Literature Review on Big Data Concept

Quiz-3:

1. Summarize the article in one paragraph.

In this paragraph author try to explain about the big data concept and data mining like the characteristics of the big data, demonstrate and examples of big data. This article giving the information about a HACE theorem and it characteristic features, process model of the big data, and also data mining perspective of the big data. How the large volume of data, complexity difficulties of the massive volumes of data storage and analyze, challenging issues in the data driven models. And also introduction about the Dr. Yan MO and his Nobel Prize in Literature demonstrate the big data big data applications with few examples, finally key challenges in the big data mining.

2. What 5 lessons did you learn from reading this article?

1. About the big data and data mining: Big data is nothing but large volume or massive volumes of data stored in a specific data bases by using some techniques and tools. This data mining is with is a quick improvement process of various networking systems, and data storage, large data collecting capability. Big data is fast and rapidly growing massive data storage technology in all various health care domains as well as in engineering domains.
2. Introduction about Dr. Yan MO: Dr. Yan MO is a good Literature; he won Nobel Prize in 2012 in Literature. Searching on Google with “Yan MO Nobel Prize” you can get lot of information about it.
3. HACE theorem: HACE theorem about giant elephant and blind men theorem is a good concept for understanding the data mining and the big data process.
4. Characteristic of big data: The main characteristic of big data is collection of large volume of data from various and multi languages with composed of parts of different kinds of information it includes information is audio, video and textual types of data. Huge volume of data with secure   For major Big Data related applications, for example, Google, Flicker, Face book, and Wal-Mart, a massive number of server ranches are conveyed everywhere throughout the world to  continuous services and immediate  responses for local markets.
5. Key challenges of big data mining: challenges like to perform and maintaining big data by gathering information in a digital form, various organizations take their improvement to another level and create three tier big data mining platform for maintaining the massive data. Three tiers structured like Tier-1: low level data accessing and system computing, Tier-2: Concentrates on the high level semantics information and applications. Tier-3: Data mining algorithms.

3. What are the concerns of Big Data?

The main concern of big data is large volume of massive data, subsequently the quantity of large archives of Big Data has been expanded with near increment of related security concerns, privacy concerns, and somebody can target the data and try to hack the data. Notwithstanding the high estimation of Big Data target, securing Big Data has its own exceptional difficulties which are not on a very basic level deferent from those connected with traditional information. A few people think that concealing their identity alone without hiding their location would not appropriately address privacy concerns.

Governance: Big data is rich with individual personal data and confidential organizations information, and data governance is required to ensure that data is secured.

4. Why was this article written?

This article main aim is to explain the concept of big data with data mining with few examples, big data characteristics, HACE theorem, how handle and maintain huge heterogeneous data uses in health care domains as well as in engineering domains with different organizations. A big data processing system framework it includes mining complex and dynamic data, local learning and model fusion, mining from spares, uncertain and incomplete data. Explain about research initiative and some projects to investigate for the big data management.   These projects try to create strategies, calculations, frameworks, and research foundations which permit us to bring the large volume of data down to a human reasonable and interpretable scale

5. Give Big Data characteristics using the HACE Theorem?

In this HACE theorem author try explains the concept of big data mining and data collecting gather the data from various sources and finally stored in a one large volume data base. This theorem mainly explains about the two types of data structured and unstructured data. Actually big data starts with the massive volume Heterogeneous, Autonomous source with distributed and seeks to maintain or explore Complex and Evolving relationship among the data. Sources of big data are log data, social media, transactions, events, images, audios, videos and emails.

(Deepak S. Tamhane, January 2015)

6. What are the most fundamental challenges of Big Data mining?

The main fundamental challenges of big data are to investigate large volume of massive data and extract useful information for future activities. In Big data have different layers in every layer will give the technology required to reduce different challenges every one of these layers give the complete solution.

Data Secure and Privacy: This has various implementations and it concerns people and organizations too. People have the privilege, as indicated by Universal Telecommunications Union, to control the data that might be revealed with respect to them.

Sharing the large volume of data is most important characteristic feature in the development process. And few challenges those are data acquisition, and recording, voluble information extraction and cleaning, data aggregation and integration, integrating data base system and analytics tools, and interpretation like wrong modeling, application bugs.

Volume: Large volume of information being put away is significantly expanding each and every moment, massive of information put away everywhere throughout the websites.

7. How is the “Blind Men and Giant Elephant” explain Big Data Mining?

These characteristic make it an extraordinary challenge for discovering voluble information from the Big Data. In a local sense, we can estimate that various visually blind men are attempting to survey a giant elephant, which will be the Big Data in this specific circumstance. So every blind man can measure and estimates the particular region a part of information they collected during this process, because each person limited to his local region. In this concept every person feels like a hose, wall, tree and rope so exploring the big data in this situation is equal to aggregating heterogeneous data from various sources to draw the exact picture of elephant so collecting the data from various sources and various types of data, various languages of data.

(Chun-Wei Tsai, 1 October, 2015)

Chun-Wei Tsai, C.-F. L.-C. (1 October, 2015). SpringerOpen . Journal of Big Data .

Deepak S. Tamhane, S. N. ( January 2015). BIG DATA ANALYSIS USING HACE THEOREM. International Journal of Advanced Research in Computer Engineering & Technology (IJARCET) .