Circuit design of 32 bit logarithmic skip adder (LSA) is introduced to implement high performance,low power addition.ELM carry lookahead adder is included into groups of carry skip adder and the hybrid structure cost...Circuit design of 32 bit logarithmic skip adder (LSA) is introduced to implement high performance,low power addition.ELM carry lookahead adder is included into groups of carry skip adder and the hybrid structure costs 30% less hardware than ELM.At circuit level,a carry incorporating structure to include the primary carry input in carry chain and an 'and xor' structure to implement final sum logic in 32 bit LSA are designed for better optimization.For 5V,1μm process,32 bit LSA has a critical delay of 5 9ns and costs an area of 0 62mm 2,power consumption of 23mW at 100MHz.For 2 5V,0 25μm process,critical delay of 0 8ns,power dissipation of 5 2mW at 100MHz is simulated.展开更多
针对目前机场群发展不平衡,国际枢纽机场的延误率居高不下,航班时刻短缺,资源紧张,而区域枢纽机场却存在资源空闲的问题,提出一种基于跳过门的长短时记忆网络(Skip-LSTM,Skip Long Short Term Memory)的机场群延误预测模型。该模型首先...针对目前机场群发展不平衡,国际枢纽机场的延误率居高不下,航班时刻短缺,资源紧张,而区域枢纽机场却存在资源空闲的问题,提出一种基于跳过门的长短时记忆网络(Skip-LSTM,Skip Long Short Term Memory)的机场群延误预测模型。该模型首先将机场群中各个机场的信息,机场群航班信息以及机场群地区的气象信息进行融合及处理,然后搭建Skip-LSTM网络对融合后的数据信息进行特征提取,最后利用Softmax分类器对机场群的延误状况进行分类预测。Skip-LSTM网络在传统的长短时记忆网络(LSTM,Long Short Term Memory)的基础上增加了Skip门,能更加充分地提取机场群数据信息的时间相关性,获得更高的准确率。实验结果表明,基于Skip-LSTM的机场群延误预测模型的准确率可达95.35%,预测性能优于传统的网络模型,能对机场群的延误状况进行有效的预测。展开更多
文摘Circuit design of 32 bit logarithmic skip adder (LSA) is introduced to implement high performance,low power addition.ELM carry lookahead adder is included into groups of carry skip adder and the hybrid structure costs 30% less hardware than ELM.At circuit level,a carry incorporating structure to include the primary carry input in carry chain and an 'and xor' structure to implement final sum logic in 32 bit LSA are designed for better optimization.For 5V,1μm process,32 bit LSA has a critical delay of 5 9ns and costs an area of 0 62mm 2,power consumption of 23mW at 100MHz.For 2 5V,0 25μm process,critical delay of 0 8ns,power dissipation of 5 2mW at 100MHz is simulated.
文摘针对目前机场群发展不平衡,国际枢纽机场的延误率居高不下,航班时刻短缺,资源紧张,而区域枢纽机场却存在资源空闲的问题,提出一种基于跳过门的长短时记忆网络(Skip-LSTM,Skip Long Short Term Memory)的机场群延误预测模型。该模型首先将机场群中各个机场的信息,机场群航班信息以及机场群地区的气象信息进行融合及处理,然后搭建Skip-LSTM网络对融合后的数据信息进行特征提取,最后利用Softmax分类器对机场群的延误状况进行分类预测。Skip-LSTM网络在传统的长短时记忆网络(LSTM,Long Short Term Memory)的基础上增加了Skip门,能更加充分地提取机场群数据信息的时间相关性,获得更高的准确率。实验结果表明,基于Skip-LSTM的机场群延误预测模型的准确率可达95.35%,预测性能优于传统的网络模型,能对机场群的延误状况进行有效的预测。
