A Hybrid Method for Detecting Data Stream Changes with Complex Semantics in Intensive Care Unit

Abstract. Detecting changes in data streams is very important for many applications. This paper presents a hybrid method for detecting data stream changes in intensive care unit. In the method, we first use query processing to detect all the potential changes supporting semantics in big granularity, and then perform similarity matching, which has some features such as normalized subsequences and weighted distance. Our approach makes change detection with a better trade-off between sensitivity and specificity. Experiments on ICU data streams demonstrate its effectiveness.

• Type: Conference
• Year: 2005
• Where: ASIAN
• Authors: Ting Yin, Hongyan Li, Zijing Hu, Yu Fan, Jianlong Gao, Shiwei Tang
• Keywords: Algorithms, ASIAN 2005, Changes Supporting Semantics, Data Stream Changes, Data Streams