Skip to main content
Top

2021 | Book

Advances in Information Communication Technology and Computing

Proceedings of AICTC 2019

Editors: Dr. Vishal Goar, Dr. Manoj Kuri, Dr. Rajesh Kumar, Prof. Tomonobu Senjyu

Publisher: Springer Singapore

Book Series : Lecture Notes in Networks and Systems

insite
SEARCH

About this book

This book features selected research papers presented at the International Conference on Advances in Information Communication Technology and Computing (AICTC 2019), held at the Government Engineering College Bikaner, Bikaner, India, on 8–9 November 2019. It covers ICT-based approaches in the areas ICT for energy efficiency, life cycle assessment of ICT, green IT, green information systems, environmental informatics, energy informatics, sustainable HCI and computational sustainability.

Table of Contents

Frontmatter
Blockchain Integrated Secured Scenarios in Advanced Wireless Networks

The wireless networks are nowadays quite susceptible towards the assorted assaults, and thereby the needs arise to secure the overall scenarios. The Blockchain technology is one of the prominent and high-performance approaches that can be used for the integration of security with wireless networks to enforce a greater degree of security and overall performance. Blockchain refers to the high-performance and security-aware technology in which a digital ledger is maintained. The digital ledger is quite transparent, and there is no scope of any manipulations in the records by the intermediates or any administrator. The records of all the transactions are logged in the Blockchain ledger, and the operations are committed finally with different protocols and algorithms which cannot be hacked by the third-party intrusions.

Kailash Aseri
Analysis of Docker Performance in Cloud Environment

In the present scenario, the technology is going very different, and this difference lies on different–different platforms. The platform is assured of reliability, consistency, and quickness. These bundles of quality are called container (Docker and LXC). Container helps to produce operational efficiency, version control, developer productivity, and environment consistency. The technical industry is adopting the container technology in both internal and commercial uses. In this paper, we analyze the performance of Docker by using different applications or tools in cloud environment.

Deepika Saxena, Navneet Sharma
A Review of Metaheuristic Techniques for Solving University Course Timetabling Problem

Educational timetable generation is one of the major administrative requirements in schools and universities. University course timetabling problem falls in the category of NP-hard problems having various constraints, objectives, and limited resources. Generating an optimized timetable is challenging and time-consuming process. The objective here is to present a concise review of some recent techniques that researchers have tried to resolve university course timetabling problem having single/multiple objectives.

Manpreet Kaur, Sanjay Saini
Using Social Media Analytics to Predict Social Media Engagement Outcome for Fortune CEOs

Social media has been broadly adopted by corporates for communicating and networking. Social media platforms help firms in building a relationship with the outside world. The study highlights how the adoption of social media is changing the way firms connect with their stakeholders. It highlights how CEOs’ social media engagement on behalf of the firm contributes to building up firms’ reputation amongst consumers. Influencer CEOs from top Fortune 500 companies have been used for this purpose. Social media analytics has been used in this study to get relevant insights from Twitter using methods of content analytics. Mining of user-generated content and further analysis of its impact on engagement outcome of CEOs has been done using methods such as web-scraping, topic modelling, bag-of-words, and dictionary methods. The study analyses CEOs’ engagement with tweets specific to a firm’s orientation towards adopting sustainable development goals (SDG). The study reveals how SDG-related messages on the Twitter timeline of CEOs have high user engagement and helps build customer reputation.

Hitesha Yadav, Arpan K. Kar, Smita Kashiramka
Smart Heart Attack Forewarning Model Using MapReduce Programming Paradigm

The information and communication technology (ICT)-related exponential growth has increased the demand for big data analytics (BDA). BDA involves the handling of a gigantic data for storage and investigation. The evolving field of BDA owns many challenges in various fields including drug delivery, healthcare, surveillance, weather forecasting, etc. In comparison with other industries, the need for big data in healthcare experiences more attention in present days. Initially, the data collected from remote healthcare services vary based on value, variety, velocity, veracity, and volume since the collection occurs at different locations using various devices. In research and development, there is an urge for an algorithm in risk prediction of heart attack. One of the major diseases related to mortality is cardiovascular disease (CVD). Further, an approach is introduced, and this approach has improved performance in terms of accuracy of 99%. However, in future works, it is recommended to focus on various other nature-inspired algorithms for diseases such as thyroid, diabetes, and so on.

Arushi Jain, Vishal Bhatnagar, Annavarapu Chandra Sekhara Rao
Tuning of CNN Architecture by CSA for EMNIST Data

Convolutional neural network is the deep learning model which has several hidden layers in contrast to feed-forward neural network. Modeling of CNN layers depends upon the dataset and very challenging task as several trials are required to select the CNN parameters. In our work, we presented an optimal solution to tune the hyperparameters of CNN architecture by clonal search algorithm (CSA). This is tested on a challenging dataset of EMNIST, which is enhanced from ML benchmark dataset of NIST. With the proposed algorithm, it is possible to get the accuracy up to 98.7%.

Navdeep Bohra, Vishal Bhatnagar
Efficient Emergency Message DHC Broadcasting in Vehicular Ad Hoc Networks

Vehicular ad hoc networks have many access points for communication, transmission, and collecting information of nodes and environment for organization traffic loads. In this paper, we study emergency messaging connectivity in vehicular ad hoc networks (VANETs). Intelligence transportation system applications include two types applications. Comfort applications providing information to the driver about weather, maps and directions, locations, and safety applications are crucial for safety of the driver. This includes such as emergency warning, lane-changing assistance, intersection coordination, which are provided by inter-vehicle communication. Higher No of road accidents demands an intelligent transportation system. Implanting smart sensors, communication capabilities, memory storage, and information processing units in vehicles help us to design an intelligent transportation systems. We are studying the effect of delay of emergency message dissemination. Broadcasting is the familiar way of emergency message dissemination in VANETs. To reduce the broadcasting storm problem and improve scalability of VANET networks, we use a double-head cluster-based broadcasting mechanism. In this research paper, we study the broadcasting delay emergency message of VANET network. The minimum cluster size that achieves acceptable message delivery latency is provided. The simulation results matched those of the analytical model, which showed the analytical model developed in this paper is effective and efficient.

