Skip to main content

Über dieses Buch

This book highlights cutting-edge research on various aspects of human–computer interaction (HCI). It includes selected research papers presented at the Third International Conference on Computing, Communication and Signal Processing (ICCASP 2018), organized by Dr. Babasaheb Ambedkar Technological University in Lonere-Raigad, India on January 26–27, 2018. It covers pioneering topics in the field of computer, electrical, and electronics engineering, e.g. signal and image processing, RF and microwave engineering, and emerging technologies such as IoT, cloud computing, HCI, and green computing. As such, the book offers a valuable guide for all scientists, engineers and research students in the areas of engineering and technology.



Realization of Bandpass Filter Based on Spoof Surface Plasmon Polariton Technique at Microwave Frequency

Spoof surface plasmon polaritons (SSPPs) are a form of electromagnetic surface wave which, share similar behavior with surface plasma polariton (SPP). The dispersion relation of SSPP is regulated by the geometry of the corrugation using plasmonic metamaterial. In this paper, the SSPP transmission line having double side corrugated strip and bandpass filter which is composed of two opposite oriented single side corrugated strips coupled to one double side corrugated strips are discussed. The re-configurability aspects of SSPP structures are also explored.

Gaurav Mittal, Nagendra Prasad Pathak

Design of Spoof Surface Plasmon Polaritons Based Transmission Line at Terahertz Frequency

In this paper, we report a plasmonic metamaterial, i.e., spoof surface plasmon polaritons based back to back broadband transition at terahertz frequency. Also we have designed another structure using a unit cell that is made up of by combining three SSPP strip together. This structure shows a way to realize stopband within the operating frequency of spoof surface plasmon polaritons. Using the new type of unit cell disturbs the surface impedance matching and thus gives band stop in the transmission spectrum of SSPP. The first design of transition has reflection coefficient less than −10 dB and transmission loss is less than 5 dB in 0.1–0.8 THz range of frequency. The second designed structure shows strop band from 0.569 to 0.6124 THz and band pass is maintained from 0.1 to 0.569 THz and from 0.6124 to 0.6516 THz. Reflection coefficients in the band-pass region is less than −10 dB and transmission loss is less than 8 dB while in the band stop region reflection coefficient is −3 dB and transmission coefficient is −24 dB has been obtained. Such type structures will show promising application in plasmonic device and systems.

Rahul Kumar Jaiswal, Nidhi Pandit, Nagendra Prasad Pathak

Multiband Multimode Filter for Wireless Applications

This paper reports, design, analysis, and characterization of multimode resonator based multiband band pass filter. In support to the actual response, principle of resonating structure is explained with related mathematical explanations. For validating the concept, a quad-band BPF have been implemented on Neltec substrate and characterized through Keysight vector network analyzer N9918A. All the measured and simulated results are in good agreement with each other.

Nidhi Pandit, Rahul Kumar Jaiswal, Nagendra Prasad Pathak

Design of Graphene-Based THz Antennas

This paper first reports the design of the tunable graphene-based patch antenna at THz frequencies. After that a tunable graphene-based U slot loaded patch antenna has been designed to increase the bandwidth at THz frequencies. The simulated results for both the antennas are presented for different values of chemical potential.

Arun Kumar Varshney, Nagendra Prasad Pathak, Debabrata Sircar

Concurrent Dual-Band Double-Layer High Gain Planar Antenna for WAICs/ITS Application

Safety is the prime concern which drives the development of vehicular communication as support to intelligent transportation systems. The communication networks play a key role and supported by different components among which antenna plays a very crucial role. This paper presents a compact and new design of circular polarized (CP) patch antenna for use in wireless avionics intra-communications (WAICs) and intelligent transportation systems (ITS). Experimental results of the reflection coefficient, gain, and the radiation pattern is consistent with simulation. The prototype antenna can operate in a 4.4 GHz WAICs band with reflection coefficient under −15 dB and gain 8.3 dBi. In 5.9 GHz ITS band it operates with reflection coefficient under −15 dB and gain 8.8 dBi.

Shivesh Tripathi, Nagendra Prasad Pathak, M. Parida

Compact Rat-Race Coupler-Based Microstrip Balun Without Any Isolation Port

In this work, a compact miniaturized microstrip balun is proposed by removing the isolation port of a Rat-Race Coupler (RRC). The proposed balun consists of six quarter-wavelength Transmission Line (TL), and the TL is designed using interdigital capacitor and high impedance TL in parallel configuration. The fractional bandwidth (FBW) of RRC and balun are 37.5% and 33%, respectively, at centre frequency 2.4 GHz for amplitude imbalance of ±1 dB and phase imbalance of ±8°. The size occupied by the proposed balun is 0.51 λg × 0.22 λg.

Ankita Kumari, Tamasi Moyra, Priyansha Bhowmik

Application of the Fractal Defected Ground Structure in Design of the Bandpass Filter

The design of planar filter using stepped impedance type distributed synthesis has been proposed for 8.6–9.5 GHz frequency band. To improve the return loss characteristics, instead of using traditional defected ground structure (DGS), the combination of fractal geometry and DGS, known as ‘fractal DGS’ has been embedded in the ground plane of the filter. The filter using fractal geometry gives 65% better return loss as compared to filter without DGS. Three laboratory prototypes (without DGS, first iteration DGS and second iteration DGS) have been developed to validate the simulated and measured results. The measured results are agreed with simulated one.

Chandni V. Desai, Pravin R. Prajapati

Design of UWB Monopole Antenna with Enhanced Gain Using Partially Reflective Surface

The A low cost, high gain microstrip line feed UWB monopole antenna embedded with partially reflective surface is proposed in this paper. The antenna structure consists of UWB antenna, which acts as a main radiating element and that is fed with a array of total 30 square copper cells, which are considered on low permittivity substrate and suspended in air with the help of dielectric rods at height of 0.5 λ0. The antenna with partially reflective surface gives enhancement of 1–2.7 dB gain in UWB range. The proposed structure is an attractive solution of poor gain problem in ultra wideband communication systems.

Pravin R. Prajapati, Shailesh B. Khant

Reconfigurable Inset-Fed Patch Antenna Design Using DGS for Human Vital Sign Detection Application

The manuscript reports a simple reconfigurable inset-fed Microstrip patch antenna using defected ground structure (DGS). The DGS serves two folds in the proposed design; first it eliminates the higher order resonance and second, supports the resonance at other band with the incorporation of switching diode in it. Initially, the patch antenna has been designed to operate at 5.6 GHz. With the incorporation of the switch, a resonance at 3.36 GHz was obtained. The measured prototype shows a return loss (S11) better than −12 dB in each case with a gain of 4.2 dBi and 2.2 dBi at ‘OFF’ and ‘ON’ condition, respectively. The proposed antenna is specially designed to cater the needs of portable human non-invasive vital sign detection (NIVSD) system for medical and defense applications. Low cost, high directivity and light weight are desired for antenna used in these applications.

Brijesh Iyer, Mahesh P. Abegaonkar, S. K. Koul

Asymmetric Double U-Slot Multi-frequency Antenna for WLAN/5G Communication

A compact microstrip planar antenna with asymmetrical slot width on single dielectric layer has been investigated for multi-frequency operation. The antenna is especially designed for 5G communication and WLAN communication. The geometry of the proposed antenna comprises of a single dielectric layer with a single radiating element, in which the rectangular patch is introduced with dual U-Slot to achieve multiple resonances. The antenna is excited by a transmission line feeding, presents on the same layer. The antenna first resonates at 4.2 GHz, later resonates at 5.2 and 5.8 GHz. Proposed patch configuration shows improved bandwidth of 180, 350, and 250 MHz with the offset transmission line feed and asymmetric slot. Both symmetric and asymmetric behavior of dual U slot has been studied. The antenna was fabricated using a single FR4 substrate of dimension 16 × 20 × 1.56 mm3.

Sraddhanjali Mohapatra, Debaprasad Barad, Subhrakanta Behera

Performance Analysis of Optimal Versus Energy-Based Selection of Receiver Antenna for MIMO Systems

The paper reports the performance analysis of antenna selection at receiver end. The optimal and energy-aware antenna selection techniques are compared for multiple input multiple output (MIMO) antenna systems. The analysis is carried out with a very simple cost function, i.e., CDF. The performance analysis is carried out with Simulink tool of MATLAB. The plots of CDF versus channel capacity and bit error rate (BER), for each case, are taken into consideration for the analysis of antenna selection. It is found that the antenna selection at the receiver side is more impactful in MIMO system.

Nitin Deotale, Uttam Kolekar

Public Auditing for Shared Data in Cloud Storage with an Effective User Dismissal

Cloud computing is an extensive technique which is changing the IT infrastructure swiftly. Data storage and sharing is the foremost and significant research area in cloud computing. Major security issues in cloud storage include missing folders, privacy settings, synchronization issues, etc. One of the topmost exigent research issues in data storage is data integrity. This research study identifies the security issue in data storage and achieves data integrity and privacy by providing public auditing using third-party auditor. To attain an effective key sharing, Shamir’s secret sharing technique is exploited. The proposed system supports an efficient user dismissal by group admin in case if any user is found troublesome while sharing data in cloud storage. To provide a beneficial auditing for users, batch auditing is additionally presented to reduce the auditing time.

S. Samundiswary, Nilima Dongre

Lightweight Effective Encryption Algorithm for Securing Data in Cloud Computing

Communication in the environment of cloud computing is implemented through the Internet and its backbone. Some issues of network security in the cloud environment are caused by its essential characteristics such as resource pooling, virtualized nature, elasticity, and other measured services. Though many algorithms have been used to secure the data communication in the cloud environment, some problems in the use of such algorithms still exist. Some of such problems are the mathematical complexity, key and security weakness, time complexity, and slow performance. In this paper, an algorithm called hyper data encryption (HDE) is proposed to combine the symmetric ciphers, secret sharing, and Diffie–Hellman key exchange concepts in order to enhance the security and solve the mentioned problems. Performance analysis is conducted in terms of key-space analysis, key sensitivity analysis, correlation analysis, information entropy analysis, time complexity, and execution time. The results show that the proposed algorithm is better in a cloud environment, which can provide strong security and high performance.

Basel Saleh Al-Attab, H. S. Fadewar, Mahmoud E. Hodeish

Predictive and Prescriptive Analytics in Big Data Era

The notion of data analytics and its real-time application is important in the big data era owing to the voluminous data generation. Predictive and prescriptive analytics provides the future trends from the available data effectively. This will help to decide the usability of the data and thereby its retention for future applications. The paper reports the predictive and prescriptive analytics notion in big data regime, various platforms for its analysis, and the future research directions.

