Abstract： The layered decoding algorithm has been widely used in the implementation of Low Density Parity Check （LDPC） decoders, due to its high convergence speed. However, the pipeline operation of the layered dec...Abstract： The layered decoding algorithm has been widely used in the implementation of Low Density Parity Check （LDPC） decoders, due to its high convergence speed. However, the pipeline operation of the layered decoder may introduce memory access conflicts, which heavily deteriorates the decoder throughput. To essentially deal with the issue of memory access conflicts,展开更多
The conventional methodology for designing QC-LDPC decoders is applied for fixed configurations used in wireless communication standards, and the supported largest expansion factor Z (the parallelism of the layered de...The conventional methodology for designing QC-LDPC decoders is applied for fixed configurations used in wireless communication standards, and the supported largest expansion factor Z (the parallelism of the layered decoding) is a fixed number. In this paper, we study the circular-shifting network for decoding LDPC codes with arbitrary Z factor, especially for decoding large Z (Z P) codes, where P is the decoder parallelism. By buffering the P-length slices from the memory, and assembling the shifted slices in a fixed routine, the P-parallelism shift network can process Z-parallelism circular-shifting tasks. The implementation results show that the proposed network for arbitrary sized data shifting consumes only one times of additional resource cost compared to the traditional solution for only maximum P sized data shifting, and achieves significant saving on area and routing complexity.展开更多
临床医生可通过观察眼底视网膜血管及其分支对人体是否患有疾病进行早期诊断,但由于视网膜中的血管错综复杂,模型在分割时会出现对微细血管分割精确度不足的问题。为此,提出一种结合残差模块Res2-net以及高效通道注意力机制(efficient c...临床医生可通过观察眼底视网膜血管及其分支对人体是否患有疾病进行早期诊断,但由于视网膜中的血管错综复杂,模型在分割时会出现对微细血管分割精确度不足的问题。为此,提出一种结合残差模块Res2-net以及高效通道注意力机制(efficient channel attention,ECA)的D-Linknet模型。首先,利用Res2-net代替基础模型中的残差模块Res-net以提升每个网络层的感受野;其次,在Res2-net中添加一种结合压缩激励(squeeze and excitation,SE)和门通道(gated channel transformation,GCT)的注意力机制模块,改善处于复杂背景下的血管分割效果和效率;在网络的解码层加入ECA确保模型计算的性能,避免因降维导致的精度下降;最后,融合改进的模型输出图与掩膜图细化分割结果。在公开数据集DRIVE、STARE上进行分割实验,模型准确度(accuracy,AC)分别为97.11%、96.32%,灵敏度(sensitivity,SE)为84.55%、83.92%,曲线下方范围的面积(area under curve,AUC)为0.9873和0.9766,分割效果优于其他模型。实验证明了算法的可行性,为后续研究提供科学依据。展开更多
Self-attention has been innovatively applied to text-to-speech(TTS)because of its parallel structure and superior strength in modeling sequential data.However,when used in end-to-end speech synthesis with an autoregre...Self-attention has been innovatively applied to text-to-speech(TTS)because of its parallel structure and superior strength in modeling sequential data.However,when used in end-to-end speech synthesis with an autoregressive decoding scheme,its inference speed becomes relatively low due to the quadratic complexity in sequence length.This problem becomes particularly severe on devices without graphics processing units(GPUs).To alleviate the dilemma,we propose an efficient decoding self-attention(EDSA)module as an alternative.Combined with a dynamic programming decoding procedure,TTS model inference can be effectively accelerated to have a linear computation complexity.We conduct studies on Mandarin and English datasets and find that our proposed model with EDSA can achieve 720%and 50%higher inference speed on the central processing unit(CPU)and GPU respectively,with almost the same performance.Thus,this method may make the deployment of such models easier when there are limited GPU resources.In addition,our model may perform better than the baseline Transformer TTS on out-of-domain utterances.展开更多
研究了安全通信意义下,单向译码转发(decode-and-forward,DF)协作无线网络的中继选择问题。针对窃听者既能获得信源发出的信号,又能窃取中继节点转发数据的通信系统,提出了3种中继选择方案来对抗窃听者,增强系统物理层安全性。其中,方...研究了安全通信意义下,单向译码转发(decode-and-forward,DF)协作无线网络的中继选择问题。针对窃听者既能获得信源发出的信号,又能窃取中继节点转发数据的通信系统,提出了3种中继选择方案来对抗窃听者,增强系统物理层安全性。其中,方案一选择到窃听者信噪比(signal-to-noise ratio,SNR)最小的中继节点;方案二为最大最小(max-min)选择方案,即选择信源到中继节点和中继节点到信宿的较差信噪比中最大值所对应的中继节点;方案三根据窃听信道和主信道的瞬时信道状态信息(channel state information,CSI)选择使得窃听网络有最大保密容量的中继节点。在对各方案的性能分析过程中,得到了各中继选择方案拦截概率的闭式表示,进一步对拦截概率作渐近分析,获得了各中继选择方案的分集阶数。具体地,方案一的分集阶数为1,另外2个中继选择方案的分集阶数均为中继节点个数M。数值结果验证了理论分析得到的结论。展开更多
