| Foreword |
|
xix | |
| Preface |
|
xx | |
| Acknowledgment |
|
xxviii | |
| Section 1: Applications and Approaches to Big Data |
|
|
Chapter 1 Big Data Challenges and Solutions in the Medical Industries |
|
|
|
|
|
|
|
Big data today is being investigated to find the bits of knowledge that prompt better choices and vital business moves. The data innovations are developing to a point in which an ever-increasing number of associations are set up to pilot and embrace big data as a center part of the data administration and examination framework. It is a range of research that is blasting yet at the same time confronts many difficulties in utilizing the esteem that information brings to the table. The battle against "spam information" and information quality is a pivotal issue. Big data challenges are discussed and some solutions are proposed because the volume of made information will surpass the capacity limits and will require cautious determination. |
|
|
|
Chapter 2 Investigation on Deep Learning Approach for Big Data: Applications and Challenges |
|
|
25 | (14) |
|
|
|
|
|
|
|
In recent years, big data analytics is the major research area where the researchers are focused. Complex structures are trained at each level to simplify the data abstractions. Deep learning algorithms are one of the promising researches for automation of complex data extraction from large data sets. Deep learning mechanisms produce better results in machine learning, such as computer vision, improved classification modelling, probabilistic models of data samples, and invariant data sets. The challenges handled by the big data are fast information retrieval, semantic indexing, extracting complex patterns, and data tagging. Some investigations are concentrated on integration of deep learning approaches with big data analytics which pose some severe challenges like scalability, high dimensionality, data streaming, and distributed computing. Finally, the chapter concludes by posing some questions to develop the future work in semantic indexing, active learning, semi-supervised learning, domain adaptation modelling, data sampling, and data abstractions. |
|
|
|
Chapter 3 An Application of Big Data Analytics in Road Transportation |
|
|
39 | (16) |
|
|
|
|
|
Data is being captured in all domains of society and one of the important aspects is transportation. Large amounts of data have been collected, which are detailed, fine-grained, and of greater coverage and help us to allow traffic and transportation to be tracked to an extent that was not possible in the past. Existing big data analytics for transportation is already yielding useful applications in the areas of traffic routing, congestion management, and scheduling. This is just the origin of the applications of big data that will ultimately make the transportation network able to be managed properly and in an efficient, way. It has been observed that so many individuals are not following the traffic rules properly, especially where there are high populations, so to monitor theses types of traffic violators, this chapter proposes a work that is mainly based on big data analytics. In this chapter, the authors trace the vehicle and the data that has been collected by different devices and analyze it using some of the big data analysis methods. |
|
|
|
Chapter 4 Big Data and Analytics: Application to Healthcare Industry |
|
|
55 | (12) |
|
|
|
|
|
|
|
|
|
In today's world, humungous and heterogeneous data are being generated from every action of researchers, health organizations, etc. This fast, voluminous, and heterogeneous generation leads to the evolution of the term big data. Big data can be computationally analyzed to uncover hidden trends and patterns that help in finding solutions to the problems arising in various fields. Analysis of big data for manufacturing operational acquaintance at an unparalleled specificity and scale is called big data analytics. Proper utilization of analytics can assist in making effective decisions, improved care delivery, and achieving cost savings. Recognizing hidden trends and useful patterns can lead us to have a clear understanding of the valuable information that these data holds. This chapter presents a quality overview of big data and analytics with its application in the field of healthcare industries as these industries requires their stream of data to be stored and analyzed efficiently in order to improve their future perspective and customer satisfaction. |
|
|
|
Chapter 5 Insight Into Big Data Analytics: Challenges, Recent Trends, and Future Prospects |
|
|
67 | (13) |
|
|
|
|
|
|
|