Jaipal, Dhanroop Mal Nagar, Vinay Baghela
Software Effort Estimation Using Machine Learning Techniques

The product/software effort/cost-estimation techniques are applied to predict the effort required to finish the project. An incorrect estimation leads to increase in deadline and budget of the project which may further consequence to failure of the project. The estimation models and techniques are used in different phases of software engineering like budgeting, risk analysis, planning, etc. The effort estimation must be done meticulously in SDLC to avoid any slippage to timelines and over budgeting problems. Techniques of effort estimation can be grouped into two categories, i.e. parametric/algorithmic and non-parametric/non-algorithmic models. To overcome the limitations of algorithmic models, non-algorithmic methodologies have been explored which are based on soft-computing methods. Non-algorithmic techniques include Parkinson, expert judgement, machine learning (ML) and price to win. The ML models have been introduced to handle the flaws of parametric estimation models. These models also complement the modern project development and management. Neural networks, fuzzy logic, genetic algorithms, case-based reasoning, etc., are part of the non-algorithmic models. This review paper focuses on software effort estimation techniques based on machine learning techniques, their application domain, method to calculate software cost estimation and analysis on existing ML techniques to explore possible areas of further research.

Ripu Ranjan Sinha, Rajani Kumari Gora
Sentiment Analysis of English-Punjabi Code-Mixed Social Media Content to Predict Elections

On social media, the number of users are increasing exponentially. The information contents posted and tweeted by the user are also increasing exponentially. A different meaning of the sentiment is hidden inside the message. Analysing the nature of the text is still a very challenging task. The sentiment analysis is one of the emerging and challenging fields. In the proposed work, the data has been extracted from Twitter with the dataset of around 145,464 comments. In particular, the English-Punjabi dictionary has been created for opinionated word. The opinionated words are categorized into two parts as positive dictionary and negative dictionary. These are stored in gazetteer list and then a statistical technique has been applied for sentiment analysis.

Mukhtiar Singh, Vishal Goyal, Sahil Raj
Automatic Understanding of Code Mixed Social Media Text: A State of the Art

Social media content is often addressed as noisy or informal text due to the existence of zigzag conversational patterns. People do not always use Unicode rather they mix multiple languages. Hence, the processing of code mixed data postures computational challenges ahead. Since decades, social media content and its analysis have gained momentum worldwide. In parallel, the pace of research on Indian languages is also commendable. In India, the users of social media hail from different religions, regions, subdivisions and culture. The major concern of the paper is to throw light on the works done in Indian languages with code mixed social media as a concern. The journey of the research in the respective field has various milestones between basic tasks of natural language processing and deep learning. This paper focusses on the works done on Indian languages with respect to language identification, normalization and POS tagging. Efforts have been done to discuss the tools, techniques and the corpora used by researchers in different Indian languages. In the digital age, we have an abundancy of tools and APIs available for extracting code mixed text. Still, there is paucity of public data available for analysis. The need of the hour seems to be protruding toward deep learning and extending the public availability of code mixed corpora.

Neetika, Vishal Goyal, Simpel Rani
Secure Server Virtualization Using Object Level Permission Model

Virtualization is a framework or methodology that is used to divide the resources of a computer into multiple execution environments by applying concepts or technologies storage virtualization, client virtualization, and server virtualization are different ways to achieve virtualization. Our goal in this paper is to implement server virtualization with attacks and threats with possible solutions. Server virtualization is best suitable for dividing a server into a multiple virtual servers via software such as VMware and Hyper V. This method is used to increase the resource utilization by performing the same. In this each virtual server act and look like a physical server by increasing the capacity of every single physical machine (Kuche et al. in Int J Comput Netw Wireless Mobile Commun (IJCNWMC) 4:5–10 (2014), [1] with problems like efficient resource management, more downtime and privacy and security of data are associated with server virtualization. The problem is unauthorized users are accessing the access of machine/server in VMware platform. This can be done by proposing model named object level permission model to provide security by assigning permissions and roles as per level.

Varsha Grover, Gagandeep
Implementing Slowloris DoS Using Docker

In this article, we are going to introduce the implementation of Slowloris attack on Apache web server running inside docker container. We will show how a server running inside docker container can be exploited. As we know, a server is a computer or a computer program that manages access to centralized resource or a service in a network and therefore is the core of the internet. One of the attack by which a server can be exploited is denial of service (DoS) Attack. The main aim of DoS attack is to shutdown a service or a network making it inaccessible to the intended users. Slowloris is a tool which is being used for DoS attack. Slowloris is a tool which lets single machine to take down web server with minimal bandwidth. Detailed implementation of this attack will be illustrated in this paper.

Ishaan Sharma, Manohit, Abhinav Bhandari
Sentiment Analysis of Pulwama Attack Using Twitter Data

Microblogging sites like Twitter have become significant sources of real-time information during a disaster. Millions of tweets are Microblogging sites like Twitter have become significant sources of real-time information during a disaster. Millions of tweets are posted during disasters. This algorithm is applied to twitter tweets to extract the sentiments of the public on such types of manmade disasters. In order to use microblogging sites effectively during disaster events, it is needed to summarize the large amounts of real-time non-situation information posted on twitter. In this study, non-situational tweets were analyzed which were posted during the recent disaster event of the Pulmawa attack. The proposed methodology is to develop a Gradient Boosting classifier using machine learning techniques to achieve better performance compared to support vector machine and random forest classifier to categorize various types of non-situation tweets collected during disaster into a set of different classes. Well-known sentiments were used for mining that exhibits eight basic emotions, that is, joy, Trust, fear, surprise, sadness, disgust, anger, and anticipation.

