Skip to main content
main-content

Über dieses Buch

This book features selected papers presented at the 3rd International Conference on Recent Innovations in Computing (ICRIC 2020), held on 20–21 March 2020 at the Central University of Jammu, India, and organized by the university’s Department of Computer Science & Information Technology. It includes the latest research in the areas of software engineering, cloud computing, computer networks and Internet technologies, artificial intelligence, information security, database and distributed computing, and digital India.

Inhaltsverzeichnis

Frontmatter

Advanced Computing

Frontmatter

Performance Analysis of Commodity Server with Freeware Remote Terminal Application in Homogeneous and Heterogeneous Mutli-computing Environments

The technology is bringing new changes rapidly in terms of hardware and software which leads to the increase in the computing cost. One of the prevalent challenges involved in the research endeavors of researchers is to diminish the cost involved in possession of hardware and network technologies. Open source technologies have tried to cut down costs involve at software level, but learning on the software technologies is still a challenge. Commodity hardware utilization is still an option to decrease the hardware level cost. This paper presents the study of the performance of a commodity hardware server in heterogeneous multi-computing environment. Using the commodity hardware of our university and on a client–server-based model, we have developed a system of remote terminal application on a commodity server in homogeneous and heterogeneous multi-computing environments. The nodes used in the current experimental environment are independent of system architecture.

Shamneesh Sharma, Manoj Manuja, Digvijay Puri

Machine Learning-Based Information Retrieval System

The machine learning-based information retrieval model would encourage the user(s) to register on a user platform by authentication of identity information by assigning them a unique membership number. The platform would register the user(s) for a paid membership. The user would be able to search for da keyword(s) or phrase(s) on which the platform would apply auto-correction and clustering of the keyword into the databases would be done. The user would be alerted on his search, and the information would be displayed to the logged-in user, using a plagiarism detection algorithm. This system would come on handy as a tool for efficient search, the results displayed are more to the point and of significant relevance of the keyword or phrase entered by the user. The platform would integrate machine learning-based search giving benefits to students, teachers and scholars as a way of efficient searching protocol.

Manpreet Singh Bajwa, Ravi Rana, Geetanshi Bagga

Web Service Clustering Approaches to Enhance Service Discovery: A Review

Due to the emergence of Internet technologies and service-oriented computing, there is a rapid growth in the quantity and variety of services on the web. Discovering the web services as per the request is not an easy task because of the advancement of service-oriented computing which includes web services, cloud services, mobile services, etc. These services are dynamic and published according to the emerging standards in repositories. Web service clustering plays a crucial role in web service discovery. When services are grouped according to the similarity, then it reduces the search space and time, so that services can be discovered efficiently. Many eminent researchers have proposed approaches for efficient web service discovery by incorporating web service clustering. In this paper, we review different approaches that are proposed for web service clustering to enhance the discovery process. A comparison among existing approaches is carried out based on the vector representation approach, dimensionality reduction technique, method to capture semantic relationship among features, clustering technique, type of input dataset, number of web services in dataset and service repository. This review will help the researchers to understand the existing techniques to group services in similar clusters to improvise service discovery and the scope for improvement by future directions.

Neha Agarwal, Geeta Sikka, Lalit Kumar Awasthi

Path Finding Using PSO Cooperated with Randomized Noise Functions

Path planning is a crucial navigation technology for routing and shortest path problems. The paper discusses a modified approach to the collision-free searching problem using particle swarm optimization incorporated with noise functions like Gaussian and Perlin noise. Aiming at PSO’s shortcoming of quickly diving into local minima, the added random noise functions escape the local minima in the convergence process; hence, look for global convergence maintaining fast speed in the early phase. The random sampling improves the particle update procedure to look for broader search space, which is otherwise constraint to global best of population. This variation guarantees solution space exploitation. Particle position vector precision is improved by adding noise (by some predefined factor), and the PSO algorithm is run to get the best particle as a candidate solution. Particle swarm optimization is a low-overhead and easy to implement the technique. Obstacles are incorporated into the algorithm to improve effectiveness. Particles need to reach the destination without colliding with any of the obstacles. Finally, simulation scenarios demonstrate effectiveness considering multiple target positions.

Aridaman Singh Nandan, Geeta Sikka

A Comparative Study of NoSQL Databases

The need and trend of data record analysis has seen an enormous rise in the past. More and more organizations are realizing the need for a schematic decision making procedure which makes them rely on past data to make future predictions. In this run, the data analysis techniques have also developed along with the advancement of data formats available and now trends are more towards NoSQL (Not Only SQL) type of data stores than the relational ones. This paper explores the types of NoSQL which offer high availability, performance, and eventual concurrency applications but losing the ACID properties of the traditional databases. The authors discuss various data stores in brief and also compare these data stores based on different aspects.

Simmi Bagga, Anil Sharma

SMT Versus NMT: An Experiment with Punjabi–English

In this paper, a comparison of the Statistical machine translation (SMT) and neural machine translation (NMT) for Punjabi to English in the fixed domain of health and tourism is provided. We have tried to answer does NMT perform equivalent well or better with respect to the SMT system? We have developed the three base models viz., SMT-based model using the Moses toolkit, followed by long short-term memory (LSTM) model and bidirectional LSTM model using the OpenNMT toolkit. All three models used the Punjabi–English parallel corpus of TDIL health and tourism. Finally, the quality of translation is validated using the automatic parameter like the BLEU score and the TER score. We observed that bidirectional LSTM performs better than simple LSTM an SMT system.

Kamal Deep, Ajit Kumar, Vishal Goyal

Performance Enhancement of MIMO Configurations in FSO System Under Different Weather Conditions

Free-space optics (FSO) is an optical wireless communication technique in which free space (air, outer space or vacuum) acts as a medium between transceivers, and for the effective transmission of the optical signal, line of sight (LOS) is necessary between the transceivers. FSO works as same as in optical fiber communication but in this optical beam propagates over free space rather than cores of fiber. FSO communication is also known as terahertz communication and optical wireless communication (OWC). Weather condition (clear air, haze and fog) is one of the main impairments affecting free-space optical communication. In this simulation model under different weather conditions such as clear air, haze and fog, the two systems MIMO-FSO (4 × 4) and MIMO-FSO (8 × 8) have been analyzed. Free-space optics emerged as one of the various merits over the radio spectrum. FSO can achieve high capacity with huge unlicensed optical spectrum and less operational costs and the MIMO technique in wireless communication systems is widely used because it provides huge data throughput and increased link range without the addition of neither bandwidth nor transmitted power. To bring out results under different weather conditions (clear air, haze and fog), simulation model has been analyzed for an array of 1 km at the frequency of 193.1 GHz. The parameters of the MIMO-FSO system, i.e., Q-factor and BER, have been analyzed for MIMO-FSO (4 × 4) and MIMO-FSO (8 × 8). In this, we analyze the difference between the two MIMO-FSO (4 × 4) and MIMO-FSO (8 × 8) system and this shows that 8 × 8 MIMO-FSO has better performance to the 4 × 4 MIMO-FSO system in different weather conditions.

Arjun Dubey, Harmeet Singh

A Low-Power Hara Inductor-Based Differential Ring Voltage-Controlled Oscillator

The most important component needed for all wireless and communication systems is the voltage-controlled oscillator (VCO). In this paper, a four-stage low-power differential ring voltage-controlled oscillator (DRVCO) is presented. The proposed DRVCO is designed using new differential delay cell with dual delay path and Hara inductor to obtain a high frequency VCO with low-power consumption. Results have been obtained at supply voltage of 1.8 V using 0.18 µm TSMC complementary metal oxide semiconductor (CMOS) process. The tuning range for the proposed VCO varies from 4.6 to 5.5 GHz. This low-power VCO has a power consumption of about 5–10 mW over a control voltage variation of 0.1–1.0 V. The proposed VCO circuit at an offset frequency of 1 MHz achieves a phase noise of −67.9966 dBc/Hz. The figure of merit of proposed circuit is −135 dBc/Hz.

