Automatic Discovery of Basic Motion Classification Rules

There is a keen demand for a method of sharing better work practices in a factory because better work practices are the key to improving productivity. We have developed a system that can measure a worker's motion and automatically generate a manual that describes his movements. This system employs motion study as used in Industrial Engineering to identify the important steps in a job, and it has proven to be effective especially in the fields of factory machine operation and maintenance. However, work procedures often include unique basic motions. The determination of basic motions and the creation of an algorithm that can classify these basic motions are time consuming and complex tasks. Therefore we have employed the C4.5 algorithm to discover rules that classify the basic motions. Experimental results prove that our method can successfully discover rules for various work procedures.

• Type: Journal
• Year: 2006
• Where: KES
• Authors: Satoshi Hori, Mizuho Sasaki, Hirokazu Taki
• Keywords: Basic Motions, Information Technology, Keen Demand, KES 2006, Work Procedures