Ranu Lal Chouhan
A Survey on Architecture and Protocols for Wireless Sensor Networks

Wireless sensor networks (WSN) are employed in many application areas such as environmental monitoring and battlefield strategy planning. Mainly, wireless sensor networks(WSN) are application specific. However, protocol-specific requirements of WSN are same as traditional networks, but the solutions are different. Many existing WSN implementations do not address security requirements, routing algorithms, MAC etc. That is, a drawback of WSN network protocol. WNS sensor nodes are constrained by memory, bandwidth, and power requirements, which makes it difficult to deploy complex algorithms, perform bulky calculations, and store a large data set in any sensor node. In this paper, we will describe the architecture and protocols, generally used to provide a variety of services in WSN. The introduction is started with architecture and principles of wireless sensor networks. The next section describes protocol stack for WSNs. After that, there is a brief survey of various protocols categorize on the based on layers and services.

Anita Chandel, Vikram Singh Chouhan, Dhawal Vyas
A Survey on Routing Protocols for Wireless Sensor Networks

In recent advances, wireless sensor network energy efficiency is the prime consideration. The routing protocols in WSNs are different from traditional network, application-oriented and depending on network architecture. This paper consists of a survey in the area of routing protocol for WSNs. The routing is categorized into five major sections: data-centric, self-organizing, hierarchical-oriented, location-aware and network flow and QoS-aware. Various protocols fall in these categories described in appropriate section.

Anita Chandel, Vikram Singh Chouhan, Sunil Sharma
Drive into Future World Using Artificial Intelligence with Its Application in Sensor-Based Car Without Driver

In the cutting edge period, artificial intelligence (AI) revolutionizes the world. Intelligent machines will alter the human capabilities in several areas. Artificial knowledge is the insight shown by different machines and software. It is considered as the subordinate of software engineering. Computerized analysis is turning into a renowned field in as it has upgraded the life of humans in many areas. Artificial insight over the last two decades has significantly improved the execution of the manufacturing and management systems. Study in the sector of artificial intelligence has offered ascend to the master framework, and its application in the vehicles is engaged to be computerized to give human driver loosened up driving. In the field of car, different viewpoints have been viewed as which makes a vehicle computerized. This paper discusses the artificial intelligence, types, space of artificial intelligence and its applications in field of the car without the driver using sensor-based technology and also talks about difficulty in the pathway of sensor-based cars and its future scope.

Ridhima Sehgal
Linking and Digital Story Telling Approach in Teaching Towards Enhancing and Engagement of Smart Study

Today, there are many new technological devices such as smart board, projector, computer, camera, scanner and much useful software are available to teach the students in efficient way. By using these tools and devices, educators get more opportunities to enhance and elaborate their knowledge; standard and skill with students and students also feel comfortable and well engaged, motivate and achieve good outcomes. Linking and digital storytelling aspect perfectly worked to enhance and makes interesting teaching methodology with full engagement of learner while class is going on. Education system still suffers from many challenges such as to enhance student’s engagement for better results, how to use innovative instructional approach to engage students. Aim of this research paper is to introduce and present constructive part of linking and storytelling approach. This paper will also explore the standardization, efficiency, impact and challenges in executing linking and storytelling approach. Linking and digital storytelling method is powerful technique to integrate learning process with knowledge activities to produce more attractive and moving commanding educational surrounding. Thus, move towards in this way will be potential to improve learner’s engagement and deliver enhanced education-related results. This paper is also trying to present the inclination in education in modern technique that is smart learning prevailing in education by the execution of smart learning.

Sanjay Tejasvee, Manoj Kuri
Classifying Titanic Passenger Data and Prediction of Survival from Disaster

The sinking of the ship named Titanic is one of the most historic shipwrecks in the world. It was held on April 14, 1912. Thousands of people died in this accident. Out of 3000 passenger, almost 1500 cause death in this accident. The reason behind this accident is due to less lifeboat because they never thought that this ship would ever sink because it is one of the largest ships in history at that time. So in this paper, an analytical approach has been proposed by the authors in order to predict the survival rate of people on the Titanic ship. For the experimental study, authors have selected Titanic dataset and applied suitable classifiers with the help of Python programming. For study purpose, spot check algorithm has been applied to predict what kind of people was survived. The experimental results have shown the model prediction value around 86.29% through spot check algorithm which found most satisfactory over results found in the literature varied from 72 to 82% only.

Shashank Shekhar, Deepak Arora, Puneet Sharma
Soft Skills: An Integral Part of Technical Education

Soft skills also known as social or people skills is the interpersonal quality that a student should possess; it is a very important attribute for the engineers to get into the job. They have become the integral part of one’s life in their workplace. It is something that one cannot learn by any training program or in the classroom. It can only be acquired through education, work, and life experiences. The present study deals with the soft skills like communication skills, positive attitude, teamwork, leadership quality, presentation skills, and interviews skills.