Misbah Manzoor Kiloo, Vikram Singh, Mrinalini Gupta

Design and Simulation of Optimum Digital Filter for Removal of Power Line Interference Noise

The optimal digital filter design emerged as one of the key research issues from the past few years in biomedical engineering field. Digital filters are designed to preprocess the raw biomedical signal and extract useful information from them. Generally, all the biomedical signals are corrupted from the power line interference (PLI) noise. In this research work, an optimal and stable notch filter is designed for the elimination of PLI noise. The entire simulations were carried out using LabVIEW, and the results are validated using MATLAB. After analyzing theoretically and experimentally, it is inferred that window techniques perform better as compared to the existing filter designing techniques. The Kaiser window function gives better performance as compared to other traditional window techniques due to its sharp lobe that helps in reduction of PLI noise. Additionally, to mark the effectiveness of the selected window function, various parameters like effect of order, threshold frequencies, and side lobe attenuation are analyzed and compared.

Shruti Jain, Manasvi Kashyap, Mohit Garg, Shailu Srivastava

Centralized Blood Bank Database and Management System

A blood bank is a place where blood is collected and stored to be used by other individuals who need them either due to health emergencies or blood shortages. Blood banks are scattered all over places and not easily assessable to donors and patients who need them. So, it is important to have an organized database to help in allowing donors easily locate the nearest blood banks and donate blood, and also to make patients easily access blood when they need them within the shortest possible time. The aim of this research is to build a feasible system to help in the efficient management of blood bank activities and also provide easy platforms for patients to easily access blood during emergencies. This app would be built on the android platform connected with a secured online cloud-based database to keep the patients, donors and blood banks’ details safe. This is an efficient management system for blood banks as their strenuous process is now being made easy using technology.

Osunlana Ismail, Sanjay Misra, Jonathan Oluranti, Ravin Ahuja

Effect of Supercapacitor on Power Supply for Rechargeable Implanted Medical Devices

The need for medical devices to be planted into living organisms to perform the function of a dysfunctional body part is increasing by the day. Most of these devices require power supply of some sort to function appropriately. The supply can be taken care of by batteries but the batteries have a life span which will never be long enough, especially if the implant is in a human. This will mean that every time the battery dies the device will have to be brought out and the batteries changed. This paper seeks to explore the existing energy storage capacities for a wireless setup. The addition of a supercapacitor to the battery or replacement in the power pack was simulated and analyzed. Then, a proffered solution which is introducing a microcontroller to determine the switching between battery and super capacitor was proposed. Also some level of communication and control of the implant by the external circuit through the capacitor.

Attah Amarachi Rita, Sanjay Misra, Ravin Ahuja, Jonathan Oluranti

Intelligent Networking

Frontmatter

Particle Swarm Optimization and Genetic Mutation Based Routing Technique for IoT-Based Homogeneous Software-Defined WSNs

Recent advancement in wireless sensor network has evolved as an open system which can be reconfigured dynamically. Generally, these networks have different limitations and challenges such as energy consumption in data collection, control node election, load balancing, etc. An efficient load balancing in terms of data collection and forwarding is depended on the routing techniques which are responsible to provide an effective path to transmit the collected data such that the minimum amount of energy should be consumed in the process. The control nodes are responsible for assigning the task and data transmission in the cluster-based routing techniques. The selection of the control node is an NP-hard problem. In this paper, an adaptive particle swarm optimization (PSO) ensemble with genetic mutation-based routing is introduced to select control nodes for IOT-based software-defined WSN. The proposed method plays a significant role in selecting the control nodes based on the fitness value. Fitness value takes energy and distance parameters into consideration. First, the proposed work is implemented for homogeneous nodes that can be deployed with single and multiple sinks. Further, the proposed work can also implement for the heterogeneous sensor nodes having different computing power accompanied by single and multiple sinks. The simulation result of the proposed method outperforms over some other existing algorithms under the different arrangements of the network.

Rohit Ramteke, Samayveer Singh

Defining and Evaluating Network Communities Based on Ground-Truth in Online Social Networks

A social network is a cluster or aggregation of vertices such as persons or social entities, and edges which are used to depict personal relationship between these nodes. Social networks have a noteworthy role in the movement of data, and social network exploration has gained a focus in research. The analysis of these social networks has resulted into uncovering of variety of communities in the network. The main objective of uncovering the structure of a community is to break the network into dense areas of the graph, and these dense areas represent entities which are related closely and hence they belong to a community. Plentiful algorithms have been suggested and recommended, and surveys have been conducted currently. In this manuscript, we will discuss numerous strategies for uncovering the structure of communities and techniques which have been suggested so far. We will divide these algorithms into several categories. These categories correspond to traditional approach of community detection, overlapping community detection, established clustering techniques for uncovering the structure of communities, nonclique-based techniques for uncovering the structure of communities, community detection using genetic algorithms, improved modularity approach for uncovering the structure of communities and so forth. We will start by discussing and understanding several metrics which can be used to ascertain the structure and hence the quality of communities. We will also compare all these community detection algorithms based on approaches used, along with parameters these algorithms depend on.

Sanjeev Dhawan, Kulvinder Singh, Amit Batra

Microstrip Patch Antenna with Truncated Edges for Bandwidth Improvement for Wireless Applications

In the research article, microstrip patch antenna with truncated edges is designed. Truncated technique is used for bandwidth improvement. Antenna is fabricated using Rogers RT Duroid (5880) substrate with h = 1.6 mm and dielectric constant of 2.2, loss tangent 0.0009. Microstrip feed line used to excite patch. Antenna overall size is 12 × 35 mm. Proposed antenna simulation is carried out using HFSS antenna simulation software, and performance is analyzed using antenna parameter like return loss (S11), VSWR, radiation pattern, Bandwidth, and Gain.

Amandeep Kaur, Praveen Kumar Malik

A Deep Network Model for Paraphrase Detection in Punjabi

Paraphrase refers to the text which tells the same meanings but with different expressions. It is important in NLP as it deals with many applications such as information retrieval, information extraction, machine translation, query expansion, question answering, summarization and plagiarism. Paraphrase detection is to find that given two texts are semantically similar or not similar. Though paraphrase detection has wide literature, there is no proper algorithm for paraphrase detection in Punjabi language. A new paraphrase detection model for Punjabi language is developed in this paper. We use two deep learning methods to map sentences as vectors, and these vectors are further used to detect paraphrases. Despite other implementations of paraphrase detection, our model is simple and efficient to detect paraphrases. Qualitative and quantitative evaluations prove the efficiency of the model and can be applied to various NLP applications. The proposed model is trained on Quora’s question pair dataset which makes new directions for paraphrasing in Indian languages.

Arwinder Singh, Gurpreet Singh Josan

Design and Development of Software and Hardware Modules of Bioimpedance System Using LTSpice

One of the crucial components of each bioimpedance measuring device is a constant current source. Finite element numerical device simulation was used to analyze track to track capacitances and compared to measurements on developed PCB with soldering elements. Here, we present an analysis based on a modified circuit of a single constant current source. Finite element numerical system simulation was used to evaluate track to track capacitances and compared to measurements on built PCB without soldering elements. One of the most important components of the bioelectric impedance devices and Bio-Electrical Impedance Analyzer (BIA) is the current source circuit. There are many types of circuits, such as current source, enhanced current source, general impedance convertor, Wien bridge circuit, voltage pick-up amplifier. This paper presents the modules of bioimpedance creation of software.

K. M. Brajesh, Kirti Pal, Munna Khan

Investigations on Various Designs of Dielectric Resonator Antennas (DRA) for C Band Applications

The overall growth of wireless communication is going on at such a rapid pace that a lot has been going on day to day basis leading to a number of changes in antenna designs to make their performance as per the required parameters. In this communication, various dielectric resonator antenna designs and their performance parameters like size, shape, feeding mechanism, bandwidth, substrate material and peak gain are discussed in the C band. DRA antenna has emerged as a good option in the microwave and millimeter frequency range due to the use of low loss dielectric material which reduces surface wave losses and metallic losses and in turn increases antenna efficiency. DRA due to its advantages like small size, wider bandwidth, much better efficiency, higher dielectric strength, low profile, higher power handling capacity, easy fabrication and low cost is widely used antenna.

Dishant Khosla, Kulwinder Singh Malhi

Planar Rectangular Micro-strip Patch Antenna Design for 25 GHz

The research article demonstrates the unconstrained optimization of planer rectangular micro-strip patch antenna for 5G communications. Proper dimensions of the antenna were adhering as per the accord and analogy of theoretical concept and adapted. The proposed antenna design is for the operation of the 5G band, especially at 25 GHz. The design of the antenna and its simulation are done on antenna simulation software and are optimized to have better return loss, transmission efficiency, directivity, and gain. For the entire band of operation of frequency as keen obtained results from the simulation are found close agreement with those obtained theoretically is unprecedented.

