Aiming at the problem that some existing traffic flow prediction models are only for a single road segment and the model input data are not pre-processed,a heuristic threshold algorithm is used to de-noise the origina...Aiming at the problem that some existing traffic flow prediction models are only for a single road segment and the model input data are not pre-processed,a heuristic threshold algorithm is used to de-noise the original traffic flow data after wavelet decomposition.The correlation coefficients of road traffic flow data are calculated and the data compression matrix of road traffic flow is constructed.Data de-noising minimizes the interference of data to the model,while the correlation analysis of road network data realizes the prediction at the road network level.Utilizing the advantages of long short term memory(LSTM)network in time series data processing,the compression matrix is input into the constructed LSTM model for short-term traffic flow prediction.The LSTM-1 and LSTM-2 models were respectively trained by de-noising processed data and original data.Through simulation experiments,different prediction times were set,and the prediction results of the prediction model proposed in this paper were compared with those of other methods.It is found that the accuracy of the LSTM-2 model proposed in this paper increases by 10.278%on average compared with other prediction methods,and the prediction accuracy reaches 95.58%,which proves that the short-term traffic flow prediction method proposed in this paper is efficient.展开更多
We propose a systematic method to construct the Mel’nikov model of long–short wave interactions,which is a special case of the Kadomtsev–Petviashvili(KP)equation with self-consistent sources(KPSCS).We show details ...We propose a systematic method to construct the Mel’nikov model of long–short wave interactions,which is a special case of the Kadomtsev–Petviashvili(KP)equation with self-consistent sources(KPSCS).We show details how the Cauchy matrix approach applies to Mel’nikov’s model which is derived as a complex reduction of the KPSCS.As a new result wefind that in the dispersion relation of a 1-soliton there is an arbitrary time-dependent function that has previously not reported in the literature about the Mel’nikov model.This function brings time variant velocity for the long wave and also governs the short-wave packet.The variety of interactions of waves resulting from the time-freedom in the dispersion relation is illustrated.展开更多
短码扩频长码加扰的直扩信号可视为特殊的长码直扩信号,将其短扩频码和长扰码作为复合码。首先通过特征值分解和酉矩阵去位置模糊实现复合码的盲估计;然后利用m序列的三阶相关函数特性识别短扩频码的类型;最后根据识别结果采用三阶相关...短码扩频长码加扰的直扩信号可视为特殊的长码直扩信号,将其短扩频码和长扰码作为复合码。首先通过特征值分解和酉矩阵去位置模糊实现复合码的盲估计;然后利用m序列的三阶相关函数特性识别短扩频码的类型;最后根据识别结果采用三阶相关法或延迟三阶相关法实现长短伪码的盲估计。仿真表明,复合码估计在信噪比-7.5 d B以上可达到1%以下的误码率;当信噪比高于-6 d B时,三阶相关法估计长短伪码本原多项式的正确率可以达到90%以上;当信噪比高于-4 d B时,延迟三阶相关法估计长短伪码序列的误码率低于1%。展开更多
由于长短码直扩码分多址(LSC-DS-CDMA)信号包含了多个用户的长码和短码,已有的直扩码分多址信号的盲伪码估计方法不再适用。为此该文提出一种基于矩阵填充和三阶相关的伪码估计方法。首先从理论上将结构复杂的LSC-DS-CDMA信号构建为多...由于长短码直扩码分多址(LSC-DS-CDMA)信号包含了多个用户的长码和短码,已有的直扩码分多址信号的盲伪码估计方法不再适用。为此该文提出一种基于矩阵填充和三阶相关的伪码估计方法。首先从理论上将结构复杂的LSC-DS-CDMA信号构建为多用户短码扩频的缺失矩阵模型,将复合码矩阵估计建模为盲源信号分离问题;然后将矩阵填充理论应用于复合码矩阵估计,提出基于奇异值阈值算法和快速独立成分分析算法的各用户复合码序列估计方法;最后利用m序列的移位相加性特性,提出延迟三阶相关算法,从各用户复合码序列中估计其包含的长短伪码序列。仿真表明,当信噪比高于-2 d B时,该文算法的长短伪码估计平均误码率低于0.1%。展开更多
