Skip to main content
main-content

Über dieses Buch

These proceedings gather cutting-edge papers exploring the principles, techniques, and applications of Microservices in Big Data Analytics.

The ICETCE-2019 is the latest installment in a successful series of annual conferences that began in 2011. Every year since, it has significantly contributed to the research community in the form of numerous high-quality research papers. This year, the conference’s focus was on the highly relevant area of Microservices in Big Data Analytics.

Inhaltsverzeichnis

Frontmatter

Adaptive VM Migration and Allocation Mechanism in Cloud Environment

Abstract
The cloud computing is still important in research area, the extent that exploration and down-to-earth usage are concerned. Cloud designs and hardware are frequently heterogeneous and are for the most restrictive part. Information migration is the way towards transporting information between systems, servers, or organizations and in addition over the networks. Cloud comprises servers with each and every server focusing on having a substantial number of physical machines. In this chapter, we create a VM allocation over each physical machine; a virtual machine is made for the VM migration in the cloud environment and B&B-based approach for assigning multidimensional variable estimated to VMs at the virtual server. These results are formulated and make the analysis between the various allocation techniques like first fit approach, best fit technique, and modified technique, and we proposed an approach to do better VM migration in the cloud computing environment. After, energy-efficient VM migration procedure is presented to lessen energy utilization in the cloud environment.
Narander Kumar, Surendra Kumar

Educational Cloud Framework—A Literature Review on Finding Better Private Cloud Framework for Educational Hub

Abstract
This paper is based on the review of cloud computing in educational field. The technology provides IT-level facilities with services-on-demand-based feature, i.e., cloud computing, one of the growing technologies in today’s era. The reason why all IT and educational societies are moving toward cloud computing is it offers such kinds of services which help to reduce the initial investment and take back the maximum output in terms of processing power, storage, and networking. But, for using cloud computing in educational society, there are two ways: First is taking services from third parties like Amazon, IBM, and so on. Second is developing our own cloud platform within the educational society by using commodity hardware or by current working systems in that society. Many educational hubs invested already on their own infrastructure instead of buying from third parties and using same services and same features without paying too much money. This paper also focuses on the how some educational societies are currently working on the cloud platform and why other schools, colleges, and universities must move toward cloud platform with proper data security assurance. To use this cloud services freely, there are some open-source platforms currently present in the market. This research is based on finding better private cloud platform for educational societies based on their performance.
Nikhil Wagh, Vikul Pawar, Kailash Kharat

Improved DYMO-Based ACO for MANET Using Distance and Density of Nodes

Abstract
A mobile ad hoc network (MANET) is an accumulation of moving node, in which node conveys without the utilization of any settled foundation or any brought together space. In such case, a versatile host can act both as a host and as a switch for sending information parcels to other portable nodes in the system. As there is no settled foundation in this way, MANETs are thought to be vulnerable. Huge overheads are required to keep up the courses consistently. Receptive conventions send control parcels just amid the correspondence. Dynamic mobile ad hoc network on-demand (DYMO) proposed for routing in MANET by using moving nodes is a reactive protocol. It can effectively adjust to the changing topology of system and can discover courses between end nodes. This paper proposes a new framework which upgrades the DYMO protocol by including ant colony optimization (ACO). The upgraded form of the convention is contrasted and alternate conventions of its classification on the premise of different execution parameters. Result analysis shows that proposed protocol performs superior to the different existing protocols like AODV, TORA, DYMO, M-DYMO, and ACO.
Sumit Kumar, Madan Lal Saini, Sandeep Kumar