Prachi Deshpande

Indexing in Big Data

Nowadays communication is through social media for almost all activities like business, knowledge, personal updates, etc. This leads to the generation of large amount of data related to different activities. Hence, social media have become a vital content of our life. But going through this huge data for analysis is a tedious and complex task. There are many solutions to overcome this problem. Data reduction, indexing, and sorting can be the solutions. Further, which will be used for visualization, recommendation, etc. Indexing techniques for highly repetitive data group have become a relevant discussion. These techniques are used to accelerate queries with value and dimension subsetting conditions. There are different types of indexing with the suitability of data type, data size, dimension, representation, storage, etc. Indexing is of vital need as whatever electronic text collection is available, it is mostly large scale and heterogeneous. Hence, the motto is to find an improved approach for text search as it is used right from the help services built into operating systems to locate file on computers. Tree-based indexing, multidimensional indexing, hashing, etc., are few indexing approaches used depending on the data structures and big data analysis (BDA). Indexing’s need is to address the speed of search. So, size of index shall be a fraction of original data and to be built at the speed of data generation to avoid delay in result. Here, few indexing techniques/search structures are discussed based on data structure, frame work, space need, simplified implementations, and applications.

Madhu M. Nashipudimath, Subhash K. Shinde

DataSpeak: Data Extraction, Aggregation, and Classification Using Big Data Novel Algorithm

A huge amount of data is coming due to large set of computing devices. As a birth of the variety of data, data processing and analysis is a big issue in big data analytics. On other hand, data consistency and scalability is also a major problem in the large set of data. Our research and proposed algorithm aims to data extraction, aggregation, and classification based on novel approach as “DataSpeak”. We have used k-Nearest Neighbors with Spark as reference and produced a novel approach with modified algorithm. We have analyzed our approach on the large dataset from travel and tourism, placement papers, movies and historical, smartphone, etc., domains. As for ability and accuracy of our algorithm, we have used cross validation, precision, recall, and comparative statistical analysis with the existing algorithm. Our approach returns with the fast accessing of data with efficient data extraction in a minimal time when compared to the existing algorithm in same domain. As concerned with the data aggregation and classification, our approach returns 98% of data aggregation and classification based on the data structure.

Venkatesh Gauri Shankar, Bali Devi, Sumit Srivastava

Design and Implementation of Internet of Things Based Multi-sensor Device

As the technology use in the world progresses the multiple devices and things will co-operate with each other to achieve high reliability and accuracy in the information sharing and processing for better future. To achieve this, the integration of various sensors in single device is designed with the help of standard enclosure and wireless communication technology. The device consists of various physical parameter sensors like temperature, humidity, light intensity, proximity are integrated in single enclosure which communicates its parameters over wireless standard 802.11 a/b/g/n. The access to the information and or sensor data is achieved using Secure Message Queuing Telemetry Transport (SMQTT) standard protocol. The Multi-sensor Device have 32-bit controller based chip ESP8266 programmed to establish the communication with other devices using IBMs Node-Red programming tool running on Raspberry Pi. The data is logged locally on the memory of Raspberry pi. The data is accessible from outside network with secured authentication. The display of sensor data is done on the Node Red based user interface for easy access.

Ravikant Khamitkar, Farid Valsangkar

Internet of Things for Irrigation Monitoring and Controlling

The three things that the world runs on are water, wheel, and fire. Agriculture is largely based on water, its proper usage, storage, and management. This is a very key issue. With the advent of technology, manual systems evolved from being mechanized to being automatic and recently to being smart. The technology wave of Internet of Things can further ease the tedious task of watering and irrigating the fields, especially in the water scarce regions as well as in situations where fields are far away from residential areas. Also it saves the excess use of water for any crop. Erratic climate behavior in the Indian subcontinent in the last few years has led to extreme water scarcity in many regions. This paper proposes an irrigation monitoring and controlling system based on Wireless Sensor Network (WSN) and Internet of Things. The WSN remotely collects the data from the fields and transfers it to the cloud. The wireless sensor network uses two sensors: DHT and soil moisture sensor. A management server accesses the information over the cloud, a graphics user interface processes it and generates a feedback. This feedback is based on a user-selected crop name (stored in database) in the GUI. The information is sent over the cloud via IoT gateway. In this work, the hotspot from the mobile phone is used as an IoT gateway. The ESP8266-12E is used as controller as well as a Wi-Fi module. The feedback device is a 12 V DC pump. Whenever the soil moisture level senses dry soil (0-min %), the management system will generate a feedback signal to switch on the pump.

R. J. Muley, V. N. Bhonge

Hostel Rooms Power Management and Monitoring Using Internet of Things

Power saving is the important issue nowadays, and it is more critical in hostels because of some irresponsible students who leave the room without switching OFF the tubes lights and fans. So, for controlling this wastage of electricity in hostels, we have tried here to develop this system that helps in monitoring and managing the electrical power requirement. In this system, IR sensors sensed the presence of students in the room with the help of counter. When it counts one, it means students enters the room, this counter increases and so on. When the student leaves the room, it decreases the count and when it reaches up to zero, this indicates that no one is present in the room. At this time, after few seconds, the switches will automatically turn OFF, if it is ON, and this information will be sent to the server/cloud where the authorized person can see or watch all the activities in the room. Here, we need only Internet for watching the online process. This will be in the form of notification where it will show the room number, OFF time. The other feature of this system is, when such notifications will be seen on the screen, one SMS will be sent to the student about Rs. 100/- penalty or punishment. Internet of Things plays a vital role in this system. This promotes students to become responsible about careful utilization of electricity.

Meenakshi Patil, Vijay D. Chaudhari, Hemraj V. Dhande, H. T. Ingale

Performance Analysis of LAN, MAN, WAN, and WLAN Topologies for VoIP Services Using OPNET Modeler

Visual and Vocal communication can be transferred through Circuit switched Network or Packet Switched Network. Public Switched Telephone Network (PSTN) is not an affordable option therefore over existing packet switched network, Voice over Internet Protocol (VoIP) has become a preferable alternative due to its reduced cost. However, despite its reduced cost it has so many challenges which affect its successful deployment. This is because; the quality of VoIP is mainly affected by jitter, delay, packet loss and some other parameters. This research was carried out to evaluate voice quality in VoIP experimentally under different scenarios using OPNET network simulator. A VoIP network was simulated using Riverbed modeler academic edition 17.5 and the behavior and quality of VoIP was studied and analyzed under different scenarios. The results of the analysis and the performance evaluation are presented in this paper. This work can guide researchers and designers to design a network for VoIP services and its deployment. It can also guide the operators to choose speech compression technique for better voice quality.

Poonam Chakraborty, Aparna M. Telgote

Intelligent Attribute Based Encryption (IABE) Mechanism for Health Records in Cloud

Various possible definitions are to be found in appropriated figuring. A vast bit of them focuses on the development in a manner of speaking. Research has been done to merge all these particular definitions to come up with one uniform definition. Conveyed processing can best be depicted as a mammoth pool which contains gear, programming and diverse organizations that can be gotten to through the “cloud”. Each one of these advantages can be gotten to at whatever point generally. A significant part of the time the provider of the cloud offers his organization as pay-per-use. This infers there is high versatility in the use of these organizations as extra resources are always available. Moving fragile data from in-house IT system to a cloud arrange has transformed into a mind-boggling and testing undertaking. This paper proposes another protected technique to secure customer fragile data. In this methodology, we are considering therapeutic administrations data. We are using multilevel quality based encryption plot for securing customer’s wellbeing records. The trial comes to fruition demonstrate ideal results over existing techniques.

Ranjith Kumar Vollala, L. Venkateswara Reddy

Analysis of Probabilistic Models for Influence Ranking in Social Networks

Influence is a phenomenon occurring in every social network. Network science literature on Influence ranking focuses on investigation and design of computational models for ranking of nodes by their influence and mapping the spread of their influence in the network. In addition to this contemporary literature seeks efficient and scalable influence ranking techniques that could be suitable for application on massive social networks. For this purpose joint and conditional probabilistic models could be a way forward as these models can be trained on data rapidly making them ideal for deployment on massive social networks. However identification of suitable predictors that may have a correlation with influence plays a major role in deciding the successful outcome for these models. The present investigation proceeds with the intuition that interaction is positively correlated with influence. Furthermore, through extensive experimentation it identifies a joint probabilistic model and trains it on interaction characteristics on nodes of a social network for influence ranking. A qualitative analysis of these models is presented to highlight its suitability.

Pranav Nerurkar, Aruna Pavate, Mansi Shah, Samuel Jacob

Smart City Project Management System Using Cloud

Massive increase in population around the world and the advent of more and more number of people moving to cities for livelihood has increased the demand for better transportation and infrastructure. It has given rise to conflicts between multiple smart city services and demands the better project management. Here, we are putting forward a fresh approach for smart city project management using the live data feed through which we detect the conflict in real time, which in turn helps the authorities for better decision-making.

Revati M. Wahul, Santosh S. Lomte

Performance Scaling of Wireless Sensor Network by Using Enhanced OMRA Routing Algorithm

In modern scenario it has become inherent to employ of Wireless Sensor Networks (WSN) for government and other sectors including defense. Sensor networks can be employ in society, industries, military areas, roads, forests, etc. In a traditional networks it becomes complicated to employ denser node deployment and other problems, e.g., node failure, energy consumption and asymmetric are also prominent. Sensor nodes usually works on battery-powered source and these nodes do not operate for longer time without any manual intervention and it is a very tedious and time-consuming task in forest and defense areas. Hence, it becomes a necessity to reduce energy consumption of sensor, it will also increase energy lifetime. Traditional algorithms like Radio Aware (RA), Distance Source Routing (DSR) and Directed Diffusion (DD) do not solve problems like network connectivity and asymmetric links. To overcome this problem Optimized Mobile Radio Aware (OMRA) technique is demonstrated in this paper.

Tanaji Dhaigude, Latha Parthiban, Avinash Kokare

A Study on LoRaWAN for Wireless Sensor Networks

Wireless sensor network plays a tremendous role in various fields such as agriculture, environmental monitoring, military applications, health care, etc. There are many challenges in designing wireless sensor network that are specific to the application under consideration. The developments of Internet of Things with interconnected physical objects improve the application space, flexibility and sophistication of wireless sensor networks. LoRaWAN is a long range wide area network which uses low power and unlicensed Lora Band for wireless communication among battery operated devices. The characteristics such as transfer rate 300 bps to 50 kbps, low power and very low duty cycle makes LoRaWAN a potential candidate for IOT applications. In this paper the possibility of implementing LoRaWAN for variety of wireless sensor network application have been analyzed.

S. Subashini, R. Venkateswari, P. Mathiyalagan

Avalanche Effect Based Vertical Handoff System for Wireless Communication

Nowadays, due to increasing usage of the wireless technologies the movable node infrastructure always inviting lots of threats to worsen the network. Among these network failures is biggest and disturbing factors. Like a boon to this problem vertical handoff technology is acting like an effective approach in a wireless network. So many of the methodologies are introduced to handle vertical handoff more efficiently, but all are having one or another problem in the process. The proposed paper puts forwards an idea of vertical handoff situation awareness to minimize decision time as compared to other methods by comparing the hash keys at the pool manager of a wireless network pool with another network pool for successful handoff. Therefore, definitely our method enhanced the overall performance by taking a decision in a short time compared to vertical handoff system suing fuzzy logic.

