In final observation, we found out the reduction in iteration count as well as time in comparison to literal fuzzy c-means algorithm that is 10.65 s and 9.84 s, respectively, for pen digits and cement dataset in comparison to PCA that is 8 s and 9 s and EFA that is 5.74 s and 8 s, respectively, for both the datasets.

Kanika Maheshwari, Vivek Sharma
Model-Based Test Case Prioritization Using UML Activity Diagram and Design Level Attributes

This paper presents a prioritization technique that prioritizes the test cases using different design attributes like cohesion, coupling, the number of database access, and non-functional requirements. First, the system requirements are modeled using UML activity diagram (AD). The AD is turned into activity diagram graph (ADG), and the ADG is traversed to find out the test scenarios that are identified by the linearly independent paths in the ADG. Depending upon the different design attributes, weights for each node in the graph are identified and a final priority value is assigned to each node. The nodes executed for every test are identified, the priority value (PV) of the nodes is summed up, and the test case is assigned with a final priority value. Finally, depending on the priority value, the test cases are prioritized. The efficiency of the suggested approach is evaluated using the APFD metric.

Shaswati Dash, Namita Panda, Arup Abhinna Acharya
An Ensemble-Based Approach for the Development of DSS

A typical classification problem pertaining to DSS can be solved by employing any classification algorithm such as Bayesian classifiers, neural network, decision tree. But, existing single classifier-based predictive modeling has limited scope to provide a generalized solution for different learning contexts. In this paper, an ensemble-based classification approach using voting methodology is proposed for the decision support system. The proposed ensemble-based system combines three heterogeneous classifiers, namely decision tree, K-nearest neighbor, and aggregating one-dependence estimator classifiers using product of probability voting rule. This paper presents a comparative study of the proposed voting algorithm with the other well-known classifiers for 15 standard benchmark datasets and proved that the proposed method achieves better accuracy for most of the datasets.

Mrinal Pandey
Classification of Amazon Book Reviews Based on Sentiment Analysis

Since the dawn of internet, e-shopping vendors like Amazon have grown in popularity. Customers express their opinion or sentiment by giving feedbacks in the form of text. Sentiment analysis is the process of determining the opinion or feeling expressed as either positive, negative or neutral. Capturing the exact sentiment of a review is a challenging task. In this paper, the various preprocessing techniques like HTML tags and URLs removal, punctuation, whitespace, special character removal and stemming are used to eliminate noise. The preprocessed data is represented using feature selection techniques like term frequency-inverse document frequency (TF–IDF). The classifiers like K-Nearest Neighbour (KNN), Decision Tree (DT), Support Vector Machine (SVM), Random Forest (RF) and Naive Bayes (NB) are used to classify sentiment of Amazon book reviews. Finally, we present a comparison of (i) Accuracy of various classifiers, (ii) Time elapsed by each classifier and (iii) Sentiment score of various books.

K. S. Srujan, S. S. Nikhil, H. Raghav Rao, K. Karthik, B. S. Harish, H. M. Keerthi Kumar
A Secured Framework for Encrypted Messaging Service for Smart Device (Crypto-Message)

The involvement of technology in our life makes it more advance and provides access on our fingertip. It provides us with the capability to get connected with people and explore the information on the topics which is very beneficial for the ease of life. Thus our lives are dependent on several mobile chatting applications which offer different security to user and chatting details but leads to increase in vulnerabilities and risk of attack on data. As in sensitive business and legal conversation data security is most important for preventing from unwanted hacking activities. To overcome this kind of situation, it is proposed an encrypted messaging protocol for secure conversation. In the present world, there is a lot of encrypted messaging applications, but all those are based on a software generated encryption key along with SQLite database which is used to store the message of respective users which are not secure and the messages of any user can be obtained by a third party. But the proposed protocol uses a user-defined password for SHA-2 hash generation which is used as the key of AES-256 encryption for encrypting the message during the transition of message; on the other hand, our software stored encrypted message which will be decrypted by user in time of accessing the conversation by the introduction of user-defined key only. Through this approach, it can create a more secure atmosphere for the transition of data across the globe.

Shopan Dey, Afaq Ahmad, Anil Kr. Chandravanshi, Sandip Das
Robust Adaptive Backstepping in Tracking Control for Wheeled Inverted Pendulum

The previous papers (Olfati-Saber PhD. thesis, 2001) [1], (Khac Duc Do, Gerald Journal of Intelligent and Robotic Systems 60(3), 2010) [2] (Wei et al. Automatica, 841–850 1995) [3] applied feedback linearization or global change coordinates to separate system model into rotate and straight movement, leading to difficulty in control design for uncertain parameter systems. Additionally, paper (Culi et al. Nonlinear control of a swinging pendulum. Automatica 31(6), 1995, 851–862) [4] presenting robust adaptive law ignored time-varying inertia matrix to design control Lyapunov function (CLF) easily, leading to wrong theoretical proof. In this paper, we propose a new adaptive law and a new controller to control WIP system, in that the error tracking of heading angle and position is bounded and tilt angle converges to the small arbitrary ball of origin and tracking position, which is not be ensured (Culi et al. Nonlinear control of a swinging pendulum. Automatica 31(6), 1995, 851–862) [4] (Li et al. Automatica 2010, 1346–1353) [5]. Moreover, time-varying inertia matrix is considered to choose a proper CLF via backstepping technique. The simulation results are implemented to demonstrate the performances of the proposed adaptive law and controller.

Nguyen Thanh Binh, Nguyen Anh Tung, Dao Phuong Nam, Nguyen Thi Viet Huong
Bandwidth Enhancement of Microstrip Patch Antenna Array Using Spiral Split Ring Resonator

This communication presents a spiral split ring resonator (SSRR) loaded four-element microstrip patch antenna array for 5.8 GHz WiMAX applications. The unloaded antenna array resonates at 5.8 GHz with gain of 7.15 dBi and bandwidth of 480 MHz. Whereas, when the patches of this array are loaded with SSRR, the bandwidth increases to 700 MHz with almost no variation in gain. The proposed antenna array has been designed on 1.48 mm thick FR-4 substrate and simulated in FEM-based HFSS commercial electromagnetic simulator.

Chirag Arora, Shyam S. Pattnaik, R. N. Baral
An Ensemble Classifier Approach on Different Feature Selection Methods for Intrusion Detection

Knowing a day’s monitoring and analyzing events of network for intrusion detection system is becoming a major task. Intrusion detection system (IDS) is an essential element to detect, identify, and track the attacks. Network attacks are divided into four classes like DoS, Probe, R2L, and U2R. In this paper, ensemble techniques like AdaBoost, Bagging, and Stacking are discussed which helps to build IDS. Ensemble technique is used by combining several machine learning algorithms. Selection of features is one of the important stages in intrusion detection model. Some feature selection methods like Cfs, Chi-square, SU, Gain Ratio, Info Gain, and OneR are used in this paper with suitable search technique to select the relevant features. The selected features are applied on AdaBoost, Bagging, and Stacking with J48 as a base classifier and along with that J48 and PART are used as single classifies. Finally, results are shown that the use of AdaBoost improves the classification accuracy. Experiments and evaluation of the approaches are performed in WEKA data mining tool by using benchmark dataset NSL-KDD ‘99.

H. P. Vinutha, B. Poornima
Study of Image Segmentation Techniques on Microscopic Cell Images of Section of Rat Brain for Identification of Cell Body and Dendrite

Present paper illustrates the study and comparison of different image segmentation techniques on microscopic cell images—a part of computerization for cell image analysis. The process of segmentation is highly required for analysis and to study the behavior of live cell structure. The error is less in the computerized system of cell image analysis as compared to the manual system. Region growing, region split and merging, FCM, k-mean, and hybrid clustering segmentation technique are used for comparison. Hybrid clustering gives better results than other techniques in terms of accuracy and time, while region spit and merging and FCM give poor results. For performance evaluation, some parameters are used.

