针对多变量时序(Multivariate Time Series,MTS)分类中长序列数据难以捕捉时序特征的问题,提出一种基于双向稀疏Transformer的时序分类模型BST(Bidirectional Sparse Transformer),提高了MTS分类任务的准确度.BST模型使用Transformer框...针对多变量时序(Multivariate Time Series,MTS)分类中长序列数据难以捕捉时序特征的问题,提出一种基于双向稀疏Transformer的时序分类模型BST(Bidirectional Sparse Transformer),提高了MTS分类任务的准确度.BST模型使用Transformer框架,构建了一种基于活跃度得分的双向稀疏注意力机制.基于KL散度构建活跃度评价函数,并将评价函数的非对称问题转变为对称权重问题.据此,对原有查询矩阵、键值矩阵进行双向稀疏化,从而降低原Transformer模型中自注意力机制运算的时间复杂度.实验结果显示,BST模型在9个长序列数据集上取得最高平均排名,在临界差异图中领先第2名35.7%,对于具有强时序性的乙醇浓度数据集(Ethanol Concentration,EC),分类准确率提高30.9%.展开更多
Neuronal ensemble activity codes working memory.In this work,we developed a neuronal ensemble sparse coding method,which can effectively reduce the dimension of the neuronal activity and express neural coding.Multicha...Neuronal ensemble activity codes working memory.In this work,we developed a neuronal ensemble sparse coding method,which can effectively reduce the dimension of the neuronal activity and express neural coding.Multichannel spike trains were recorded in rat prefrontal cortex during a work memory task in Y-maze.As discretesignals,spikes were transferred into cont inuous signals by estinating entropy.Then the normalized continuous signals were decomposed via non-negative sparse met hod.The non-negative components were extracted to reconstruct a low-dimensional ensemble,while none of the feature components were missed.The results showed that,for well-trained rats,neuronal ensemble activities in the prefrontal cortex changed dynamically during the.working memory task.And the neuronal ensemble is more explicit via using non-negative sparse coding.Our results indicate that the neuronal ensemblesparse coding method can effectively reduce the dimnension of neuronal activity and it is a useful tool to express neural coding.展开更多
Video synopsis is an effective and innovative way to produce short video abstraction for huge video archives,while keeping the dynamic characteristic of activities in the original video.Abnormal activity,as the critic...Video synopsis is an effective and innovative way to produce short video abstraction for huge video archives,while keeping the dynamic characteristic of activities in the original video.Abnormal activity,as the critical event,is always the main concern in video surveillance context.However,in traditional video synopsis,all the normal and abnormal activities are condensed together equally,which can make the synopsis video confused and worthless.In addition,the traditional video synopsis methods always neglect redundancy in the content domain.To solve the above-mentioned issues,a novel video synopsis method is proposed based on abnormal activity detection and key observation selection.In the proposed algorithm,activities are classified into normal and abnormal ones based on the sparse reconstruction cost from an atomically learned activity dictionary.And key observation selection using the minimum description length principle is conducted for eliminating content redundancy in normal activity.Experiments conducted in publicly available datasets demonstrate that the proposed approach can effectively generate satisfying synopsis videos.展开更多
基金supported by the National Natural Science Foundation of China(No.61074131,91132722)the Doctoral Fund of the Ministry of Education of China(20101202110007).
文摘Neuronal ensemble activity codes working memory.In this work,we developed a neuronal ensemble sparse coding method,which can effectively reduce the dimension of the neuronal activity and express neural coding.Multichannel spike trains were recorded in rat prefrontal cortex during a work memory task in Y-maze.As discretesignals,spikes were transferred into cont inuous signals by estinating entropy.Then the normalized continuous signals were decomposed via non-negative sparse met hod.The non-negative components were extracted to reconstruct a low-dimensional ensemble,while none of the feature components were missed.The results showed that,for well-trained rats,neuronal ensemble activities in the prefrontal cortex changed dynamically during the.working memory task.And the neuronal ensemble is more explicit via using non-negative sparse coding.Our results indicate that the neuronal ensemblesparse coding method can effectively reduce the dimnension of neuronal activity and it is a useful tool to express neural coding.
基金Supported by the National Natural Science Foundation of China(No.61402023)Beijing Technology and Business' University Youth Fund(No.QNJJ2014-23)Beijing Natural Science Foundation(No.4162019)
文摘Video synopsis is an effective and innovative way to produce short video abstraction for huge video archives,while keeping the dynamic characteristic of activities in the original video.Abnormal activity,as the critical event,is always the main concern in video surveillance context.However,in traditional video synopsis,all the normal and abnormal activities are condensed together equally,which can make the synopsis video confused and worthless.In addition,the traditional video synopsis methods always neglect redundancy in the content domain.To solve the above-mentioned issues,a novel video synopsis method is proposed based on abnormal activity detection and key observation selection.In the proposed algorithm,activities are classified into normal and abnormal ones based on the sparse reconstruction cost from an atomically learned activity dictionary.And key observation selection using the minimum description length principle is conducted for eliminating content redundancy in normal activity.Experiments conducted in publicly available datasets demonstrate that the proposed approach can effectively generate satisfying synopsis videos.