In the present digital era, more data are generated and collected than ever before. But, this huge amount of data is of no use until it is converted into some useful information. This huge amount of data, coming from a number of sources in various data formats and having more complexity, is called big data. To convert the big data into meaningful information, the authors use different analytical approaches. Information extracted, after applying big data analytics methods over big data, can be used in business decision making, fraud detection, healthcare services, education sector, machine learning, extreme personalization, etc. This chapter presents the basics of big data and big data analytics. Big data analysts face many challenges in storing, managing, and analyzing big data. This chapter provides details of challenges in all mentioned dimensions. Furthermore, recent trends of big data analytics and future directions for big data researchers are also described. |
|
|
|
Chapter 6 Big Data Analytics Tools and Platform in Big Data Landscape |
|
|
80 | (11) |
|
|
|
|
|
|
|
|
|
The term big data analytics refers to mining and analyzing of the voluminous amount of data in big data by using various tools and platforms. Some of the popular tools are Apache Hadoop, Apache Spark, HBase, Storm, Grid Gain, HPCC, Casandra, Pig, Hive, and No SQL, etc. These tools are used depending on the parameter taken for big data analysis. So, we need a comparative analysis of such analytical tools to choose best and simpler way of analysis to gain more optimal throughput and efficient mining. This chapter contributes to a comparative study of big data analytics tools based on different aspects such as their functionality, pros, and cons based on characteristics that can be used to determine the best and most efficient among them. Through the comparative study, people are capable of using such tools in a more efficient way. |
|
|
| Section 2: Data Mining and Computing |
|
|
Chapter 7 Harnessing Collective Intelligence Through Pattern Mining in Social Computational Systems |
|
|
91 | (20) |
|
|
|
|
|
Due to the digital nature of the web, the social web mimics the real-world social dynamics that manifest themselves as data and can be easily mined as patterns, making the web a fertile ground for business and research-oriented analytical applications. Collective intelligence (CI) is a multifaceted field with roots in sociology, biology, and many other disciplines. Various manifestations of CI support the successful existence of large-scale social systems. This chapter gives an overview of the principles of CI and the concept of "wisdom of crowds" and highlights how to maximize the potential of big data analytics for CI. Also, various techniques and approaches have been described that leverage these CI concepts across a diverse range of ever-evolving social systems for commercial business applications like influence mining, expertise discovery, etc. |
|
|
|
Chapter 8 Machine Learning Models for Forecasting of Individual Stocks Price Patterns |
|
|
111 | (19) |
|
|
|
|
|
Stock investors always consider potential future prices before investing in any stock for making a profit. A large number of studies are found on the prediction of stock market indices. However, the focus on individual stock closing price predictions well ahead of time is limited. In this chapter, a comparative study of machine-learning-based models is used for the prediction of the closing price of a particular stock. The proposed models are designed using back propagation neural networks (BPNN), support vector regression (SVR) with SMOReg, and linear regression (LR) for the prediction of the closing price of individual stocks. A total of 37 technical indicators (features) derived from historical closing prices of stocks are considered for predicting the future price of stock in a time window of five days. The experiment is performed on stocks listed on Bombay Stock Exchange (BSS), India. The model is trained and tested using feature values extracted from the past five-year closing price of stocks of different sectors including aviation, pharma, banking, entertainment, and IT. |
|
|
|
Chapter 9 Sentiment Analysis: Using Artificial Neural Fuzzy Inference System |
|
|
130 | (23) |
|
|
|
|
|
E-commerce has become a daily activity in human life. In it, the opinion and past experience related to particular product of others is playing a prominent role in selecting the product from the online market. In this chapter, the authors consider Tweets as a point of source to express users' emotions on particular subjects. This is scored with different sentiment scoring techniques. Since the patterns used in social media are relatively short, exact matches are uncommon, and taking advantage of partial matches allows one to significantly improve the accuracy of analysis on sentiments. The authors also focus on applying artificial neural fuzzy inference system (ANFIS) to train the model for better opinion mining. The scored sentiments are then classified using machine learning algorithms like support vector machine (SVM), decision tree, and naive Bayes. |
|
|
|
Chapter 10 A Relative Performance of Dissimilarity Measures for Matching Relational Web Access Patterns Between User Sessions |
|
|
153 | (24) |
|
|
|