G. U. Mali, D. K. Gautam

Energy-Aware Approach for Routing Protocol by Using Centralized Control Clustering Algorithm in Wireless Sensor Networks

Routing in wireless sensor networks (WSNs) has a primary task for data transfer from source to the sink. Due to restricted battery power of the sensor nodes, there is a necessity to take in consideration while designing a routing protocol in WSNs the power saving of sensor nodes. Several routing protocols employing hierarchical-based clustering technique have been proposed for WSNs, however most of them still have such challenges which can be represented in minimizing the energy consumption and maximizing the network lifetime, simultaneously. In this paper, an improved method EACCC is proposed by extending the centralized clustering technique in order to achieve higher efficiency for energy, longer lifespan of network and network scalability. The performance of EACCC is evaluated and justified through extensive analysis, analytical proof, comparison, and implementation. The results show that the proposed method is highly efficient and effective in term of balancing the consumption of energy and prolonging network lifetime.

Nada Al-Humidi, Girish V. Chowdhary

Security Challenges and Solutions for Wireless Body Area Networks

Wireless Body Area Networks (WBANs) are special purpose Wireless Sensor Networks, which is used to provide competent communication solutions for health care and medicinal applications. The rapid technological advancements in the field of sensors, MEMS, and the wireless communication enable the design and implementation of Wireless Body Area Networks. The most prominent application of WBANs is in healthcare but it also finds its applications in consumer electronics, sports safety, lifestyle, defense, and much more. WBANs are usually smaller networks when compared to WSNs but still, they are vulnerable to a massive number of security attacks. In this paper, we provide an overview of the Wireless Body Area Networks (WBANs), its applications, and security aspects. Various security threats and their countermeasures in WBANs are discussed based on the latest reviews and publications.

K. R. Siva Bharathi, R. Venkateswari

Minimizing Congestion in Mobile Ad hoc Network Using Adaptive Control Packet Frequency and Data Rate

An effective congestion control algorithm should ensure reliable message delivery, quality of service, and energy optimization. This paper presents a method in which data rate and control packets such as Hello packet interval is selected according to the channel conditions depending on the node mobility and energy consumed by the nodes in transmission. The method enables nodes to adjust their data rate and frequency of their Hello messages depending on the transmission power and current speed of the nodes. The improved protocol detects and reacts to congested parts of the network by using adaptive data rate and Hello packet interval. This helps in reducing congestion and improve throughput. The functionality of the proposed method is tested using the Network simulation tool. The results have been analyzed in various scenarios to evaluate the performance parameters. This mainly improves throughput and reduces end-to-end delay and jitter in high mobility cases. The average queue length is also controlled.

Navneet Kaur, Rakesh Singhai

Network Selection Scheme Using Taguchi Method for Real-Time Streaming Media Over Heterogeneous Networks

Next generation wireless communication networks needs to integrate various heterogeneous technologies based on an IP core network. Thus it guarantees service continuity, optimum network selection, user mobility and integration of new applications and resources. Integration of various wireless technologies in heterogeneous environment offers best service to every application. However, an automatic interface selection and user preferences based on quality of service parameters such as available resources, bandwidth, network delay or speed, security, and power consumption is desired. Hence network selection scheme explicitly based on user preferences and available resources is required. In this paper, network selection scheme using Taguchi method over heterogeneous wireless communication networks is proposed. Taguchi method assists in analyzing the quality of service parameters so as to satisfy or establish best optimum parameters of the network that further assist in network selection. It also estimates the contribution from the individual parameters affecting the overall performance of the network. Moreover, our results ensure optimum selection of suitable matching network for every flow considering quality of service parameters and user preferences. Network selection scheme finds applications in the area of real-time streaming media, online traffic offloading, reduced delay, optimum utilization of the services, integration of heterogeneous wireless technologies, incorporation of new applications and quality of services through user preferences.

Renuka Deshpande, Lata Ragha, Satyendra Kumar Sharma

Performance of Internal Cluster Validations Measures For Evolutionary Clustering

Clustering is an NP-hard grouping problem and thus there are advantages of using a metaheuristic (swarm intelligence) strategy to find the near global optimal solution to it. To effectively guide the agents of the swarm in the metaheuristic strategy, a suitable cost function is needed for successful outcome. The current inquiry focuses on the use of internal validation criteria as cost functions as they achieve the dual goals of clustering which are compactness and separation. Out of the multiple internal validation criteria included in the literature, two are identified for this purpose, viz. BetaCV and Dunn index. These were used as cost functions of the swarm optimizer metaheuristic (PSO-BCV and PSO-Dunn). To demonstrate the validity of the proposed technique, it was compared with other metaheuristics differential evolution as well as the traditional swarm optimizer based on distance-based criteria (PSO). The analysis of the results obtained on clustering benchmark datasets highlighted the suitability of this approach.

Pranav Nerurkar, Aruna Pavate, Mansi Shah, Samuel Jacob

Performance Analysis of Polar Coded IHDAF Relaying for Next Generation Cellular Networks

Cooperative relay networks play a vital role in improving the coverage and capacity of cellular networks. In order to achieve high reliability, relaying should be used with channel codes. In this paper, the hybrid relaying protocol based on the incremental procedure is proposed through polar codes. It provides 40% gain when the threshold signal-to-noise ratio between source and relay equals 5 and threshold signal-to-noise ratio between source and destination is optimal. Simulation result illustrates that incremental HDAF using polar codes outperform in Alamouti scheme compared to single-input-single-output systems.

N. Madhusudhanan, R. Venkateswari

A Proposed Architecture for Cold Start Recommender by Clustering Contextual Data and Social Network Data

Recommender Systems (RS) help users in selecting the apt items based on their taste from a pool of items. These systems are able to do a proper recommendation with the aid of Machine Learning algorithms. The context of a user plays an important role in recommending relevant and important product/item to a user. Social media networks are useful knowledge sources to elicit more ratings from new users than state-of-art active Learning strategies. If we are designing an RS for users whose tastes differ according to the current context (e.g., feeling), we can collect contextual data and social media information so that we will be able to recommend the right product or item. We can do this recommendation by using cross-domain RS, Selective Context Acquisition, and Implicit Feedback. This paper provides insights based on the state-of-the-art contextual data and social media environments in providing the cold-start recommendations and also propose the architecture for recommending the items to solve the cold-start issue.

V. R. Revathy, Anitha S. Pillai

Performance Issues of Parallel, Scalable Convolutional Neural Networks in Deep Learning

In this work, we investigate the performance issues in the parallel and scalable of Convolutional Neural Networks (CNNs). This will accelerate the training performance of CNN. In this paper we propose the parallel recognition using Compute Unified Device Architecture (CUDA) Technology and Message Passing Interface (MPI). We demonstrate scalability and performance that can be achieved on the GPU using CUDA framework where the computation-intensive tasks shifted on GPU. It compares result on GPU hardware architecture with the serial algorithm on CPU. The main novelty of our method is a new scalable CNN architecture that integrates a category hierarchy with deep CNN.

Umesh Chavan, Dinesh Kulkarni

An Efficient Approach to Feature Extraction for Crowd Density Estimation

Crowd feature extraction is important step for crowd density estimation. This paper proposes a simple and novel approach of feature extraction applicable for crowd density estimation. A 5 × 5 mask is proposed for extraction of density, which finds isolated components in the image. This helps in classification of the density in five levels using SVM and ANN classifiers. The method can be used for intelligent surveillance system in public places. It can easily be used for embedded applications.

Neeta Anil Nemade, V. V. Gohokar

Unsupervised Feature Selection Using Correlation Score

Data of huge dimensionality is generated because of wide application of technologies. Using this data for the very purpose of decision-making is greatly affected because of the curse of dimensionality as selection of all features will lead to overfitting and ignoring the relevant ones can lead to information loss. Feature selection algorithms help to overcome this problem by identifying the subset of original features by retaining relevant features and by removing the redundant ones. This paper aims to evaluate and analyze some of the most popular feature selection algorithms using different benchmarked datasets. Relief, ReliefF, and Random Forest algorithms are evaluated and analyzed in the form of combinations of different rankers and classifiers. It is observed empirically that the accuracy of the ranker and classifier varies from dataset to dataset. This paper introduces the concept of applying multivariate correlation analysis (MCA) for feature selection. From results, it can be inferred that MCA exhibits better performance over the legacy-based feature selection algorithms.

Tanuja Pattanshetti, Vahida Attar

Sustainability Assessment by Use of Fuzzy Logic—A Review

This paper discusses the use of fuzzy logic for assessment of sustainability. The paper also reviews the social, economic, and environmental factors on which sustainability of the current and future generations is based. Barriers towards achieving sustainability are enlisted. The major objective of this paper is to review Sustainability Assessment by Fuzzy Evaluation (SAFE) model for assessment of sustainability. As fuzzy logic is able to deal with data that is not well defined, ambiguous and also there is a complex relationship between the parameters involved, it is well suited to the assessment of sustainability. The SAFE model is useful for policy makers to decide on the measures to be taken for sustainable development in the years to come for a sustainable future for life on planet earth.

Pratibha R. Dumane, Anuja D. Sarate, Satishkumar S. Chavan

Sentence Level Sentiment Identification and Calculation from News Articles Using Machine Learning Techniques

Sentiment analysis is a widely used phenomenon for analyzing online user responses to infer collective response and it is used in various applications. Negation is a very common morphological creation that affects polarity. This research paper focuses on sentence level negation identification from news articles this work uses online news articles Data from BBC news. Results are analyzed using Machine Learning Algorithms like Support vector Machine and Naïve Bayes. Support Vector Machine achieves 96.46% accuracy and Naive Bayes achieves 94.16%.

Vishal S. Shirsat, Rajkumar S. Jagdale, Sachin N. Deshmukh

Multi-constraint QoS Disjoint Multipath Routing in SDN

Efficient path computation that sustains varying quality of service requirements is a key networking concern. Even though modern networks turned to multipath routing schemes as a first step in this path, existing solutions still resulted in sub-flows being directed to the same paths. Moreover, maintaining the quality of service subject to multiple criterions while selecting the paths and handling connection requests dynamically has proved to be challenging tasks. Addressing all these issues requires a centralized, real-time- and fine-grained control of the network facilitated by Software Defined Networks (SDN) that have emerged as a revolutionary networking paradigm. In this paper, we deal with the former issue by computing k-max min disjoint paths and for the latter we use an analytic hierarchy process. The proposed solution combines the two approaches for deployment in an SDN environment.

Manan Doshi, Aayush Kamdar, Krishna Kansara

Performance Analysis of Trust-Based Routing Protocol for MANET

Mobile Ad hoc network (MANET) is a self-motivated network. Nodes are freely moved anywhere inside the network. They can enter and depart the network at any instance. Due to loss of infrastructure in the network frequent link failures occurred. So the special classes of routing protocols are taken into account for reducing the link failures. Categories of protocols are Reactive, Proactive, and Hybrid. This reactive protocol reduces the routing overhead via sending the routing packets on every occasion there is want of communication. This paper mainly focused on the reactive protocols such as AODV, DSR, and AOMDV. Proposed work utilizes trust concept for finding the reliable route. In this work, we implemented Secure Routing Protocol which establishes a secure path between the nodes, totally based on the node trustworthiness. Based on the nodes past experience we calculate the nodes present trust value and finds the better route for data transmission. Proposed method improves the packet delivery ratio and throughput.