Amandeep Kaur, Praveen Kumar Malik, Ramendra Singh

Intelligent Opportunistic Routing Protocol in Wireless Sensor Networks: A Security Perspective

Wireless sensor networks (WSNs) applications have grown huge in the recent years. WSN is very popular due to its abilities to record, process, and transmit data related to various parameters of the environment. Due to WSN inherent nature, these networks are vulnerable to various types of attacks, especially at the network layer of the protocol stack in WSN. In this paper, an analysis about different security threats w.r.t different layers of the protocol stack using opportunistic routing (OR) is presented. The wireless nature and broadcast feature of WSN cause many attacks in the network layer and security of the transmitted data becomes an important issue. Different machine learning (ML) techniques are used for solving various security issues of the WSN. Also, in this paper, we focus on the analysis of different ML methods used for detection of security related attacks on the routing process in WSN.

Deep Kumar Bangotra, Yashwant Singh, Arvind Selwal

OSEP: An Optimized Stable Election Protocol in Heterogeneous Wireless Sensor Networks

The wireless sensor networks (WSNs) are attracting researchers because of their extensive variety of applications in different aspects. They perform monitoring responsibility in all kinds of the environment including harsh environments. Thus, a stable network is required for gathering data for a long duration from the monitoring areas. This constancy of the networks depends on the load balancing among the deployed nodes. The stability of networks can be enlarged by the clustering which executes a commanding role in the effective exploitation of energy degeneracy of their batteries and assistances in extending the network lifespan. The communication among the nodes and sink is consumed the highest energy which requires a procedure that can decrease the communication cost. In this paper, we deliberate an enhanced stable election protocol for improving the lifecycle of the heterogeneous WSNs. In the optimization of SEP protocol, three parameters are considered for effective cluster heads selection, namely the nodes remaining energy, node distance from the base station, and total network energy. In this methodology, a threshold-based formula is proposed which considers a different type of energies of the networks such as current energy of the networks, and preliminary and residual energy of the nodes which provides even load balancing. The proposed method contributes a dynamic clustering to lowering energy consumption and avoiding the load over the cluster heads. The number of active and dead, the sum of energy depletion, and the number of messages transferred to the control node matrices are considered to examine the enactment of the proposed scheme by using the MATLAB. After comprehensive analysis, it has been evident that the projected scheme accomplishes superior to that of the existing methods.

Samayveer Singh, Pradeep Kumar Singh, Aruna Malik

Bot Detection in Social Networks Using Stacked Generalization Ensemble

In recent times, the reach and influence of social media have grown tremendously across the entire globe. The ease of access, simplicity, publicity and reach offered by giant social networking sites have come to hold immense value nowadays. However, this has led to the widespread use of fake accounts or programmed bots in order to inflate one’s social media popularity and further spread favourable content. Many recent studies have highlighted the impact of such bots in fields like advertising, commercial promotion and even elections. In this paper, we propose a method to detect bots on social networking sites and distinguish them from genuine user accounts by using a stacked learning approach whereby a convolutional neural network model is trained to feed forward to a machine learning model. This is achieved by using a supervised learning approach to build a layered classifier that makes predictions based on a user’s profile information, tweets and activity information from a dataset of Twitter users. Our paper also analyses the comparative performance of many machine learning models applied to this problem.

Rahul Katarya, Raghav Mehta, Ryan Bansal, Pradyot Raina, Mukul Mahaliyan

Internet of Things (IoT): Vulnerabilities and Remediation Strategies

Iot being a transformative approach for imparting countless services raises consequential security flaws as well. These flaws germinate from the embedded vulnerabilities in IoT devices. The market is flooded with these vulnerable smart devices, which are easy to play with to remotely enter into an IoT system. This becomes more serious as communication protocols and Internet technologies were not devised to support IoT. In this paper, we mainly focus on the evolving vulnerabilities in IoT that can affect its sustenance in the long run. We also elaborated on the remediation strategies to be incorporated to lessen the fertility of the ground to launch numerous attacks. Finally, we conclude with the challenges and recommendations.

Pooja Anand, Yashwant Singh, Arvind Selwal

DACHE: A Data Aggregation-Based Effective and Optimized Cluster Head Election Routing Protocol for HWSNs

Most of the wireless sensor networks (WSNs) are having intrinsic resource limitations such as energy, link, and computational resources since energy is consumed by all the resources. Thus, there is a dare need to develop energy-efficient protocols that escalate the longevity of the network for collecting data over a long time. In this work, we propose a data aggregation-based effective and optimized CHs election routing protocol for heterogeneous WSNs. These networks consist of three levels of heterogeneity. In this method, a threshold-based formula is used which helps in optimized cluster heads (CHs) election. A new chain-based data aggregation process is also discussed in this paper which helps in the effective data gathering process. This threshold formula considered three criteria namely node and sink distance, node remaining energy, and total networks energy which decreases the energy depletion in both inter and intra communication between the sensor, CHs, and sink. This efficient data gathering process also removes the duplicate at the time of data collection from the deployed nodes and reduced the energy depletion and network overheads. The number of alive and dead, the sum of energy depletion, and a number of the message transferred to the control node matrices are considered to investigate the enactment of the proposed scheme by using the MATLAB. After a comprehensive analysis, it has been evident that the proposed method accomplishes healthier than that of the existing methods.

Aruna Malik, Samayveer Singh, Pradeep Kumar Singh

Image Processing and Computer Vision

Frontmatter

A Hybrid Approach with Intrinsic Feature-Based Android Malware Detection Using LDA and Machine Learning

World is becoming small with the increase in the number of mobile phone users. The most influential and having huge market among mobile phones is android. Android is a software used in nowadays smart phones, which not only consists of operating system but also myriad number of key applications. These applications make large number of day to day tasks easy. There are millions of android applications in the market with over 3 billion or more downloads. The growing market of this platform not only invites smart phone users, but it also becomes a point of interest for black hat hackers. Hackers use this technology for large number of activities by spreading the android applications in this platform which are not actually android packages rather malicious codes or malware. Therefore, these malwares must be handled in a smart way; otherwise, they lead to huge loss. Different techniques have been used for detection of android malware which consists of network traffic analysis, static analysis, and dynamic analysis. In this paper, a combined approach of static, dynamic, and intrinsic features for android malware detection using k-nearest neighbor (k-NN), random forest, decision tree, SVM, and ensemble learning techniques. The calculation uses a publicly available dataset of Androtrack. The estimation results shows that both the decision tree and random forest classifiers produced accuracy of 99%. With the help of newly added feature and a different approach of preprocessing, i.e., linear discriminant analysis.

Bilal Ahmad Mantoo

Towards Recognition of Normal Versus Pneumonia Infected Patients Using Deep Neural Network Technique

Pneumonia disease treatment, mostly death records can be found in hospitals due to not early diagnosis or detection of disease in the world, which is of great concern. In this article, the radiological chest X-ray images dataset from the Kaggle website which includes various sample images was used here for classification purposes. Deep convolutional neural network approach was used for binary classification. In this technique, a pre-trained convolutional neural network model ResNet50 was used for extracting the features, then fine-tuned or using transfer learning via chest X-ray images for classification. In this research, three optimization algorithms named stochastic gradient descent (SGD), Adam, and Rmsprop were used. The uppermost prediction accuracy of the Adam with ResNet50 was achieved 99.34% and validated on the training ratio of 80:20. The Adam algorithm outperformed others in the prediction accuracy. The proposed deep learning model exhibited outstanding performance in predicting pneumonia from the X-ray image and could aid in better diagnosis of patients.

Deepak Kumar, Chaman Verma

Edge Detection Using Guided Image Filtering and Ant Colony Optimization

Edge detection is an important phenomenon in various classes of engineering problems. The classical methods which are based on the kernel designs are not very accurate and edges are falsely detected. Recent methods which are based on soft computing are adaptive in nature, and therefore using soft computing methods accuracy of detected edges can be improved. This paper presents an ant colony optimization-based edge detection process, and where edges are enhanced using guided filtering. The simulation results clearly show that the proposed scheme is much superior to recently proposed edge detection methods.