Nisha Srivastava, Manoj Kuri
Virtual Machine Migration Approach in Cloud Computing Using Genetic Algorithm

The technology of cloud computing is decentralized in nature due to which various issues in the network get raised which reduce its efficiency. The cloud computing technology is applied to fulfill the demands of hosts over the internet. For the purpose of using or sharing, the resource cloud computing can be used. The virtual machine migration is the major issue of cloud computing, and it gets raised when uncertainty get happened in the network. Due to extensive use of the virtual machine resources, machine gets overloaded which increase delay for the cloudlet execution. In the base paper, the threshold algorithm has been proposed which assign task to most capable machine and hosts maintain checkpoints on the virtual machines. When the virtual machine get overloaded, the task needs to migrate to another VM (Virtual Machine). In this study, weight-based technique will be proposed which migrate cloudlet from one virtual machine to another.

Gursharanjit Kaur, Rajan Sachdeva
A Survey on Electronic Health Records Using Cloud Computing Environment

One of the serious problems existing in the cloud is to oversee or to verify the information’s as of unapproved people. Here in the restorative field, the patient-driven model depicts the patient’s personal health record, wherever health data is to be verified from the outside servers. Electronic health record difficulties incorporate expensive programming bundles, framework security, tolerant secrecy, and obscure prospect government guidelines. Impending advancements via electronic health records incorporate bar coding, radio-recurrence ID, also discourse acknowledgment. We have provided a study on electronic health records in cloud computing with various technical aspects. Also, there is a detailed description of their applications. Load balancing is also the most significant aspect of cloud computing.

Vivek Gehlot, S. P. Singh, Akash Saxena
IoT Security Architecture with TEA for DoS Attacks Prevention

The Internet of Things (IoT) is important in now a day’s development of wireless networks enabling to acquire information from the environment, devices, and machines. A number of applications have been implemented in various kinds of technologies. IoT has high coverage to security attacks and threats. There are a number of requirements in terms of security. Confidentiality is one of the main concerns in the wireless network. Integrity and availability are key matters along with the confidentiality. This research focuses on identifying the DoS attacks that can occur in IoT. This paper uses Tiny Encryption Algorithm (TEA) to address these above mentioned security matters. From the algorithms, our proposed solutions can control DoS attack on IoT and any other networks of small devices.

Vishal Sharma, Anand Sharma
Comparative Study of SVM and Naïve Bayes for Mangrove Detection Using Satellite Image

Mangroves are a kind of plant which assumes an extremely fundamental job for security of our biological system. We presented the better approach for mangrove discovery by utilizing the help vector machine (SVM) and Naïve Bayes both are going under managed AI, and this calculation is utilized to group the image. The high-goals satellite information from Google earth is procured from an alternate locale of Mumbai, Maharashtra district, for recognition of mangroves. This exploration paper utilized two unique calculations, for example, Naïve Bayes classifier and Support Vector Machine for the discovery of perusing highlights from satellite images, and there are two calculations which are actualized utilizing the Matlab recreation tool stash. Support Vector Machine and Naïve Bayes are a directed grouping strategy applied on satellite image. In the wake of applying the calculations on the picture satellite, the precision of classifiers is determined utilizing perplexity grid and kappa coefficient. The execution of both methods of Support vector machine and Naive Bayes generate the detected area of mangrove in Mumbai, Maharashtra region. Exactness of Naïve Bayes saw as 99% with kappa value 0.9831, and the precision of help vector machine saw as 97% with a kappa estimation of 0.9631. The precision figuring utilizing disarray lattice and kappa coefficient shows that the Naïve Bayes classifiers is superior to help vector machine for the discovery of mangroves utilizing satellite picture.

Anand Upadhyay, Santosh Singh, Nirbhay Singh, Ajay Kumar Pal
Identification and Assessment of Black Sigatoka Disease in Banana Leaf

Detecting a disease in plants is one of the challenging works. Identifying the disease through naked eyes is difficult. India is famous for agriculture. There were no modern techniques used in machine learning to find disease in banana leaf. Diseases like bacterial wilt and Black Sigatoka in banana leaf cause massive loss to the farmers. With the help of image processing technique and support vector machine algorithm, we can detect the disease called Black Sigatoka in banana leaf. Since this technique is cost effective, it is helpful for the farmers and one can easily detect the disease.

Anand Upadhyay, Neha Maria Oommen, Siddhi Mahadik
Water Resource Detection Using High Resolution Satellite Image and GRNN

Water is the most important for human body, environment, and transportation and so on. One of the interesting areas of research is the use of satellite image. We can use the various techniques and compare them to check the result to each other. Survey the very dry area for water and conventional techniques used the satellite image. The objective of the paper is water resource detection using satellite image. Satellite image provides the data and information about any earth surface or object without making physical contact with it. It will help to come up with the best idea or technique that can be used for our research. We have used GRNN algorithm to detect the water resources that are available on the surface of earth, and we found 97.10% accuracy. Please check and confirm if the author names and initials are correct.correct

Anand Upadhyay, Manisha Pandey, Ajay Kumar Pandey
Retinopathy Detection Using Probabilistic Neural Network

We propose a diabetic retinopathy (DR) analysis algorithm based on probabilistic neural network (PNN). This algorithm is used to recognize the pattern problem. By this algorithm, we can help in diagnosis of a diabetic patient regarding their damage to the back of retina (eye) occurred in tissue of blood vessels using probabilistic neural network. PNN is also known as feed forward neural network. This algorithm has been tested on a small image database and compared with the performance of a human eye. Confusion matrix and kappa coefficient are used to find the accuracy rate of the diabetic eye.

Anand Upadhyay, Parth Kantelia, Rohan Parmar
Application of Unscented Kalman Filter for Parameter Estimation of Nonlinear Systems

Sometimes the parameters of a system dynamics are not exactly known while these are required to set the control law and update the existing control scheme. This becomes much difficult when the dynamics of the system is nonlinear. Thus, this paper deals with the estimation of the parameters of a nonlinear system using unscented Kalman filter (UKF). The UKF handles the nonlinear dynamics without linearization and approximation during the estimation and hence estimates the parameters as well as states perfectly. A well-known example of nonlinear dynamics, Van Der Pol oscillator system, has been used to illustrate the parameter estimation. The simulation of the Van Der Pol oscillator has been done first to generate the measurements, and then, the state and measurement model of the system have been setup which further have been used during the estimation.