Ashish Kumar, Pankaj Agham, Ravi Shanker, Mahua Bhattacharya
Performance Evaluation of Machine Learning and Deep Learning Techniques for Sentiment Analysis

Since the proliferation of opinion-based web content, sentiment analysis as an application of natural language processing has attracted the attention of researchers in the past few years. Lot of development has been brought in this domain that has facilitated in achieving optimal classification of text data. In this paper, we experimented with the widely used traditional classifiers and deep neural networks along with their hybrid combinations to optimize relevant parameters so as to obtain the best possible classification accuracy. We conducted our experiments on labeled movie review corpus and have presented relevant results and comparisons.

Anushka Mehta, Yash Parekh, Sunil Karamchandani
Improved RAKE Models to Extract Keywords from Hindi Documents

In this paper, we have proposed several improved versions of rapid automatic keyword extraction (RAKE) algorithm for extracting keywords from Hindi documents. As RAKE requires a stopword list to generate the set of candidate keywords, which is unavailable in Hindi, we have constructed the Hindi stopword list for this purpose. We have found some weakness in keyword scoring measures of RAKE and proposed several models such as N-RAKE, SD-RAKE, NSD-RAKE, and WOS-RAKE to improve upon the effectiveness of RAKE. We have found that our modifications yield better results in general than original RAKE.

Sifatullah Siddiqi, Aditi Sharan
An Information Systems Design Theory for Knowledge-Based Organizational Learning Systems

The field of information systems (IS) is divided into “design science,” which is more engineering oriented, and “natural science,” which is more management oriented. This paper believes that such a conflict is detrimental to the cause of research in IS, especially because both design and natural science have a wealth of knowledge to give to and to learn from each other, and a symbiotic relationship between the two research interests could tremendously increase the contribution of IS research as a whole. As an example, this paper uses theory from natural science to guide building and evaluating an artifact using design science. Specifically, I develop an information systems design theory to provide a prescriptive conceptual design of an organizational learning system using design science that addresses the shortcomings of on knowledge management systems and organizational learning systems identified in natural science research.

Vishnu Vinekar
Image Saliency in Geometric Aesthetic Aspect

This paper introduces a geometric aesthetic approach for the analysis of visual attention to extract regions of interest from images. Modulation awareness, such as that perceived by visual features, can be represented by attractive proportions of visual objects. Together with supporting techniques such as similarity estimation and lighting condition manipulation, the aesthetic geometry-based analysis can be implemented to form refined attentive shifting observed from image scenes. In this paper, we propose robust kernels which comply with the golden ratio for analysis of aesthetic attractiveness which can raise visual awareness. Properties and relations of points and regions are evaluated by the corresponding kernels for images scenes. We also establish robust likelihood reasoning for the kernels with respect to human aesthetic attraction. The experimental results with a benchmark show the efficiency of the proposed method for identifying region of visual interest in images.

Dao Nam Anh
Delay-Based Reference Free Hardware Trojan Detection Using Virtual Intelligence

Virtual instrumentation is a powerful tool that has been largely left unexplored in the domain of hardware security. It facilitates creation of automated tests to detect the presence of Trojans in a circuit thereby reducing the chance of human errors and the time required for testing. The presence of a stealthy Trojan in large VLSI circuits could lead to leakage of confidential information even in high-security applications such as defense equipment. Here, we propose the usage of virtual instrumentation to detect the presence of a delay-based Trojan in a circuit. Our results confirm that VI-based systems provide a cheap, self-sufficient, easy-to-use interface, and flexible scheme which can be easily modified to accommodate any VLSI circuit. This can also be used in other detection techniques without the need for use of complex systems.

S. Kamala Nandhini, S. Vallinayagam, H. Harshitha, V. A. Chandra Shekhar Azad, N. Mohankumar
Compact RCA Based on Multilayer Quantum-dot Cellular Automata

The full adder is a basic logical circuit that performs an addition operation in any arithmetic circuits. In our paper, a bettered 1-bit full adder is proposed based on quantum-dot cellular automata (QCA). It confirms that the proposed circuit works properly and it can be used as a highly efficient design in arithmetic circuits. Finally, by connecting four 1-bit QCA full adders, we present a 4-bit ripple carry adder successfully. Our design has been realized with a simulation tool QCA Designer. The performance of our structure has significantly achieved improvements in terms of cell count, occupied area, and delay.

Nuriddin Safoev, Jun-Cheol Jeon
Control of the Motion Orientation and the Depth of Underwater Vehicles by Hedge Algebras

In this paper, we present an application of the hedge algebra controller in control of the orientation and the depth of underwater vehicles. The experiments simulated on computers are done to prove the effectiveness and the feasibility of the proposed algorithm of the neural controller under different actions such as the noise in the measuring devices, the influence of the flow to the motion of underwater vehicles.

Nguyen Quang Vinh
The Relation of Curiosity and Creative use of IT

It is essential to identify factors influencing the creative use of IT that can enhance organizational performance. Based on self-determination theory, our approach investigates the intermediate role of employees’ curiosity in the relationships between inherent psychological needs and employees’ creative use of IT. By using the quantitative method, this study develops a model regarding the creative use of IT. To test the model, surveys are distributed to employees working for organizations located in one of the biggest city in Vietnam. The results indicate that curiosity has partial mediation in the relation between inherent psychological needs and creative use of IT. The findings of this paper are expected to shed a new light into the study of users’ behavior, especially in their creative use of IT. This paper also provides valuable insight to practitioners on how to improve their employees’ creative use of IT.

Nhu-Hang Ha, Yao Chin Lin, Nhan-Van Vo, Dac-Nhuong Le, Kuo-Sung Lin
Advanced Interference Aware Power Control (AIAPC) Scheme Design for the Interference Mitigation of Femtocell Co-tier Downlink in LTE/LTE-A and the Future 5G Networks

LTE femtocell base stations (FBSs) can not only expand the coverage of wireless communication systems but also increase frequency reuse. Therefore, they play an important role in the development of future 5G networks. However, the growing use of FBSs has brought a serious issue of inter-FBS interference (also referred to as co-tier interference) due to their easy and convenient installation. In this article, we propose an advanced systematic approach to reduce FBS co-tier downlink interference under the scenario that FBSs are densely deployed in an environment compared to our past proposed scheme. A femtocell user equipment (FUE) can detect interference from FBSs and send an alarm signal to each FBS which interferes with it. To minimize the negative effects of interference, power levels are reduced for FBSs once they identify themselves as excessive interference (EI) cells defined as FBSs that have received a number of alarm signals above the number of its served UEs. Our simulations show that the throughput of our proposed scheme can be boosted by at least 120% compared to that of our previous proposed IAPC scheme at cost of somewhat little-reduced power consumption, because it could effectively reduce co-tier downlink interference in shared spectrum femtocell environments, thereby improving system performance.

Kuo-Chang Ting, Chih-Cheng Tseng, Hwang-Cheng Wang, Fang-Chang Kuo
Design and Implementation of Unauthorized Object and Living Entity Detector with PROTEUS and Arduino Uno

This paper presents and implements an unauthorized object detector using ultrasonic waves. Ultrasonic refers to the waves with frequencies over 20 kHz. It is insensitive to human ears having audible perception range of 20 to 20 kHz. Thus, ultrasonic waves are useful for distance measurement in driverless cars. The distance can be measured by using two techniques; pulse echo and phase measurement methods. In this work, pulse echo method is considered where the target is detected via ‘non-contact’ technology. The Ultrasonic Module keeps monitoring and checks the echo reflected back by the entity to display the exact angle and distance on the screen. The novelty of this work is the development of an alert system that not only detects the target but also measures and displays its exact distance. PROTEUS software has been used for simulation. Hardware is also developed and tested to detect any entity in the prescribed range.