Archana Mandhare, Sujata Kadam

VANET-Based Distributed Platoon System

Intelligent Transportation Systems (ITS) targets to streamline the vehicle operation, also assist driver with various safety, on board, and surrounding information. On highway grouping of vehicles forms a Platoon. Vehicular Ad hoc Network (VANET) enables Vehicle to Vehicle (V2V) and Vehicle to Infrastructure (V2I) communication that helps to increase the performance of platoon. Platoon helps to improve road capacity, more comfortable and safe driving, reduce in emissions. In previous year the most of the research is done on string stability analysis, latency, and data dissemination. The control of position, speed, and acceleration to the preceding vehicle in platoon is referred as longitudinal control. This work focus on the basic and mini platoon control design strategy. The design is proposed with Ad hoc demand distance Vector (AODV) routing protocol, used for application of platoon the new developed algorithm Distributed platoon system (DPTS) is proposed. The comparative study of strategy based on parameters like Packet delivery ratio (PDR), Throughput, Routing Overhead, End-to-end (e2e) delay. Traffic disturbance scenario for failure of vehicle in platoon is developed.

Vanshri Deshpande, Swati Kamthekar

Unconventional Prediction Algorithm for Quick Route Convergence and Stability in MANET

Mobile Ad hoc Network (MANET) is infrastructureless network. Data between source and destination can be communicated through intermediate nodes. Nodes can move randomly and there is no central administration in ad hoc networking. Connectivity with corresponding nodes can be lost due to high mobility, battery power consumption, traffic, and node depletion. This results in repeated route failure. This intrudes the node association and degrades the network’s ability to offer the services to its colleague nodes. This makes route maintenance difficult, reduces the stability of the network, and hampers the flow of data. Information related to the route collapse cause can be used to improve the stability of the route. On this basis, Advance AODV (A-AODV) is proposed based on unconventional prediction algorithms without and with fuzzy logic to converge the route quickly for continuos data transmission. In this paper, the modifications have been made to the Ad hoc on-demand distance vector (AODV) route maintenance mechanism. Simulations are performed on qualnet 5.0. This paper covers comparative performance analysis of AODV and A-AODV techniques in reference of mobility and traffic. The results illustrated that the route stability can be enhanced through fuzzy prediction algorithm.

Mehajabeen Fatima, T. K. Bandopadhyay, Roopam Gupta

Analysis on Logical Key Hierarchy and Variants for Secure Group Communication

In secure group communication for applications such as pay-per-view, teleconferencing, and video conferencing, key management method with logarithmic computation is expected along with storage and bandwidth efficiency. Major aspects with key management are formation of group key with initial group members and updating the group key with any change in number of group members. Rekeying is mandatory due to group join/leave operations or periodic rekeying. Logical Key Hierarchy has logarithmic rekeying cost. This paper explores Logical Key Hierarchy (LKH), LKH variants with centralized and distributed approach are analyzed and presented. This paper explores their way of achieving and persisting logarithmic cost for secure group communication, to decide the suitable method for a current application.

Aparna S. Pande, Yashwant Joshi, Manisha Y. Joshi

Performance Analysis of SLM Technique for PAPR Reduction in OFDM Using QPSK Modulation

Multi-carrier communication is a backbone of fourth-generation (4G) mobile communication due to high-data-rate capability. This multi-carrier communication is facilitated using orthogonal frequency-division multiplexing (OFDM). But high peak-to-average power ratio (PAPR) is a serious problem present in OFDM. High PAPR causes huge battery power consumption. To reduce PAPR, selected mapping (SLM) is one of the good technique from the set of scrambling methods. The performance of SLM technique for QPSK-modulated data with phase offsets of π/4, π/2, and 3π/2 using N = 64, 128, 512, 1024, and 2048 number of subcarriers in MATLAB environment is presented in this article. PAPR results of original OFDM and OFDM with SLM technique are plotted and also presented in tabular form for comparison. We have also investigated the computational complexity of SLM scrambler and descrambler block using Freescale StarCore SC140 architecture simulator.

Amol B. Kotade, Anil Nandgaonkar, S. L. Nalbalwar

Spatial Modulation Technique: Achievements and Challenges

Multiple antenna techniques are becoming one of the key technologies used for wireless communications these days. They trade-off higher data rates and superior error performance for increased complexity and cost. Spatial Modulation (SM) is a transmission technique using MIMO system to offer low-system complexity, improved data rate and better error performance in correlated channel environments. It exploits the properties of randomness and uniqueness of the wireless communication channel. This is done by using a coding method to establish a one is to one mapping of the transmitted information bits along with spatial positions of the transmitting antennas which are arranged in an array. The transmitted signal and the transmitting antenna number are estimated using this information for de-mapping the information block. This avoids Inter-channel Interference though a high spectral efficiency is maintained. This paper outlines the research achievements along with challenging research issues of this transmission technique.

Namita Agarwal

A Novel Cluster Based Algorithm for Outlier Detection

Nowadays an important issue as well as challenge in data mining is obviously is outlier detection. Outlier detection has been used in many areas such as Fraud detection, Intrusion detection, Health care, Fault detection, etc., where detection of outliers is based on the different characteristics of data or datasets. In this current age of ‘Information Technology’, large numbers of processes are obtainable in the domain of data mining to discover the outliers by successfully creating the clusters and after that detecting the outliers from these created clusters. In data mining, cluster methods are highly essential and have been applied from micro- to macro-applications. Basically clusters are a pool of similar data objects put together grounded on the attributes and district features they have. Specifically outlier detection is used to recognize and exclude inconsistency from the available data sets. In the presented work an algorithm has been suggested which is based on clustering approach to the given data sets. The proposed algorithm efficiently detects outliers inside the clusters by using clustering algorithm and weight based approach.

Manish Mahajan, Santosh Kumar, Bhasker Pant

Sentimental Analysis of Twitter Data on Hadoop

Data is something without which organizations can never reach any conclusion and cannot extract any particular pattern. These data sets are the sources on which organizations rely while taking important strategic decisions. There are many social platforms on which people around the world are accessing and these platforms are generating a huge amount of data. This data can be differentiated on the basis of their volume, velocity and variety. Organizations term such a huge amount of data as Big Data. These social data sets are of great use for improving business strategies. Nowadays, twitter has become a great social platform for expressing different opinions. This paper focuses on MapReduce-based sentiment analysis of data received through twitter. The data is first cleaned to retain only text, then MapReduce is applied to get the frequency of each word which is then matched with the dictionary created for positive and negative words over Hadoop environment. The results are compared with Naïve Bayes and SVM classifier. It has been observed that time consumed by the proposed system is 45% less than SVM and 38% less than Naïve Bayes. The accuracy in terms of a total number of words detected, positive and negative words, was also observed to be 11%, 16%, 18% respectively in case of SVM and 9%, 13%, 16% respectively in case of Naïve Bayes.

Jayanta Choudhury, Chetan Pandey, Anuj Saxena

Multi-GPU Approach for Development of Parallel and Scalable Pub-Sub System

Event matching plays an important part in the overall attainment of the content-based Publish-Subscribe system. These systems demand guaranteed message delivery, high throughput and low matching time. Existing parallel content matching algorithms make use of multiple cores and off the shelf hardware easily available in today’s modern computers. For a large number of events and subscriptions, these algorithms suffer from performance degradation. In this paper, we propose high-performance Publish-Subscribe system designed to run efficiently on multiple GPUs. Performance comparison with existing CCM (CUDA Content Matching) algorithm clearly demonstrates 32% improvement in matching latency.

Medha A. Shah, Dinesh Kulkarni

Artificially Talented Architecture for Theme Detection

Intelligent systems are the need of today’s world. Collections of data and various data sets are made available to naive users. Understanding what is contained within the dataset is quite difficult by referring just the name. Some of the datasets have quite a difficult, weird names so users do not have any clue what is inside, so there is a need of the theme of the document or dataset so as to understand what are the contents. User satisfaction and convenience is of prime importance. In this paper, we try to propose a system along with a working prototype of such intelligent system that essentially is a Chatbot which uses facility of Theme Detection in semantic analysis stage while processing the user input. This makes the system more productive. This paper talks about Chatbot and improvement in intelligent responses using theme detection. We have built a prototype of the system.

A. Karamchandani, T. Agey, A. Chavan, Vaibhav Khatavkar, Parag Kulkarni

Study and Effect of Architecture Deployed in BPO on Screen Recording Compliance for In-Centre Versus at-Home Agents

In business process outsourcing (BPO), Voice and Screen recording systems are deployed. Deploying these systems addresses the varied BPO needs such as compliance, quality management, improving customer experience, and dispute resolution. As per the architecture, recording systems record the agent and the customer voice. In addition, they screen capture the transactions carried out by an associate on his desktop—while handling the customer. The associate can be either physically on the BPO premises connected to the LAN (in-centre) or work from home (WFM) which allows to work at-home in any country. The main purpose of this study is to compare the recording effectiveness between associates operating in the contact centre premises (in-centre) verus associates working from home. The experiments show that there is a difference in the percentage of recordings achieved for in-centre associates verus the recordings carried out for work-from-home associates. The results clearly point out the need to bring about architectural changes to improve the effectiveness in the recordings at both types of working places. This paper also undertakes the experiment to verify if rebooting or restarting a user desktop at the end of each shift can impact recording percentages in a positive manner.

Rajendra Deshpande, Ulhas Shiurkar, Satish Devane

Document Theme Extraction Using Named-Entity Recognition

The text mining can be implemented by term analysis of word or phrase. This term which describes the concepts of particular sentence is use to define the document theme. The new context-based mining technique is introduced which uses the concept-based mining model to analyze the terms present in sentence, document, and corpus levels. We find the theme of document like organization, medical, entertainment, sport, and so on. Context-based mining apply on statistical data as well as real-time data like Export data from Wikipedia. The theme of document is extracted by using Natural Language processing (NLP) for communication between computer and human languages and name entity recognition (NER) algorithm for identification of entity, entity chunking, and entity extraction. It used to get name entity in text such as person name, organization name, specific locations, time expressions, percentages quantities and so on. NLP and NER are used in context-based mining for finding name of entity and their relationship. Context Vector containing set of documents is used to extract the context of the document. Finally K-Mean algorithm is used for clustering to find inherent groupings of the text documents, then set of clusters are generated where each cluster exhibit high intra cluster similarity and low inter cluster similarity. The text document clustering is used to separate documents into groups or clusters based on their similarity so all groups define the distinct topics.

Deepali Nagrale, Vaibhav Khatavkar, Parag Kulkarni

AnaData: A Novel Approach for Data Analytics Using Random Forest Tree and SVM

Big Data has been coined to refer different types of automated and non-automated system, which generated huge amount of data like audio, video, PDF documents, medical, biometric, etc., in the form of structured, unstructured or semi-structured data. In this paper, we are representing data analytics using Random Forest Tree and SVM (Support Vector Machine). The Big Data Analytics is utilized after integrating with digital capabilities of business or other. As per our novel algorithm approach, we have modified a combination of two robust algorithms of data mining such as Random Forest Tree and SVM. To check the robustness and feasibility of our approach, we are using some statistical techniques like precision, recall, sensitivity, specificity and confusion matrix for proving accuracy and ability benchmark. At last, the accuracy and speed-up time for doing the analysis is low as compared to existing algorithm. As for the accuracy calculation, our approach ‘AnaData’ gives result as 95% approximately.