Urmila Solanki, Ganesh P. Prajapat, Manoj Chhimpa
Question Answering System Using LSTM and Keyword Generation

Question answering system is an area under natural language processing and information retrieval which automatically answers the questions generated by humans. This work represents an approach for building a system that generates answers for the question based on deep learning neural network which has the competence of processing the information present inside the dataset and enables the user to obtain an insight from the SQuAD dataset by inviting questions in natural language form. Key stages of this approach cover corpus pre-processing, question pre-processing, answer generation, deep neural network for answer extraction and keyword generation. The concept of keyword generation is a novel idea implemented to enable naïve user of the system to apprehend the passage. The system is competent in interpreting the question, responding to the user’s query in natural language form along with generating the keywords. The performance was measured on SQuAD dataset using EM and F1 score.

Minakshi Tomer, Manoj Kumar
Classification of LISS-III Image Using Fuzzy Logic

The LISS-III is the multi-phantom camera working in four groups. The main reason behind accompanying the work is to apply calculation dependent on regulated characterization of systems to comprehend the land spread and land utilized region in Mumbai. Here, we have used the IRS P6 LISS-III satellite picture of Mumbai locale is utilized to group the regions of Mumbai, Navi Mumbai, and Thane district. The classifier utilized is a fuzzy inference system and band pictures. The various regions of Mumbai locale are grouped, for example, zone secured by mangroves, forest, water, and developed area. It is been seen that the accuracy of fuzzy inference system is 77.88%.

Anand Upadhyay, Sonam Mishra, Aishwarya Khavadkar
Optimized Text Classification Using Deep Learning

As there is tremendous hike in the amount of data created in the world, the need for text classification is on rise. Data from all the online sources: e-mails, web pages, social media, chats, and more results in a huge amount of unstructured text. To extract the information from the text that is unstructured in nature is very cumbersome and time-taking. Therefore, text classification becomes a pre-requisite for the businesses to improve the decision-making process. Different deep learning-based models for text classification with respect to different activation functions are analyzed in the paper.

Neeti Sangwan, Vishal Bhatnagar
Digital Learning: A Proficient Digital Learning Technology Beyond to Classroom and Traditional Learning

Education is a vital basis of any country towards the development and sustainability of continuous growth for a long term. The system of education should be ahead with new technologies to achieve more benefits at every stage of improvement or enlargement of a nation. Today’s era is fully digital era in every sectors; however, the education system is always trying to function according to latest trends, move parallel with new technological aspects throughout the earlier few years. Digital learning and ICT (information and communication technology) tools bond the teachers, academics, parents, experts and institutions. Digital learning also motivates to use latest technologies to deliver, communicate and share to each role players and vice versa. The key concern of the paper is to represent a clear glance of digital learning phenomena and to touch almost every aspects concern to digital learning in brief. This paper will try to deliver from general idea aspect to analysis aspect about digital learning.

Sanjay Tejasvee, Devendra Gahlot, Rakesh Poonia, Manoj Kuri
Data Security & Future Issues for Cloud Computing

In current vogue, it is required more storage space as well as security being increasing internet user’s day by day. Cloud computing is appropriate platform to provide services over the internet. Cloud computing influences some technologies such as SOA to data security. In future, some of industry and vendors are expecting changes in IT trends and processes. We discuss here the data security & future of cloud computing. We will also review of current services provided by cloud computing in different arena.

Devendra Gahlot, Sanjay Tejasvee, Kunal Bhushan Ranga, Rishi Raj Vyas
Weather Event Prediction Using Combination of Data Mining Algorithms

Weather event prediction offerings suitable from the obsolete occurrences as a main gigantic obligation, since it depends on upon dissimilar constraints to forecast the destitute factors like air temperature, humidity, precipitation, wind speed, and dampness, which are fluctuating intermittently. A multi-model data mining approach is a unique process for merging the prognostic capability of multiple prototypes for better forecasting accuracy. In this paper, we proposed multi-model ensemble for forecasting weather events. The data mining algorithms Random forest, C5.0, AdaBoost, and Support Vector Machine (SVM) models are implemented in combination as ensemble. The combinations of (RF + SVM + AdaBoost) perform better accuracy with 82.73% in compare with other combinations of multi-model ensembles. For experimental work we used, weather data of Barajas Airport, Madrid, between 1997 and 2015 were gathered from web https://www.wunderground.com/ The Weather Company, LLC.

Yogesh Kumar Jakhar, Nidhi Mishra, Rakesh Poonia
Data Compression and Visualization Using PCA and T-SNE

This paper examines two commonly used data dimensionality reduction techniques, namely, PCA and T-SNE. PCA was founded in 1933 and T-SNE in 2008, both are fundamentally different techniques. PCA focuses heavily on linear algebra while T-SNE is a probabilistic technique. The goal is to apply these algorithms on MNIST dataset and to see how they practically work and what conclusions we could draw from their application. The objective is to reduce the dimension of the data while retaining most of the information. We perform both these techniques and make a comparison between them by observing the results. We note the behavior of the reduced components obtained from both techniques, by visualizing it in 2-dimensional space. Upon further research and application, it became apparent that the data dimensionality reduction is sensitive to the parameter settings and must be fine-tuned carefully to be successful.