An Efficient ATM Surveillance Framework Using Optical Flow with CNN

Abstract
For our daily need, we often visit nearby automatic teller machine (ATM) to withdraw our deposited cash in bank. With increase in bank robberies, money snatching and attack on the customer visiting bank or ATM, our money is no longer safe. To prevent these types of abnormal activities, there is a need of better accuracy security surveillance system which can detect abnormal activities instantly. Our paper tends to work in this direction where we have used normal video, dense optical flow and Lucas–Kanade optical flow for detecting the abnormal motion of customer coming for withdrawal of money at ATM booth, with the help of convolution neural network we trained the model for single normal, multiple normal and multiple abnormal classes with different number of iteration to form 15 different training models. While testing those models, the average accuracy for Lucas–Kanade methods for 1000 iteration is 92.3984%.
Ankit Bisht, Himanshu Singh Bisht, Vikas Tripathi

An Efficient Approach for Image Encryption Using Zigzag, Arnold Transformation and Double Random-Phase Encoding in Fractional Fourier Transform Domain

Abstract
Data security is one of the dominant essential problems these days where data is delivered from one to other location with fast values. Image encryption is the technique of encoding image in like a way that detectives or hackers cannot understand it, but that permitted groups can. In this work, we have proposed an efficient approach of image encryption with the help of combination of Arnold cat map, zigzag transformation and pixel scrambling technology in fractional Fourier transform and compared with the previous existing techniques. Some performance parameters such as peak signal-to-noise ratio (PSNR), mean squared error (MSE) and normalized cross-correlation are also measured. All the simulations are carried out in MATLAB simulation tool.
Anmol Mathur, Ajay Khunteta, Atul Kumar Verma

Comparison of Execution Time of Mobile Application Using Equal Division and Profile-Based Algorithm in Mobile Cloud Computing

Abstract
The advent of smartphones has enabled us to develop powerful and sophisticated applications. Even though the smartphone is become hugely popular, it still has not been able to reach in hands of billions of people. Many mobile applications fail to perform well because of the mobile device shortcomings of low resource availability and battery limitations. These limitations can be overcome through offloading execution and distributing computation execution on to more resourceful devices. This paper proposes a solution to execute Android applications through a mobile ad hoc network formed by devices in the proximity. The mobile ad hoc network is formed using Wi-fi Direct technology that enables fast and seamless communication. We have proposed a method for distribution of mobile application and migration of computation to nearby mobile devices in the mobile ad hoc network. The paper shows the implementation of execution of the compute-intensive mobile application on the local mobile device and mobile ad hoc cloud and compares the execution time. This paper also compares the application execution time with the application which is distributed equally and based on the profile of mobile devices. The application is migrated on the system according to available device resources and computation capacity.
Kailas K. Devadkar, Dhananjay R. Kalbande

Ontological Design of Information Retrieval Model for Real Estate Documents

Abstract
There is plethora of information lying over Internet which requires effective retrieval such that there is best utilization of information. The scenario becomes all the more critical when it is dealing with semantic information access in e-governance domain. Hence, for an efficient information retrieval in Semantic Web, applying ontological design and rules is the most suitable research technology. This research paper proposes a real estate information retrieval model that will semantically retrieve legal documentation formats for real estate transactions. The paper also depicts the creation of real estate ontology using Protégé 4.3 which shows the formulation of the first step of the model.
Namrata Rastogi, Parul Verma, Pankaj Kumar

Parameter Optimization in Convolutional Neural Networks Using Gradient Descent

Abstract
The aim of the present study is to develop an algorithm by exploring the basic structure and functional operation of convolution neural network's (CNN) design as well as the features of back propagation (BP) and gradient descent (GD). The hierarchical approach employing BP and GD offers a reliable form of an algorithm. Most of the algorithms share weight to minimize the size of parameter and cost function that can be joined with the BP and the GD. Backpropagation provides an opportunity for backward feedback to enhance the reliability with minimizing error, while the gradient descent is used to solve the issues related with deep learning as well as the machine learning algorithms.
Swaleha Zubair, Anjani Kumar Singha

Empirical Investigation of Usability Evaluation Methods for Mobile Applications Using Evidence-Based Approach

