Owing to continuous production lines with large amount of consecutive controls, various control signals and huge logistic relations, this paper introduced the methods and principles of the development of knowledge bas...Owing to continuous production lines with large amount of consecutive controls, various control signals and huge logistic relations, this paper introduced the methods and principles of the development of knowledge base in a fault diagnosis expert system that was based on machine learning by the four-layer perceptron neural network. An example was presented. By combining differential function with not differential function and back propagation of error with back propagation of expectation, the four-layer perceptron neural network was established. And it was good for solving such a bottleneck problem in knowledge acquisition in expert system and enhancing real-time on-line diagnosis. A method of synthetic back propagation was designed, which broke the limit to non-differentiable function in BP neural network.展开更多
OBJECTIVE: To survey assesses the perception of pattern identification(PI) diagnosis of Traditional Medicine(TM)by Korean medical doctors(KMDs).METHODS: A total of 14 485 KMDs affiliated with the Association of Korean...OBJECTIVE: To survey assesses the perception of pattern identification(PI) diagnosis of Traditional Medicine(TM)by Korean medical doctors(KMDs).METHODS: A total of 14 485 KMDs affiliated with the Association of Korean Medicine were sent surveys via email, and 1646(11.1%) responded to the questionnaire on their perception of PI diagnosis.RESULTS: Of the 1646 respondents, more than ninety percent(1562, 94.9%) reported that they treated patients using PI.The most critical problem with PI diagnosis was the lack of objective diagnostic indicators(561, 34.1%). Ninety percent had issues diagnosing patients because of different diagnoses between KMDs(1491, 90.5%). The majority of respondents thought herbal medicine was most related to PI(1528, 92.8%). Half of the respondents answered that PI of Ba Gang was the most commonly used PI system. Participants reported that it was most important to study standardisation of PI diagnosis and to develop standardised PI diagnoses using the classification system of the Korean Standard Classification of Diseases. The foremost PI type that physicians thought should be included in standardisation and objectification of PI of TKM was the PIof Ba Gang.CONCLUSION: Our data suggest that we should focus on the standardisation of PI diagnosis and PI of Ba Gang in future research on PI diagnosis inTM.However, we cannot completely discount the possibility that a biased selection of subjects and a low response rate limit the generalisability of the findings.展开更多
文摘Owing to continuous production lines with large amount of consecutive controls, various control signals and huge logistic relations, this paper introduced the methods and principles of the development of knowledge base in a fault diagnosis expert system that was based on machine learning by the four-layer perceptron neural network. An example was presented. By combining differential function with not differential function and back propagation of error with back propagation of expectation, the four-layer perceptron neural network was established. And it was good for solving such a bottleneck problem in knowledge acquisition in expert system and enhancing real-time on-line diagnosis. A method of synthetic back propagation was designed, which broke the limit to non-differentiable function in BP neural network.
基金Supported by the Korea Institute of Oriental Medicine(K12130)
文摘OBJECTIVE: To survey assesses the perception of pattern identification(PI) diagnosis of Traditional Medicine(TM)by Korean medical doctors(KMDs).METHODS: A total of 14 485 KMDs affiliated with the Association of Korean Medicine were sent surveys via email, and 1646(11.1%) responded to the questionnaire on their perception of PI diagnosis.RESULTS: Of the 1646 respondents, more than ninety percent(1562, 94.9%) reported that they treated patients using PI.The most critical problem with PI diagnosis was the lack of objective diagnostic indicators(561, 34.1%). Ninety percent had issues diagnosing patients because of different diagnoses between KMDs(1491, 90.5%). The majority of respondents thought herbal medicine was most related to PI(1528, 92.8%). Half of the respondents answered that PI of Ba Gang was the most commonly used PI system. Participants reported that it was most important to study standardisation of PI diagnosis and to develop standardised PI diagnoses using the classification system of the Korean Standard Classification of Diseases. The foremost PI type that physicians thought should be included in standardisation and objectification of PI of TKM was the PIof Ba Gang.CONCLUSION: Our data suggest that we should focus on the standardisation of PI diagnosis and PI of Ba Gang in future research on PI diagnosis inTM.However, we cannot completely discount the possibility that a biased selection of subjects and a low response rate limit the generalisability of the findings.