Samridhi Sajwan, Shabana Urooj, Manoj Kumar Singh
A Simulink-Based Closed Loop Current Control of Photovoltaic Inverter

In this paper, a system is proposed for maintaining alternating current with the desired characteristics of a closed loop configuration photovoltaic (PV) system. The generated output current from the PV system is highly dependent on the temperature and intensity of the solar radiation. The proposed system overcomes these critical issues by using a closed loop current control, resulting in an alternating current (AC) output of constant frequency and amplitude. The proposed system consists of a photovoltaic cell array, current controlled inverter, closed loop current control and LC filter. The closed loop strategy helps to get nearly ideal AC output. Low pass filtering is employed to further enhance the AC response. The system is developed and verified in MATLAB–Simulink.

Nidhi Upadhyay, Shabana Urooj, Vibhutesh Kumar Singh
Three-Phase PLLs for Utility Grid-Interfaced Inverters Using PSIM

This paper deals with the simulation model of synchronous rotating reference frame and trigonometric phase lock loop (PLL). For grid-connected inverters, a synchronization control technique is required for maintaining high power quality and efficiency of the system. There are many phase lock loop algorithms used for synchronization like enhanced PLL, power PLL, quadrature-based PLL. This paper presents two phase lock loops for utility grid-connected inverters. The circuits are simulated using PSIM simulation package, the generated phase angle of the PLL as its output is converted into a sine wave by adding a sine block, and results have been analyzed and discussed by the suitable input and output waveforms.

Kartik Kamal, Kamal Singh, Shabana Urooj, Ahteshamul Haque
Occlusion Vehicle Segmentation Algorithm in Crowded Scene for Traffic Surveillance System

Traffic surveillance system (TSS) is an essential tool to extract necessary information (count, type, speed, etc.) from cameras for further analysis. In this issue, vehicle detection is considered one of the most important studies as it is a vital process from which modules such as vehicle tracking and classification can be built upon. However, detecting moving vehicles in urban areas is difficult because the inter-vehicle space is significantly reduced, which increases the occlusion among vehicles. This issue is more challenging in developing countries where the roads are crowded with 2-wheeled motorbikes in rush hours. This paper proposes a method to improve the occlusion vehicle detection from static surveillance cameras. The main contribution is an overlapping vehicle segmentation algorithm in which undefined blobs of occluded vehicles are examined to extract the vehicles individually based on the geometry and the ellipticity characteristics of objects’ shapes. Experiments on real-world data have shown promising results with a detection rate of 84.10% in daytime scenes.

Hung Ngoc Phan, Long Hoang Pham, Duong Nguyen-Ngoc Tran, Synh Viet-Uyen Ha
Anomaly Detection in a Crowd Using a Cascade of Deep Learning Networks

Anomaly detection allows to detect whereabouts of aberrant objects. In this paper, we propose anomaly detection using two connected neural networks. At the front, the convolutional neural network is used to extract visual features and the recurrent neural network implemented using a long short-term memory (LSTM) is followed to track and detect anomaly. In comparison to the conventional CNN and RNN method, the proposed method is capable of faster learning and is able to effectively detect anomaly objects.

Peng Qiu, Sumi Kim, Jeong-Hyu Lee, Jaeho Choi
HAPMAD: Hardware-Based Authentication Platform for Malicious Activity Detection in Digital Circuits

Hardware Trojans pose a major threat to the security of many industries and government agencies. This paper proposes a non-destructive method for detection of Hardware Trojans named HAPMAD—Hardware-Based Authentication Platform for Malicious Activity Detection in Digital Circuits using a combination of enhanced voting algorithm and hybrid voting algorithm (power and time analysis). Detecting a hardware Trojan is a cumbersome task. In most cases, the hardware Trojan can be detected only by activating it or by magnifying the Trojan activity. The detection efficiency using enhanced weighed voting is promising but in the case of Trojan circuits where there is no change in the output of the circuit; enhanced weighed voting algorithm fails to detect the Trojans effectively. Therefore, a two-phased voting algorithm is performed to increase the detection efficiency. ISCAS ‘85 Benchmark circuits were used to test the efficiency of the proposed technique.

Venkata Raja Ramchandar Koneru, Bikki Krishna Teja, Kallam Dinesh Babu Reddy, Makam V. GnanaSwaroop, Bharath Ramanidharan, N. Mohankumar
Sparse Nonlocal Texture Mean for Allocation of Irregularity in Images of Brain

The medical image analysis for irregularity studies has always been a refreshing research topic for the need of efficient and precise diagnosis. A new method based on patch analysis for detection of disorder in images of brain is introduced with machine learning techniques. In the method, a sparse nonlocal texture mean filter is proposed to evaluate the similarity of each spot in the image. The spot-based similarity allows initial identification of place of abnormality which is then refined by the support vector machines to efficiently perform extraction of disorder’s region. Experimental results on a benchmark’s real data are assessed and compared objectively to ensure sufficient certainty of the method.

Dao Nam Anh
Performance Evaluation of DC MicroGrid Using Solar PV Module

This paper presents the performance parameters of DC microgrid system using solar photovoltaic module. The solar power is fed through DC–DC boost converter, which is also equipped with MPPT to extract maximum solar energy. Boost converter connected along with PV module and Li-ion battery boosts up output voltage to the desired value, which is being fed to the DC bus. In order to obtain the highest efficiency and highest output power, MPPT is essential to drive the system till maximum power point. The voltage across DC bus is maintained to a certain desired value so that load can be applied to the circuit. Comparison and validation of DC output voltage are done by changing the load (resistive and inductive). Reduction of ripples in the DC output voltage is done by connecting inductors and capacitors in series and parallel, respectively. Three-phase AC source is also used and converted to DC by rectifier. Buffer circuits are used to handle the instantaneous power imbalance between source and load of the entire circuit. The system is modeled in the PSIM software, and the results obtained show that the ripples in resistive load are less as compared to the inductive load.

Shabana Urooj, Rushda Rais, Ahteshamul Haque
A Customized Hardware Architecture for Multi-layer Artificial Neural Networks on FPGA

This paper presents a novel and customized hardware architecture for the realization of artificial neural networks on reconfigurable computing platforms like FPGAs. The proposed architecture employs only one single-hardware-computing layer (namely SHL-ANN) to perform the whole computing fabric of multi-layer feed-forward neural networks. The 16-bit half-precision floating-point number format is used to represent the weights of the designed network. We investigate the scalability and hardware resource utilization of the proposed neural network architecture on the Xilinx Virtex-5 XC5VLX-110T FPGA. For performance evaluation, the handwritten digit recognition application with MNIST database is performed, which reported the best recognition rate of 97.20% when using a neural network architecture of size 784-40-40-10 with two hidden layers, occupying 91.8% FPGA hardware resource. Experimental results show that the proposed neural network architecture is a very promising design choice for high-performance embedded recognition applications.