Abstract
Mobile learning or m-learning is novel learning medium, and consequently, there is a lot of research required to design usable m-learning applications. With the advent of new m-learning applications and their indulgence in imparting education, it poses new usability challenges. M-learning has to be investigated from various perspectives for its effectiveness and efficiency. So to have an effective and usable m-learning application, it is quintessential to discover an appropriate set of usability evaluation methods [UEMs] to evaluate the usability of m-learning application. For the aforesaid purpose, an evidence-based study of UEMs is carried out in this paper to compare and then assess different UEMs. To bridge the gaps between research evidence and software development practices and to avoid expensive and ineffective decision making during application development, an evidence-based approach is suggested by [1, 2]. Evidence-based study is the process of systematically finding, evaluating, and using contemporary research conclusions as the basis for decision making. An evidence-based study is required before the adoption of UEM/UEMs because sufficient evidences should be gathered as a decision factor before testing an application. This study presents an empirical analysis for selecting effectual UEM(s) for a set of mobile learning applications using evidence-based approach [EBA].
Priyanka Mathur, Swati V. Chande

Prediction of Underwater Surface Target Through SONAR: A Case Study of Machine Learning

Abstract
The discovery of rocks and minerals would have been very difficult past the development of the SONAR technique, which relays on certain parameters to be able to detect the obstacle or the surface is a rock or a mine. Machine learning has drawn the attention of maximum part of the technology-related and based industries, by showing advancements in the predictive analytics. The main aim is to emanate a capable prediction representative, united by the machine learning algorithmic characteristics, which can figure out if the target of the sound wave is either a rock or a mine or any other organism or any kind of other body. This attempt is a clear-cut case study which comes up with a machine learning plan for the grading of rocks and minerals, executed on a huge, highly spatial and complex SONAR dataset. The attempts are done on highly spatial SONAR dataset and achieved an accuracy of 83.17%, and AUC came out to be 0.92. With random forest algorithm, the results are further optimized by feature selection to get the accuracy of 90%. Assuring results are found, when the fulfillment of the designed groundwork is set side by side with the standard classifiers like SVM, random forest, etc., using different evaluation metrics like accuracy, sensitivity, etc. Machine learning is performing a major role in improving the quality of detection of underwater natural resources and will tend be better in the near future.
Harvinder Singh, Nishtha Hooda

Big Data Machine Learning Framework for Drug Toxicity Prediction

Abstract
The exposure of humans to toxic drug samples adversely affects lives of many beings. The drug molecule data is vast, complex and mostly unstructured. Big Data predictive analytics using machine learning techniques helps in analyzing such data and is currently an active area of research in biological computing. The objective of this research paper is to predict the toxicity of drug samples; here, the hot topic of the era comes into the role; machine learning plays a significant role in predicting toxicity of drug samples on the basis of various features of samples. The proposed framework predicts the toxicity of drug sample which can help in identifying adverse effects caused from it with an accuracy of 91.15% with random forest. The results are further optimized by building an ensemble of J48 and random forest, the two best performing classifiers on drug data. With a prediction accuracy of 96.20%, the results are compared with standard machine learning models like random forest, AdaBoost, Naive Bayes, etc., and are found to be much better than these classifiers. With the increase in toxicity in environment, this framework will play a significant role in improving lifestyle.
Sankalp Sharma, Nishtha Hooda

Implementation of Block-Based Symmetric Algorithms for Real Image Encryption

Abstract
The security is considered as the most challenging aspect in any of the networks. Since the growth of Internet and online applications is increasing at a rapid rate, security of data being transmitted over network is a major concern today for users. The first line of security is cryptography which is important for securing the data over insecure networks. Data transmitted over the network can be in any form such as text, images, videos, etc. This paper addresses various cryptographic algorithms implemented over a real image of Indian airbase station taken from Google image, and a fair comparison among symmetric algorithms AES, DES, and Blowfish has been done. The paper further examines various parameters to compare the efficiency of these algorithms over the image. The encryption and decryption processes are carried out in Java followed by the testing and analysis of various parameters using MATLAB.
Ritu Shaktawat, Rajdeep Singh Shaktawat, Isha Suwalka, N. Lakshmi

