Total views : 174

The Study on the Analysis System of Effective Attack Patterns in Kendo Match using Hadoop-based Hive


  • Department of Computer Science and Engineering, Kongju National University, Chungnam Cheonam Subuk Cheonam-Dearo 1223-24 (Budeadong275), 32588, South Korea


Objectives: To analyze the effective attack pattern of Kendo for the use of effective training through Hive. Methods/ Statistical Analysis: The qualified three referees of Kendo competition analyze a video image of a real contest to extract the attack pattern, and store the extracted data in a database by pattern and in HDFS through the classification process. After purifying the stored data through the Mapping and Reducing, the results are extracted by using HiveQL, one of the sub-project ecosystems of Hadoop. Findings: In this paper, by using Hadoop and analysis tool Hive, a big data analysis system for performance enhancement of Kendo athlete is proposed. Experiment subjects were implemented for one game, but after collecting and purifying the recorded historical data over several years, various types of information will be collected. For example, many types of information can be collected such as changes in the age-specific, player-specific pattern, the contextual pattern, and so on by using such information effectively. Then, it may provide a pattern of the Kendo training. Improvements/Applications: In the future research, the methods of collecting data by image analysis techniques and the coaching environment for research and Kendo training should be studied continuously.


Data Collection, HDFS, Hadoop, Hive, Kendo.

Full Text:

 |  (PDF views: 138)


  • Ahn CG. A three-dimensional kinematic analysis of the front side head hitting motion in Kumdo, Master’s Thesis, Korea University; 2001.
  • Kim YH, Kwon EH. Systematic analysis on coaching behaviors of Kumdo coaches. The Korean Journal of Kumdo.2006; 21(1):22–34.
  • Kim YT, Park GH. An analysis study of scoring and technique according height difference in Kumdo players.Journal of Sport and Leisure Studies. 2006; 27:429–38.
  • Motoki O. A critical interpersonal distance switches between two coordination modes in kendo matches. Plos One. 2012; 7(12).
  • Tanaka Y, Kazuhiro K. Dynamic attack motion prediction for Kendo agent. IEEE/RSJ International Conference on Intelligent Robots and Systems; 2014.
  • Jeong YS, Kim YT, Park GC. Subnet Selection Scheme based on probability to enhance process speed of Big Data.Journal of Digital Convergence. 2015; 13(9):201–8.
  • Kyoo-sung N, Lee DS. Bigdata platform design and implementation model. Indian Journal of Science and Technology. 2015Aug; 8(18):1–8.
  • Lakshmi AGVNS. Comparison of machine learning algorithm on map reduction for performance improvement in big data. Indian Journal of Science and Technology. 2015 Nov; 8 (29):1–6.
  • Kim JY, Park KR, Jeong YS. Comparative study on data analysis techniques of big data. Proceedings of 6th ICCP, Jeju; 2015. p. 63–4.
  • JK Video Media, Latest Kendo Introduction, KugilmediaPubl: Korea; 1995.
  • Lee CM. A consideration of development progress of Japanese Modern Kendo. The Korea Journal of Kumdo.2015 Nov; 26(1):83–92.
  • Kim SR, Kang MM. Bigdata analytics technology today and the future. Journal of Computing Science and Engineering.2014 Jan; 32(1):8–17.
  • Choi SW, Kim HY, Kim YK. Research trend of bigdata technology and analysis technique. Proceedings of Computing Science and Engineering. 2012 Nov; 39(2A):194–6.
  • Chui MJ, Brown M, Bughin B, Dobbs J, Roxburgh RC, Byers AH. Big data: The next frontier for innovation, competition, and productivity; 2011.
  • Yong YH. The advent of bigdata technology. Journal of JKIIT. 2012 Sep; 10(3):39–43.
  • Kim SW, Kim GG, Yoon BK. A study on a way to utilize big data analytics in the defense area. Journal Korean Management Science Review. 2014 Jun; 29(2):1–19.
  • Lee HJ. Utilization of bigdatahadoop platform. Journal of Communications and Networks. 2012 Oct; 29(11):43–7.
  • Mann K, Jones MT. Distributed computing with Linux and Hadoop. IBM [Internet]. 2012. Available from:
  • MapReduce [Internet]. [cited 2016 Sep 21]. Available from: http:/
  • Cho SH, Lee SH, Pang SC, Kim YW. Design of file manager for dynamic data management based on HDFS.Proceedings of Korean Society for Internet Information; 2010 Jun. p. 203–6.
  • Dokeroglu T, Ozal S, Bayir MA, Cinar MS, Cosar A.Improving the performance of Hadoop Hive by sharing scan and computation tasks. Journal of Cloud Computing.2014; 3(12):1–9.
  • Lee YH, Lee YS. Yet another BGP archive forensic analysis tool using Hadoop and hive. Journal of KIISE. 2015 Apr; 42(4):541–9.


  • There are currently no refbacks.

Creative Commons License
This work is licensed under a Creative Commons Attribution 3.0 License.