目前的脑电(EEG)情感识别模型忽略了不同时段情感状态的差异性,未能强化关键的情感信息。针对上述问题,提出一种多上下文向量优化的卷积递归神经网络(CR-MCV)。首先构造脑电信号的特征矩阵序列,通过卷积神经网络(CNN)学习多通道脑电的...目前的脑电(EEG)情感识别模型忽略了不同时段情感状态的差异性,未能强化关键的情感信息。针对上述问题,提出一种多上下文向量优化的卷积递归神经网络(CR-MCV)。首先构造脑电信号的特征矩阵序列,通过卷积神经网络(CNN)学习多通道脑电的空间特征;然后利用基于多头注意力的递归神经网络生成多上下文向量进行高层抽象特征提取;最后利用全连接层进行情感分类。在DEAP(Database for Emotion Analysis using Physiological signals)数据集上进行实验,CR-MCV在唤醒和效价维度上分类准确率分别为88.09%和89.30%。实验结果表明,CR-MCV在利用电极空间位置信息和不同时段情感状态显著性特征基础上,能够自适应地分配特征的注意力并强化情感状态显著性信息。展开更多
A globally optimal solution to vector quantization (VQ) index assignment on noisy channel, the evolutionary algorithm based index assignment algorithm (EAIAA), is presented. The algorithm yields a significant reductio...A globally optimal solution to vector quantization (VQ) index assignment on noisy channel, the evolutionary algorithm based index assignment algorithm (EAIAA), is presented. The algorithm yields a significant reduction in average distortion due to channel errors, over conventional arbitrary index assignment, as confirmed by experimental results over the memoryless binary symmetric channel (BSC) for any bit error.展开更多
2-D RAKE receiver is an efficient way to realize the space-time processing for CDMA systems with aperiodic spreading codes. The Direction Of Arrival (DOA) and the relative time delay of every user's multipath must...2-D RAKE receiver is an efficient way to realize the space-time processing for CDMA systems with aperiodic spreading codes. The Direction Of Arrival (DOA) and the relative time delay of every user's multipath must be known to realize the 2-D RAKE receiver. In the third generation CDMA mobile communication system, auxiliary pilot channel is used in the uplink channels The different user's Vector Channel Impulse Response (VCIR) can be estimated from the pilotichannel easily. The VCIR contains spatial and temporal information. In this paper,by utilizing the known pulse shape function, a parameter matrix method used to estimate the Spatial Signature Vector (SSV) and the relative time delay is proposed in frequency domain.The DOA can be estimated from the SSV. By reconstructing the SSV and utilizing approximate Capon space filter, the performance of the 2-D RAKE receiver with uniform circular array can be improved with a little additional computation work.展开更多
Ad hoc on-demand distance vector( AODV) routing is one of the typical reactive routing protocols of vehicular ad hoc networks( VANET). Considering link stability and channel switching can greatly improve the QoS of pr...Ad hoc on-demand distance vector( AODV) routing is one of the typical reactive routing protocols of vehicular ad hoc networks( VANET). Considering link stability and channel switching can greatly improve the QoS of protocols,in this paper,we propose a novel routing protocol: optimized cross-layer AODV( CL_ AODV) designed for VANET. It utilizes the frame transmission efficiency( FTE),path bandwidth in media access control( MAC) layer and signal-to-noise ratio( SNIR) in physical( PHY) layer to improve the link stability. In other words,it can increase packet delivery ratio effectively. In addition,end-to-end delay will be decreased based on the channel switching. According to the simulation,it is shown that the packet delivery ratio of CL_AODV is almost up to 99% and the highest compared to AODV and muti-constrained QoS AODV( MQ_ AODV). The delay of CL_AODV is almost half of MQ_ AODV's and 1 /3 of AODV's.Meanwhile,CL_AODV has the highest routing overhead or energy consuming. Because of the feature of VANET,the disadvantage can be ignored.展开更多
A new method based on phase difference analysis is proposed for the single-channel mixed signal separation of single-channel radar fuze.This method is used to estimate the mixing coefficients of de-noised signals thro...A new method based on phase difference analysis is proposed for the single-channel mixed signal separation of single-channel radar fuze.This method is used to estimate the mixing coefficients of de-noised signals through the cumulants of mixed signals,solve the candidate data set by the mixing coefficients and signal analytical form,and resolve the problem of vector ambiguity by analyzing the phase differences.The signal separation is realized by exchanging data of the solutions.The waveform similarity coefficients are calculated,and the time鈥攆requency distributions of separated signals are analyzed.The results show that the proposed method is effective.展开更多
This paper proposes an integrated joint source-channel decoder （I-JSCD） using Max-Log-MAP method for sources encoded with exp-Golomb codes and convolutional codes, and proposes a system applying this method to decod...This paper proposes an integrated joint source-channel decoder （I-JSCD） using Max-Log-MAP method for sources encoded with exp-Golomb codes and convolutional codes, and proposes a system applying this method to decoding the VLC data, e.g. motion vector differences （MVDs）, of H.264 across an AWGN channel. This method combines the source code state-space and the channel code state-space together to construct a joint state-space, develops a 3-D trellis and a maximum a-posterior （MAP） algorithm to estimate the source sequence symbol by symbol, and then uses max-log approximation to simplify the algorithm. Experiments indicate that the proposed system gives significant improvements on peak signal-to-noise ratio （PSNR） （maximum about 15 dB） than a separate scheme. This also leads to a higher visual quality of video stream over a highly noisy channel.展开更多