Customized web services are offered to users by grouping them according to their access patterns. Clustering techniques are very useful in grouping users and analyzing web access patterns. Clustering can be an object clustering performed on feature vectors or relational clustering performed on relational data. The relational clustering is preferred over object clustering for web users' sessions because of high dimensionality and sparsity of web users' data. However, relational clustering of web users depends on underlying dissimilarity measures used. Therefore, correct dissimilarity measure for matching relational web access patterns between user sessions is very important. In this chapter, the various dissimilarity measures used in relational clustering of web users' data are discussed. The concept of an augmented user session is also discussed to derive different augmented session dissimilarity measures. The discussed session dissimilarity measures are used with relational fuzzy clustering algorithms. The comparative performance binary session similarity and augmented session similarity measures are evaluated using intra-cluster and inter-cluster distance-based cluster quality ratio. The results suggested the augmented session dissimilarity measures in general, and intuitive augmented session (dis)similarity measure, in particular, performed better than the other measures. |
|
|
|
Chapter 11 Wavelet Transform Algorithms |
|
|
177 | (16) |
|
|
|
|
|
|
|
Digital image processing has an enormous impact on technical and industrial applications. Uncompressed images need large storage capacity and communication bandwidth. Digital images have become a significant source of information in the current world of communication systems. This chapter explores the phenomenon of digital images and basic techniques of digital image processing in detail. With the creation of multimedia, the requirements for the storage of a larger amount of high quality pictures and data analysis are increasing. |
|
|
|
Chapter 12 Web Access Patterns of Actual Human Visitors and Web Robots: A Correlated Examination |
|
|
193 | (23) |
|
|
|
Web robots are autonomous software agents used for crawling websites in a mechanized way for non-malicious and malicious reasons. With the popularity of Web 2.0 services, web robots are also proliferating and growing in sophistication. The web servers are flooded with access requests from web robots. The web access requests are recorded in the form of web server logs, which contains significant knowledge about web access patterns of visitors. The presence of web robot access requests in log repositories distorts the actual access patterns of human visitors. The human visitors' actual web access patterns are potentially useful for enhancement of services for more satisfaction or optimization of server resources. In this chapter, the correlative access patterns of human visitors and web robots are discussed using the web server access logs of a portal. |
|
|
|
Chapter 13 Web Usage Mining: Concept and Applications at a Glance |
|
|
216 | (14) |
|
|
|
|
|
Websites have become the major source of information, and analysis for web usage has become the most important way of investigating a user's behaviour and obtaining information for website owners to use to make any strategic decisions. This chapter sheds light on the concept of web usage mining, techniques, and its application in various domains. |
|
|
|
Chapter 14 Management and Monitoring Patterns and Future Scope |
|
|
230 | (23) |
|
|
|
|
|
|
|
Extricating information from expansive, heterogeneous, and loud datasets requires capable processing assets, as well as the programming reflections to utilize them successfully. The deliberations that have risen in the most recent decade mix thoughts from parallel databases, dispersed frameworks, and programming dialects to make another class of adaptable information investigation stages that shape the establishment of information science. In this chapter, the scene of important frameworks, the standards on which they depend, their tradeoffs, and how to assess their utility against prerequisites are given. |
|
|
| Section 3: Data-Oriented Security and Networking |
|
|
Chapter 15 Secure Opportunistic Routing for Vehicular Adhoc Networks |
|
|
253 | (21) |
|
|
|
|
|
More study is needed to make VANETs more relevant. Opportunistic routing (OR) is a new model that has been proposed for wireless networks. OR has emerged from the research communities because of its ability to increase the performance of wireless networks. It benefits from the broadcast characteristic of wireless mediums to improve network performance. The basic function of OR is its ability to overhear the transmitted packet and to coordinate among relaying nodes. In this chapter, an exhaustive survey of existing OR protocols is done by considering various factors. More precisely, existing secure OR protocols are deliberated. Future directions of research are also included, which provide a superior way to overcome some of the limitations of these existing protocols. Through this detailed survey, an outline and in-depth knowledge of existing OR protocols can be acquired. |