Akshi Kumar, Sahil Raheja

A-VQA: Attention Based Visual Question Answering Technique for Handling Improper Count of Occluded Object

Recently, visual question answering (VQA) system is being used in various research disciplines for extracting meaningful data from images and communicating this meaningful data to humans. Thus, to implement VQA system, computer vision and natural language processing fields are combined. Existing VQA system contains many open research issues such as improper count of occluded object problem, single word answer, time-specific answer problem and many more problems because of its wide assortment of utilizations and its more extensive region of research. In this paper, we present attention-based visual question answering (A-VQA) method for handling improper count of occluded object. A-VQA systems generate the textual answer by extracting image and textual features and applying multi-layer attention mechanism on these images and textual features. A-VQA system handle object recognition, counting, color and activity recognition types of visual questions. For training and evaluating A-VQA method, visual genome dataset is used.

Shivangi Modi, Dhatri Pandya

Wireless Sensing with Radio Frequency Identification (RFID): Instrumental in Intelligent Tracking

Currently, all technologies and associated applications based on Internet of things (IoT) facilitate the user mobility and likely to contribute immensely in all future mobile applications. Radio frequency identifications (RFIDs) along with wireless sensor networks (WSNs) have potential to offer a great value addition on IoT platforms. Intelligent RFID tags powered through independent energy sources when attached to an object and networked through a wireless link allow seamless integration of some of the physical parameters like humidity and temperature in addition to their location data with the user information system on the IoT [1]. This paper provides a brief insight of the RFID technology with its sensing capabilities. It reviews design considerations of RFID-driven wireless sensors from their implementation perspective. It has primarily focused on intelligent operational logistics and its monitoring which have tremendous potential for both civil and defence logistic applications. A two-layer data networked architecture of RFID has been introduced over IoT platform in the proposal which is comprised of an asymmetric RFID tag-reader connectivity along with the interconnected RFID readers linked through the Wi-Fi or cellular networks [2]. This paper also discusses that how ultra wide band (UWB) RFID is considered today as a promising technique for cost-effective wireless sensing and ultra-low power mobile applications.

Praveen Kumar Singh, Neeraj Kumar, Bineet Kumar Gupta

Impact of Distortions on the Performance of Feature Extraction and Matching Techniques

An image feature, such as edges and interest points, provides rich information on the image content and plays an important role in the area of image processing. These correspond to local regions in the image and are fundamental in many applications in image analysis. Raw data are complex and difficult to process without extracting or selecting appropriate features in advance. Feature extraction, a data reduction technique, is the transformation of large input data into a low-dimensional feature vector. It lowers the computational cost and also helps in controlling the issue of dimensionality. There are different methods of exacting features from an image and these techniques have different domains of applications. In this paper, four widely used feature detection algorithms, Harris, SURF, FAST, and BRISK feature detection algorithms are compared in terms of accuracy and time complexity for extraction and matching of feature points correctly. For this purpose, different types of transformations are added to the original images for computing the evaluating parameters like the number of features detected, matched features, and execution time required by each algorithm. Experimental results show that SURF performs better than other feature extractions and matching algorithms in terms of accuracy and run time.

Richha Sharma, Pawanesh Abrol

Realization of a Robust Watermarking System in Spatial Domain

In this paper, we have proposed a watermarking system that is based on the spatial domain and is blind and robust in nature. This scheme is developed to withstand most of the image processing attacks. The watermark has been embedded in the cover image by modification of the DC coefficients calculated in the spatial domain. This method directly calculates DC coefficients in the spatial domain. The values of pixels can be changed/modified in the spatial domain in accordance with available watermark information. Since we have avoided the time-consuming transform operation, i.e., Discrete Cosine Transform, the computational efficiency is very high. For embedding a watermark bit, a particular image is disintegrated into 8 × 8 blocks, followed by further division of each block into two 4 × 4 blocks. After calculation of the DC coefficient of each 4 × 4 block, the watermark bit is embedded by modifying the DC values such that the DC coefficient of one block becomes greater than the other. The output results prove our proposed technique is highly robust to commonly occurring signal processing attacks. Experimental results obtained against numerous signal processing attacks are represented in terms of quality measuring parameters like PSNR, SSIM, and BER to check the efficiency and execution of our scheme.

Ishrat Qureshi, Shabir A. Parah, Nazir A. Lone, Nasir Hurrah, G. J. Qureshi

Investigations on Mathematical Modeling of Imaging Infrared (IIR) Missile

The IIR is the most advanced technology and the design is applicable to many missiles which are projected to exist in the next decade. Infrared technology has replaced the radar-guided missiles. The missile guidance system based on infrared technology or the IIR seekers does not provide any indication that they are tracking the missile and therefore called as passive devices. It has become very necessary to study the defense strategy related to Infrared technology. The effectiveness of the overall missile system is determined by the individual components and the key parameters that describe them. The design equations corresponding to the efficiency of different components used in the substems are discussed. The IIR seeker is a very critical element used in the guidance system of the missiles. Many disciplines related to the IIR missile such as signal processing, optics, microelectronics, manufacturing, and stabilization are integrated together and are discussed in the paper.

Rahul Kakkar, Sohni Singh, Joginder Singh, Sumeet Goyal, Dishant Khosla, Manvinder Sharma

Recommendation Systems Based on Collaborative Filtering Using Autoencoders: Issues and Opportunities

With the advancement of deep-learning-based approaches, complex problems under Artificial Intelligence can now be addressed in a comparatively easier way. One such application domain is Recommendation Systems. Recommendation systems are powerful tools in this age of data explosion for providing meaningful insights from data. Collaborative Filtering is one of the popular approaches for building recommendation systems and extensive literary works suggest that it is very effective. In recent years deep-learning-based models have been bounteously applied for the development of recommendation systems using collaborative filtering. Autoencoders are a deep-learning based neural architecture which can be used for implementing collaborative filtering. This paper presents a survey of different autoencoder based models which employ collaborative filtering methodology for making recommendation systems. The paper initially provides an understanding of models and thereafter summarizes various works reported in the literature in the light of the methodology used, taxonomy, datasets used for experimentation, limitations and results reported.

Ria Banerjee, Preeti Kathiria, Deepika Shukla

An Algorithm to Recognize and Classify Circular Objects from Image on Basis of Their Radius

For the computer vision, fast and accurate detection of an object is challenging. Detecting a circular object in a cluttered image has always been a problem. Circular object detections has wide applications in the field of biometrics, automobile and other mechanical production industries. The traditional existing circular object detection are maximum likelihood estimation (MLE) and voting-based methods. The voting based methods have high memory requirements and more computational complexity while these are less sensitive to noise. MLE approach consumes less memory and are efficient in terms of computational complexity but these approaches are more prone to noise. This paper proposes modified Hough transform based algorithm for detection of circular objects within other shaped objects also it can identify circular objects on basis of diameter. The proposed algorithm worked efficiently and detected the circular objects on basis of diameters with very less computational time and less memory consumption.

Bhim Sain Singla, Manvinder Sharma, Anuj Kumar Gupta, Vandana Mohindru, Sunil Kumar Chawla

A Systematic Review on Various Techniques on Image Segmentation

In the present situation, image processing is one of the huge developing fields. It is a strategy which is ordinarily used to improve raw image which is collected from different assets. It is a sort of sign processing. The image segmentation is considered one of the most essential processes in the production of images. Some of these methods use only the histogram of the gray scale, some use spatial information, while others use conceptual approaches of the fuzzy set. In noisy environments, these methods are not appropriate. Some work has been done using the method of MRF, which is robust to noise but involves computing. This paper gives an outline of image processing techniques. The fundamental concern of this paper is to characterize different methods utilized in various periods of image processing.

Diksha Thakur, Nitin Mittal, Saumya Srivastava

On Performance Analysis of Biometric Methods for Secure Human Recognition

In recent years, the necessity of secure and reliable human identification has led to increasingly fast growth in development and demand of biometric systems. Human recognition is the technique for identifying the person using their biological, chemical, and behavioral characteristics. Biometric system is a computer-based automatic system to establish identity of the users by using their biological and physiological traits. The most popular traits in modern applications are biological aspects of the prospective user for identification. Although using chemical traits of the human for identification is more accurate and reliable, but these are very difficult to achieve. In this paper, performance of automatic human recognition system is presented based on various parameters like users psychology, easiness of use, security, reliability, and market share. Furthermore, various analysis and comparison of different notable biometric techniques are discussed in tabular format. It has been observed that these systems provide authentication and recognition but security of these systems at template level is also one of the challenges for designers.