Huynh Minh Vu, Huynh Viet Thang
Reconstructing B-patch Surfaces Using Inverse Loop Subdivision Scheme

B-patch surface is the main block to construct the triangular B-spline surfaces and has many interesting properties of the surfaces over a triangular parametric domain. This paper proposes a new method for reconstructing the low-degree B-patch surfaces using inverse Loop subdivision scheme, along with geometric approximation algorithm. The obtained surfaces are the low-degree B-patches over the triangular domain and almost cross through the data points of the original triangular meshes after several steps of the geometric approximating. Comparing with techniques use the original mesh as the surface control polyhedron, our method reconstructed B-patches with the degree reduces to 2i times after i steps of the inverse. The accuracy of the result B-patches can be improved by adjusting the location of control points and knot vectors in each step of iterations. Some experimental results demonstrate the efficacy of the proposed approach. Because most the low-degree parametric surfaces are often employed in CAGD, mesh compression, inverse engineering, and virtual reality, this result has practical significance.

Nga Le-Thi-Thu, Khoi Nguyen-Tan, Thuy Nguyen-Thanh
A Rule-Based Method for Text Shortening in Vietnamese Sign Language Translation

Sign languages are natural languages with their own set of gestures and grammars. The grammar of Vietnamese sign language has significantly different features compared with those of Vietnamese spoken/written language, including the shortening, the grammatical ordering, and the emphasis. Natural language processing research on Vietnamese sign language including study on spoken/written Vietnamese text shortening into the forms of Vietnamese sign language is completely new. Therefore, we proposed a rule-based method to shorten the spoken/written Vietnamese sentences by reducing prepositions, conjunctions, and auxiliary words and replacing synonyms. The experimental results confirmed the effectiveness of the proposed method.

Thi Bich Diep Nguyen, Trung-Nghia Phung, Tat-Thang Vu
Vehicle Classification in Nighttime Using Headlights Trajectories Matching

Vehicle detection and classification is an essential application in traffic surveillance system (TSS). Recent studies have solely focused on vehicle detection in the daytime scenes. However, recognizing moving vehicle at nighttime is more challenging because of either poor (lack of street lights) or bright illuminations (vehicle headlight reflection on the road). These problems hinder the ability to identify vehicle’s shapes, sizes, or textures which are mainly used in daytime surveillance. Hence, vehicles’ headlights are the only visible features. However, the tracking and pairing of vehicle’s headlights have its own challenge because of chaotic traffic of motorbikes. Adding to this is various types of vehicles travel on the same road which falsifies the pairing results. So, this research proposes an algorithm for vehicle detection and classification at nighttime surveillance scenes which consists of headlight segmentation, headlight detection, headlight tracking and pairing, and vehicle classification (two-wheeled and four-wheeled vehicles). The novelty of our work is that headlights are validated and paired using trajectory tracing technique. The evaluation results are promising for a detection rate of 81.19% in nighttime scenes.

Tuan-Anh Vu, Long Hoang Pham, Tu Kha Huynh, Synh Viet-Uyen Ha
A Scaled Conjugate Gradient Backpropagation Algorithm for Keyword Extraction

In modern days, it is highly important that one can get the defining content from any desirable source. When it comes to excessively large documents, it becomes an issue to effectively get the most important parts of it. Every document’s main topic can be conveyed using a few defining words. This paper provides a novel approach to extract such words from a given document corpus. Domain-specific keyword extraction is the principle highlight of our work. A series of documents from a specific domain is provided to us as the working set, and identification of the top three to five words will be done to convey the documental message. Our experiments show an accuracy of 80.6%.

Ankit Aich, Amit Dutta, Aruna Chakraborty
Probabilistic Model and Neural Network for Scene Classification in Traffic Surveillance System

Traffic surveillance system (TSS) has seen great progress in the last several years. Many algorithms have been developed to cope with a wide range of scenarios such as overcast, sunny weather that created shadows, rainy days that result in mirror reflection on the road, or nighttime when low lighting conditions limit the visual range. However, in real-world applications, one of the most challenging problems is the scene determination in a highly dynamic outdoor environment. As also pointed out in recent survey, there have been limited studies on a mechanism for scene recognition and adapting appropriate algorithms for that scene. Therefore, this research presents a scene recognition algorithm for all-day surveillance. The proposed method detects and classifies outdoor surveillance scenes into four common types: overcast, clear sky, rain, and nighttime. The major contributions are to help diminish hand-operated adjustment and increase the speed of responding to the change of alfresco environment in the practical system. To obtain high reliable results, we combine the histogram features on RGB color space with the probabilistic model on CIE-Lab color space and input them into a feedforward neural network. Early experiments have suggested promising results on real-world video data.

Duong Nguyen-Ngoc Tran, Long Hoang Pham, Ha Manh Tran, Synh Viet-Uyen Ha
An Evaluation of Virtual Organizational Structure on Employee Performance of Selected Telecommunication Companies in Kaduna State, Nigeria

The business environment will no doubt require firms to become even more flexible and agile to bring products and services to market at an increasing rapid pace with the advent of IT in Nigerian in the context of MTN, ETISALAT, and GLO. Traditional organizational structure is no longer capable of sustaining the needs of their relentless pace, new forms of organizing such as the virtual organization hold promise as organizational leaders experiment and learn new strategies for managing in the twenty-first century and beyond. Thus, this study seeks to evaluate the extent to which virtual organizational structure enhances employees’ performance. A census survey research design was used in which data was sourced via questionnaire and the data was analyzed using descriptive statistics SPSS V.20 and regression analysis in testing the hypothesis. This study found out that virtual organizational structure has significant effect on employees’ performance in some selected telecommunication in Kaduna state, and it was recommended that the organization should take advantage by improving on managerial training and study virtual organizational structure so as to enhance employees’ performance.

Fadele Ayotunde Alaba, Yunusa Salisu Tanko, Sani Danjuma, Rajab Ritonga, Abulwafa Muhammad, Tundung Subali Patma, Tutut Herawan
An Impact of Transformational Leadership on Employees’ Performance: A Case Study in Nigeria

The objective of this paper is to determine the extent to which transformational leadership has impact on staff performance in Federal College of Education, Zaria, Nigeria. Statement of the problem under study was employees’ affirmation to lack of direction to the organization’s transformational style of leadership and an intellectual excursion was undertaken to review related literatures on transformational leadership and performance. A survey research design was used as primary data and was sourced via questionnaire and interview which was complimented with secondary data. The analysis of data was conducted using SPSS version 20, and regression was used as tool for hypothesis testing, and it was found out that there is significant relationship between transformational leadership and staff performance in the college. The study concludes that a sound and viable leadership with individual consideration at heart, encourages innovation, and creativity, and it was recommended that management should adopt fully the transformational leadership role with leadership qualities such as role modeling, perseverance, empathy, pragmatism, visionary, innovative, coaching, stimulating, and valuing employees so as to enhance staff performance.

Yusuf Musa, Sani Danjuma, Fadele Ayotunde Alaba, Rajab Ritonga, Abulwafa Muhammad, Ludfi Djajanto, Tutut Herawan
Future Private Cloud Architecture for Universities

Cloud computing is one of the new and recently emerged research field which offers resource on demand facility. Education is must for each society, and this medium of education is imparted through schools, colleges, and universities. Universities are regarded as highest and elite learning centers. Technology is rapidly progressing day by day and so the universities have to update their technical resources too like new tools, equipment, and so on, so that students can learn new technologies and be better professionals in future. However, this is quite tedious task as it involves lot of budget considerations. Even some universities which cannot afford to cope with time due to inadequate facilities are on verge of extinction. Thus, concept of cloud computing can be implemented in Universities, and using cloud will not involve much expense as compared to owning equipment. Hence, in this paper, theoretical concept of architecture as how private cloud can be used in universities to impart better education is proposed.