Human Emotion Recognition Using Body Expressive Feature

Abstract
Recognition of emotions from human plays a vital role in our day-to-day life and is essential for social communication. In many application of human–computer interaction using nonverbal communication like facial expression, body movements, eye movements and gestures are used. Among these methods, body movement method is widely used because it predicts the emotions of human. In this paper, body expressive features (angle, distance, velocity and acceleration) are proposed to recognize the emotion from human body movements. The GEMEP corpus (straight view) videos are used for this experiment. The 12-dimensional features were extracted from the head point, left-hand point and right-hand point of body movements of the human present in the frame. The features are given to the random forest (RF) classifier to predict the human emotions. The performance measure can be calculated using qualitative and quantitative analyses.
R. Santhoshkumar, M. Kalaiselvi Geetha

Self-energizing Wireless Sensor Network

Abstract
The autonomous deployments using wireless sensor networks (WSNs) and their ability to self-organize play a vital role in data gathering in hostile environment or mission-critical applications. The contributions of this paper are threefold. First, the study in this paper proposes a preliminary model for peer-to-peer wireless power transfer (WPT) between sensor nodes, which is termed as self-energizing technique. Second, a fundamental design of a sensor node suitable for the self-energizing model is proposed, and third, using a clustering algorithm along with the flow mechanism to utilize the self-energizing technique is demonstrated. The study in this paper is a preliminary step toward proposing self-energizing technique between the peer sensor nodes of a deployed WSN. The paper concludes with the fact that the implications of self-energizing capabilities have the potential to enhance the fundamental deployment and design of such ad hoc networks.
Aditya Singh, Manisha J. Nene

A Fuzzy Logic-Based Control System for Detection and Mitigation of Blackhole Attack in Vehicular Ad Hoc Network

Abstract
Vehicular ad hoc network enables the vehicle in the network to establish a connection when they required to communicate with the other vehicle in the network. These networks are the attraction point for many researchers for last five to six years because of its recompense. There are various researches surrounding VANET to increase its competence to put good use of the advantage these networks tend to provide. The proposed paper will not only provide a comparative analysis of traditional protocol approaches but also will suggest design and analysis of the framework against blackhole and their effect on the difference performance parameter. We have studied and analyzed the AODV protocol in different scenarios in VANET and identified the vulnerabilities available in this protocol. We have proposed a new technique based on fuzzy logic-based control. This technique is used for detection and identification of blackhole attack in VANET. In our proposed technique, every node wants to transmit the packet to other node; they have to send the route request packet and wait until they receive the acknowledgement from receiver node. Then, the packet receiver node analyzes the packet and identifies and calculates the trust value of the packet based on how this packet is used by the sender. It is used as how this packet is transmitted in the network and how it is used by the node whose behavior is as malicious node. It increases the throughput of the network in data transmission speed.
Ankit Kumar, Pankaj Dadheech, Mahender Kumar Beniwal, Basant Agarwal, Pawan Kumar Patidar

Cloud Computing-Based Approach for Accessing Electronic Health Record for Healthcare Sector

Abstract
Big data has revolutionized all the small and major promising areas that include education, banking and finance, Governance, health sector, and others in the recent decade. Analytics techniques of big data provide various tools to store investigate methods and manage this vast volume of data that is being generated in every field. The quick and vast expansion of big data has revolutionized health sector and research quite remarkably. The rate of medical health care usage has been increasing day by day owing to the growing population throughout the world. Keeping in view, that the medical data of different individuals remains scattered across various public institutions, there is a need of a platform that can be used to assimilate these records and then provide an efficient means to access and process these records. This paper tries to address this challenging task by suggesting a new framework that uses cloud computing as a backbone for healthcare sector.
Ashish Kumar Mourya, Shafqat-Ul-Ahsaan, Sheikh Mohammad Idrees
Weitere Informationen

Premium Partner

    Bildnachweise