Annu Sharma, Shwetank Arya, Praveena Chaturvedi

Automatic System for Text Detection and Localization Using Cellular Automata

The cellular automata are a discrete and abstract way of representing dynamic model which change state based on some relationship with other members in the system. These patterns are used to map an object within the image. The present research used the cellular automata-based system to detect the text region in the natural seen image. Automatic text detection is gaining attention day by day due to its versatile range of applications. The present research used cellular automata to develop a system to detect Gurmukhi text in the natural scene images. The natural scene may contain signboard images, text on banners, text written on walls and text viable on any vehicle. The Gurmukhi script has its own set of unique features which helps to classifier to recognize. The efficiency of the text recognition heavily depends on the text extracted from the images. An algorithm was developed to detect and localize the text (in the present study, only Gurmukhi script is considered for study) in the natural scene images. In absence of benchmark dataset of natural scene images, we have developed our own dataset to test the efficiency of the system. The system was tested with well-known matrices named as recall metric, precision metric and P-value.

Sukhdev Singh, Monika Pathak

Obstacle Avoidance in Robot Navigation Using Two-Sample T-Test-Based Obstacle Recognition

In this paper, a solution to the obstacle avoidance problem in autonomous robot navigation is presented using two-sample t-test. A procedure to perform t-test on two-independent LASER scan distance-range vectors is provided. The proposed strategy compares the LASER scan readings of the obstacles in the navigation path. Similarity of the obstacles is recognized on the basis of the acceptance of the null-hypothesis. Robot navigation results are simulated using Turtlebot-Gazebo simulator and MATLAB software. A discussion is made on the results produced using the proposed strategy with the previously existing results in the literature.

Neerendra Kumar, Zoltán Vámossy

On Data-Driven Approaches for Presentation Attack Detection in Iris Recognition Systems

With the development of modern machine learning-based techniques for accurate and efficient classification, the paradigm has shifted to automatic intelligent-based methods. The iris recognition systems constitute one of the most reliable human authentication infrastructures in contemporary computing applications. However, the vulnerability of these systems is a major challenge due to a variety of presentation attacks which degrades their reliability when adopted in real-life applications. Hence, to combat the iris presentation attacks, an additional process called as presentation attack detection mechanism is integrated within the iris recognition systems. In this paper, a review of the modern intelligent approaches for iris presentation attack detection (PAD) mechanisms is presented with a special focus on the data-driven approaches. The presented study shows that the machine learning-based approaches provides better classification accuracy as compared to conventional iris PAD techniques. However, one of the open research challenge is to design the robust intelligent iris PAD frameworks with cross-sensor and cross-database testing capabilities.

Deepika Sharma, Arvind Selwal

Anomaly Detection and Qualitative Analysis of Diseases in Tomato

Disease detection in the crops is a difficult work as crops get affected due to various attacks from different bacteria, fungi and viruses. The disease symptoms on the infected crop plant can be seen as usually color change, circular spots, specks and hollow areas having concentric rings. This paper proposes a solution for identification of crop diseases (i.e., bacterial and fungal diseases) in tomato cash crop of Himachal Pradesh. Detecting the disease at an early stage enables the farmers to act and treat the plants at the appropriate time and effectively. Accurate and timely detection of plant diseases can help mitigate the agriculture loss experienced by the local farmers. An initial evaluation system and statistical analysis proposed in this work show a positive impact. The dataset has been created by the authors by collecting real-time pictures from various fields of Himachal Pradesh state which contains images with different diseases for tomato plant. The proposed approach provides efficient result that can lead to connection between farmers and agriculturists.

Meenakshi Sood, Anjna, Pradeep Kumar Singh

To Study the Effect of Varying Camera Parameters in the Process of Matching and Reconstruction

In computer vision, there are many methods of reconstructing the image point. 3D reconstruction from digital image sequence of scene or object is a difficult and important task in computer vision. However, such a reconstruction requires a large computational effort for finding the point of correspondence between different views. Furthermore, the accuracy should not be reduced in case of noisy data. There is one important technique to digitization of physical object which is binocular stereo vision. From two subsequent digital images of the physical object taken from different viewpoints, we can make a 3D virtual model for the physical object by using this approach. Basically, the common processes for binocular stereo vision comprise digital image acquisition, camera’s calibration, feature point extractions, feature points matching and 3D reconstructions. In this paper, we have discussed the problem of varying camera parameter in the process of matching and reconstruction. we have the studied the problem and how it affects when the camera parameter varies in the process of matching; two types of parameter are as follows: intrinsic parameter and extrinsic parameter; image setup and some equation help to set the parameter, and a robust algorithm is proposed for reconstructing free-form space.

Anuj Kumar, Naveen Kumar, Rakesh Kumar Saini

E-Learning Cloud and Big Data

Frontmatter

Loop Holes in Cookies and Their Technical Solutions for Web Developers

Session hijacking is the term used to describe the theft of session cookies, i.e., sniff the cookies and use those to impersonate the end user. A cookie is a small-sized text file sent by the Web server to the user’s browser and is store at the client side. When a user visits a Web site first time, the Web server generates a fresh cookie. The Web site uses that cookie to track the movements of an authorized user. Main threats of cookies are session fixation attack, cross-site scripting (XXS) attack, session sniffing attack, cookies cloning attack, and cookies controlling malware. The hacker sniffs the network traffic for cookies and uses same to impersonate the user. With performing session hijacking attack, the attacker acts as actual user on Web. In this paper, we are going to discuss some of the technique that helps in optimizing the cookie attacks in Web applications.

Talwinder Singh, Bilal Ahmad Mantoo

Fog Computing Enabled Healthcare 4.0

Industry 4.0 has revolutionized the utilization of information technology (IT) in the contemporary scenario. Different disruptive technologies have imparted their contribution in the success of Industry 4.0. In the transition from Industry 1.0 to 4.0, the ideas from mechanical to electrical engineering, from electrical to telecommunication and information technology and then artificial intelligence have switched abruptly. Artificial intelligence (AI), big data analytics (BDA) and machine learning (ML) contributed its leading role. The competence of artificial intelligence brings machine at the capability to handle the human health issues. In Healthcare 4.0, the whole efforts are to resolve the multi-dimensional problems of treatments faced in daily life. Healthcare 4.0 is the rebellion paradigm where hospital-centric environment, artificial intelligence and computing resources are integrated to provide the real-time treatment to patients. The fog computing can play the major role for real-time treatment. This paper illustrates the applicability of fog computing in Healthcare 4.0 and the transition of hospital-centric healthcare (HCH) system to patient-centric care (PCC). The solution for tracking health record is also proposed in this paper by analysing the case study of diabetic patient in India.

Shaheen Parveen, Pawan Singh, Deepak Arora

DAMS: Dynamic Association for View Materialization Based on Rule Mining Scheme

In data warehousing, view selection (VS) is an important aspect. Optimal VS needs to be materialized in order to minimize the overall data retrieval time. To support the same, performance metrics like memory constraints to save materialized views, query execution time, and query workloads needs to be addressed to reduce the overall retrieval time. As far as static view materialization (VM) is concerned, pre-computing strategies are required to execute the query workload prior to VM, but the approach is not scalable for small disk sizes. In the current era, the memory requirement is humongous to store pre-computed views in the materialized query table (MQT) that adds an overhead to view maintenance cost and disk sizes. To address the aforementioned issues, the authors propose a novel VM scheme DAMS. DAMS operates in three phases. In the first phase, the scheme chooses a materialized view in a dynamic and on-demand basis to reduce the query processing time. Then, in the second phase, a novel attribute selection algorithm is proposed based on association rule mining (ARM) technique in VS to address historical queries. It selects a candidate view from a pool of such views. As the number of queries is large, the proposed algorithm reduces the computational latency in fetching the view result. Finally, selected views are prioritized by grouping items as clusters set based on support and confidence metrics to speed up VM operations.

Ashwin Verma, Pronaya Bhattacharya, Umesh Bodkhe, Akhilesh Ladha, Sudeep Tanwar

Multimodal Sentiment Analysis of Social Media Data: A Review

With the exploration of the Internet, social media platforms provide users to share their views toward various products, people, and topics. Nowadays, social media platforms have not limited their users to post or share only text but also images and videos to express their opinion or other social media activity. Multimodal sentiment analysis is an extension of sentiment analysis that is used to mine the heterogeneous type of unstructured data together. This paper gives a review of sentiment analysis and various studies contributed in the field of multimodal sentiment analysis and also discusses some important research challenges in the sentiment analysis of the social media data.