Bali Devi, Sarvesh Kumar, Anuradha, Venkatesh Gauri Shankar

A Decision Support System Using Analytical Hierarchy Process for Student-Teacher-Industry Expectation Perspective

Communication gap between expectations or requirements of student, teacher and industry is major issue for every engineering institute as well as for nation. It is necessary to make engineering or professional students skilled and employable for industries. Therefore, there is a need of proper understanding between student, teacher and industry with respect to various skills and making them aware of various engineering, professional and management practices and methodologies. The National Institutional Ranking Framework (NIRF) of Government of India (GoI) provides ranks for institutes based on various parameters however the proposed study focuses on common perspectives of student-teacher and industry for better employability, understandings and interactions. One of the parameter ‘Graduation Outcomes’ of NIRF has been used in present study. Analytical Hierarchy Process (AHP) has been applied to identify common perspective on expectations (POE) of Student, Teacher and Industry (S-T-I) for bridging the perspective gap using S-T-I survey data. The obtained result shows that there is a gap in expectations for few identified criterias among S-T-I. However these gaps can be minimized by increasing communication among S-T-I’s.

S. S. Pawar, R. R. Rathod

English Language Adoptability in Engineering Graduates: A Case Study

Unanimously accepted as Lingua Franca, English language has attained the status of global language with an important role in our daily life. Non-technical skills like problem solving, interpersonal skills, critical and independent thinking, positive attitude, active listening, a trait of enthusiasm, etc. are very important for Engineers. The prominent among all these non-technical skills is English communication skills. Engineers may become obsolete if they do not possess good communication skills in English. This paper reports the empirical study of engineering graduates regarding their adoptability towards English language in practice. The analysis was carried out with the help of a comprehensive questionnaire. It is observed that the problem of English communication can be overcome easily with a systematic approach of teaching-learning process for engineering graduates.

Sushama Deshpande, Amit Shesh, Brijesh Iyer

Design and Development of E-Care Management System for Hospitals

E-care management system is a system which provides support to doctor, patient, management and other stake holders with the required information to carry out their day-to-day routine work. It is a complete solution for recording and retrieving all possible transactions in a hospital. This system provides complete solution to patient for getting appointment from doctor, getting treatment. The main aim of this paper is to clarify the importance of linking hospitals electronically and sharing patient medical history records, so it becomes available and accessible for all authorized users throughout all the regional hospitals, which saves time by reducing queries about medical history and medical condition updates. In this paper we focused on administration modules, patient Module, doctor Module and billing Module. We developed an application named “Med Application”. It provides required information to the operational management for planning and executing their operations. This intelligent application provides all the information to the management from their day-to-day routine work to their future planning to assist the patient in all the aspects.

Mrutyunjaya S. Yalawar, Basava S. Dhanne, Rakesh Ranjan, Telugu Satyanarayana

Study of Classification Techniques on Medical Datasets

Medical science is using digital equipment and generates and gathers large volume of data. These medical datasets are analyzed to get useful information which helps in making decision about diagnosis and treatment. Data mining techniques solve the problem of knowledge extraction from databases from different sources. Several data mining methodologies like Classification, Clustering are used to analyze the data. Classification is a technique used in prediction and to classify the unknown data to a class. This paper presents a study of application of classification algorithms on different kinds of medical datasets.

Girish Kumar Singh, Rahul K. Jain, Prabhati Dubey

Feature Ensemble Learning Based on Sparse Autoencoders for Diagnosis of Parkinson’s Disease

Parkinson’s disease detection through proper representation of the vocal and speech datasets remains an important classification problem. For this problem, we proposed a feature ensemble learning method based on sparse autoencoders. The dataset for this purpose was obtained from UCI, an online repository of comprehensive datasets. Some simulations were conducted over the UCI dataset to confirm the effectiveness of the proposed model. In this paper, the outcomes of the experimentation are compared with the outcomes of stacked sparse Autoencoders and softmax classifier based deep neural network and many classification techniques. Our proposed method yields superior results than DNN. With the proposed model, we obtained a true promising accuracy more than 90%. The outcome of the study also proves that the Feature ensemble learning based on sparse autoencoders method is comparable to other methods present in the literature. The experimental results and statistical analyses are pointing out that the proposed classifier is really useful and practical model for Parkinson’s disease investigation.

Vinod J. Kadam, Shivajirao M. Jadhav

PCA Fusion for ANN-Based Diabetes Diagnostic

Diabetes is a result of inability to respond felicitously to insulin requirement for glucose regulation (sugar). In this paper, diabetes detection system is developed utilizing Principal Component Analysis (PCA) and Multilayer Perceptron Artificial Neural Network (MLPANN). Primary investigation focuses on combining source information and PCA transformed features under MLPANN framework. Confusion matrix based analysis has been performed to analysis the effect of source and PCA information fusion. In analysis standard UCI diabetes dataset, the maximum accuracy of 76.5% has been recorder for source features and accuracy of 85.2% with 6 level PCA features while fusion resulted in highest success rate of 87.8%. It acquires 15% and 3% relative accuracy increase when compared with source and PCA features used alone, respectively.

Sandeep Sangle, Pramod Kachare, Jitendra Sonawane

MHD Flow with Heat and Mass Transfer Over a Radiating Cone Due to a Point Sink in Presence of Partial and Solutal Slips

An analysis has been carried out to study the effects of velocity, thermal and solutal slips on a magnetohydrodynamic, steady, and incompressible laminar boundary layer flow with heat and mass transfer over a radiating cone due to a point sink. The problem has been solved by using a semi-analytical method called DTM-Padé. Graphical representations are obtained for velocity, temperature, and concentration distributions for various values of the governing parameters like suction/injection parameter s, magnetic parameter M, velocity slip $$\mathscr {L}$$ , thermal slip $$\delta _1$$ , concentration slip $$\delta _2$$ , radiation parameter R, Prandtl number Pr, and Schimdt number Sc. Also, the numerical results obtained for skin-friction coefficient have been compared with the corresponding results available in the literature and a good conformity has been found in between them.

Nasreen Bano Shaikh, B. B. Singh, S. R. Sayyed

MHD Stagnation-Point Dissipative Flow in a Porous Medium with Joule Heating and Second-Order Slip

The present paper deals with the MHD stagnation-point dissipative flow in a porous medium over a flat plate with variable wall temperature. The effects of viscous dissipation, Joule heating, and second-order slip on the flow field have been studied both numerically and graphically for several values of governing parameters. The physical model of the problem is governed by coupled partial differential equations reducible to a set of coupled nonlinear ordinary differential equations (ODEs) using similarity transformations. The system of the coupled nonlinear ODEs has been solved analytically using optimal homotopy analysis method (OHAM). The results obtained in the present analysis have been compared with the results available in the literature, and have been found in excellent agreement.

S. R. Sayyed, B. B. Singh, Nasreen Bano

Design Optimization of 10 nm Channel Length InGaAs Vertical Gate-All-Around Transistor (Nanowire)

This paper proposes a cylindrical vertical Gate-All-Around Transistor with nanowire of compound III-V semiconductor material In0.53Ga0.47As n-type device with channel length of 10 nm. The effect of variation of channel diameter and spacer length on the performance of the device is simulated. The device gives an acceptable Subthreshold Slope and Drain Induced Barrier Lowering along with satisfactory ION/IOFF ratio. The device is simulated in Sentaurus Synopsys using Hydrodynamic model for III-V semiconductors with Poisson equation to give the transfer characteristics.

Shreyas Kulkarni, Sangeeta Joshi, Dattatray Bade, Subha Subramaniam

Design of Micro-heater on 3D-SnO2 Gas Sensor

Design of the heater on resistive gas sensors plays an important role since the performance of the gas sensor depends on temperature of the sensing materials. Heater on the SnO2 gas sensor is designed in 3D geometry. The meander structure of heater is designed in such a way that the distribution of temperature is uniform on the sensor. COMSOL Multiphysics 5.0 simulating tool based on finite element method is used to study Joules heating in heater. Temperature of the sensor is maintained in the range of 617–621 K (344–348 °C). Uniform distribution of temperature is found on the surface of the sensors with variation of ±2 °C.

Gajendrasingh Y. Rajput, Manoj S. Gofane, Sandip Dhobale

Blackbox-Based Night Vision Camouflage Robot for Defence Applications

Camouflage robot plays a big role in saving human loses as well as the damages that occur during disasters. The main purpose of the paper is to design Blackbox with camouflage robot. One of the main features of this robot is camouflaging, i.e., sensor will catch the image of the surrounding, and the color of the surrounding will be detected by the color sensor and according to that the camouflage robot will change its color. Because of this feature, the robot cannot be easily detected by the enemies. Thus, it will gain more importance in the upcoming era. The robot basically consists of a vehicle mounted with color sensor, which is a part of camouflaging technique and night vision camera is used for observation purpose. Camouflage robot can be sent up to the required area for capturing the unusual happening from attacker. The camouflage robot basically works as an aid for the military. The motion of the camouflage robot can be operated by ZigBee module.

Harsh Surana, Nitesh Agarwal, Akash Udaykumar, Rucha Darekar

IOT-Based Wi-Fi Surveillance Robot with Real-Time Audio and Video Streaming

In this paper, the wireless robot refers to the mini robot which live streams the monochromatic video, takes and stores the images. The robot is being controlled through a local Wi-Fi server by a compatible web page. The objective of the proposed method is to implement the aforementioned technology pertaining to the mini robot, which is capable of performing multiple tasks at an affordable cost. Arduino Uno R3-Based Robot Control Board will be used to design the robot and. In this paper, we have proposed a surveillance robot with the facility of real-time video streaming, audio transfer, and ability to avoid obstacles in the process. The system will be designed as such to stream the video live to the person monitoring the robot. We have used two Android phones in the proposed method for the purpose of video streaming and audio transfer. An entire new approach for controlling the robot through web page has been used. We have used NodeMCU ESP Module, to incorporate wireless connectivity in the proposed method.

Diksha Singh, Anil Nandgaonkar

Genetic Algorithm Approach for Obstacle Avoidance and Path Optimization of Mobile Robot

The path planning is an important issue of mobile robots. Its task is to find a collision free path from the start position to the target position with an algorithm which requires less time and minimum path distance. The scheduling and planning is NP-Hard (NP-Complete) problem. Autonomous robot vehicles can be used in variety of applications including space exploration, household and transportation. In known static environment path planning algorithms such as Sub Goal network, A* algorithm, D* Star algorithm, Artificial Potential Method are used. These are classical and heuristic search based algorithms. The above mentioned algorithms have some drawbacks such as local minima, deadlock of robot, and oscillation of robot. We have proposed an algorithm which will overcome these drawbacks present in existing classical algorithms.

