Leveraging Big Data Analytics Utilizing Hadoop Framework in Sports Science
The first ever utilization of statistics in professional sports has been made possible to make better personal decisions with the assistance of Big Data. Each day, a number of matches are played under different categories of sports and each day, new recor
- PDF / 625,509 Bytes
- 14 Pages / 439.37 x 666.142 pts Page_size
- 23 Downloads / 218 Views
and Sarabjeet Kaur
Abstract The first ever utilization of statistics in professional sports has been made possible to make better personal decisions with the assistance of Big Data. Each day, a number of matches are played under different categories of sports and each day, new records are set up and old records are broken and all the concerned data, statistics, and records undergo major changes. With the introduction of innovative sensor enabled technologies and wearable devices, the data generated from different sources can be collecting easily and accurately and analysts can make most of it. This helps in taking decisions like when to substitute the player. A team can predict the policies and tactics to be adopted by the opposition prior to the next scheduled encounter with the assistance of Big Data. The same can be applied on the team itself to check out the shortcomings and flaws in the game plan of the team. The fundamental purpose of the research work is to investigate how sports have profited with the utilization of Big Data and how further enhancement can be made possible in this field. The major challenge in sports science is to gain the competitive advantage over opposition using big data and it can be accomplished via appropriately mining the collected data. The research work focuses on the comparison of conventional Apriori data mining algorithm with the Hadoop-based MapReduce algorithm capable of handling the enormous amount of data. With the use of the Apache Hadoop framework, all this generated data can be collected in huge servers and can be mined when and as required with much ease. Keywords Apriori algorithm
Big data MapReduce
G. Jagdev (&) Department of Computer Science, Punjabi University Guru Kashi College, Damdama Sahib, Punjab, India e-mail: [email protected] S. Kaur Research Scholar, Punjabi University, Patiala, Punjab, India e-mail: [email protected] © Springer Nature Singapore Pte Ltd. 2019 A. K. Luhach et al. (eds.), Smart Computational Strategies: Theoretical and Practical Aspects, https://doi.org/10.1007/978-981-13-6295-8_22
259
260
G. Jagdev and S. Kaur
1 Introduction With the advent of innovative technologies and knowledge, there has been tremendous growth in the pool of data and as much one tries to get to the surface, the level rises more above. It requires mining, and appropriate mining yields accurate results [1]. The data has grown to such an extent that new terms like Exabyte, Zettabyte, and Yottabyte have been introduced to measure the amount of accessible data [2]. Big Data has influenced the majority of public and private sectors where strategic decisions are of utmost importance, comprising banks, retail sector, medical science, stock market, elections, and sports science. There is no exact size which can be used as an indicator to declare data as a big data. It depends upon the planned purposes and economic sector.
1.1
Issues Related with Big Data
Major concerns relevant to big data are mentioned as under [3–5]. • Data degree—Degree refers to the size
Data Loading...