文摘目前的脑电(EEG)情感识别模型忽略了不同时段情感状态的差异性,未能强化关键的情感信息。针对上述问题,提出一种多上下文向量优化的卷积递归神经网络(CR-MCV)。首先构造脑电信号的特征矩阵序列,通过卷积神经网络(CNN)学习多通道脑电的空间特征;然后利用基于多头注意力的递归神经网络生成多上下文向量进行高层抽象特征提取;最后利用全连接层进行情感分类。在DEAP(Database for Emotion Analysis using Physiological signals)数据集上进行实验,CR-MCV在唤醒和效价维度上分类准确率分别为88.09%和89.30%。实验结果表明,CR-MCV在利用电极空间位置信息和不同时段情感状态显著性特征基础上,能够自适应地分配特征的注意力并强化情感状态显著性信息。
文摘A globally optimal solution to vector quantization (VQ) index assignment on noisy channel, the evolutionary algorithm based index assignment algorithm (EAIAA), is presented. The algorithm yields a significant reduction in average distortion due to channel errors, over conventional arbitrary index assignment, as confirmed by experimental results over the memoryless binary symmetric channel (BSC) for any bit error.
基金Supported in part by the National Nature Sciences, Doctor Education and HuaWei Corporation Foundation
文摘2-D RAKE receiver is an efficient way to realize the space-time processing for CDMA systems with aperiodic spreading codes. The Direction Of Arrival (DOA) and the relative time delay of every user's multipath must be known to realize the 2-D RAKE receiver. In the third generation CDMA mobile communication system, auxiliary pilot channel is used in the uplink channels The different user's Vector Channel Impulse Response (VCIR) can be estimated from the pilotichannel easily. The VCIR contains spatial and temporal information. In this paper,by utilizing the known pulse shape function, a parameter matrix method used to estimate the Spatial Signature Vector (SSV) and the relative time delay is proposed in frequency domain.The DOA can be estimated from the SSV. By reconstructing the SSV and utilizing approximate Capon space filter, the performance of the 2-D RAKE receiver with uniform circular array can be improved with a little additional computation work.
基金National Natural Science Foundation of China(No.71171045)
文摘Ad hoc on-demand distance vector( AODV) routing is one of the typical reactive routing protocols of vehicular ad hoc networks( VANET). Considering link stability and channel switching can greatly improve the QoS of protocols,in this paper,we propose a novel routing protocol: optimized cross-layer AODV( CL_ AODV) designed for VANET. It utilizes the frame transmission efficiency( FTE),path bandwidth in media access control( MAC) layer and signal-to-noise ratio( SNIR) in physical( PHY) layer to improve the link stability. In other words,it can increase packet delivery ratio effectively. In addition,end-to-end delay will be decreased based on the channel switching. According to the simulation,it is shown that the packet delivery ratio of CL_AODV is almost up to 99% and the highest compared to AODV and muti-constrained QoS AODV( MQ_ AODV). The delay of CL_AODV is almost half of MQ_ AODV's and 1 /3 of AODV's.Meanwhile,CL_AODV has the highest routing overhead or energy consuming. Because of the feature of VANET,the disadvantage can be ignored.
文摘A new method based on phase difference analysis is proposed for the single-channel mixed signal separation of single-channel radar fuze.This method is used to estimate the mixing coefficients of de-noised signals through the cumulants of mixed signals,solve the candidate data set by the mixing coefficients and signal analytical form,and resolve the problem of vector ambiguity by analyzing the phase differences.The signal separation is realized by exchanging data of the solutions.The waveform similarity coefficients are calculated,and the time鈥攆requency distributions of separated signals are analyzed.The results show that the proposed method is effective.
基金Supported by the Foundation of Ministry of Education of China (211CERS10)
文摘This paper proposes an integrated joint source-channel decoder （I-JSCD） using Max-Log-MAP method for sources encoded with exp-Golomb codes and convolutional codes, and proposes a system applying this method to decoding the VLC data, e.g. motion vector differences （MVDs）, of H.264 across an AWGN channel. This method combines the source code state-space and the channel code state-space together to construct a joint state-space, develops a 3-D trellis and a maximum a-posterior （MAP） algorithm to estimate the source sequence symbol by symbol, and then uses max-log approximation to simplify the algorithm. Experiments indicate that the proposed system gives significant improvements on peak signal-to-noise ratio （PSNR） （maximum about 15 dB） than a separate scheme. This also leads to a higher visual quality of video stream over a highly noisy channel.