Jyoti Pareek, Joel Jacob
Appscrumfall: APP Development Methodology Based on ScrumFall

Agile is a combination of iterative and changeable process which is adopted by IT organization. All software projects are specialized. It is necessary to choose a software model to build any software but a single software development model may not be suitable for all types of projects. Developers face difficulties with existing models for the duration of development. They tackle challenges by balancing the software development lifecycle according to their needs. Therefore, in this paper, we have introduced a software process methodology that features both the scrum and waterfall approaches and is named “appscrumfall.” Software development of mobile app using the model ““Scrum-Fall” (scrum blended with waterfall)” is practicing in the company to solve the deficiencies of the traditional model. We have analyzed the performance and availability to implement this process model. The result shows that this process model is effective for software projects. The aim of this model is to provide a formula for better implementation in large IT sectors.

Prerna Bisaa
Multiple Sequence Alignment Algorithm Using Adaptive Evolutionary Clustering

In the present manuscript, an adaptive evolutionary multiple sequence alignment algorithm is proposed that uses a combination of consensus and SP-score methods. The algorithm searches intermediate pairwise consensus strings that are used to identify the final consensus string for a given set of DNA/RNA/protein sequences. The proposed algorithm is an extension of MPSAGA algorithm that uses positional matrix representation of sequences. An empirical study was performed in the present work to compare the proposed algorithm with the other three contemporary ClustalW, TCOFFEE, and MUSCLE algorithms on the four datasets. The overall observations from the various experiments revealed that the proposed algorithm outperforms than the other algorithms tested in aligning multiple sequences with an average increase of 0.03% in alignment length by inserting 0.02% increased number of gaps.

Jyotı Lakhani, Ajay Khunteta, Anupama Chowdhary, Dharmesh Harwani
Theft Security System for Automatic Teller Machines Using IoT

This research paper suggests a system that efficiently and effectively provides a mechanism of anti-theft ATM by using Internet of things and fog computing by considering two solution: First, a instant solution at the beginning of stealing using fog computing and second, cloud-based messages technique system for ATM security and preventing from being stolen by thieves and unsocial elements. As we know that technology reaches its successful step when it fulfills every section of the public or society. As nowadays, it is very common in India that the entire ATM with public money is being stolen by some unsocial elements or thieves. So, this paper proposes an ATM safety while it is being tempered and gives a new system that works using the Internet of things and fog computing methods that would make the ATM and its places very secure and establishes entirely new technologies in ATMs which provides a Theft proof system. The system gives an instant solution while the machine system is being tempered and when criminals try to steal it. Once the ATM experience any vibration, the preventive mechanism will activate and the nearby police station will receive notification messages of the location of the ATM using the cloud. The text message comprises of GPS location of ATMs and also a cautionary message. The fog computing method activates to close the outer shutter of the ATM and the microcontroller to activate the ATM in a new mode of theft preventing by switching on an inbuilt backup supply of the ATM. The remarkable advantage of this system provides the banking system a new way of anti-theft management for money and ATM as well.

Vinay Verma, Anjali Verma, Gaurav Sharma, Anand Sharma
Tree-Based Multi-Keyword Rank Search Scheme Supporting Dynamic Update and Verifiability upon Encrypted Cloud Data

Due to large scale use and many applications of cloud maximum data, owners upload the information at cloud space to save time and local disk space. Here, the authors provided a TBMKRS (Tree-Based Multi-Keyword Rank Search) scheme which also supports dynamic update (insert/delete) and verifiability of encrypted information upon cloud. For the evaluation of performance and analysis of result, the Enron data set have been used by the authors.

Pawan Kumar Tanwar, Ajay Khunteta, Vishal Goar, Manoj Kuri
Techniques, Applications, and Issues in Mining Large-Scale Text Databases

The discovery of knowledge from large-scale text data or semi-structured data is very difficult. In text mining, useful information is extracted out of such large text corpus which fulfills a user current information need. This process is being exploited by various organizations for quality improvement, business need, and understanding user behavior. The text available in unstructured and semi-structured form can come through sources such as medical, financial, market, scientific, and others documents. Text mining applies quantitative approach to analyze massive amount of textual data and tries to solve information overload problem. The main objective is to review text mining techniques, application areas, and existing issues.

Sandhya Avasthi, Ritu Chauhan, Debi P. Acharjya
Vehicle Number Extraction Using Open Source Tools

Although intelligent monitoring and recording system (IMRS) is used in many fields such as aviation traffic control, transportation, real estate, medical science and more. One of these is vehicle traffic on roads. This paper covers the techniques of extraction of vehicle number by using open source tools which will be used in many fields such as automated parking system, toll tax system, supervising road traffic on highways, searching stolen cars, and more. Time and accuracy are two challenges in performing the above in a real-life scenario. The proposed vehicle number extraction works on OpenCV Library to convert the image to Mat, and after that, the discussed methodology is applied to detect the vehicle number. This paper introduces a framework which includes preprocessing of vehicle image and applies non-maxima suppression with edge detection and segmentation, and then, OCR has been applied to convert the numbers to digital form and store in HBase database along with an image of the car. It has been observed that the proposed methodology of this paper runs 27% faster than automatic number plate recognition (ANPR). Precision and recall are also observed to be better.

Chetan Pandey, Amit Juyal, Ankur Dumka
Classification of Energy Efficiency in Mobile Cloud Computing

Mobile cloud computing (MCC) is a methodology, which is developed due to the inability of mobile devices to process large of amount of data and utilize less amount of energy as such the computers that can process the large amount data as compared to mobile devices. So in order overcome this problem, MCC came into existence which is used to increase the computation power and utilize energy of mobile devices that is required to process large data; to overcome this issue, there are several techniques that we discuss in this paper and their proposed solution to enhance the computation ability of mobile devices by using less energy. Techniques involve in taking off the data from mobile devices to the cloud server and perform the computation in cloud server, and when the computation of data is completed, then send back that particular data to the mobile devices. Thus, this paper studies about how to reduce the energy consumption of mobile devices by using certain parameters such as bandwidth and execution time.

