Deep Learning: Convergence to Big Data Analytics

verfasst von: Dr. Murad Khan, Dr. Bilal Jan, Haleem Farman

Verlag: Springer Singapore

Buchreihe : SpringerBriefs in Computer Science

Enthalten in: Springer Professional "Wirtschaft+Technik" , Springer Professional "Technik" , Springer Professional "Wirtschaft"

Einloggen, um Zugang zu erhalten

Über dieses Buch

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.

Inhaltsverzeichnis

Frontmatter

Chapter 1. Introduction

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.

Bilal Jan, Haleem Farman, Murad Khan

Chapter 2. Big Data Analytics

Abstract

During the last few decades, with the emergence of smart things and technological advancements of embedded devices, Big Data (BD) and Big Data Analytics (BDA) have been extensively popularized in both industrial and academic domains. The initial portion of the chapter aims to deliver a generic insight toward BD and BDA. In later sections, details that are more specific to BD and BDA are discussed. In fact, BD notion is characterized by its distinctive features such as large amounts of data, high-speed data generation, and wide variety among data type and sources. Consideration on these characteristics assists in determining potential data processing techniques. Hence, this chapter further elaborates on key BD analytical scenarios. Moreover, application of BD, BD analytical tools, and data types of BD are described, in order to enlighten the readers about this broad subject domain. Finally, the chapter concludes by identifying potential opportunities as well as challenges faced by BD and BDA.

Bhagya Nathali Silva, Muhammad Diyan, Kijun Han

Chapter 3. Deep Learning Methods and Applications

Abstract

This chapter introduces the various methods existing beneath the umbrella of deep learning paradigm, their intricate details, and their applications in various fields. Deep learning has substantially improved the predictive capacity of computing devices, due to the availability of big data, with the help of superior learning algorithms. It has made it possible as well as practical to integrate machine learning with sophisticated applications including image recognition, object detection, self-driving cars, drug discovery, and disease detection. The superior and reliable performance of deep learning methods has attracted the attention of researchers working in every field of science to utilize their strengths in order to solve problems. In addition to that, the knowledge reuse in deep learning is an interesting aspect of this technology which will also be discussed.

Jamil Ahmad, Haleem Farman, Zahoor Jan

Chapter 4. Integration of Big Data and Deep Learning

Abstract

The traditional algorithms of artificial intelligence and neural networks have many limitations to process big data in real time. Therefore, the researchers introduce the concept of deep learning to address the aforementioned challenge. However, big data analytics required a process consists of various steps where in each step an algorithm or a bunch of algorithm can be used. This chapter explains the role of machine learning in processing big data to meet various applications and users’ demands in real time. Similarly, various techniques of deep learning are studied to show how they can be used to address various challenges and issues of big data. Similarly, other similar techniques such as transfer learning are also discussed to support the study of deep learning.

Muhammad Talha, Shaukat Ali, Sajid Shah, Fiaz Gul Khan, Javed Iqbal

Chapter 5. Future of Big Data and Deep Learning for Wireless Body Area Networks

Abstract

Deep learning is an innovative set of algorithms in machine learning and requires minimum efforts of human engineering in extraction of features from data. It has the ability to find the optimum set of parameters for the network layers using a back-propagation algorithm, thereby modeling intricate structures in the data distribution. Further, deep learning architectures have resulted in tremendous performance on most recent machine learning challenges included working with sequential data such as text and time series data. In this connection, big data technology is an asset for modern businesses and is useful if powered by intelligent automation. Big data involves huge datasets that can be analyzed by machine learning such as deep learning algorithms to find insightful patterns and trends. With modern-day machine learning and big data technology, organizations can drive its long-term business value far more successful than ever before. Potential real-world applications of big data are not limited to healthcare, retail, financial services, and the automotive industry. In this way, the deep learning can have a great impact on analyzing the patient’s data generated from wireless body area networks (WBANs). WBAN is the emerging technology in healthcare to assist in monitoring of vital signs of patients using biomedical sensors. The monitored data is transmitted to the medical doctor for an optimal treatment in a life-threatening situation. At the end of this book, open research issues in WBAN and big data have discussed.

Fasee Ullah, Ihtesham Ul Islam, Abdul Hanan Abdullah, Atif Khan

Backmatter

Titel: Deep Learning: Convergence to Big Data Analytics
verfasst von: Dr. Murad Khan
Dr. Bilal Jan
Haleem Farman
Verlag: Springer Singapore
Electronic ISBN: 978-981-13-3459-7
Print ISBN: 978-981-13-3458-0
DOI: https://doi.org/10.1007/978-981-13-3459-7