In this paper, the complexity and performance of the Auxiliary Vector (AV) based reduced-rank filtering are addressed. The AV filters presented in the previous papers have the general form of the sum of the signature ...In this paper, the complexity and performance of the Auxiliary Vector (AV) based reduced-rank filtering are addressed. The AV filters presented in the previous papers have the general form of the sum of the signature vector of the desired signal and a set of weighted AVs,which can be classified as three categories according to the orthogonality of their AVs and the optimality of the weight coefficients of the AVs. The AV filter with orthogonal AVs and optimal weight coefficients has the best performance, but requires considerable computational complexity and suffers from the numerical unstable operation. In order to reduce its computational load while keeping the superior performance, several low complexity algorithms are proposed to efficiently calculate the AVs and their weight coefficients. The diagonal loading technique is also introduced to solve the numerical unstability problem without complexity increase. The performance of the three types of AV filters is also compared through their application to Direct Sequence Code Division Multiple Access (DS-CDM A) systems for interference suppression.展开更多
利用脑电图信号,结合深度学习方法进行抑郁症辅助诊断目前仍存在特征提取不足及模型诊断准确率不高的问题。为了提取更具抑郁症表征的特征,提高抑郁症辅助诊断的准确率,本文从特征提取和网络框架两个方面进行改进,提出一种结合改进VGG–...利用脑电图信号,结合深度学习方法进行抑郁症辅助诊断目前仍存在特征提取不足及模型诊断准确率不高的问题。为了提取更具抑郁症表征的特征,提高抑郁症辅助诊断的准确率,本文从特征提取和网络框架两个方面进行改进,提出一种结合改进VGG–16(visual geometry group–16)和基于压缩激励网络的通道注意力机制(modified VGG–16 network based on SE–NET,SEMod–VGG)的抑郁症辅助检测模型。首先,提取脑电图信号中α(Alpha)、θ(Theta)和β(Beta)频段的微分熵特征,与对应通道的功率谱密度特征相融合,构成一种同时具有时频属性和能量属性的4维融合特征;其次,针对该4维特征,改进现有的VGG–16模型,同时采用5×5和7×7两种不同尺度的卷积核,在提取脑电信号的时频信息和功率信息的同时,提高特征的泛化表征能力;再将基于压缩激励网络的通道注意力机制与改进的检测模型相结合,对电极通道的权重进行2次标定;最后采用10折交叉验证使得最小二乘支持向量机取得最佳检测准确率。对所提模型在准确率,召回率以及网络性能这3个方面进行实验评估,在MODMA数据集上的结果表明:当使用4维融合特征作为输入时,SEMod–VGG可达到最佳检测性能,其抑郁症检测准确率在3通道、16通道及128通道分别为92.21%、93.47%和95.76%;检测召回率在3通道、16通道以及128通道分别为91.57%、92.46%和96.80%。相较于现有的抑郁症辅助检测模型,本研究所提出的融合特征对抑郁症的表征性更强,且所提出的模型在检测准确率,召回率以及模型效率上均取得明显提升。展开更多
文摘In this paper, the complexity and performance of the Auxiliary Vector (AV) based reduced-rank filtering are addressed. The AV filters presented in the previous papers have the general form of the sum of the signature vector of the desired signal and a set of weighted AVs,which can be classified as three categories according to the orthogonality of their AVs and the optimality of the weight coefficients of the AVs. The AV filter with orthogonal AVs and optimal weight coefficients has the best performance, but requires considerable computational complexity and suffers from the numerical unstable operation. In order to reduce its computational load while keeping the superior performance, several low complexity algorithms are proposed to efficiently calculate the AVs and their weight coefficients. The diagonal loading technique is also introduced to solve the numerical unstability problem without complexity increase. The performance of the three types of AV filters is also compared through their application to Direct Sequence Code Division Multiple Access (DS-CDM A) systems for interference suppression.
文摘利用脑电图信号,结合深度学习方法进行抑郁症辅助诊断目前仍存在特征提取不足及模型诊断准确率不高的问题。为了提取更具抑郁症表征的特征,提高抑郁症辅助诊断的准确率,本文从特征提取和网络框架两个方面进行改进,提出一种结合改进VGG–16(visual geometry group–16)和基于压缩激励网络的通道注意力机制(modified VGG–16 network based on SE–NET,SEMod–VGG)的抑郁症辅助检测模型。首先,提取脑电图信号中α(Alpha)、θ(Theta)和β(Beta)频段的微分熵特征,与对应通道的功率谱密度特征相融合,构成一种同时具有时频属性和能量属性的4维融合特征;其次,针对该4维特征,改进现有的VGG–16模型,同时采用5×5和7×7两种不同尺度的卷积核,在提取脑电信号的时频信息和功率信息的同时,提高特征的泛化表征能力;再将基于压缩激励网络的通道注意力机制与改进的检测模型相结合,对电极通道的权重进行2次标定;最后采用10折交叉验证使得最小二乘支持向量机取得最佳检测准确率。对所提模型在准确率,召回率以及网络性能这3个方面进行实验评估,在MODMA数据集上的结果表明:当使用4维融合特征作为输入时,SEMod–VGG可达到最佳检测性能,其抑郁症检测准确率在3通道、16通道及128通道分别为92.21%、93.47%和95.76%;检测召回率在3通道、16通道以及128通道分别为91.57%、92.46%和96.80%。相较于现有的抑郁症辅助检测模型,本研究所提出的融合特征对抑郁症的表征性更强,且所提出的模型在检测准确率,召回率以及模型效率上均取得明显提升。