Saqib Hakak, Gulshan Amin Gilkar, Guslendra, Rajab Ritonga, Tutut Herawan
Towards a Privacy Mechanism for Preventing Malicious Collusion of Multiple Service Providers (SPs) on the Cloud

Cloud computing is cyberspace computing, where systems, packages, data and other required services (such as appliances, development platforms, servers, storage and virtual desktops) are dispensed. It has generated a very significant interest in educational, industrial and business set-ups due to its many benefits. However, cloud computing is still in its early stage of development and is faced with many difficulties. Researchers have shown that security issues are the major concerns that have prevented the wide adoption of cloud computing. One of the security issues is privacy which is about securing the personal identifiable information (PII) or attributes of users on the cloud. Although researches for addressing privacy on the cloud exist (uApprove, uApprove.JP and Template Data Dissemination (TDD)), users’ PII remains susceptible as existing researches lack efficient control of user’s attribute of sensitive data on the cloud. Similarly, users are endangered to malicious service providers (SPs) that may connive to expose a user’s identity in a cloud scenario. This paper provides a mechanism to solve the malicious SP collusion problem and control the release of user’s attribute in the cloud environment. This will require the use of policies on the SPs, where SPs are only allowed to request for attributes that are needed only to process a user’s service at any point in time. This can be achieved using a combination of Kerberos ticket concept, encryption and timestamp on the attribute to be released to SPs from the identity provider (IdP), thereby helping to control attributes given to SPs for processing the release of services to users for one-time usage by the SPs and not kept for future use by them. Thus, replay attacks and blocking other SPs from accessing them are prevented. Hence, any malicious intention of assembling users’ attributes by other SPs to harm them is defeated.

Maria M. Abur, Sahalu B. Junaidu, Sani Danjuma, Syafri Arlis, Rajab Ritonga, Tutut Herawan
Model-Based Testing for Network Security Protocol for E-Banking Application

Model-based testing is one of the promising innovations to meet the difficulties required in program design testing. In model-based testing, a system under test is tried for consistency with a model that portrays the required behavior of the system. In this paper, model-based strategies are utilized for recognizing vulnerabilities as a part of system security conventions and testing for right behavior of e-banking applications in which system security conventions are actualized. The Kerberos V5 network authentication protocol is used in this research to demonstrate customers’ identity to a server (and the other way around) over an uncertain connection. Password-based encryption (PBE) algorithm is used for message exchange between client and Kerberos.

Fadele Ayotunde Alaba, Saqib Hakak, Fawad Ali Khan, Sulaimon Hakeem Adewale, Sri Rahmawati, Tundung Subali Patma, Rajab Ritonga, Tutut Herawan
A Framework for Authentication of Digital Quran

Increment of Internet users accessing content related to digital Quran and Hadith has increased from past few years. This has increased the need of Quran and Hadith authentication system that can authenticate between fake and original verses. In this work, complete framework related to automatic authentication and distribution of digital Quran and Hadith verses is proposed. Authentication process is divided into two phases, i.e., verification and security. For verification part, existing and standard exact matching algorithm, i.e., Boyer-Moore algorithm, is used. In case of security phase, watermarking technique will be used to secure the verified and tested verse. Furthermore, only verification phase of proposed framework is tested as system is still under development phase. For dealing with diacritics involved in Quranic text and Hadith text, segmentation is done based on clitics using UTF-16 encoding. On testing the proposed framework with comparison to popular search engines and other related existing works, our approach is 96.8% accurate in terms of full verse detection.

Saqib Hakak, Amirrudin Kamsin, Jhon Veri, Rajab Ritonga, Tutut Herawan
Computing Domain Ontology Knowledge Representation and Reasoning on Graph Database

In this paper, we solve problem of the ineffectiveness of using RDFS/OWL-stored mechanism for large-scale domain ontology. In particular, when the constructed ontology contains a huge amount of entities and semantic relations, it causes difficulties in managing and visualizing the ontological knowledge as well as low performance in data querying. We resolve these issues by using graph database as the storage mechanism for representing the constructed ontology. The approach of using graph database provides the advantages not only in better ontological data management and visualization but also in the higher performance and flexible of knowledge extracting from ontology via cypher querying language.

Phu Pham, Thuc Nguyen, Phuc Do
An Efficient Model for Finding and Ranking Related Questions in Community Question Answering Systems

The task of finding- and ranking-related questions plays the most important role for any real-world Community Question Answering (cQA) systems. This paper proposes a new method to solve this problem by considering multi-views for measuring the similarities between the input questions and the question-answering pairs in the database. Our model will investigate various aspects for understanding questions. Beside the traditional features such as bag of n-grams, we will use more efficient aspects that include word embeddings and question categories. We will use a word representation model for generating word embeddings, a question classification module for determining the category for an input question. Then all these obtained features are combined into a machine learning-based framework for getting similarity existing question-answering pairs as well as for ranking these pairs. We tested our proposed approach on the dataset SemEval 2016 and the experiment shows obtained results with the Accuracy and MAP of 80.43% and 77.43%, respectively, which are the highest accuracies in comparison with previous studies.

Van-Tu Nguyen, Anh-Cuong Le, Dinh-Hong Vu
Haralick Features-Based Classification of Mammograms Using SVM

The contrast enhancement of mammograms at preprocessing stage optimizes the overall performance of a computer-aided detection (CAD) system for breast cancer. In the proposed approach, contrast enhancement is performed using a sigmoidal transformation mechanism followed by extracting a set of 14 Haralick features. For classification purposes, a support vector machine (SVM) classifier is used which sorts the input mammogram into either normal or abnormal subclasses. The performance of the classifier is estimated by calculating parameters like accuracy, specificity, and sensitivity. The performance of the proposed approach has been reported to be better in comparison to other existing approaches.

Vikrant Bhateja, Aman Gautam, Ananya Tiwari, Le Nguyen Bao, Suresh Chandra Satapathy, Nguyen Gia Nhu, Dac-Nhuong Le
A Genetic Algorithm Approach for Large-Scale Cutting Stock Problem

This work investigates the one-dimensional integer cutting stock problem, which has many applications in Information and Communications Technology for green objectives. The problem consists of cutting a set of available objects in stock to produce smaller items with minimum the wastage of materials. On the basis of the traditional group-based Genetic Algorithm, we solve the large-scale cutting stock problems by adding two new proposals. Firstly, we put two additional steps to the First Fit heuristic to utilize wastage stock rolls when items are added to genes. These steps are applied to initialize the first population and to perform the mutation operation between two parents. Secondly, we propose a new heuristic in the crossover operation to create new individuals. The heuristic increases good genes and decreases bad genes which appeared in the population. We use them to improve traditional Genetic Algorithm in terms of the individual’s quality and the diversity of good genes in the populations. As a result, the wastage of stock rolls decreases. These heuristics are empirically analyzed by solving randomly generated instances and large instances from the literature, then results are compared to other methods. We specify an indicator to show some solutions are optimal. The numerical simulation shows that our approach is effective when it is applied to large-scale data sets, with better result in 40% of instances than the traditional cutting plane algorithm. On the other hand, we show that our approach can reach 289 optimal solutions out of 400 generated instances.

Nguyen Dang Tien
Fuzzy Linguistic Number and Fuzzy Linguistic Vector: New Concepts for Computational Intelligence

This paper introduces concepts of fuzzy linguistic number (FLN) and fuzzy linguistic vector (FLV). Each FLN contains a linguistic term and a membership degree. A FLV is defined as a tuple of FLNs. Some relevant notions are also proposed, in which, similarity measures for FLNs and FLVs play central contributions of the paper. Then, based on proposed measures, a novel algorithm for classification problem is given. Finally, the rationality of our method is shown by comparative evaluations.

