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
Deforestation is a major environmental challenge in the mountain areas of Pakistan. The study assessed trends in the forest cover in Chitral tehsil over the last two decades using supervised land cover classification ...Deforestation is a major environmental challenge in the mountain areas of Pakistan. The study assessed trends in the forest cover in Chitral tehsil over the last two decades using supervised land cover classification of Landsat TM satellite images from 1992, 2000, and 2009, with a maximum likelihood algorithm. In 2009, the forest cover was 10.3% of the land area of Chitral(60,000 ha). The deforestation rate increased from 0.14% per annum in 1992–2000 to 0.54% per annum in 2000–2009, with 3,759 ha forest lost over the 17 years. The spatial drivers of deforestation were investigated using a cellular automaton modelling technique to project future forest conditions. Accessibility(elevation, slope), population density, distance to settlements, and distance to administrative boundary were strongly associated with neighbourhood deforestation. A model projection showed a further loss of 23% of existing forest in Chitral tehsil by 2030, and degradation of 8%, if deforestation continues at the present rate. Arandu Union Council, with 2212 households, will lose 85% of its forest. Local communities have limited income resources and high poverty and are heavily dependent on non-timber forest products for their livelihoods. Continued deforestation will further worsen their livelihood conditions, thus improved conservation efforts are essential.展开更多
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.
基金funded by the Ministry of Foreign Affairs,Norway and Swedish International Development Agency(Sida)supported by the United States Agency for International Development(USAID)National Aeronautics and Space Administration(NASA)
文摘Deforestation is a major environmental challenge in the mountain areas of Pakistan. The study assessed trends in the forest cover in Chitral tehsil over the last two decades using supervised land cover classification of Landsat TM satellite images from 1992, 2000, and 2009, with a maximum likelihood algorithm. In 2009, the forest cover was 10.3% of the land area of Chitral(60,000 ha). The deforestation rate increased from 0.14% per annum in 1992–2000 to 0.54% per annum in 2000–2009, with 3,759 ha forest lost over the 17 years. The spatial drivers of deforestation were investigated using a cellular automaton modelling technique to project future forest conditions. Accessibility(elevation, slope), population density, distance to settlements, and distance to administrative boundary were strongly associated with neighbourhood deforestation. A model projection showed a further loss of 23% of existing forest in Chitral tehsil by 2030, and degradation of 8%, if deforestation continues at the present rate. Arandu Union Council, with 2212 households, will lose 85% of its forest. Local communities have limited income resources and high poverty and are heavily dependent on non-timber forest products for their livelihoods. Continued deforestation will further worsen their livelihood conditions, thus improved conservation efforts are essential.
