To overcome some drawbacks of Viterbi algorithm （VA）, such as exponential growing complexity of decoding, and its poor performance under bad channel conditions, some available known information must be used as cons...To overcome some drawbacks of Viterbi algorithm （VA）, such as exponential growing complexity of decoding, and its poor performance under bad channel conditions, some available known information must be used as constrained condition and apriori knowledge for decoding. A new constrained VA is proposed by adding con- straint bits directly for conventional codec. Compared with the conventional VA, under the bad channel condi- tion, the proposed scheme can improve the peak signal to noise ratio （PSNR） of the decoding image 2--10 dB by changing the number of constrained bits. Experimental results show that it is an efficient error-controlling way for the transmission of set partitioning in hierarchical trees （SPIHT） coded image.展开更多
In order to fully utilize the soft decision ability of the outer decoder in a concatenated system, reliability information (called soft output) from the inner decoder or equalizer is required. In this paper, based on...In order to fully utilize the soft decision ability of the outer decoder in a concatenated system, reliability information (called soft output) from the inner decoder or equalizer is required. In this paper, based on the analysis of typical implementations of soft output VA, a novel algorithm is proposed by utilizing the property of Viterbi algorithm. Compared with the typical implementations, less processing expense is required by the new algorithm for weighting the hard decisions of VA. Meanwhile, simulation results show that, deterioration in performance of this algorithm is usually small for decoding of convolutional code and negligible for equalization.展开更多
Overlapped time domain multiplexing(OvTDM)is an innovative encoding scheme that can obtain high spectral efficiency.However,the intentional inter-symbol interference(ISI)caused by OvTDM will make the decoding process ...Overlapped time domain multiplexing(OvTDM)is an innovative encoding scheme that can obtain high spectral efficiency.However,the intentional inter-symbol interference(ISI)caused by OvTDM will make the decoding process more complex.The computational complexity of maximum likelihood sequence detection increases exponentially with the growth of spectral efficiency in OvTDM.As a consequence of high complexity,the decoding effort for a given spectral efficiency may occasionally exceed the physical limitations of the decoder,leading inevitably to buffer overflows and information erasures.In this paper,we propose a bidirectional Viterbi algorithm(BVA)based on the bidirectional sequence decoding for OvTDM.With the BVA,the decoding operation starts simultaneously from the both ends of the corresponding trellis and stops at the middle of trellis.The simulation results show that compared with Viterbi algorithm(VA),the decoding time of BVA can be reduced by about half.And the memory space of two decoders in BVA are about half of that in VA,which means that the BVA has lower memory requirements for decoder.And the decoding performance of BVA is almost the same as VA.展开更多
In this article, we consider the faster than Nyquist(FTN) technology in aspects of the application of the Viterbi algorithm(VA). Finite in time optimal FTN signals are used to provide a symbol rate higher than the &qu...In this article, we consider the faster than Nyquist(FTN) technology in aspects of the application of the Viterbi algorithm(VA). Finite in time optimal FTN signals are used to provide a symbol rate higher than the "Nyquist barrier" without any encoding. These signals are obtained as the solutions of the corresponding optimization problem. Optimal signals are characterized by intersymbol interference(ISI). This fact leads to significant bit error rate(BER) performance degradation for "classical" forms of signals. However, ISI can be controlled by the restriction of the optimization problem. So we can use optimal signals in conditions of increased duration and an increased symbol rate without significant energy losses. The additional symbol rate increase leads to the increase of the reception algorithm complexity. We consider the application of VA for optimal FTN signals reception. The application of VA for receiving optimal FTN signals with increased duration provides close to the potential performance of BER,while the symbol rate is twice above the Nyquist limit.展开更多
针对航空发动机的突发故障,提出了一种基于多状态混合高斯隐马尔科夫模型(mixture of Gaussian-hidden Markov model,简称MOG-HMM)和Viterbi算法相结合的预测方法。首先,根据航空发动机突发故障的历史监测数据建立多状态MOG-HMM模型,确...针对航空发动机的突发故障,提出了一种基于多状态混合高斯隐马尔科夫模型(mixture of Gaussian-hidden Markov model,简称MOG-HMM)和Viterbi算法相结合的预测方法。首先,根据航空发动机突发故障的历史监测数据建立多状态MOG-HMM模型,确定状态数、状态转移矩阵、观察值概率分布以及最终的突发故障状态;然后,对新采集的观测数据,通过Viterbi算法解码出该观测数据对应的当前状态;最后,计算该状态到达突发故障状态的时间间隔,从而可以对突发故障进行预测。仿真和实验结果表明,该方法能够实现对突发故障的预测,并且符合标准预测指标的要求。展开更多
结合旋转机械启停阶段振动信号的特点,提出一种基于Viterbi算法的Gabor阶比跟踪(Gabor order tracking based on Viterbi,V_GOT)算法,此算法采用Viterbi算法代替了传统的Gabor阶比跟踪(Gabor order tracking,GOT)算法中的时频滤波技术。...结合旋转机械启停阶段振动信号的特点,提出一种基于Viterbi算法的Gabor阶比跟踪(Gabor order tracking based on Viterbi,V_GOT)算法,此算法采用Viterbi算法代替了传统的Gabor阶比跟踪(Gabor order tracking,GOT)算法中的时频滤波技术。V_GOT算法和传统的GOT算法相比,其能够对复杂机械振动信号产生的邻近阶比和交叉阶比分量进行有效的跟踪和分离,并且具有计算量小、精度高、无需转速计等硬件和用纯软件的方法实现等优点。详细讨论了V_GOT技术的基本原理、算法及进行阶比跟踪的实现过程,另外,对偶函数对Gabor阶比跟踪结果的影响进行了深入的研究。采用仿真和实际试验对V_GOT算法进行了验证,试验结果表明该方法能够在时频域准确地提取幅值和复杂频率变化的阶比,适合于复杂旋转机械振动响应特征提取。展开更多
文摘To overcome some drawbacks of Viterbi algorithm （VA）, such as exponential growing complexity of decoding, and its poor performance under bad channel conditions, some available known information must be used as constrained condition and apriori knowledge for decoding. A new constrained VA is proposed by adding con- straint bits directly for conventional codec. Compared with the conventional VA, under the bad channel condi- tion, the proposed scheme can improve the peak signal to noise ratio （PSNR） of the decoding image 2--10 dB by changing the number of constrained bits. Experimental results show that it is an efficient error-controlling way for the transmission of set partitioning in hierarchical trees （SPIHT） coded image.