Vu Thi Hue, Hoang Thi Minh Chau, Pham Hong Phong
An Isolated Bipolar Single-Valued Neutrosophic Graphs

In this research paper, we propose the graph of the bipolar single-valued neutrosophic set (BSVNS) model. This graph generalized the graphs of single-valued neutrosophic set models. Several results have been proved on complete and isolated graphs for the BSVNS model. Moreover, an essential and satisfactory condition for the graphs of the BSVNS model to become an isolated graph of the BSVNS model has been demonstrated.

Said Broumi, Assia Bakali, Mohamed Talea, Florentin Smarandache
Enhance Link Prediction in Online Social Networks Using Similarity Metrics, Sampling, and Classification

Link prediction in an online social network aims to determine new interactions among its members which are probably to arise in the near future. The previous researches dealt with the prediction task after calculating similarity scores between nodes in the link graph. New links are then predicted by implementing a supervised method from the scores. However, real-world applications often contain sparse and imbalanced data from the network, which may lead to difficulty in predicting new links. The selection of an appropriate classification method is indeed an important matter. Firstly, this paper proposes several extended metrics to calculate the similarity scores between nodes. Then, we design a new sampling method to make the training and testing data based on the data created by the extended metrics. Lastly, we assess some well-known classification methods namely J48, Weighted SVM, Gboost, Naïve Bayes, Random Forest, Logistics Regressive, and Xgboost in order to choose the best method and equivalent environments for the link prediction problem. A number of open directions to the problem are suggested further.

Pham Minh Chuan, Cu Nguyen Giap, Le Hoang Son, Chintan Bhatt, Tran Dinh Khang
Fuzzy Equivalence on Standard and Rough Neutrosophic Sets and Applications to Clustering Analysis

In this paper, we propose the concept of fuzzy equivalence on standard neutrosophic sets and rough standard neutrosophic sets. We also provide some formulas for fuzzy equivalence on standard neutrosophic sets and rough standard neutrosophic sets. We also apply these formulas for cluster analysis. Numerical examples are illustrated.

Nguyen Xuan Thao, Le Hoang Son, Bui Cong Cuong, Mumtaz Ali, Luong Hong Lan
One Solution for Proving Convergence of Picture Fuzzy Clustering Method

Fuzzy clustering on the picture fuzzy set is widely applied to practical problems. However, the assessment on its convergence has not been considered yet. In this paper, we investigate the theoretical analysis of FC-PFS especially the convergence of the algorithm. Future directions are also discussed.

Pham Huy Thong, Tong Anh Tuan, Nguyen Thi Hong Minh, Le Hoang Son
Bone Segmentation from X-Ray Images: Challenges and Techniques

Identification of the exact location of the fracture regions in the images was done based on the active contour segmentation process. Image segmentation process identifies the regions in the images that contain the interested portions in the images. A process that identifies the fracture location in images lying on the contour extraction process is employed. The contour extraction process identifies the bone regions in the images. Extracted/fracture bone regions are identified using morphological operations and thresholding process. Morphological operations and thresholding process are used for the exact identification of the fracture location. It removes the excess regions segmented in the threading process, i.e., fracture pixels. The fracture location is identified by subtracting the two images resulting in the identification of the fracture region in the images. In this paper, a comparison of different fracture detection algorithms like region growing, level set segmentation, and active contour segmentation (proposed system) is done. Comparison analysis is done in terms of PSNR, accuracy, segmentation time, and detection ratio. Results obtained show the higher accuracy of proposed work over existing algorithm.

Rutvi Shah, Priyanka Sharma
Sparse Coded SIFT Feature-Based Classification for Crater Detection

Morphological classification of impact craters upto now is done through visual interpretation which suffers from high degree of subjectivity. We are proposing a classification approach to classify a given crater into crater or non-crater class. The approach has been implemented and tested on Lunar images. We have also implemented some of the existing approaches like Hough transform, template matching and supervised classification using AdaBoost and found limitations of these. Our proposed framework uses sparse coded SIFT as local features and use SVM as classifier. We have compared this with other classification approaches employing pixels as features; using SIFT as local feature without applying sparse coding; using SIFT + sparse coding but employing KNN. Since SIFT demands huge memory requirement, we suggest a two phase process in which crater candidates are identified and SIFT features are extracted only for these identified areas. This drastically reduces memory and processing requirements. On testing, our approach is found to reduce the memory and time requirements almost to 50% yet outperforming in terms of accuracy as well as robustness against noise, occlusion, different viewing angles, and various illumination effects.

Savita R. Gandhi, Suchit Purohit
eLL: Enhanced Linked List—An Approach for Handwritten Text Segmentation

In document image analysis, the interesting and challenging lie in textline segmentation of handwritten documents. This work emphasizes on developing an enhanced handwritten textline segmentation technique based on the concept of linked list. The proposed system consists of three phases namely preprocessing, enhanced linked list (eLL), and morphology processing. The experiment is evaluated on a document containing handwritten Kannada and English script, and the results are promising.

M. Yashoda, S. K. Niranjan, V. N. Manjunath Aradhya
Intensity Normalization—A Critical Pre-processing Step for Efficient Brain Tumor Segmentation in MR Images

In this paper, we present the pre-processing approaches for MRI brain scans. The magnetic bias field correction of MR images is a preliminary step and the subsequent pre-processing step of intensity normalization of MR images. Both of these pre-processing steps facilitate as promising inputs to the segmentation models, and the promising outputs from these segmentation models aid for better diagnosis and prognosis of diseases. The BRATS 2015 dataset is used in the experimental work; the intensity normalization techniques applied to this dataset yield good results in segmenting the gliomas, thus enhancing the further image analysis pertaining to gliomas.

S. Poornachandra, C. Naveena, Manjunath Aradhya
Indexing-Based Classification: An Approach Toward Classifying Text Documents

This paper proposes an indexing-based classification technique to classify text documents. The most important purpose of this paper is to index the reduced feature set of text documents. To reduce the feature set, this paper uses locality preserving index (LPI) and regularized locality preserving indexing (RLPI) techniques. The reduced feature sets are indexed using B-Tree. Further, the indexed terms are matched with class indices to categorize the known text document. To reveal the efficacy of the proposed model, large experimentations are carried out on standard benchmark datasets. The outcome of the paper reveals that the presented work outperforms the existing methods.

M. S. Maheshan, B. S. Harish, M. B. Revanasiddappa
Network Intrusion Detection Systems Using Neural Networks

With the growth of network activities and data sharing, there is also increased risk of threats and malicious attacks. Intrusion detection refers to the act of successfully identifying and thwarting malicious attacks. Traditionally, the help of network security experts is sought owing to their familiarity with the network technologies and broad knowledge. Recently, data mining techniques have been increasingly adopted to perform network intrusion detection. This paper presents the comparison between multi-layer perceptron and radial basis function networks for designing network intrusion detection system. Multi-layer perceptron proved to be more effective than radial basis function when applied on the benchmark NSL_KDD dataset.

Sireesha Rodda
A Study of the Optimization Techniques for Wireless Sensor Networks (WSNs)

WSN has become one of the important technologies in the present decade. Energy consumption is the major challenge in the field of wireless sensor network. In WSN, there are some hard problems that cannot be solved in deterministic time. These hard problems can be solved by using optimization techniques. Clustering, routing, node localization, maintenance of the nodes, etc., are some of the hard problems that could be addressed. The main aim of these techniques is to provide the solution within specific time and also to minimize the consumption of the energy thus prolonging the lifetime of the network. This paper clearly describes the application of the different published optimization techniques in the field of WSN.