Sunil B. Mane, Sharan Vhanale

Performance Verification of DC–DC Boost Converter

The DC–DC boost converters had marked their importance in the field of renewable energy sources with their excellent features. Along with the time, various topologies of boost converters have been introduced to enhance its efficiency and make it more reliable. These boost converters are associated in many applications along with certain drawbacks and a research trend is developed to improve the performance of boost converters. This paper carries out the simulation of the proposed converter and tries to prove the effectiveness of the converter that overcomes the drawbacks of many boost converter topologies such as low voltage gain, high-input ripple current, high duty ratio, high inductor core losses and high stress on switch. The simulation has been performed on PSIM tool and the results of the proposed converter are verified using PSIM software.

Vaibhav Marne, K. Vadirajacharya

Comparison of Multiple Attribute Decision-Making Methods—TOPSIS and PROMETHEE for Distribution Systems

Distribution system (DS) is considered the weakest link in the power system with 5–13% technical losses. Utilities are under pressure to trim down these losses, improve reliability, and power quality of supply to consumers in the deregulated, competitive environment. This has attracted researchers again for reconfiguration with many alternatives available for decision-making such as losses, power factor, voltage profile, cost, and reliability indices like SAIFI, SAIDI, CAIFI, AENS, etc. Multi-Attribute Decision-Making (MADM) is one such popular method available for decision-making which deals with problems through a number of qualitative and quantitative criteria in reconfiguration. In this paper, MADM methods like TOPSIS and PROMETHEE are proposed for finding the compromised best configuration by considering loss minimization, and reliability indices from available alternatives. Two examples are furnished in this paper to show the effectiveness of the methods.

S. G. Kamble, K. Vadirajacharya, U. V. Patil

Interconnection of Grid and Renewable Energy Sources Using Voltage Source Inverter

Nowadays renewable energy is used in large amount to compensate the grid power need and for onsite production in remote places. Due to variable nature of renewable energy sources and due to high penetration level of intermittent renewable energy sources they pose power quality problems to the system which can be resolved by using power electronics technology. In this paper voltage source converter based interconnection technology is demonstrated, a four leg VSI is used as interconnecting device between renewable energy source and grid network. A closed loop SPWM technique is used for controlling the VSI. It gives improved power quality features by reducing the harmonic content in the RES system and better control on duty cycle of the VSI. The performance of designed controller is verified on PSIM platform.

Anish Vijay Patil, K. Vadirajacharya

Performance Comparison of Sliding Control Law for Dynamical Systems

In this paper, a sliding mode control approach with PID sliding surface and first-order filter are implemented for single-input-single-output (SISO) devices. The proposed controller performs satisfactorily even for parameter variations in the system. In order to verify the applicability to the disturbances, an external load is applied and the performance of the controller is validated. The stability can be tested using the concept of Lyapunov stability theorem. In sliding mode approach, the effect of chattering phenomenon is significantly reduced by selecting appropriate switching (gain) of interest along with the known parameters of the system. In case of the proposed approach, it can verified that this approach has applications to the physical systems. The applicability and the performance of the proposed control structure are confirmed by a simulation example and the analysis of the proposed controller is carried out with the similar controllers available in the literature.

S. S. Sankeswari, R. H. Chile

A Novel Method for Detection of Atrial Fibrillation Based on Heart Rate Variability

Atrial Fibrillation (AF) detection is one of most important part of clinical testing. We propose a novel method to detect AF episodes based on heart rate variability feature of AF. In this method, scatter plot of the heart rate is found and histogram of the Y axis data of scatter plot is used for calculations. Depending upon amount of data present in each bin of histogram ECG signal is classified as Atrial Fibrillation (AF) or Normal Sinus Rhythm (NSR). Physionet 2017 challenge database, MIT-BIH AF database and MIT-BIH NSR database are used to validate the algorithm. Physionet Challenge contains 5787 ECG records of 30/60 s classified as AF or NSR, MIT-BIH AF database contains 25 full length ECG records and MIT-BIH NSR database contains 18 full length ECG records. Using the method, we got the accuracy of 97.23% for Physionet 2017 challenge database and 97.15% for MIT-BIH AF database. MIT-BIH NSR database didn’t show any AF episode. This method can also be used for real time monitoring of ECG for AF detection.

Akib Shah, Vaishali Ingale

Investigation on Daubechies Wavelet-Based Compressed Sensing Matrices for ECG Compression

In this paper, we have investigated the different Daubechies (DB) wavelet-based compressed sensing (CS) matrices, namely db3, db4, db5, db6, db7, db8, db9, and db10 measurement matrices for ECG compression. The performance of the proposed Daubechies wavelet-based measurement matrices and state-of-the-art measurement matrices are evaluated using different performance measures such as Compression Ratio (CR), PRD, SNR, RMSE, and signal reconstruction time. The result demonstrates that the db3 and db10 measurement matrices outperform the state-of-the-art measurement matrices. Moreover, db3 and db4 measurement matrices show superior performance compared to db4, db5, db6, db7, db8, and db9 measurement matrices. Thus, this study exhibits the successful implementation of Daubechies (DB) wavelet-based sensing matrices for ECG compression.

Yuvraj V. Parkale, S. L. Nalbalwar

Statistical Characterization of an Underwater Channel in a Tropical Shallow Freshwater Lake System

Underwater acoustics has made significant strides over the last century, which finds applications over a wide range from basic bathymetry study to high-end research extensions. The acoustic propagation in underwater is typically governed by physical properties of the underwater channel, such as temperature, pressure, and salinity. The seasonal fluctuations in the physical properties of the tropical region manifest as thermal stratification. The random thermal stratification has a significant impact on the Sound Speed Profile (SSP), thereby distorting the received echoes from the surface and the bottom. The site-specific behavior in the tropical region makes it an interesting research problem to investigate the correlation of the surface parameters like temperature with the surface and bottom reflection due to variations in the SSP. In this work, we attempt to present underwater channel characteristics of the tropical freshwater lake system at Khadakwasla (18.43° N, 73.76° E), located in the municipal limits of Pune city in India. The temperature gradient along the water column is computed using the one-dimensional Freshwater Lake Model (FLake) to derive the SSP using Medwin relation. The statistical analysis of the sound speed fluctuations resulted due to seasonal variation in the water temperature is presented using the Kolmogorov–Smirnov (KS) Goodness-of-Fit test is used to find a close Probability Density Function (pdf) match for the surface and the bottom path impulse response. The results indicate a good match of the surface and bottom path impulse response with Weibull distribution with a high confidence level. Such characterization can facilitate the design of adaptive algorithms to minimize the underwater channel impact based on a precise estimate of the channel impulse response.

Jyoti A. Sadalage, Arnab Das, Yashwant Joshi

Nonuniform Frequency Sampling Approach to FIR Filter Design

This paper investigates the new approach to FIR filter design based on nonuniform frequency sampling. This method generates the nonuniform samples in passband and stopband separately using Gaussian function. For the generated nonuniform sample, the desired frequency response values are generated using ideal filter characteristics. Then, taking its nonuniform IDFT gives the required filter coefficients. The proposed method is compared with existing methods like uniform frequency sampling and optimal filter design method and results show that the investigated approach has a better advantage over uniform frequency sampling and Parks–McClellan method with regard to the frequency response of designed filter.

Mahesh Ladekar, Yashwant Joshi, Ramchandra Manthalkar

Detection of Epileptic Seizure Using Wavelet Transform and Neural Network Classifier

The electroencephalograph (EEG) signals are most widely used for identification of neurological diseases like epilepsy, Alzheimer’s, and other brain diseases. Detection of epileptic activity requires a detailed analysis of the entire length of the EEG data. In this paper, we proposed an automated detection of epileptic seizure using energy distribution of wavelet coefficient in each sub-band frequencies of the EEG signals. The performance of the proposed method is investigated using signals obtained from public EEG database at the University Hospital Bonn, Germany. Initially, the EEG signals are de-noised and decomposed into sub-bands using discrete wavelet transform (DWT), Then wavelet energy distribution in each sub-band is calculated and used as a feature set. Finally, artificial neural network (ANN) used to classify the feature set with ANN. The method was tested on EEG data sets obtained from that belongs to three subject groups: (a) healthy, (b) seizure-free interval, and (c) epileptic syndrome during a seizure. The test result shows that the proposed method for detecting epileptic seizure can achieve an overall classification accuracy of 95%. The proposed method can be used efficiently for recognition of epileptic seizures.

S. M. Wani, S. Sabut, S. L. Nalbalwar

Comparative Analysis of ICA, PCA-Based EASI and Wavelet-Based Unsupervised Denoising for EEG Signals

Electroencephalography (EEG) can be used to study various brain activities related to human responses and disorders. EEG signal is prone to noises which are caused due to eye movements, power-line interference, muscle movements, etc. Therefore, to obtain refined EEG signals for further processing, it should be denoised. There are several methods by which EEG signals can be denoised, among which we have used Independent Component Analysis (ICA), Principal Component Analysis (PCA)-based Equivariant Adaptive Separation by Independence (EASI), and Wavelet-based unsupervised denoising methods. The performance of these methods is compared using Signal-to-Noise Ratio (SNR) and Percentage Root-mean-square Difference (PRD).

Ankita Bhatnagar, Krushna Gupta, Utkarsh Pandharkar, Ramchandra Manthalkar, Narendra Jadhav

Analyzing Effect of Meditation Using Higher Order Crossings and Functional Connectivity

People are experiencing difficulties in adapting to the rapid changes in work and social fabric due to the evolution of advanced technologies in everyday life. Health and well-being of an individual in the existing world is important for proper living. Meditation improves the adaptability of an individual to live a healthy and social life. To verify this, an experiment is designed with the simple meditation practice called Focused Attention for 8 weeks. The brain activity is recorded of 11 subjects using EMOTIV EPOC+ EEG device before (pre-meditation) and after (post-meditation) meditation. Features called Higher Order Crossings and Functional Connectivity are used to analyze the effect of meditation. The results indicated a decrease in HOC values for frontal, parietal, and occipital lobes and increase in HOC of temporal lobe. The interhemispheric connectivity increased after meditation practice.

Shruti Phutke, Narendra Jadhav, Ramchandra Manthalkar, Yashwant Joshi

The Detrended Fluctuation Analysis of EEG Signals: A Meditation-Based Study

The Detrended Fluctuation Analysis is a widely used method for analysis of non-stationary time series which has been applied to EEG signals. The Detrended Fluctuation Analysis (DFA) of the EEG signals in pre- and post-meditation (mindfulness) intervention are compared. It is observed that the EEG data obtained from 8 subjects out of total 11 subjects shows reduction in the DFA values. The reduction in DFA values represents the lower intrinsic fluctuations in the EEG time series, which is a measure of better (higher) complexity of these vital rhythms. The reduced DFA values after 8 weeks of Focused Attention (mindfulness) meditation practice in more number of subjects, indicates that the meditation practice enhances the ability to handle complexity. The reduced DFA values indicate improved neuronal functioning of these subjects.