文摘In order to fully utilize the soft decision ability of the outer decoder in a concatenated system, reliability information (called soft output) from the inner decoder or equalizer is required. In this paper, based on the analysis of typical implementations of soft output VA, a novel algorithm is proposed by utilizing the property of Viterbi algorithm. Compared with the typical implementations, less processing expense is required by the new algorithm for weighting the hard decisions of VA. Meanwhile, simulation results show that, deterioration in performance of this algorithm is usually small for decoding of convolutional code and negligible for equalization.
文摘Overlapped time domain multiplexing(OvTDM)is an innovative encoding scheme that can obtain high spectral efficiency.However,the intentional inter-symbol interference(ISI)caused by OvTDM will make the decoding process more complex.The computational complexity of maximum likelihood sequence detection increases exponentially with the growth of spectral efficiency in OvTDM.As a consequence of high complexity,the decoding effort for a given spectral efficiency may occasionally exceed the physical limitations of the decoder,leading inevitably to buffer overflows and information erasures.In this paper,we propose a bidirectional Viterbi algorithm(BVA)based on the bidirectional sequence decoding for OvTDM.With the BVA,the decoding operation starts simultaneously from the both ends of the corresponding trellis and stops at the middle of trellis.The simulation results show that compared with Viterbi algorithm(VA),the decoding time of BVA can be reduced by about half.And the memory space of two decoders in BVA are about half of that in VA,which means that the BVA has lower memory requirements for decoder.And the decoding performance of BVA is almost the same as VA.
基金supported by the Grant of the President of the Russian Federation for state support of young Russian scientists(agreementМК-1571.2019.8 No.075-15-2019-1155)。
文摘In this article, we consider the faster than Nyquist(FTN) technology in aspects of the application of the Viterbi algorithm(VA). Finite in time optimal FTN signals are used to provide a symbol rate higher than the "Nyquist barrier" without any encoding. These signals are obtained as the solutions of the corresponding optimization problem. Optimal signals are characterized by intersymbol interference(ISI). This fact leads to significant bit error rate(BER) performance degradation for "classical" forms of signals. However, ISI can be controlled by the restriction of the optimization problem. So we can use optimal signals in conditions of increased duration and an increased symbol rate without significant energy losses. The additional symbol rate increase leads to the increase of the reception algorithm complexity. We consider the application of VA for optimal FTN signals reception. The application of VA for receiving optimal FTN signals with increased duration provides close to the potential performance of BER,while the symbol rate is twice above the Nyquist limit.
文摘针对航空发动机的突发故障,提出了一种基于多状态混合高斯隐马尔科夫模型(mixture of Gaussian-hidden Markov model,简称MOG-HMM)和Viterbi算法相结合的预测方法。首先,根据航空发动机突发故障的历史监测数据建立多状态MOG-HMM模型,确定状态数、状态转移矩阵、观察值概率分布以及最终的突发故障状态;然后,对新采集的观测数据,通过Viterbi算法解码出该观测数据对应的当前状态;最后,计算该状态到达突发故障状态的时间间隔,从而可以对突发故障进行预测。仿真和实验结果表明,该方法能够实现对突发故障的预测,并且符合标准预测指标的要求。
文摘结合旋转机械启停阶段振动信号的特点,提出一种基于Viterbi算法的Gabor阶比跟踪(Gabor order tracking based on Viterbi,V_GOT)算法,此算法采用Viterbi算法代替了传统的Gabor阶比跟踪(Gabor order tracking,GOT)算法中的时频滤波技术。V_GOT算法和传统的GOT算法相比,其能够对复杂机械振动信号产生的邻近阶比和交叉阶比分量进行有效的跟踪和分离,并且具有计算量小、精度高、无需转速计等硬件和用纯软件的方法实现等优点。详细讨论了V_GOT技术的基本原理、算法及进行阶比跟踪的实现过程,另外,对偶函数对Gabor阶比跟踪结果的影响进行了深入的研究。采用仿真和实际试验对V_GOT算法进行了验证,试验结果表明该方法能够在时频域准确地提取幅值和复杂频率变化的阶比,适合于复杂旋转机械振动响应特征提取。