Pritee Parwekar, Sireesha Rodda, Neeharika Kalla
Classification of Hepatitis C Virus Using Case-Based Reasoning (CBR) with Correlation Lift Metric

Hepatitis is a widespread and one of the most dangerous liver diseases, affecting millions of people around the globe. Hepatitis C virus (HCV) may be present in many other body parts; however, its primary target is the liver. In this paper, a diagnosis system based on Case-Based Reasoning (CBR) with correlation lift metric for hepatitis C virus (HCV) is presented. Data mining is an extremely useful technique that can play an important role in the push towards healthcare reform. The proposed algorithm gives an efficient and precautionary way to predict the presence of hepatitis C virus which helps immensely in early diagnosis of the infection.

B. Vikas, D. V. S. Yaswanth, W. Vinay, B. Sridhar Reddy, A. V. H. Saranyu
Software Effort Estimation Using Grey Relational Analysis with K-Means Clustering

Software effort estimation is described as a method of predicting the amount of person/months ratio to build a new system. Effort estimation is calculated in terms of persons involved per month for the completion of a project. During the launch of any new project into the market or in industry, the cost and effort of a new project is estimated. In this context, a numerous models have been developed to measure the effort and cost. This becomes a challenging task for the industries to predict the effort. In the present paper, a novel method is proposed called the Grey Relational Analysis (GRA) for estimating the effort of a particular project by considering the most influenced parameters. To achieve the same, one-way ANOVA and Pearson correlation methods are combined. Experimental results obtained with the help of clustering and without clustering by using the proposed method on the data set are presented. An attempt has been made to show the minimum error rate by using GRA for predicting the effort estimation on COCOMO 81 data set and clustered data set. The proposed method demonstrated better results compared to the traditional techniques used for estimation. The efficiency of the proposed system is illustrated through experimental results.

M. Padmaja, D. Haritha
Application of the Apriori Algorithm for Prediction of Polycystic Ovarian Syndrome (PCOS)

Data mining is a powerful technology having the potential to find practical solutions to problems in diverse fields. The advent of vast information in the medical field has lead to requirement of extracting useful information through data mining techniques. Medical conditions such as the polycystic ovarian syndrome (PCOS) do not have effective diagnosis and proper treatment methods. Unfortunately, PCOS is the most common endocrinal disease which has been, till date, ignored by many. In this paper, an attempt has been made to recognize recurring patterns among symptoms of PCOS patients using frequent itemset mining. The present research also focuses on Apriori algorithm which has been used to predict those who are susceptible to the syndrome.

B. Vikas, B. S. Anuhya, K. Santosh Bhargav, Sipra Sarangi, Manaswini Chilla
A Novel DNA- and PI-Based Key Generating Encryption Algorithm

Effective network security methods are essential for a private communication. In this paper, the authors achieved high security for the data to be transferred using a self-complementing algorithm. They suggested an innovative method for the key generation using a part of the DNA sequence and another part of the very large value of PI. With 3.3 billion combinations of the DNA sequence and infinitely long PI sequence, it makes it difficult for general code-breaking techniques. The values taken are converted into a key using a typical algorithm. Being a symmetric algorithm, the key is used to generate secure text/ciphertext which is shared using standard norms of the industry, ensuring secure transmission of data.

B. Vikas, A. K. Akshay, Sai Pavana Manish Thanneeru, U. M. V. Raghuram, K. Santosh Bhargav
A Sentimental Insight into the 2016 Indian Banknote Demonetization

On the 8 November 2016, the Government of India effectively demonetized banknotes representing the nation’s two largest and most commonly used denominations: Rs. 500 and Rs. 1000. The abrupt nature of the move and the shortage of cash that followed the announcement invited a lot of polarizing opinions from the public. Social media platforms—which have now become an integral part of daily life, saw an unprecedented inflow of opinions, thereby becoming important repositories of people’s views on demonetization. In this paper, an attempt has been made to understand public consensus on demonetization by utilizing data from one such social media platform—Twitter—and performing a sentimental analysis of the tweets. To this end, the R language was employed in combination with the Twitter Web API. A dictionary-based approach was taken towards classifying tweets as either positive, negative, or neutral.

Rajesh Dixit Missula, Shyam Nandan Reddy Uppuluru, Sireesha Rodda
Encryption Model for Sensor Data in Wireless Sensor Networks

Wireless sensor networks have become very prevalent in many industries due to its ease of implementation, high performance, and applicability in numerous areas. The widespread use of this technology brings with it the challenge of providing confidentiality to the data that wireless sensor network carries. The challenge is due to the limitation of resources of energy, memory, and computational power. This paper describes a model for encrypting the sensor data after it is collected by the sink from the sensor. This paper discusses the evolution of the model for encrypting this data from a very simplified scheme with a single key to a more sophisticated scheme which performs dual encryption over the data. The models may implement any symmetric cryptographic scheme with the encryption implemented at the sink and the decryption implemented at the base station.

Anusha Vangala, Pritee Parwekar
A Prototype Model for Resource Provisioning in Cloud Computing Using MapReduce Technique

Cloud Computing is an emerging technology in this digital world. Many organizations are starting using Cloud Computing technology for reducing their expenses. Instead of buying resources, they are renting the resources from Cloud Service Providers (CSPs) as per their need. Thus, Cloud Resource provisioning is a challenging task in the research world. Many researchers have found their own approaches for provisioning the resources in the cloud. This paper explains a new provisioning approach for large applications. It uses MapReduce technique to reduce execution delays in the job. The main aim of this model is to schedule the tasks using MapReduce technique which is a parallel programming model for distributed environment. It will maximize the customer satisfaction level (CSL) by reducing execution delays and implementing cost of Cloud.

Ananthi Sheshasaayee, R. Megala
A Purview of the Impact of Supervised Learning Methodologies on Health Insurance Fraud Detection

A plethora of researches is happening in almost all sectors of insurance to improve the vitality and vibrance of its existence. As years pass, the volume of insurance policy holders increases which is directly proportional to the occurrence of frauds in these sectors. The presence of fraud is always an obstacle to the growth of an insurance organization. This paper confers the various supervised learning methodologies employed in detecting health insurance frauds.

Ananthi Sheshasaayee, Surya Susan Thomas
An Improvised Technique for the Diagnosis of Asthma Disease with the Categorization of Asthma Disease Level

The functioning of the lung tissues will be affected by asthma; the proper treatment needs to be given to the asthma patients to ensure the human’s safety. In the earlier research work, vote-based ensemble classifier approach is utilized for disease diagnosis. Nevertheless, the level of the disease may differ for every patient in terms of different factors like age and environmental situations which might affect the proper treatment. This problem is resolved by presenting the asthma disease finding and level categorization technique (ADF-LCT) which is utilized to detect the various categories of asthma disease level in terms of patient’s health status. In the proposed work, the Bayesian network is utilized to detect the existence of the disease by calculating the probability difference among the asthma genome profile and the input gnome details. Then, the disease level is detected by classifying patient’s health details into three main categories such as low severe asthma (LSA), middle severe asthma (MSA), high severe asthma (HSA), and very high severe asthma (VHSA). The overall research of the work is executed in MATLAB simulation environment by utilizing the genome expression which proved proposed work leads to efficient prediction outcome.

Ananthi Sheshasaayee, L. Prathiba
Analyzing Online Learning Effectiveness for Knowledge Society

In the recent years, there has been rapid development of integrate new technologies into educational processes. Educational system is determined to encourage the use of learning technologies that enhance and offer a successful learning outcome. An e-learning is the process of changing from instructor-interest to learner-interest. In this paper which provides an e-learning strengths, opportunities and also customizing the effectiveness of the learning system in an educational institution. Internet technologies and learning management system (LMS) are the process of communicating and interacting between instructors and students, students with students and instructors with instructors. Finally, this paper shed light on importance of online learning systems and benefits of employing e-learning system in learning perspectives and also proposed a solution to deal with the e-learning and m-learning trends.

