Case Studies in Amalgamation of Deep Learning and Big Data

Case Studies in Amalgamation of Deep Learning and Big Data

Balajee Jeyakumar, M.A. Saleem Durai, Daphne Lopez
DOI: 10.4018/978-1-7998-0414-7.ch054
(Individual Chapters)
No Current Special Offers


Deep learning is now more popular research domain in machine learning and pattern recognition in the world. It is widely success in the far-reaching area of applications such as Speech recognition, Computer vision, Natural language processing and Reinforcement learning. With the absolute amount of data accessible nowadays, big data brings chances and transformative possible for several sectors, on the other hand, it also performs on the unpredicted defies to connecting data and information. The size of the data is getting larger, and deep learning is imminent to play a vital role in big data predictive analytics solutions. In this paper, we make available a brief outline of deep learning and focus recent research efforts and the challenges in the fields of science, medical and water resource system.
Chapter Preview


2. Overview of Big Data

Big data defined as datasets size is away from the capacity of the usual database, capture by software tools, store, manage, and analyze. Handling the data is not easy, and analysis in the standard database likes SQL. The data is too outsized, moves very quick, or it is not related to the structure of database architectures (Parimala & Lopez, 2016).

The key fact of V-based characterization is to focus the big data’s maximum thoughtful challenges are capture, cleaning, curation, integration, storage, processing, indexing, search, sharing, transfer, mining, analysis and visualization of huge sizes of rapid moving high complex data (Manogaran et al., 2016). Big data can be categorized as 10 V’s (Figure 1) are Volume, Variety, Velocity, Veracity, Validity, Value, Variability, Venue, Vocabulary, and Vagueness.

Figure 1.

10 V’s of big data


Complete Chapter List

Search this Book: