An Intelligent Context-Sensitive System Based on Improved Self-adaptive BP Algorithm
Since the context plays a significant role in ubiquitous computing environment, many researches have been done on context-awareness system to improve the performance. In this paper, we concentrate on improving the predict ability and reducing the system workload by proposing a brandnew middleware using improved back propagation (BP)algorithm. An efficient learning mechanism is in importance of context-aware system, but there are seldom algorithms focused on convenience of systems by elaborating the learning mechanism with users context information. As one of the most adaptable algorithm, BP provides us favorable inference capability. The middleware we proposed drastically improves the predicate capability by using improved BP algorithm. Thus, the overall performance is far better than other systems. By adding system cache to middleware, it is possible for the context-aware system to act in real time and further improve the workload efficiency. Experiments show that there is an obvious improvement in overall performance of the contextawareness systems by using the proposed middleware.
Sang-Hun Eo Byeong-Seob You Dong-Wook Lee Jae-Dong Lee Hae-Young Bae
Dept, of Computer Science & Information Engineering, Inha University Division of Information and Computer Science, Dankook University
国际会议
重庆
英文
392-397
2007-04-24（万方平台首次上网日期，不代表论文的发表时间）