Ananthi Sheshasaayee, M. Nazreen Bee
Review on Software-Defined Networking: Architectures and Threats

Software-defined networking offers various benefits to network control and opens new ways of communication by defining powerful and simple switching elements that can use any field of a packet to determine the outgoing port to which it will be forwarded providing efficient formation, edge in performance, security and higher litheness to house inventive network proposals. This paper studies most recent developments in the exploration of software-defined networking through various architectures. Technically, all architectures are very diverse in footings of design, forwarding model, and protocol interfaces. The architectures of software-defined networking with their advantages and flaws have been discussed thoroughly followed by the beneficial provisions of software-defined networking in the field of security and as to why software-defined networking itself needs security, questioning the amount of work and research required in arena.

Sanchita Bhatia, Kanak Nathani, Vishal Sharma
Analytical Comparison of Concurrency Control Techniques

In database management system, there always comes a time where we need to execute various transactions simultaneously, and thus the database consistency must be maintained. The way to make sure that this consistency between the shared databases is maintained is to use concurrency control techniques. Most of the concurrency control techniques are developed using the serializability property in mind. The serializability property makes sure that the accessed data is in the manner of mutual exclusion, meaning that whenever one transaction is accessing a data, other transaction will not be able to access the same data. This paper deals with another viewpoint of various concurrency control techniques, there comparison based on the data obtained practically. Furthermore, a comparison of pessimistic, optimistic, multiversion, and two-phase locking techniques is done. We have set up an environment to analyze the performance and compare these techniques analytically.

Nabeel Zaidi, Himanshu Kaushik, Deepanshu Jain, Raghav Bansal, Praveen Kumar
Inspection of Fault Tolerance in Cloud Environment

Cloud environment is a set of various types of software and hardware that are connected with each other and works collectively to provide various services to the user as an online utility. It basically is the efficient use of hardware and software to work coherently to deliver services. Through the use of cloud computing, users are able to access files from almost anywhere or any device that have access to Internet. We are already familiar with the market of cloud computing, and how everyone is shifting to cloud because of the benefits it provides. But many of them are very less aware about the situations when there comes a failure. The task of facing the failure is not limited to the cloud providers but also to the customers. They must know what can be done when such a situation arises. Fault tolerance is basically a property that makes the system to work properly even though there is a failure. In order to be more robust and dependable, failure should be handled effectively. This paper deals with the Inspection of various fault tolerance technologies that are available. There is no existing algorithm that considers reliability and availability in fault tolerance as well. We tried to consider these things when discussing about fault tolerance. Furthermore, a brief analysis of the already proposed FTC model with some new functionally is also presented.

Deepanshu Jain, Nabeel Zaidi, Raghav Bansal, Praveen Kumar, Tanupriya Choudhury
Analytical Planning and Implementation of Big Data Technology Working at Enterprise Level

Today, a number of technologies are available for building of Big Data architecture deciding which technology will provide the maximum value out of the architecture depending on the extensive study of the present architecture in use, the type of data being ingested, and the desired value expected by the enterprise. In this research paper, we highlight Big Data and its characteristic, Big Data architect, various technologies involved at different levels, pipeline architecture of Big Data architecture, technologies used, planning and designing, and challenges faced while building Big Data architecture at enterprise scale.

Pooja Pant, Praveen Kumar, Irshad Alam, Seema Rawat
A Study of Exposure of IoT Devices in India: Using Shodan Search Engine

As the world is getting digitized and Internet of Things (IoT) devices are becoming more and more popular, this has led us to an advantage of improving our life in perspective of quality. The security threat related to IP is also increasing. But unlike in other technologies, a common way to prevent these threats is not possible. And when it comes to a developing Nation such as India, it becomes more difficult to prevent from such threats. Shodan is one of the world’s most acknowledged search engine. In this paper, we have given an overview of Shodan in perspective of India. Furthermore, we have evaluated various IoT devices using Shodan based on different parameter in India. We have also given our views on how these devices can easily be exploited using Shodan.

Nabeel Zaidi, Himanshu Kaushik, Dhairay Bablani, Raghav Bansal, Praveen Kumar
Real-Time Business Analytical Model Using Big Data Strategies for Telecommunication Industry

The volume of data is growing exponentially. By 2020, about 1.7 MB of new information will be created every second for every human being on the planet. There will also be about 6 billion smartphone users and over 50 billion smart connected devices in the world. The traditional data analysis techniques will not be scalable to match the storage and processing capabilities of such high volume of data. Moreover, it becomes important to analyse these data at real-time speed. Distributed computing and platforms, such as Hadoop, will play a vital role to process these data at real-time speed to provide users with real-time reports to help users to make critical decisions. Telecommunication industry will be one of the first industries that will need to handle big data. Most of the users are connected all the time creating multiple sessions per user as well as communicating with multiple devices creating the complex high volume of data that need to be analysed. This paper will highlight the conceptual design of a real-time business intelligence model that provides insights into the telecommunication industry.

M. Maheswaran, David Asirvatham
Dynamics of Data Mining Algorithms in Diversified Fields

Data mining is a concept which looks for valuable resources as examples from substantial measure of information, i.e., from a large amount of data. The theory or the information in this paper examines few of the data mining procedures, calculations, and a portion of the associations which have adjusted information mining innovation to enhance their organizations and discovered great outcomes. In this paper, it has been centered on assortment of strategies, methodologies, and diverse zones of the examination which are useful and set apart as the essential field of information mining technologies. As per prior knowledge that many MNC’s and vast associations are worked in better places of the distinctive nations. This paper bestows more number of utilizations of the information mining and furthermore o centers extent of the information mining which will accommodating in the further research.

Harshit Sinha, Jyoti Rajput, Achint Kaur, Shubham Baranwal, Tanupriya Choudhury, Soniya Rajput, Kashish Gupta, Gaurav raj
Application of Genetics Using Artificial Immune System Through Computation

One of the key characteristics of the human being insusceptible framework is to spot the nearness of pathogens, and all things considered there are numerous invulnerable calculation and algorithms which perform inconsistency uncovering and example acknowledgment. An extra aspect of the human safe framework is that a fitting effector comeback is created upon the identification of a pathogen “a procedure named the essential reaction. Moreover, the human invulnerable framework can recall the appropriate reaction to a specific pathogen—the auxiliary reaction. The unpredictable coordination of both the essential and optional reactions is profoundly progressive—portrayed in immunological terms as plastic. In this research work in which it will be shown an outline of the correct sections of the era of a T-helper cell essential reaction and the instruments by which it educates optional reactions and talk about how this can be computationally helpful in artificial immune framework advancement.”

Harshit Sinha, Jyoti Rajput, Achint Kaur, Shubham Baranwal, Kashish Gupta, Tanupriya Choudhury, Soniya Rajput
Backmatter
Metadaten
Titel
Information Systems Design and Intelligent Applications
herausgegeben von
Prof. Dr. Vikrant Bhateja
Dr. Bao Le Nguyen
Dr. Nhu Gia Nguyen
Dr. Suresh Chandra Satapathy
Dr. Dac-Nhuong Le
Copyright-Jahr
2018
Verlag
Springer Singapore
Electronic ISBN
978-981-10-7512-4
Print ISBN
978-981-10-7511-7
DOI
https://doi.org/10.1007/978-981-10-7512-4