Shubham Pal, Ankur Dumka
Perspectives of Blockchain in the Education Sector Pertaining to the Student’s Records

Blockchain has been enforced in many sectors, and its implementation has drastically improved those sectors. Diamond trade has been greatly helped by the employment of blockchain to digitally track the diamonds being well-mined and sold-out within the market. The potential of the blockchain is being tested by varied government agencies for distribution of the various services. Through this paper, we’ve explored the entities concerned within the blockchain network enforced in an academic institute. This paper focuses the employment of the blockchain account for each student maintaining the records of the scholare that helps to spot the talents of the scholars by their prospective employers.

Poonam Verma, Ankur Dumka
Ground-Level Water Predication Using Time Series Statistical Model

With exponential increase in population, scarcity of water in Nation Capital of India, Delhi, has become the most critical issue over last few years. The change in climatic conditions, usage of lands and immense abstraction of water are plausible reasons for depletion of groundwater at a rapid rate. To deal with this issue, authors predict the groundwater level using time series model in various regions of Delhi. To understand the reasons of decline in groundwater level and its quality is necessary for the development and livelihood in all regions of Delhi. The results depict that decline in number of wells from 125 in year 2012 to 82 in the current year. Over the period of six years, lower rain falls and high population growth is the major reasons for depletion of groundwater level in Delhi. Along with this, the quality of ground water has been deteriorated which has also become a prime issue of concern.

Sandeep Kumar Mittal, Mamta Mittal, Muhammad Sajjad Ali Khan
Prediction of Air Quality Index Using Hybrid Machine Learning Algorithm

Air pollution is an acute problem which leads to detrimental effects on human health and living conditions. Therefore, there is a need to monitor the pollution levels to inform people about the status of current air quality. This is done by an index called Air Quality Index (AQI) that maps the concentration of various pollutants into single value. To predict the AQI, a hybrid machine learning algorithm has been proposed in this paper in which the cluster classifications computed by k-means clustering algorithm are used as an input to support vector machines (SVM) algorithm. To perform the experimental work, three-year (January 2016 to January 2019) air quality data of Gurugram (Haryana) has been utilized after preprocessing it by scaling. The obtained results of the hybrid approach have been compared to the traditional SVM algorithm. Based on the empirical study, the hybrid algorithm prediction performance is better than SVM algorithm. It has been observed that the accuracy of proposed algorithm is found to be 91.25% as compared to the SVM algorithm with an accuracy of 65.93%.

Jasleen Kaur Sethi, Mamta Mittal
Employing Blockchain in Rice Supply Chain Management

Blockchain is considered to be the next paradigm in information technology after mainframes, computer, Internet, and smartphones. With so much hype around cryptocurrencies the mechanism on which these were built, “The Blockchain” has drawn attention of many scientists and developers around the world. With time, other than cryptocurrency, Blockchain had impact on several other industries such as logistics, health care, real estate, legal industries, etc. One such application leads to employing Blockchain technology into food supply chain. Rice is the major food consumed by people in India. Rice supply chains play a vital role in supplying rice from manufacturer to consumers. Hence, for attaining a corruption-free, transparent, and efficient rice supply chain, Blockchain is to be employed in the functioning of these supply chains such that safety of rice can be monitored at different stages involved in the supply chain. In this paper, a theoretical study is shown on how Blockchain can be integrated into regular rice supply chain.

M. Vinod Kumar, N. Ch. Sriman Narayana Iyengar, Vishal Goar
Supervised Learning Method and Neural Network Algorithm for the Analysis of Diabetic Mellius and its Comparitive Analysis

Diabetes is the key critical issue needs to be concerned for various problems in our body. Increase in glucose and fructose content in our body results in diabetes mellitus. When a body generates higher insulin level than the required, it results in increased urination and excessive thirstiness which in turn results in kidney failure and other cardio-related issues. Many research agencies invested their funds on defining the predictive methodology and finding the root cause of those results in mellitus. Mellitus results in the highest mortality rate compared to any other disease reported by the health organizations across the globe. In this, the predictive methodologies, various classification techniques are discussed, and the results are analyzed. The classification methodology could be on medications, food habits, personal behaviors, age factors and so on. The datasets are processed and analyzed with the neural network algorithms, and the results are compared with one another. The datasets are taken from the National Family Health Survey results published during the period of 2016–2017. The result implies that men between ages 15–49 among 1 billion people have reported with diabetes mellitus. Diagnose and forecast on this disease are done by recognizing the pattern formation and grouping the similar structures. Various algorithmic techniques like M-layer perceptron, nearest neighbor, vector machines, data regressions, binary regression and their accuracy of forecast, speed and sensitivity are calculated, analyzed and compared to define the accurate prediction methodology over a short span of time. The forecast methodologies are focussed to provide solutions to avoid the intensive care system provided proper medications with a long duration when it is been predicted to be a risk factor. A statistical method of analyzing is performed for the comparative analysis. The learning and training methodologies are discussed in this system. Accuracy, specificity, sensitivity are the key parameters to define the best forecast methodology. Classification on association, regression techniques and neural algorithmic techniques is analyzed and compared to refine the best predictive forecast methodology by processing 30 samples across the states of India with focus on determining the type of mellitus along with the accuracy on definition. The forecast data utilized to define the type of mellitus and the prediction on critical measures over a period of time.