Priyavrat, Nonita Sharma, Geeta Sikka

CrO2 Half Metal-Based Magnetic Tunnel Junction and Its Application for Digital Computing

The half metal (CrO2) ferromagnet has attracted immense research interest because of its large Curie temperature of 390 K and 100% spin polarization. Silicene a two-dimensional monolayer material shows outstanding magnetic and electronic properties. We have calculated the spin dependent transport of electron in our modeled device consisting of two CrO2 electrodes and out of plane silicene as scattering region. We have simulated the device in ATK software which uses non-equilibrium greens function and density function theory for calculation of the transport characteristics. The device is simulated to obtain IV curve and transmission spectrum. Furthermore, spin injection efficiency and tunneling magnetoresistance are calculated from the obtained transport characteristics. The transmission spectrum is found to be in agreement with the IV curve. The spin degree of freedom is expected to increase the speed, decrease power dissipation and add nonvolatility to devices. Also some basic logic functions have been realized from the modeled device.

Muzafar Gani, Khurshed A. Shah, Shabir A. Parah, Altaf A. Balki

Cloud of Things: A Systematic Review on Issues and Challenges in Integration of Cloud Computing and Internet of Things

Cloud computing and the Internet of things (IoT) are two diverse technologies having complimentary relationship. The IoT generates massive amounts of data, and cloud computing provides a pathway for that data to travel to its destination. In the modern era, by integrating cloud computing and the Internet of things, a new paradigm has been introduced, i.e., cloud of Things. Cloud-based Internet of Things or cloud of things arose as a platform for intelligent use of applications, information in a cost-effective manner. Both technologies help to raise efficiency in the future. But the integration of these two technologies is challenging and bears some key issues. Therefore, this paper provides a brief investigation of cloud of things concept. In this paper, we review the literature about integration, to analyze and discuss the need behind integration in various applications. In the end, we identify some of the issues and challenges for future work in this promising.

Sahilpreet Singh, Arjan Singh, Vishal Goyal

Data Augmentation Using GAN for Parkinson’s Disease Prediction

The disease of Parkinson is a gradual neurodegenerative disorder affecting approximately one million U.S. citizens with nearly sixty thousand new annual clinical health diagnoses [1]. Analysis of voice samples was used to detect Parkinson’s disease early (PD) as an efficient tool. The use of deep learning is dependent on the number of samples marked out, which limits the use of deep learning in the smaller sample environment. In this paper, we suggest an approach based on a GAN combined with a deep neural network (DNN). The initial samples were first divided into training and a test range. The GAN learned to generate synthetic sample data to expand the dataset. Last, the synthetic samples are prepared for the DNN classifier. Finally, the classifier testing conducted with the test set, and the indicators confirmed the efficacy of the small sample classification method. Experimental tests have shown greater precision than conventional approaches in the proposed plan. While the classification process appeared to be improved by traditional data increase, an increase of 11:68% was achieved by incorporating GAN-based additions. Moreover, even higher efficiencies can be obtained by combining conventional with GAN-based augmentation schemes.

Sukhpal Kaur, Himanshu Aggarwal, Rinkle Rani

Effective Analysis of Tweets Using Hadoop Ecosystem

Twitter has gained enough popularity nowadays and collecting people’s emotion, opinion, suggestion, feeling, knowledge and current market trends in the form of post on day-by-day basis from different countries, in multiple formats and languages; it is an absolute form of unstructured, rapidly growing million dollar worth data that is difficult to manage and process. This kind of data is mainly referred to as big data. The Hadoop ecosystem evolved around this problem space and offered effective management of this kind of data starting from capturing through processing till workflow management. This research is mainly aimed to provide an effective well-scalable framework to collect, process and analyze tweets using the Hadoop ecosystem. Here, Apache Flume is used to capture and store data in HDFS, Apache Pig and Apache Hive are used for data processing and analysis, and Apache Oozie is used for workflow management and task scheduling. This research also did the performance benchmarking over Hive and Pig on these data to find the recent trends, top influencers and top posts in various data categories. Experimental research concluded that Apache Pig outperformed over Apache Hive in terms of processing time while analytics results were same.

Ravindra Kumar Singh, Harsh Kumar Verma

Artificial Intelligence Politicking and Human Rights Violations in UK’s Democracy: A Critical Appraisal of the Brexit Referendum

Following the testimonies of Shaimaire Sanni about the negative wanton use of artificial intelligence (AI) politicking approaches by the Vote-leave group during the 2016 Brexit referendum, the decision by Great Britain (GB) to leave the European Union (EU) had stirred up heated controversies about what would have really been the outcome of the Brexit deal if the Vote-leave group had not cheated with AI politicking systems. Hence, the act of cheating via this platform and the violation of Brexit spending regulations, human rights activists (HRA) like Sanni and Wylie believed, delegitimize the results of the votes obtained for Brexit and for UK’s institutions of democracy. Others argue that the allegations raised against the Brexit referendum process justify the agitations for a second Brexit referendum by a section of UK citizens. The Marxian alienation theory and Derrida’s critical and analytical method for evaluating qualitative data and arguments gathered on the subject matter of the paper were adopted, with the view to ascertaining the degree of AI politicking approaches that altered the results of UK’s Brexit referendum. Marilyn’s ex-post facto research method was also utilized for interrogating the integrity of UK’s democracy in the light of the allegations raised against it. The study observed that most of the allegations raised against UK’s Brexit referendum process had merits to their claims, thus justifying their request for a fresh referendum. A positive implementation of AI politicking methods from ethical perspectives was recommended against the current reckless methods adopted by political campaigners.

Ikedianchi Ayodele Power Wogu, Sanjay Misra, Oluwakemi Deborah Udoh, Benedict C. Agoha, Muyiwa Adeniyi Sholarin, Ravin Ahuja

Design of 7 GHz Microstrip Patch Antenna for Satellite IoT- and IoE-Based Devices

The next industrial revolution brings machine to machine (M2M) connectivity, Internet of Things (IoT), and Internet of Everything (IoE), and this will take governments, businesses, and people interaction with each other to new level. The global satellite IoT and M2M device market will reach 5.96 million by 2020. Both machine and human can communicate sense and trigger via IoT-based frameworks over a large or remote geographical area using satellite communication. The signal can be sensed at remote location (sea, air, or other unconnected location) and can be uplinked to satellite and can be provided to a central control station. IoT devices should be compact in size so that they can be mounted easily. Microstrip Patch Antenna (MPA) is having advantage of compact design, light weight, easy fabrication method, and low profile over the conventional antennas. Due to their planar structure, microstrip patch antenna is widely used in wireless communication, satellite communication, and in many areas where electromagnetic waves are used. In this paper, inset-fed Microstrip Patch Antenna (MPA) is designed and analyzed for 7 GHz frequency band for satellite communication. The electric field norm plot, radiation pattern are analyzed. Directivity is approximately 12.016 dB, and return loss (S11) calculated is −20.5 dB, and front to back ratio is calculated as 19 dB.

Manvinder Sharma, Bikramjit Sharma, Anuj Kumar Gupta, Bhim Sain Singla

MWAMLB: Modified Weighted Active Load Balancing Algorithm

With the fast growth of technology and users, cloud computing has become an important IT paradigm where the resources are available online and on fly. Cloud computing is known for handling large amount of storage and computation data. In the cloud environment, the distinguishing feature of easy availability of resources makes their management a challenging task. One of the most important tasks is the balancing of the load among different virtual machines which in turn leads to proper utilization of resources and good response time. Many researchers have addressed the problem of resource provisioning, but the proactive approach has been gaining a lot of attention in recent years. The resource provisioning can be achieved either by allocating the resources judiciously or by predicting the demand in advance. The traditional methods make use of random selection of virtual machines(VMs) for load balancing. In this research work, a Modified Weighted Active Load Balancing framework (MWAMLB) has been offered with the emergence of cloud computing. The main objective of the MWAMLB framework is to improve the response time of the VM by selecting the virtual machine with maximum weight (W). The weight factor is being calculated on the basis of the availability of RAM, bandwidth and MIPS. The MWAMLB framework have been proposed, implemented and validated in this research paper.