|
|
|
Chapter 16 Detection Approaches for Categorization of Spam and Legitimate E-Mail |
|
|
274 | (23) |
|
|
|
|
|
|
|
The internet has become very popular, and the concept of electronic mail has made it easy and cheap to communicate with many people. But, many undesired mails are also received by users and the higher percentage of these e-mails is termed spam. The goal of spam classification is to distinguish between spam and legitimate e-mail messages. But, with the popularization of the internet, it is challenging to develop spam filters that can effectively eliminate the increasing volumes of unwanted e-mails automatically before they enter a user's mailbox. The main objective of this chapter is to examine and identify the best detection approach for spam categorization. Different types of algorithms and data mining models are proposed, implemented, and evaluated on data sets. For improvement of spam filtering technique, the authors analyze the methods of feature selection and give recommendations of their use. The chapter concludes that the data mining models using a combination of supervised learning algorithms provide better results than single data models. |
|
|
|
Chapter 17 Video Steganography Using Two-Level SWT and SVD |
|
|
297 | (13) |
|
Lingamallu Naga Srinivasu |
|
|
|
|
Secured text data transmission plays an important role in communications. Discrete wavelet transform (DWT) is a time variant transform. The drawback of DWT can be overcome by stationary wavelet transform (SWT). SWT is designed to achieve the translation invariance. This chapter presents a novel secured text data transmission through video steganography using two-level stationary wavelet transform (SWT) and singular value decomposition (SVD). SVD of an image can be factored into its three components. In this chapter, text data is encrypted in cover video file using SWT and SVD techniques. First, the cover video is split into frames and each frame of the video acts as an image. Each character in the text data is encrypted with appropriate key value in each frame of the image using two-level SWT and SVD. The encrypted images are converted into video files that are called stego-video files. The text data can be recovered from the stego-video files after converting these files into frames by applying suitable key values, two-level SWT and SVD techniques. |
|
|
|
Chapter 18 Overview of Concept Drifts Detection Methodology in Data Stream |
|
|
310 | (8) |
|
|
|
|
|
|
|
Real-time online applications and mobile data generate huge volume of data. There is a need to process this data into compact data structures and extract meaningful information. A number of approaches have been proposed in literature to overcome the issues of data stream mining. This chapter summarizes various issues and application techniques. The chapter is a guideline for research to identify the research issues and select the most appropriate method in order to detect and process novel class. |
|
|
|
Chapter 19 Fast Fractal Image Compression by Kicking Out Similar Domain Images |
|
|
318 | (14) |
|
|
|
|
|
|
|
Fractal algorithms are used to represent similar parts of images into mathematical transforms that can recreate the original image. This chapter presents a fast fractal image compression technique via domain kick-out method, based on averaging of domain images to discard redundant domain images. It accelerates the encoding process by reducing the size of the domain pool. Results of a simulation on the proposed speedup technique on three standard test images shows that performance of the proposed technique is far superior to the present kick out methods of fractal image compression. It has reported a speedup ratio of 31.07 in average while resulting into compression ratio and retrieved image quality comparable to Jacquin's full search method. |
|
|
|
Chapter 20 Performance Analysis of Mail Clients on Low Cost Computer With ELGamal and RSA Using SNORT |
|
|
332 | (22) |
|
Sreerama Murthy Kattamuri |
|
|
|
|
|
|
An intrusion detection system (IDS) focuses on determining malicious tasks by verifying network traffic and informing the network administrator for restricting the user or source or source EP address from accessing the network. SNORT is an open source intrusion detection system (IDS) and SNORT also acts as an intrusion prevention system (IPS) for monitoring and prevention of security attacks on networks. The authors applied encryption for text files by using cryptographic algorithms like Elgamal and RSA. This chapter tested the performance of mail clients in low cost, low power computer Raspberry Pi, and verified that SNORT is efficient for both algorithms. Within low cost, low power computer, they observed that as the size of the file increases, the run time is constant for compressed data; whereas in plain text, it changed significantly. |
|
|
| Compilation of References |
|
354 | (35) |
| About the Contributors |
|
389 | (5) |
| Index |
|
394 | |