J. Jayashree, J. Vijayashree, N. Ch. Sriman Narayana Iyengar, Vishal Goar
Nipah Virus Using Restricted Boltzmann Machine

Nipah virus is an infectious virus which is caused by fruit bats. Recently in 2018, there was a deadly outbreak that occurred in Kerala where many of people got infected and died due to Nipah virus. In this model, we are using deep learning concept which helps to predict the occurrence of infected virus using restricted Boltzmann machine. It is a feature selection algorithm where particular data will be selected by applying matrix of weights associated with the connection between the hidden layer and the visible layer. Firstly, it was identified in Malaysia Kampung Sungai Nipah in 1998. The fertility rate people affected with Nipah virus was around 70%. Transmission of this infected virus is done by bats-to-human, animals-to-human and human-to-human. Particular signs and symptoms will be exhibited for the person affected with Nipah virus. Cerebrospinal fluid serum test will be done by collecting white blood cells, glucose and protein by using restricted Boltzmann machine. This deep learning algorithm will give the numeric results such that we can identify whether the patient is affected with Nipah virus. Prevention measures should be taken as “prevention is better than cure” because there is no vaccine for Nipah virus which is eventually more dangerous.

Velpula Sandhya Rani, Havalath Balaji, Vishal Goar, N. Ch. Sriman Narayana Iyengar
Big Data Analytics—Analysis and Comparison of Various Tools

Big data is the latest terminology in the computer world. The data collection is increasing day by day, and many technological changes can bring some new methods for decision-making process in many areas such as health and finance. As the complexities are increasing due to volume, veracity, variety and velocity, our focus is on the methods to calculate the value of data using various big data analytics technologies. The analytics process used with respect to big data can be improvised by using new algorithms, which enhance the analytical aspects and can be used to extract the hidden knowledge very efficiently and effectively.

Amit Gupta, Bhanu Prakash Dubey, Himani Sivaraman, M. C. Lohani
Copy-Move Forgery Detection Methods: A Critique

With the advancement of image editing tools, legitimacy and creditability of the images are put in jeopardy. There are various types of image forgeries techniques like splicing, retouching, false captioning, and copy-move. But the most predominant forgery techniques are splicing and copy-move forgery. In copy-move forgery, a part of the image is copied in the same image and in splicing another image in order to conceal or to duplicate the information residing in the image. In this critique, the copy-move forgery detection (CMFD) methods from 2013 onwards are reviewed under four categories—block-based, keypoint-based, hybrid-, and deep learning-based methods.

Monika Kharanghar, Amit Doegar
Improving Website by Analysis of Web Server Logs Using Web Mining Tools

Web log data obtained from the server of the website is the key source of enormous hidden information. This information can be obtained from the analysis of web log data. Analysis of web log data is very useful for the management and improvement of the website. It also plays a vital role in the security measures of a website. Analysis of web log data is also very important for analysis of user’s behavior and for the maintenance purpose of website. This analysis is possible by many available web usage mining tools. In this paper, we have used Web Log Expert tool for analysis. Web log Expert gives lots of reports and graphs to gain insight into web log data.

Neeraj Kandpal, Devesh Kumar Bandil, M. S. Shekhawat
A New Approach for Paddy Leaf Blast Disease Prediction Using Logistic Regression

Paddy is a major agricultural crop. But the production of paddy is hindered by various kinds of diseases. Some of those diseases are leaf blast disease, brown spot disease, bacterial blight disease, etc. Amidst of all these diseases influencing the paddy production, leaf blast disease had a great influence and it is the most destructive diseases that are effecting on paddy crop. Leaf blast is risen by the fungus Magnaporthe oryzae. It will affect all the above-ground parts of a paddy crop: leaf, collar, node, neck, parts of panicle, and sometimes leaf sheath. Thus, examining and accurate forecasting for the development of blast disease are significant and early forecasting of the disease is very beneficial. Many former blast disease prediction models were only considering the attribute values but not their correlations. In this paper, logistic regression algorithm is applied for forecasting the occurrence of leaf blast disease for Adilabad district of Telangana state in India during 2007–2017 in order to prevent the paddy fields from disease. With the help of the correlation mining and clustering process among the attributes, we are classifying the attribute sets based on their impact on disease occurrence. Finally, the logistic regression algorithm calculates the leaf blast disease occurrence probability.

Sree Charitha Kodaty, Balaji Halavath
Assistive Technology for Students with Visual Impairments: A Resource for Teachers, Parents, and Students

Today is era of technology. We see everywhere technology. Technology is the skills, methods, and processes used to achieve goals. In this manner, there are special types of technology tools that can help people who learn understand and working differently. These specific tools are known as assistive technology (AT). Actually, AT is any software, device, or equipment which helps people with disability and works around there to make easier their life. Like in regard to visual impairment, Braille watch is an AT who helps the visual impaired person to know time. So, we can say that AT is one of essential parts of visually impaired child’s academic or whole life. It allows VI to use their skills engaged in school environment and uses these technologies without helping other. The Rights of Person With Disability Act, 2016 (RPWD) mandated for assistive technology is one of crucial parts of visually impaired student. There are several researches which found that use of technology (AT) is lesser in rural area as compared to urban area in India. The scope of AT is fully determined by the knowledge of teachers and their knowledge of technology. The main theme of this paper is to potency of AT for visually impaired person. Here, in this scenario, some of special provisions have been also discussed in this paper. Its focuses on various types of technology and their use in life of visually impaired child.

Amit Sadh
Metadata
Title
Advances in Information Communication Technology and Computing
Editors
Dr. Vishal Goar
Dr. Manoj Kuri
Dr. Rajesh Kumar
Prof. Tomonobu Senjyu
Copyright Year
2021
Publisher
Springer Singapore
Electronic ISBN
978-981-15-5421-6
Print ISBN
978-981-15-5420-9
DOI
https://doi.org/10.1007/978-981-15-5421-6