Sunil R. Hirekhan, Ramchandra Manthalkar, Shruti Phutke

Convex Optimization-Based Filter Bank Design for Contact Lens Detection

We have designed a novel convex optimization-based filter bank (FB), which minimizes the frequency band errors and optimizes time–frequency localization at the same time. The designed FB is regular and satisfies the constraint of perfect reconstruction (PR). In convex optimization, we have optimized quadratic constrained quadratic programs by transforming it into a semidefinite program. We have also compared the frequency band errors and time–frequency localization of proposed FB with existing FB. We have used this FB for designing a new contact lens detection (CLD) system. The IIITD database has been used for this purpose. The results have been expressed in terms of correct classification rate (CCR). The superiority of the designed FB has been shown by comparing the results with other existing CLD systems. The newly designed FB can also be effectively used for various signal processing applications.

Swati Madhe, Raghunath Holambe

EEG Waveform Classification Using Transform Domain Features and SVM

Electroencephalogram (EEG) waveforms are fluctuations in brain-recorded utilizing anodes set on the scalp. Albeit a few strategies for the evaluation of working of brain, for example, MEG, PET, CT scan, and MRI have been presented, the EEG waveform is as yet an important biological signal for checking the brain signal variations because of its moderately ease and being helpful for the patient. We have presented an approach to classify the EEG waveforms into two classes, viz. epileptic and normal. The algorithm fuses the features extracted using discrete wavelet transform, discrete cosine transform, and stationary wavelet transform. The fused features are subjected to support vector machine (SVM) classifier.

Hemprasad Y. Patil, Priyanka B. Patil, Seema R. Baji, Rohini S. Darade

Colour-Adaptive Digital Image Watermarking Technique

Copyright protection and owner authentication have become necessary due to the circulation of large number of documents, images, audios, and videos through the internet. Manipulations and duplications in multimedia files and documents are very easy due to advancement in the signal and image processing algorithms. Therefore, it is very much important to devise watermarking techniques that are robust against geometrical distortions and collision attacks. In this paper, we proposed an adaptive digital image watermarking technique through colour features and Arnold transform in wavelet domain. An attempt has been made to adaptively transform the watermark image into a set of textures that visually match the colour of the input host image since colour features are invariant with respect to translation and rotation of the image. We first separate the three colours R, G, and B of the host and watermark image. Next, we decomposed the separated images using wavelet transform into sub-bands. Finally, low-frequency sub-band of the watermark image is embedded into low-frequency sub-band of the host image using Arnold transform. Experimental results on multiple host images and under various attacks using PSNR and correlation coefficient, clearly demonstrates that the proposed algorithm is robust and can be applied in colour image watermarking.

Shailesh Sapkal, B. G. Hogade

Improved Version of Tone-Mapped Quality Index

High Dynamic Range (HDR) images were evolved to display smallest details of the captured image with high standards. To display HDR images on Low Dynamic Range (LDR) monitors compression is required, which is done by Tone Mapping Operators (TMOs). Recently, there are a lot of tone mapping algorithms that are available in market. Different TMO creates images with different quality. To measure the quality of such images Tone-Mapped Quality Index was proposed (TMQI). TMQI mainly depends on the two parameters. The first is structural fidelity (SF) which is very similar to structural similarity and the second, is statistical naturalness (SN). The limitation of TMQI-1 is some parameter is image independent described in below sections so, improved model TMQI-2 is proposed in this paper. In order to further improve the quality of image, iterative optimization algorithm is used. Our experimental results show that TMQI-2 is better than earlier TMQI. Further, iterative optimization increases the overall quality of image.

Tushar Mane, S. S. Tamboli

Robust Exemplar-Based Image and Video Inpainting for Object Removal and Region Filling

Inpainting is an art that restores old and damage image. Exemplar-based inpainting uses the patch-based approach. It uses patches to fill the target region of the image. Also, it uses simultaneously the texture synthesis and structural propagation. But after some iteration, the dropping effect of confidence term occurs in this method. The robust exemplar-based method avoids dropping effect by using robust priority function. The proposed video inpainting method is based on the robust exemplar-based inpainting algorithm using region segmentation. Our algorithm uses a robust priority function to avoid dropping effect and region segmentation to determine the adaptive patch size and reduced search region. The experimental results show the effectiveness of our method.

Ashvini V. Pinjarkar, D. J. Tuptewar

Comparative Analysis for Steganographic LSB Variants

Combining the best features of steganography and cryptography is the trending concept which is being followed for the purpose of information security. Hence, this combination is making the data more powerful and secure against the prevailing security attacks and breaches. This paper represents the implementation of this combination on the two LSB variants, namely sequential LSB and randomized LSB. A comparison among the two approaches is carried out by adding a secret text into a video cover file. The concept of chaotic sequence has been used as the security approach that converts the secret data into random bits pattern. The proposed work uses the traditional LSB approach as basic steganographic model. The inference on the basis of parameters concludes that the randomized LSB shows better results than the sequential LSB scheme.

Namrata Singh, Jayati Bhardwaj

Integrating Machine Learning Tool to Improve DSS Design

This paper describes how a machine learning tool can be applied to decision support system. We have used fuzzy logic to enhance performance of DSS. Further, system developed is implemented in agriculture domain for selection of suitable crop. Selection of crop is complex process as it involves number of parameters where uncertainty is more common for example rainfall, suitable seeds, fertilizers, number of soil parameters, temperature, air quality, humidity, and so on. The present work focuses on soil parameters and few other parameters which support proper growth of crops. Fuzzy logic is applied to those parameters for handling data uncertainty. This is an attempt to suggest proper decision and reduce the burden by designing new DSS. Experimental set-up shows increased crop production up to 10–12%.

R. G. Joshi, H. S. Fadewar

PSO-Based Text Summarization Approach Using Sentiment Analysis

In the present era of technology, most of the human activities are controlled and monitored by the electronic devices and still, people are working for more advanced technology and hence to fulfill the customers requirement. Government is also promoting digitization of data which results in large volume of data. To manage digital data, some approach is required to retrieve the data efficiently. Till now, so many techniques have been proposed for retrieving data in original form as well as compact form. This paper focuses on the technique for retrieving the data (text) in compact form or summarizes form. To achieve this goal, the concept of Particle Swarm Optimization (PSO) with sentiment analysis has been used. PSO has been used in the field of text summarization and the result is remarkable. Besides PSO, Sentiment Analysis (SA) has been proved its importance in the same research field.

Shrabanti Mandal, Girish Kumar Singh, Anita Pal

Face Recognition Using Eigenfaces

In this paper, we propose a PCA-based face recognition system implemented using the concept of neural networks. This system has three stages, viz. pre processing, PCA and face recognition. The first stage, preprocessing performs head orientation and normalization. The aspects that matter for the identification process are ploughed out using Principal Component Analysis (PCA). Using the initial set of facial images, we calculate the corresponding eigenfaces. Every new face is presented into the face space and is characterized by weighted-sum of corresponding eigenfaces that is used to recognize a face. To implement this face recognition system, we have created a database of faces with the help of neural networks and we have built one separate network per person. We obtain a descriptor by projecting a face as input on the eigenface space, then that descriptor is fed as input to the pre-trained network of each object. We select and report that which has the max output provided it passes the threshold already defined for the recognition system. Testing of the algorithm is done on ORL Database.

G. Md. Zafaruddin, H. S. Fadewar

Multi-focal Image Fusion with Convolutional Sparse Representation and Stationary Wavelet Transform

This paper illustrates a completely unique technique of multi-focus image fusion involving Stationary Wavelet Transform (SWT) and Convolutional Sparse Representation (CSR). Sparse-based fusion strategies do not retain information representation and cannot tolerate minor mistakes in registration. The SWT method does not have these issues. Multi-focus image fusion is the fusion of different parts of digital images, representing the common scene, in order to produce an image with everything in Focus, i.e., without the blur effect. Camera processors cannot fuse images by themselves. Thus, experts have to employ image editing methods to obtain clear photographs. The scheme stated in this paper uses SWT to distinguish focus levels accurately. The results suggest that the strategy is successful in ways comparable in terms of visual quality and clarity.

Gandhali A. Pawar, Sujata Kadam

Fuzzy Deep Learning for Diabetes Detection

The use of science for the betterment of society is the main cause for research for years. That is the reason the framework of diabetes diagnosis is always changing with new dimensions. The new and advance algorithms on the horizons are tried in hope of getting better accuracy and speed. Apart from normal algorithms researchers have tried the possible hybrid combinations. In recent times, the Convolution Neural Network (CNN) has outperformed most of the application areas of traditional prediction algorithms. Here is an attempt to use the deep convolutional neural network for diagnosis of diabetes. This work has two major contributions, first is the application of CNN for diabetes detection and second is data fuzzification in matrix form to suit needs of CNN. In the experiments, the comparison is made between classical NN and CNN for diabetes detection. Results prove that fuzzification of data significantly improves the accuracy of CNN and CNN outperforms classical NN.

Tushar Deshmukh, H. S. Fadewar

Classification of Magnetic Resonance Brain Images Using Local Binary Pattern as Input to Minimal Complexity Machine

Magnetic Resonance Imaging (MRI) is a powerful visualization tool that is extensively used in medical laboratories to capture images of internal anatomy of human body. Classification of MRI brain images into tumorous and non-tumorous image is a critical and time-consuming task for the radiologist. Correct and computerized classification of MRI brain images is very important for their investigation and analysis. In this paper, we have proposed to use binary patterns (LBP) as features to classify MRI brain images into tumorous and non-tumorous. The LBP computes the relationship between central pixel and neighboring pixels of the 3 × 3 window and assigns a label to each window. The histogram of these labels is then used as a feature vector that is fed into the classification stage. The images are classified using Minimal complexity machine (MCM) algorithm. As compared to Support Vector Machine (SVM) algorithm, MCM performs better generalization and makes use of lesser number of support vectors. The performance analysis of the proposed techniques is done on the basis of accuracy calculated, and it is found that the classification rate is superior to other existing algorithms.

Heena Hooda, Om Prakash Verma

Underwater Image Colour Balance by Grey World Approach with Attenuation Map

Underwater images are degraded by attenuation of light in water. This attenuation depends upon wavelength and depth in water. One of the effects of degradation of image in water is absorption of colour giving greenish-blue hue to the image. Because of this colour fading of underwater images, colour correction is the first preprocessing step in underwater image processing. Many researchers attempted colour correction methods but most of it operates globally. Global colour correction methods give reddish effect to image. The method proposed in this paper used Grey World approach for colour correction, but it is modified using attenuation map. Use of attenuation map avoids saturation of colours and colour corrects only those pixels which are significantly attenuated. Results of the proposed method are compared with state-of-the-art methods by quality metrics mean square error, structural similarity index and entropy of image. It is seen that the proposed method in this paper gives better results than state-of-the-art methods.

Sonali Sankpal, Shraddha Deshpande

Technique of Face Recognition Based on PCA with Eigen-Face Approach

PCA is utilized in the area of recognition of face, fingerprint, handprint, industrial robotics, and mobile robotics. In the face recognition, research shows that the success rate is not satisfactory for a variant of poses which have rotation gap of more than 30°. If there are lots of variations in lightning, expressions, and pose variation, then PCA results are not up to the mark in the existing algorithm. This problem is arising in mind. The objective of the present paper is to study and propose modified PCA and Eigen-face-based algorithm to improve result with the accuracy of face recognition. In this paper, we focus on the pose variations which have 30° range of pose in image.

