Fuzzy Inference of Time Adjustment in Multimedia Information Acquisition
Kabsuk Oh* and Kaoru Hirota**
*Dept. of Computer Science, Dongmyung College 505 Yongdang-Dong, Nam-Gu, Pusan 608-740, Korea Interdisciplinary Graduate School of Science and Engineering,
** Tokyo Institute of Technology 4259 Nagatsuta, Midori-ku, Yokohama 226-8502, Japan
A multimedia information data acquisition method is proposed based on fuzzy rules, in which multimedia mean the five human senses. Observed information is visual, acoustic, gustatory, olfactory, and tactile (VAGOT), time series data and the goal is to extract an appropriate subset of VAGOT data based on a given instruction. Here, multimedia information centers on image and sound, represented by membership functions. Fuzzy rules based on visual and acoustic information are used to identify the appropriate time interval in three experiments : various cars on a road, sunny-side-up eggs and fireworks.