Discontinuous and long-duration thunderstorm weather, which occurred at Guanghan in Sichuan Province, was analyzed and predicted using structural conversion of irregular information in phase-space from self-recording ...Discontinuous and long-duration thunderstorm weather, which occurred at Guanghan in Sichuan Province, was analyzed and predicted using structural conversion of irregular information in phase-space from self-recording “time sequence” records for predicting rain areas, as described in the “Non Destructive Information” method proposed by Professor OuYang Shoucheng. The results show that this method can reveal important changes of weather as well as, by using irregular self-recording information recorded every ten minutes, predict local thunderstorms with durations of only half an hour, and even predict intense convections 12 hours in advance. This is significant for civil and military aviation. It shows the necessity of full utilization of information from automatic weather stations and the necessity of improvements in recording modes in current automatic stations.展开更多
Aimed at the problem that the traditional ART-2 neural network can not recognize a gradually changing course, an eternal term memory (ETM) vector is introduced into ART-2 to simulate the function of human brain, i.e. ...Aimed at the problem that the traditional ART-2 neural network can not recognize a gradually changing course, an eternal term memory (ETM) vector is introduced into ART-2 to simulate the function of human brain, i.e. the deep remembrance for the initial impression.. The eternal term memory vector is determined only by the initial vector that establishes category neuron node and is used to keep the remembrance for this vector for ever. Two times of vigilance algorithm are put forward, and the posterior input vector must first pass the first vigilance of this eternal term memory vector, only succeeded has it the qualification to begin the second vigilance of long term memory vector. The long term memory vector can be revised only when both of the vigilances are passed. Results of recognition examples show that the improved ART-2 overcomes the defect of traditional ART-2 and can recognize a gradually changing course effectively.展开更多
基金The project is funded by Youth Scientific Research Foundation of CAFUC (Q2003-23).
文摘Discontinuous and long-duration thunderstorm weather, which occurred at Guanghan in Sichuan Province, was analyzed and predicted using structural conversion of irregular information in phase-space from self-recording “time sequence” records for predicting rain areas, as described in the “Non Destructive Information” method proposed by Professor OuYang Shoucheng. The results show that this method can reveal important changes of weather as well as, by using irregular self-recording information recorded every ten minutes, predict local thunderstorms with durations of only half an hour, and even predict intense convections 12 hours in advance. This is significant for civil and military aviation. It shows the necessity of full utilization of information from automatic weather stations and the necessity of improvements in recording modes in current automatic stations.
基金Sponsored by the National Natural Science Foundation of China (Grant No. 50305005)
文摘Aimed at the problem that the traditional ART-2 neural network can not recognize a gradually changing course, an eternal term memory (ETM) vector is introduced into ART-2 to simulate the function of human brain, i.e. the deep remembrance for the initial impression.. The eternal term memory vector is determined only by the initial vector that establishes category neuron node and is used to keep the remembrance for this vector for ever. Two times of vigilance algorithm are put forward, and the posterior input vector must first pass the first vigilance of this eternal term memory vector, only succeeded has it the qualification to begin the second vigilance of long term memory vector. The long term memory vector can be revised only when both of the vigilances are passed. Results of recognition examples show that the improved ART-2 overcomes the defect of traditional ART-2 and can recognize a gradually changing course effectively.
