Deep Learning: Convergence to Big Data Analytics

By Murad Khan, Bilal Jan and Haleem Farman

This book presents deep learning techniques, concepts, and algorithms to classify and analyze big data. Further, it offers an introductory level understanding of the new programming languages and tools used to analyze big data in real-time, such as Hadoop, SPARK, and GRAPHX. Big data analytics using traditional techniques face various challenges, such as fast, accurate and efficient processing of big data in real-time. In addition, the Internet of Things is progressively increasing in various fields, like smart cities, smart homes, and e-health. As the enormous number of connected devices generate huge amounts of data every day, we need sophisticated algorithms to deal, organize, and classify this data in less processing time and space. Similarly, existing techniques and algorithms for deep learning in big data field have several advantages thanks to the two main branches of the deep learning, i.e. convolution and deep belief networks. This book offers insights into these techniques and applications based on these two types of deep learning.

Further, it helps students, researchers, and newcomers understand big data analytics based on deep learning approaches. It also discusses various machine learning techniques in concatenation with the deep learning paradigm to support high-end data processing, data classifications, and real-time data processing issues.

The classification and presentation are kept quite simple to help the readers and students grasp the basics concepts of various deep learning paradigms and frameworks. It mainly focuses on theory rather than the mathematical background of the deep learning concepts. The book consists of 5 chapters, beginning with an introductory explanation of big data and deep learning techniques, followed by integration of big data and deep learning techniques and lastly the future directions.

• Language: English
• Publisher: Springer
• Release date: Dec 30, 2018
• ISBN: 9789811334597

Book preview

© The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2019

Murad Khan, Bilal Jan and Haleem FarmanDeep Learning: Convergence to Big Data AnalyticsSpringerBriefs in Computer Sciencehttps://doi.org/10.1007/978-981-13-3459-7_1

1. Introduction

Bilal Jan¹  , Haleem Farman²   and Murad Khan³  

(1)

FATA University, FR Kohat, Pakistan

(2)

Department of Computer Science, Sarhad University of Science and Information Technology, Peshawar, Khyber Pakhtunkhwa, Pakistan

(3)

Department of Computer Science, Islamia College Peshawar, Khyber Pakhtunkhwa, Pakistan

Bilal Jan (Corresponding author)

Email: [e-mail]

Haleem Farman

Email: [e-mail]

Murad Khan

Email: [e-mail]

Abstract

Recently, deep learning techniques are widely adopted for big data analytics. The concept of deep learning is favorable in the big data analytics due to its efficient use for processing huge and enormous data in real time. This chapter gives a brief introduction of machine learning concepts and its use in the big data. Similarly, various subsections of machine learning are also discussed to support a coherent study of the big data analytics. A thorough study of the big data analytics and the tools required to process the big data is also presented with reference to some existing and well-known work. Further, the chapter is concluded by connecting the deep learning with big data analytics for filling the gap of using machine learning for huge datasets.

List of Acronyms

AI

Artificial intelligence

ANN

Artificial neural networks

HDFS

Hadoop Distributed File System

M2M

Machine to machine

IoT

Internet of things

CPS

Cyber physical systems

ICN

Information-centric networking

WSN

Wireless sensor network

1.1 Machine Learning

The need of machine learning was felt when artificial intelligence (AI)-based systems were facing difficulties with hard-coded programs, and it was suggested that machines should be able to extract patterns from the data by itself without the involvement of human or programs for specific tasks. The idea of machine learning was introduced in 1959 by Arthur Samuel (field expert) that instead of programming machines for specific tasks, computers should be able to learn themselves (BMC blog 2018). Machine learning is the subset of artificial intelligence, in which system can adjust its activities and react to specific situation when provided with large amount of data (Ahmad et al. 2018a, b). In machine learning, systems are trained to act accordingly. These systems are provided with many examples specifically related to task, and statistical structures are identified that leads system to define rules for that particular task. Machine learning deals with large amount of datasets (Khumoyun et al. 2016), for instance, medical dataset containing millions of patient images for different diseases. There are many applications such as recommendation and navigation systems using machine learning giving more accurate and efficient result as compared to hard-coded programs. Machine learning is classified into supervised learning and unsupervised learning (BMC blog