基金the National Natural Science Foundation of China，the National Key Basic Research Program of China，The authors would like to thank all project partners for their valuable contributions and feedbacks
文摘Abstract： The layered decoding algorithm has been widely used in the implementation of Low Density Parity Check （LDPC） decoders, due to its high convergence speed. However, the pipeline operation of the layered decoder may introduce memory access conflicts, which heavily deteriorates the decoder throughput. To essentially deal with the issue of memory access conflicts,
文摘The conventional methodology for designing QC-LDPC decoders is applied for fixed configurations used in wireless communication standards, and the supported largest expansion factor Z (the parallelism of the layered decoding) is a fixed number. In this paper, we study the circular-shifting network for decoding LDPC codes with arbitrary Z factor, especially for decoding large Z (Z P) codes, where P is the decoder parallelism. By buffering the P-length slices from the memory, and assembling the shifted slices in a fixed routine, the P-parallelism shift network can process Z-parallelism circular-shifting tasks. The implementation results show that the proposed network for arbitrary sized data shifting consumes only one times of additional resource cost compared to the traditional solution for only maximum P sized data shifting, and achieves significant saving on area and routing complexity.
文摘临床医生可通过观察眼底视网膜血管及其分支对人体是否患有疾病进行早期诊断,但由于视网膜中的血管错综复杂,模型在分割时会出现对微细血管分割精确度不足的问题。为此,提出一种结合残差模块Res2-net以及高效通道注意力机制(efficient channel attention,ECA)的D-Linknet模型。首先,利用Res2-net代替基础模型中的残差模块Res-net以提升每个网络层的感受野;其次,在Res2-net中添加一种结合压缩激励(squeeze and excitation,SE)和门通道(gated channel transformation,GCT)的注意力机制模块,改善处于复杂背景下的血管分割效果和效率;在网络的解码层加入ECA确保模型计算的性能,避免因降维导致的精度下降;最后,融合改进的模型输出图与掩膜图细化分割结果。在公开数据集DRIVE、STARE上进行分割实验,模型准确度(accuracy,AC)分别为97.11%、96.32%,灵敏度(sensitivity,SE)为84.55%、83.92%,曲线下方范围的面积(area under curve,AUC)为0.9873和0.9766,分割效果优于其他模型。实验证明了算法的可行性,为后续研究提供科学依据。
基金Project supported by the National Key Research and Development Program of China(No.2019YFB1312603)the Robotics Institute of Zhejiang University,China(No.K11801)。
文摘Self-attention has been innovatively applied to text-to-speech(TTS)because of its parallel structure and superior strength in modeling sequential data.However,when used in end-to-end speech synthesis with an autoregressive decoding scheme,its inference speed becomes relatively low due to the quadratic complexity in sequence length.This problem becomes particularly severe on devices without graphics processing units(GPUs).To alleviate the dilemma,we propose an efficient decoding self-attention(EDSA)module as an alternative.Combined with a dynamic programming decoding procedure,TTS model inference can be effectively accelerated to have a linear computation complexity.We conduct studies on Mandarin and English datasets and find that our proposed model with EDSA can achieve 720%and 50%higher inference speed on the central processing unit(CPU)and GPU respectively,with almost the same performance.Thus,this method may make the deployment of such models easier when there are limited GPU resources.In addition,our model may perform better than the baseline Transformer TTS on out-of-domain utterances.
文摘研究了安全通信意义下,单向译码转发(decode-and-forward,DF)协作无线网络的中继选择问题。针对窃听者既能获得信源发出的信号,又能窃取中继节点转发数据的通信系统,提出了3种中继选择方案来对抗窃听者,增强系统物理层安全性。其中,方案一选择到窃听者信噪比(signal-to-noise ratio,SNR)最小的中继节点;方案二为最大最小(max-min)选择方案,即选择信源到中继节点和中继节点到信宿的较差信噪比中最大值所对应的中继节点;方案三根据窃听信道和主信道的瞬时信道状态信息(channel state information,CSI)选择使得窃听网络有最大保密容量的中继节点。在对各方案的性能分析过程中,得到了各中继选择方案拦截概率的闭式表示,进一步对拦截概率作渐近分析,获得了各中继选择方案的分集阶数。具体地,方案一的分集阶数为1,另外2个中继选择方案的分集阶数均为中继节点个数M。数值结果验证了理论分析得到的结论。
