高光谱影像数据的相邻波段间相关性较强,信号与噪声共存,根据最小二乘原理,使观测数据与噪声的投影误差之和最小化的HySime(hyperspectral signal identification by minimum error)算法,通过数据观测值减去噪声估计值后得到信号的估计...高光谱影像数据的相邻波段间相关性较强,信号与噪声共存,根据最小二乘原理,使观测数据与噪声的投影误差之和最小化的HySime(hyperspectral signal identification by minimum error)算法,通过数据观测值减去噪声估计值后得到信号的估计值,进而可以计算信号相关矩阵的估计值。该算法在准确估计噪声的情况下是可行的,但实际上经光谱降维去相关后得到的各像元噪声估计值往往并不准确,因此,原始的HySime算法得到的结果可能并不理想。提出一种基于噪声白化的HySime改进算法,它不必进行逐像元的噪声去除,而是先对原始数据进行噪声白化处理,然后准确获取噪声的协方差矩阵估计值,再利用HySime算法进行信号相关矩阵计算,实现了提高算法精度的目的。通过模拟和实验数据的验证,改进的算法结果更准确稳定,与经典的NSP(noise subspace projection)算法在不同情况下所得结果有很好的一致性,通过引入噪声白化的过程,提高了算法对非白噪声的适应性。展开更多
In order to study the effect of weak noise on the sound signal extraction of mouse (Mus musculus Km) inferior collicular (IC) neurons from environments,we examined the changes in frequency tuning curves (FTCs) of 32 n...In order to study the effect of weak noise on the sound signal extraction of mouse (Mus musculus Km) inferior collicular (IC) neurons from environments,we examined the changes in frequency tuning curves (FTCs) of 32 neurons induced by a weak noise relative to 5 dB below minimum threshold of tone (reMT-5 dB) under free field stimulation conditions.The results were as follows:① There were three types of variations in FTCs,sharpened (34.4%),broadened (18.8%),and unaffected (46.9%),nevertheless,only the alteration of sharpened FTCs was statistically different.② Sharpness of frequency tuning induced by a reMT-5 dB noise was very strong.Q 10 and Q 30 of FTCs were increased by (34.42±17.04)% (P=0.026,n=11) and (46.34±22.88)% (P=0.009,n=7).③ The changes of inverse-slopes (ISs,kHz/dB) between high (IS high) and low (IS low) limbs of FTCs were dissymmetry.The IS high of FTCs decreased markedly (P=0.046,n=7),however,there was little change (P=0.947,n=7) in IS low.Our data revealed for the first time that the weak noise could sharpen frequency tuning and increase the sensitivity on the high frequency of sound signal in IC neurons of mouse.展开更多
This paper presents a low complexity optimized algorithm for design of bilayer lengthened LDPC(BL-LDPC) code for decode-and-forward relay system.The design is performed over the expanded graph of the BL-LDPC code,whic...This paper presents a low complexity optimized algorithm for design of bilayer lengthened LDPC(BL-LDPC) code for decode-and-forward relay system.The design is performed over the expanded graph of the BL-LDPC code,which consists of the original bilayer graph and the extra added relaygenerated parity check bits.To build up our proposed optimized algorithm,we present a modified Gaussian approximation algorithm for the expanded structure of the BL-LDPC code.Then using the proposed optimized algorithm,we find the optimum overall expanded graph of the BL-LDPC code.Simulation results show that the BL-LDPC codes obtained by our proposed optimized algorithm have excellent bit-error-rate performances and small gaps between the convergence thresholds and the theoretical limits when transmitted over the additive white Gaussian noise channels.展开更多
文摘高光谱影像数据的相邻波段间相关性较强,信号与噪声共存,根据最小二乘原理,使观测数据与噪声的投影误差之和最小化的HySime(hyperspectral signal identification by minimum error)算法,通过数据观测值减去噪声估计值后得到信号的估计值,进而可以计算信号相关矩阵的估计值。该算法在准确估计噪声的情况下是可行的,但实际上经光谱降维去相关后得到的各像元噪声估计值往往并不准确,因此,原始的HySime算法得到的结果可能并不理想。提出一种基于噪声白化的HySime改进算法,它不必进行逐像元的噪声去除,而是先对原始数据进行噪声白化处理,然后准确获取噪声的协方差矩阵估计值,再利用HySime算法进行信号相关矩阵计算,实现了提高算法精度的目的。通过模拟和实验数据的验证,改进的算法结果更准确稳定,与经典的NSP(noise subspace projection)算法在不同情况下所得结果有很好的一致性,通过引入噪声白化的过程,提高了算法对非白噪声的适应性。
文摘In order to study the effect of weak noise on the sound signal extraction of mouse (Mus musculus Km) inferior collicular (IC) neurons from environments,we examined the changes in frequency tuning curves (FTCs) of 32 neurons induced by a weak noise relative to 5 dB below minimum threshold of tone (reMT-5 dB) under free field stimulation conditions.The results were as follows:① There were three types of variations in FTCs,sharpened (34.4%),broadened (18.8%),and unaffected (46.9%),nevertheless,only the alteration of sharpened FTCs was statistically different.② Sharpness of frequency tuning induced by a reMT-5 dB noise was very strong.Q 10 and Q 30 of FTCs were increased by (34.42±17.04)% (P=0.026,n=11) and (46.34±22.88)% (P=0.009,n=7).③ The changes of inverse-slopes (ISs,kHz/dB) between high (IS high) and low (IS low) limbs of FTCs were dissymmetry.The IS high of FTCs decreased markedly (P=0.046,n=7),however,there was little change (P=0.947,n=7) in IS low.Our data revealed for the first time that the weak noise could sharpen frequency tuning and increase the sensitivity on the high frequency of sound signal in IC neurons of mouse.
基金Supported by the National Basic Research Program of China(No.2012CB316100)the National Natural Science Foundation of China(No.61072064,61201140,61301177)
文摘This paper presents a low complexity optimized algorithm for design of bilayer lengthened LDPC(BL-LDPC) code for decode-and-forward relay system.The design is performed over the expanded graph of the BL-LDPC code,which consists of the original bilayer graph and the extra added relaygenerated parity check bits.To build up our proposed optimized algorithm,we present a modified Gaussian approximation algorithm for the expanded structure of the BL-LDPC code.Then using the proposed optimized algorithm,we find the optimum overall expanded graph of the BL-LDPC code.Simulation results show that the BL-LDPC codes obtained by our proposed optimized algorithm have excellent bit-error-rate performances and small gaps between the convergence thresholds and the theoretical limits when transmitted over the additive white Gaussian noise channels.
