Mutual information is an important information measure for feature subset. In this paper, a hashing mechanism is proposed to calculate the mutual information on the feature subset. Redundancy-synergy coefficient, a no...Mutual information is an important information measure for feature subset. In this paper, a hashing mechanism is proposed to calculate the mutual information on the feature subset. Redundancy-synergy coefficient, a novel redundancy and synergy measure of features to express the class feature, is defined by mutual information. The information maximization rule was applied to derive the heuristic feature subset selection method based on mutual information and redundancy-synergy coefficient. Our experiment results showed the good performance of the new feature selection method.展开更多
We developed an IT （Information Technology） triage system for collecting disaster medical information in real time. FeliCa cards and card readers are used to obtain the number and condition of patients. The system i...We developed an IT （Information Technology） triage system for collecting disaster medical information in real time. FeliCa cards and card readers are used to obtain the number and condition of patients. The system is composed of two elements. First, the number of patients for each triage level and the accepted number of patients in each diagnosis and treatment department are obtained in real time, including response for changing triage level. Second, this information is shared in real time among hospitals, the admim＇stration, and residents who are searching for their family. A disaster drill utilizing this system was held at the University of Yamanashi Hospital with 450 participants. From the result of that, the present system could work for those two elements. TRACY was examined its availability and practicability in this drill.展开更多
基金Project supported by the National Natural Science Foundation ofChina (No. 60075007) and the National Basic Research Program(973) of China (No. G1998030401)
文摘Mutual information is an important information measure for feature subset. In this paper, a hashing mechanism is proposed to calculate the mutual information on the feature subset. Redundancy-synergy coefficient, a novel redundancy and synergy measure of features to express the class feature, is defined by mutual information. The information maximization rule was applied to derive the heuristic feature subset selection method based on mutual information and redundancy-synergy coefficient. Our experiment results showed the good performance of the new feature selection method.
文摘We developed an IT （Information Technology） triage system for collecting disaster medical information in real time. FeliCa cards and card readers are used to obtain the number and condition of patients. The system is composed of two elements. First, the number of patients for each triage level and the accepted number of patients in each diagnosis and treatment department are obtained in real time, including response for changing triage level. Second, this information is shared in real time among hospitals, the admim＇stration, and residents who are searching for their family. A disaster drill utilizing this system was held at the University of Yamanashi Hospital with 450 participants. From the result of that, the present system could work for those two elements. TRACY was examined its availability and practicability in this drill.