传统推荐算法多基于用户兴趣的静态属性获得用户偏好,忽略了用户兴趣漂移问题,为此,提出了解决该问题的融合用户兴趣漂移的Top-N推荐算法。利用长短期记忆网络(LSTM,long short term memory)处理时序数据的优势表示用户短期兴趣漂移规律...传统推荐算法多基于用户兴趣的静态属性获得用户偏好,忽略了用户兴趣漂移问题,为此,提出了解决该问题的融合用户兴趣漂移的Top-N推荐算法。利用长短期记忆网络(LSTM,long short term memory)处理时序数据的优势表示用户短期兴趣漂移规律,用矩阵分解得到的固定向量表示用户的长期兴趣,将注意力机制纳入LSTM隐藏状态的表示中来获取用户长短期兴趣关联。实验结果表明,所提算法与当前流行算法相比,在Top-N项目推荐中具有更优性能。展开更多
基金National Natural Science Foundation of China(No.71961016)Planning Fund for the Humanities and Social Sciences of the Ministry of Education(Nos.15XJAZH002,18YJAZH148)Natural Science Foundation of Gansu Province(No.18JR3RA125)。
文摘Aiming at the problem that some existing traffic flow prediction models are only for a single road segment and the model input data are not pre-processed,a heuristic threshold algorithm is used to de-noise the original traffic flow data after wavelet decomposition.The correlation coefficients of road traffic flow data are calculated and the data compression matrix of road traffic flow is constructed.Data de-noising minimizes the interference of data to the model,while the correlation analysis of road network data realizes the prediction at the road network level.Utilizing the advantages of long short term memory(LSTM)network in time series data processing,the compression matrix is input into the constructed LSTM model for short-term traffic flow prediction.The LSTM-1 and LSTM-2 models were respectively trained by de-noising processed data and original data.Through simulation experiments,different prediction times were set,and the prediction results of the prediction model proposed in this paper were compared with those of other methods.It is found that the accuracy of the LSTM-2 model proposed in this paper increases by 10.278%on average compared with other prediction methods,and the prediction accuracy reaches 95.58%,which proves that the short-term traffic flow prediction method proposed in this paper is efficient.
基金supported by the NSF of China(Nos.11875040 and 11631007)。
文摘We propose a systematic method to construct the Mel’nikov model of long–short wave interactions,which is a special case of the Kadomtsev–Petviashvili(KP)equation with self-consistent sources(KPSCS).We show details how the Cauchy matrix approach applies to Mel’nikov’s model which is derived as a complex reduction of the KPSCS.As a new result wefind that in the dispersion relation of a 1-soliton there is an arbitrary time-dependent function that has previously not reported in the literature about the Mel’nikov model.This function brings time variant velocity for the long wave and also governs the short-wave packet.The variety of interactions of waves resulting from the time-freedom in the dispersion relation is illustrated.
文摘短码扩频长码加扰的直扩信号可视为特殊的长码直扩信号,将其短扩频码和长扰码作为复合码。首先通过特征值分解和酉矩阵去位置模糊实现复合码的盲估计;然后利用m序列的三阶相关函数特性识别短扩频码的类型;最后根据识别结果采用三阶相关法或延迟三阶相关法实现长短伪码的盲估计。仿真表明,复合码估计在信噪比-7.5 d B以上可达到1%以下的误码率;当信噪比高于-6 d B时,三阶相关法估计长短伪码本原多项式的正确率可以达到90%以上;当信噪比高于-4 d B时,延迟三阶相关法估计长短伪码序列的误码率低于1%。
文摘由于长短码直扩码分多址(LSC-DS-CDMA)信号包含了多个用户的长码和短码,已有的直扩码分多址信号的盲伪码估计方法不再适用。为此该文提出一种基于矩阵填充和三阶相关的伪码估计方法。首先从理论上将结构复杂的LSC-DS-CDMA信号构建为多用户短码扩频的缺失矩阵模型,将复合码矩阵估计建模为盲源信号分离问题;然后将矩阵填充理论应用于复合码矩阵估计,提出基于奇异值阈值算法和快速独立成分分析算法的各用户复合码序列估计方法;最后利用m序列的移位相加性特性,提出延迟三阶相关算法,从各用户复合码序列中估计其包含的长短伪码序列。仿真表明,当信噪比高于-2 d B时,该文算法的长短伪码估计平均误码率低于0.1%。
文摘传统推荐算法多基于用户兴趣的静态属性获得用户偏好,忽略了用户兴趣漂移问题,为此,提出了解决该问题的融合用户兴趣漂移的Top-N推荐算法。利用长短期记忆网络(LSTM,long short term memory)处理时序数据的优势表示用户短期兴趣漂移规律,用矩阵分解得到的固定向量表示用户的长期兴趣,将注意力机制纳入LSTM隐藏状态的表示中来获取用户长短期兴趣关联。实验结果表明,所提算法与当前流行算法相比,在Top-N项目推荐中具有更优性能。