C. B. Tatepamulwar, V. P. Pawar, S. D. Khamitkar, H. S. Fadewar

Analysis of Face Recognition Algorithms for Uncontrolled Environments

Face recognition is a challenging problem in biometric systems, which has received a lot of attention in the last two decades as it has numerous applications in computer vision and pattern recognition. There is remarkable progress in the face recognition systems under controlled conditions, but they degrade for uncontrolled conditions like pose, illumination, expression, and occlusion etc. In this paper, we discussed different algorithms like PCA, DCT, LDA, ANN, ICA, HMM, and Wavelet with its pros and cons. The different face database used for face recognition is discussed. It also discusses various challenges and possible future directions for face recognition task.

Siddheshwar S. Gangonda, Prashant P. Patavardhan, Kailash J. Karande

Line Scratch Detection in Old Motion Picture

Detecting line scratch in motion is a tedious job because it requires spatial as well as temporal features needs to be extracted. Scratches are caused by abrasion of film material as it passes through projection mechanism. One main problem in this is false detection. Spatial algorithm is used to detect scratch inside the frame using frame-wise scratch detection and temporal algorithm is used for filtering false detection. Preprocessing is required to get fine results. Experiment result shows the detection of line scratches in motion picture.

Mukkawar Vinayak, Jondhale Kalpana

Underwater Image Enhancement by Rayleigh Stretching with Adaptive Scale Parameter and Energy Correction

Attenuation of light in water causes degradation of underwater images. This attenuation is caused by water molecules, suspended particles, and dissolved chemical compounds in water. The attenuation includes scattering and absorption of light in water. Backward scattering and fading of color are two major sources of degradation of underwater images. This paper proposed a method of enhancement of underwater images by providing a solution for degradation because of backward scattering. The proposed method corrects the effect of backward scattering by enhancing contrast of the image by Rayleigh stretching of each color channel using maximum likelihood estimation of scale parameter. After contrast enhancement, loss of energy in the signal is corrected, that recovers information loss caused by contrast enhancement. The results of the proposed method are compared quantitatively with state-of-the-art methods by applying it to underwater dataset. Comparison is done with mean square error (MSE), Structural SIMilarity index (SSIM), and Average Information Entropy (AIE) quality metrics. It is seen that the proposed method in this paper produces best results when compared with state-of-the-art methods.

Sonali Sankpal, Shraddha Deshpande

Medical and Color Image Compression with Fractal Quadtree with Huffman Coding for Different Threshold Values

Fractal Image Compression (FIC) is characterized by long encoding time and high Compression Ratio (CR). Further, as medical images being voluminous, a high CR is required to reduce the storage space. Fractal Image compression adopts affine transforms. In view of this, the present paper aims in providing an implementation of a hybrid approach by combining Quadtree fractal with Huffman coding with different threshold values and a comparative analysis of the different types of input images such as color as well as different modalities of medical images as MRI and X-ray to achieve high CR by still retaining the quality of the image. The implementation is carried out and results are obtained using MATLAB. The performance parameters as encoding time, compression ratio PSNR, and decoding time are compared. The results have shown that with an increase in threshold value, CR increases with a decrease in image quality for color as well as medical images.

Sandhya Kadam, Vijay Rathod

A Novel Method to Detect Fovea from Color Fundus Images

The computer-aided diagnosis technology in retinal image analysis requires localization of different fundus structures. Efficient detection and localization of fovea are essential in the analysis of diabetic macular edema. This paper demonstrates a novel technique for detection of fovea from color fundus images based on image enhancement by adaptive manifold filter and further mathematical morphological operations for final foveal center localization. The major advantage of the proposed technique is that it does not need a spatial relationship of optic disc and vessels for the detection of fovea. It is robust to illumination changes and interference caused by retinal pathologies. Experiments show encouraging results that are analyzed on five publically available databases DRIVE, HEI-MED, DIARETDB1, HRF, and MESSIDOR with an accuracy of detection as 100%, 99.40%, 98.88%, 100%, and 98.66%, respectively. Comparative analysis of results indicates that the proposed method achieves better performance than other earlier methods present in the literature.

Samiksha Pachade, Prasanna Porwal, Manesh Kokare

Detection of Malaria Parasite Based on Thick and Thin Blood Smear Images Using Local Binary Pattern

Malaria is one of the dangerous diseases transmitted by a female Anopheles mosquito through parasites. Parasite is a type of microorganism. Microscopic examination of blood samples helps to diagnose malaria automatically and faster. It also reduces the time and human errors. This paper aims to experiment and analyze quickly the accurate number of malaria parasites using image processing techniques. Local binary pattern (LBP) technique is used to classify blood smear into thin and thick blood smears. Morphological operations and k-means clustering techniques along with intensity profiles within the cells are used to count infected cells. The experiments are performed over standard datasets using segmentation and morphological operations for thick and thin blood smear images. The performance of the proposed algorithm is evaluated using confusion matrix. The results are compared using sensitivity and specificity. This method proves to be much effective in terms of time considering large rural areas in India.

Satishkumar L. Varma, Satishkumar S. Chavan

Gender Identification from Frontal Facial Images Using Multiresolution Statistical Descriptors

Gender identification is a significant task which is very useful in many computer applications like human–computer interaction, surveillance, demographic studies, and forensic studies. Being one of the most popular soft biometrics, gender information plays a vital role in improvement of the accuracy of biometric systems. In this paper, we have presented an approach based on multiresolution statistical descriptors derived from histogram of Discrete Wavelet Transform. First, the input facial image was enhanced by applying contrast limited adaptive histogram equalization. During feature extraction, multiresolution statistical descriptors were computed and fed into the Nearest Neighbor, Support Vector Machine, and Linear Discriminant Analysis classifiers respectively. We have achieved encouraging accuracy for gender identification on complex dataset of frontal facial images.

Prabha, Jitendra Sheetlani, Chitra Dhawale, Rajmohan Pardeshi

Captioning the Images: A Deep Analysis

Image captioning is one of the fundamental tasks in machine learning since the ability to generate text captions of an image can have a great impact by assisting us in day-to-day life. However, it is not just an object classification or recognition task, because the model must know the dependencies among the recognized objects and their attributes and encode that knowledge correctly in the caption using a natural language like English. Recently, the internet is overwhelmed with the huge amount of textual and visual data consisting of billions of unstructured images and videos. Meaningful captions will serve as useful keys for retrieval, creative searching, and powerful browsing of these images. In this paper, we present the goal of analysis and classification of the recent state-of-the-art in image captioning and discuss significant differences among them. We provide a comparative review of existing models, techniques with their advantages and disadvantages. Future directions in the field of automatic image caption generation are also explored.

Chaitrali P. Chaudhari, Satish Devane

Age-Type Identification and Recognition of Historical Kannada Handwritten Document Images Using HOG Feature Descriptors

Most of the historical Kannada handwritten documents are preserved in the manuscript preservation centre and archaeological departments. The historical Kannada handwritten documents are generally degraded in nature, due to this degradation, the documents are impossible to read and understand the contents. Hence, it is very much essential to restore by digitizing the historical Kannada handwritten documents and also recognize the originality of the dynasty to which it belongs. The main objective of the research work is to reconstruct, digitize and recognize the historical Kannada handwritten document images by applying image enhancement techniques and obtain the HOG feature descriptors using K-nearest neighbour (K-NN) and SVM classifiers. In this paper, we have considered historical Kannada handwritten document images of different dynasties based on their age-type; Vijayanagara dynasty (1460 AD), Mysore Wadiyar dynasty (1936 AD), Vijayanagara dynasty (1400 AD) and Hoysala dynasty (1340 AD) for experimentation. The average classification accuracy for different dynasties: in case of K-NN classifier is 92.3% and SVM classifier is 96.7%, It is observed that the SVM classifier has got a good classification performance comparatively K-NN classifier for Historical Kannada handwritten document images. The experimental outcomes are tested with manual results and other methods in the literature, which show the thoroughness of the proposed technique.

Parashuram Bannigidad, Chandrashekar Gudada

Image Inpainting for Hemorrhage Detection in Mass Screening of Diabetic Retinopathy

Diabetic retinopathy (DR) is one of the main causes of vision loss. The severity of DR can be analyzed using human retinal images (fundus image). Affected fundus image consists of hemorrhages, microaneurysms, and exudates along with blood vessels. In order to accurately detect the level of severity of the disease, the blood vessels are inpainted using fast marching method (FMM). The technique implemented in this paper involves image enhancement using green channel image and histogram equalization followed by mask generation and inpainting. The severity of the disease can be categorized accurately by inpainting the blood vessels using FMM. The proposed technique is tested using standard test databases HRF and DRIVE. The algorithm can be effectively used for mass screening of DR. This technique is a fundamental step in designing computer-aided diagnosis system for ophthalmic disorders.

Anupama Awati, H. Chinmayee Rao, M. R. Patil

Performance Analysis and Implementation of DES Algorithm and RSA Algorithm with Image and Audio Steganography Techniques

In today’s era, data security is an important concern. It is most demanding issue nowadays. It is essential for people using online banking, e-shopping, reservations, etc. The two major techniques that are used for secure communication are Cryptography and Steganography. Cryptographic algorithms scramble the data, so that the intruder will not be able to retrieve it; however, steganography covers that data in some cover file, so that the presence of communication is hidden. There are some techniques that integrate cryptography and steganography to provide multi-layer security. This paper shows the comparison of such two techniques. These are “RSA cryptography with image steganography and with audio steganography” and “DES cryptography with image steganography and with audio steganography”. Stimulated results have been presented using MATLAB software.

Ankit Gambhir, Khushboo, Rajeev Arya

Content-Based Image Retrieval Using Color and Texture Features Through Ant Colony Optimization

Content-based image retrieval (CBIR) is retrieving relevant images from the large image database through visual characteristics. Each image in the database and query image is represented through feature vector derived from color and texture features in the image. These feature vectors are compared for relevance to obtain similar images in CBIR system. Therefore, length of the feature vector is very important in the CBIR system. Higher length of the feature vector increases number of comparison and in turn, increases the computational complexity, whereas lower length of the feature vector reduces comparison and complexity. In this paper, performance of the proposed CBIR system using color and texture feature extraction through histogram and Gabor wavelet transform, respectively, is presented. It is necessary to extract all the features of each image from image database and query images. These features are further presented for ant colony optimization to reduce the length of the feature vector. These final features are used in image retrieval process. Experiment results clearly show that the proposed CBIR system through ant colony optimization algorithm performance is better than other algorithms by 1.8% with respect to precision and recall. Also, the proposed algorithm clearly demonstrates the improvement by 10% on the precision and recall using only color and texture features. One of the biggest advantage and improvement was reduction in retrieval time in comparison with the other algorithms.

Nitin Jain, S. S. Salankar

Correction to: Performance of Internal Cluster Validations Measures For Evolutionary Clustering

Correction to: Chapter “Performance of Internal Cluster Validations Measures For Evolutionary Clustering” in: B. Iyer et al. (eds.), Computing, Communication and Signal Processing, Advances in Intelligent Systems and Computing 810,

Pranav Nerurkar, Aruna Pavate, Mansi Shah, Samuel Jacob


Weitere Informationen