Bhagyalakshmi, Deepti Malhotra

Security and Privacy

Frontmatter

Security Issues in Internet of Things: Principles, Challenges, Taxonomy

The Internet of Things (IoT) has great potential to change the fundamental way of interacting with technology in daily life, and for ease, it also observes and records user preferences that challenge privacy in another way. IoT devices are suspended to extensive usage even more than mobile phones and attain more access to private and secured data. With the growth of connected devices, mobile security is already a challenge, so perspective challenges for IoT connected devices must be much greater than considered at present and can be primarily categorized into safety, security and privacy. Rigorous development of security techniques should be an essential process toward the foundation of strong IoT systems to achieve and retain user trust. The survey in this paper reviewed and analyzed security principles, attacks and countermeasures at different layers of IoT-layered architecture, considering the bottlenecks of IoT systems.

Manik Gupta, Shaily Jain, R. B. Patel

A Review of Anomaly Detection Techniques Using Computer Vision

Obtaining videos for surveillance purpose or to use them for future predictions is a challenging task as a video has a large number of image frames displayed in a sequence, and modeling every frame is not possible, so various methods are used for building an intelligent vision system, which is used for obtaining videos and also in video anomaly detection. This paper provides an overview of research directions for different types of anomalies and also tells about different techniques in machine learning for managing the problem of anomaly detection in videos and images using computer vision. Computer vision is used to make computers capable of extracting information from digital images or videos. It trains computers to interpret and understand the visual world. When machines detect errors, abnormal or unnatural behavior of datasets, it is called anomaly detection. In this paper, anomaly detection techniques and anomaly detection in datasets using computer vision are classified accordingly.

Vandana Mohindru, Shafali Singla

Security Attacks in Internet of Things: A Review

As time flows by, the quality and quantity of technology keep on increasing in an individual’s life. Every coming day either a new technology is being discovered or an already existing popular technology is being made more and more efficient. One such technology on which lots of research is being done is IoT. IoT is one of the major technologies used these days and continuous research is being done over it to fill in the loopholes. IoT has a traditional layered architecture in which each layer has its great importance. As believed that the future will be linked with IoT all around, rigorous research on security issues of IoT is being done. As a thing with great perfection or use surely has some flaws too, in the same way, IoT too had various types of security issues associated with it. This paper deals with defining the architecture of IoT in detail. The security goals and the issues found in IoT are also explained. An analysis of some of the security attacks in IoT is done to have a closer look at the effects of attacks on the network. Various types of attacks are present in IoT among which some are easily detectable and can be prevented, but some are very difficult to detect and prevent. The paper helps in knowing about the different aspects of security issues and security attacks. Also, some future work related to research areas has been mentioned in the paper.

Vandana Mohindru, Anjali Garg

Texture Feature Technique for Security of Indian Currency

In recent years, security of currency has gain importance in the field of research. With the advent of digital technology, color printer, and color scanner are the cheapest way for counterfeiter to produce fake currency. Feature extraction is the most important technique in paper currency recognition. According to reviewer, texture feature plays an important role for paper currency detection. Texture feature is generally a statistical-based approach and in the present work, a new model is proposed for paper currency detection. The presented model is computing the texture properties like Gray Level Co-occurrence Matrix (GLCM) of Rs. 500 for real and fake currency. The Principle Component Analysis (PCA) is used for reduction of higher dimension of images. The proposed work provides better results with the collaboration of PCA and GLCM. The texture properties have been used and GLCM measured the variation in intensity at pixel of interest of the currency. The computed results have been presented in the form of table and graphs.

Snehlata, Vipin Saxena

Optimal Unit Commitment for Secure Operation of Solar Energy Integrated Smart Grid

Currently, the majority of the world’s electricity demand is met by thermal power generation stations that run purely on traditional fossil fuels. Utilities rely mainly on these sources to spend huge revenue to meet the ever-increasing demand for electricity. This motivates utilities to manage their generation most cost-effectively according to the load demand. Thus, an optimum generation allocation among the various power generating units can save considerable fuel inputs and expenses. Extending this optimization technique to decide which of these units would participate in the optimum allocation could theoretically save a greater amount of fuel costs. In other words, the determination of whether the device has to be ON/OFF is important. This is termed as unit commitment (UC). As for deciding the optimal generation dispatch for the minimum cost, a complete optimal power flow (OPF) is run over the UC time horizon for each hour’s commitment. Conventional OPF solves all constraints such as fixed bus voltage limits, line power flows, transformer tap positions, etc., for optimum dispatch adjustment, resulting in a secure solution. In this paper, with the integration of solar thermal power plant, the total generation cost is reduced. The suggested method is tested by applying it to the standard IEEE 14 bus test system. The findings of the UC, demonstrated in both the presence and absence of STPP, show the method’s efficiency. We propose a mathematical programming-based approach with alternative current optimal power flow (ACOPF) network constraints, to optimize the unit commitment problem.

Aniket Agarwal, Kirti Pal

Project Management Method-Based Cryptographic Algorithm Employing IC Engine Transmission Ratio and Simple Interest Formula

In this rationalized epoch, the orb is gyrating around technological progression with encouraging upshot. Nevertheless, it is decent being expectant, though circumstances urge for cynicism too. Being conscious of the fact that constructive facets of technology should not be a dispiriting aspect, rather emphasis should be toward curbing continuing cybercrimes, diurnal data stealth, malicious intrusions, etc. Computer systems are frequently harmed by network security. Employment of cryptography and cryptographic modus operandi is ensured to overawe such issues. The paper emphasizes utilization of cipher text in determining the critical path employing project management method. Project management method demonstrates all the activities requisite to accomplish a task in the finest feasible manner. The time though which it consumes sets out all the individual activities, partaking in crafting a colossal project. The apposite order has to be upheld as one activity could transpire only if other activity is accomplished, whereas in other cases, some activities transpire concurrently. The most convenient path forms the critical path. The proposed work is principally an amalgamation of project management method along with IC Engine Transmission Ratio and Simple Interest Formula, developed with a purpose of data safekeeping, which is an indispensable facet for apiece organizational accentuation.

Rajdeep Chowdhury, Smriti Kumari, Sukhwant Kumar

Design of Reversible Gate-Based Fingerprint Authentication System in Quantum-Dot Cellular Automata for Secure Nanocomputing

The issues faced by CMOS technology in the nanoregime has led to the research of other possible technologies which can operate with same functionalities, however, with higher speed and lower power dissipation. One such technology is quantum-dot cellular automata (QCA). In this paper, QCA and reversible logic have been combined to design a 2 × 2 Feynman reversible gate-based fingerprint authentication system (FSA). An 8 × 8 size input fingerprint image is compared with the images present in the database and upon successful match, the FSA gives an output of logic ‘1’ to confirm the match. Based on the performance analysis, it is shown that the proposed design achieves performance improvement of up to 89.05% compared to the previously reported design with respect to various parameters such as cell count, area, quantum cost, etc.

Suhaib Ahmed, Soha Maqbool Bhat, Seok-Bum Ko

A Survey on Blockchain Technologies and Its Consensus Algorithms

The evolution and development in blockchain technologies have attracted both research academia and industries. A typical blockchain stores data in a permanent and immutable way in form of blocks connecting, forming a chain of data. The whole system is made decentralized so that anyone connected to the network can verify the data, defining its P2P distributed nature. Blockchain has many components among which the core component is consensus protocol. This protocol is responsible for the security and performance of the blockchain. The consensus protocol introduced by Nakamoto in Bitcoin led the foundation stone for more innovative alternative consensus mechanisms. In this paper, we will conduct a systematic review of blockchain technology and its consensus algorithms and further analyze them based on some essential features and factors.

Rahul Katarya, Vinay Kumar Vats

Digital India

Frontmatter

Toward Prediction of Student’s Guardian in the Secondary Schools for the Real Time

To ease of school management for the identification of student’s protector during his or her schooling and evaluate the performance of a student, the guardian predictive models are presented with the help of machine learning algorithms. For this, standard secondary dataset of two secondary schools was considered from Portugal belonging to the language course. The initial dataset consisted of 649 instances and 33 features. These features belong to the student’s academic, demography, family and personal features. The guardian feature has been considered as a class variable and others (significant) features assumed as predictors. In the orange platform, three machine learning algorithms, support vector machine (SVM), random forest (RF) and neural network (NN), were used with three testing techniques. On one hand, the SVM computed the highest prediction probabilities of 0.996 for other class and another hand, the NN gives the largest prediction probabilities such as 0.906 for father class and 0.889 for mother class. The NN attained the most guardian prediction accuracy of 89% and outperformed others. Also, leave-one-out method significantly enhanced the prediction accuracy of each learner except the SVM. Also, it proved the NN learner slower with prediction time (23 s) and makes the SVM as faster with time (14 s). This study may not only helpful to the school management but also support the social administration of the district or state. Using the model, it must be significant to predict the care-taker of the student.

Chaman Verma, Veronika Stoffová, Zoltán Illés, Deepak Kumar

A Review on Enhanced Techniques for Multimodal Fake News Detection

This paper is a review of enhanced techniques for detecting the multimodal fake news. It helps to develop an insight into the characterization of a news story with different content types and its influence among the readers. We review different techniques on machine learning and deep learning with its merits and demerits. The paper is concluded with the open research challenges that can assist the upcoming researchers.

Vidhu Tanwar, Kapil Sharma

An Intelligent Student Hostel Allocatıon System Based on Web Applications

Student hostel management system is a software programme designed to manage the activities of allocating students to a hostel and other activities involved in managing the students in the hostel. Managing the student’s hostel allocation is a complex task. This study develops an algorithm and techniques for automatic student hostel allocation system based on Web applications that would allocate student to the hall and room-based certain constraints. System is faced with lot of challenges. The system will use MySQL for the manipulation and storage of data, PHP to create dynamic Web pages and Sublime Text as the integrate development environment/text editor for HTML/CSS and PHP. The proposed algorithm and techniques for automatic student hostel allocation system will perform the task of allocating student to hostel rooms in a timely fashion based on the defined constraints. The algorithms and techniques were implemented and validated. Result shows that the proposed model provides information about the room occupancy at any given time, enabling the management in making decisions to improve condition of living in hostels and grants the hostel management team the statistics they need on the hostel.

Ambrose Azeeta, Sanjay Misra, Modupe Odusami, Onyepunuka Ugochukwu Peter, Ravin Ahuja

Artificial Intelligence in the Energy World—Getting the Act Together

The chance of growing a framework that may “think” has captivated individuals on account since authentic cases. Man-made consciousness (computer-based intelligence) frameworks contain two preeminent districts, proficient/master frameworks (ES), and engineered/counterfeit neural systems (ANNs). The significant goal of this paper is to show how engineered insight methods may play a basic capacity in demonstrating and forecast of the exhibition of inexhaustible power frameworks. The paper plots know-how of how expert structures and neural systems perform by utilizing way of giving an assortment of issues inside the remarkable controls of inexhaustible force designing. The different utilizations of expert structures and neural systems are given in a topical rather than a sequential or some other request. Results introduced on this paper are declaration to the limit of manufactured knowledge as a plan instrument in heaps of locales of sustainable power engineering.

Vasundhra Gupta, Rajiv Bali

Non-functional Requirements Engineering Questionnaire: Novel Visions and Review of Literature

The aim of this research study is to evaluate the non-functional requirements (NFRs) of educational websites from the usability perspective. The online questionnaire is used for gathering and analyzing the NFRs. The non-functional questionnaires are filled by the 52 software developers. The questionnaire contains different questions related to different factors of ISO 25010. The different NFRs that are related to the usability are considered accessibility, orphan pages, irritating elements, placement and content of sitemap, website content updating, download time, hyperlink description, design consistency and compatibility of website with different web browsers to mention a few. The different views that are given by software developers on the basis of these questions are discussed. We have also added the suggestions column in questionnaire.

Naina Handa, Anil Sharma, Amardeep Gupta

Data Ingestion and Analysis Framework for Geoscience Data

Big earth data analytics is an emerging field since environmental sciences are probably going to profit by its different systems supporting the handling of the enormous measure of earth observation data, gained and produced through perceptions. It additionally benefits by giving enormous stockpiling and registering capacities. Be that as it may, big earth data analytics requires explicitly planned instruments to show specificities as far as significance of the geospatial data, intricacy of handling, and wide heterogeneity of information models and arrangements [1]. Data ingestion and analysis framework for geoscience data is the study and implementation of extracting data on the system and processing it for change detection and to increase the interoperability with the help of analytical frameworks which aims at facilitating the understanding of the data in a systematic manner. In this paper, we address the challenges and opportunities in the climate data through the climate data toolbox for MATLAB [2] and how it can be beneficial to resolve various climate-change-related analytical difficulties.

Niti Shah, Smita Agrawal, Parita Oza

Design of Waste Heat Recovery System for Green Environment

The global energy problem due to population growth, industrialization, and depletion of natural resources and environmental issues is a cause of concern. A lot of active research on energy harvesting from waste heat from various sources is being done. The prime concern is to not only reduce the wastage of energy resources but also recycle the energy resources. This will also mitigate the carbon footprints of the environment. A high potential for harvesting the energy lies in the energy obtained from household chores. The energy recycled from waste energy can be made sufficient enough required for microelectronic devices. In this research work, a novel module is designed to generate energy by utilizing the heat obtained from household cooking stoves or chullahs. The designed module employs a thermoelectric energy system coupled with heat sink, DC-DC converter, and booster circuits. Three different modules were designed by modifying different key parameters, and the performance of an energy harvesting system has been evaluated. The results obtained are in good agreement with the simulation results and capable of charging a mobile device.

Shruti Jain, Pramod Kumar, Meenakshi Sood

Template Attacks and Protection in Multi-biometric System: A Systematic Review

In the modern era of computing, the automatic authentication using human biometrical traits is being rapidly gaining popularity. The biometrical infrastructure installations are facing a variety of challenges ranging from limitations in uni-biometrics and attacks by imposters. Multi-biometric systems are being deployed to overcome the limitations of uni-biometric counterparts. The key information of all the enrolled users in biometric systems is stored centrally in the template database. The attacks on the template database in these systems may either completely result in failure or degradation in the performance of the system. This paper presents a systematic review of various template attack and their countermeasures in multi-biometric systems. The survey reveals that information fusion, compatibility of templates and size of templates are still an open challenge for researchers. Furthermore, the need is to design more robust and efficient template security schemes for multi-biometric system which meets the standard characteristics of ideal schemes.

Syed Umaya Anayat, Arvind Selwal

Predictive Analysis for User Mobility Using Geospatial Data

Extremely usage of smart wearable devices such as smartphones and smartwatches which contain various sensors for location detection such as Wi-Fi, LTE, GPS and motion detection such as accelerometer, it has become easier to obtain user mobility data. Today communication systems are becoming more popular due to the developments in communication technologies. There are various services provided which also help to access the data such as video, audio, images from which we can be used to grab the information or pattern of user mobility. The user mobility where user’s movements and locations can be predicted using various methods and algorithms. It can be predicted through data mining, machine learning, and deep learning algorithms where user’s data are fetched from the communication system. A comparative data mining model base on DBSCAN and RNN-LSTM was proposed for predicting the user’s future location-based information predicted from the last locations reported. Mobility prediction based on the transition matrix prediction is done from cell to cell and calculated with the help of the previous inter-cell movement.

Jai Prakash Verma, Sudeep Tanwar, Archies Desai, Poojan Khatri, Zdzislaw Polkowski

A Literature Review of Critical Success Factors in Agile Testing Method of Software Development

Software development process is a collaborative effort to fulfil multidimensional product requirements. The development methodology plays an important role to meet the expectations of all the stakeholders especially the client. So, agile teams are constituted having experts level of knowledge and versatility in software development. The team tests the software in errands and takes regular feedback to develop a final product. For this, researchers have suggested numerous approaches in their research works. This paper is a literature review of those earlier research works suggesting different approaches of software development using agile testing method to increase efficacy of software as compared to traditional methods. The purpose is to list the objectives considered which help in deciding the development approach to be undertaken. It brings forth the related agile attributes which influence the software development task in terms of quality, scope, timeliness and cost effectiveness. Further, a framework has been presented for use by any of the stakeholders involved in agile software development methodology.

Abhishek Srivastava, Deepti Mehrotra, P. K. Kapur, Anu G. Aggarwal

Backmatter

Weitere Informationen

Premium Partner

    Bildnachweise