Quantized Decoders that Maximize Mutual Information for Polar Codes

In this paper,we innovatively associate the mutual information with the frame error rate(FER)performance and propose novel quantized decoders for polar codes.Based on the optimal quantizer of binary-input discrete memoryless channels(BDMCs),the proposed decoders quantize the virtual subchannels of polar codes to maximize mutual information(MMI)between source bits and quantized symbols.The nested structure of polar codes ensures that the MMI quantization can be implemented stage by stage.Simulation results show that the proposed MMI decoders with 4 quantization bits outperform the existing nonuniform quantized decoders that minimize mean-squared error(MMSE)with 4 quantization bits,and yield even better performance than uniform MMI quantized decoders with 5 quantization bits.Furthermore,the proposed 5-bit quantized MMI decoders approach the floating-point decoders with negligible performance loss.

基于时空特征融合的Encoder-Decoder多步4D短期航迹预测

航迹预测在确保空中交通安全、高效运行中扮演着至关重要的角色。所预测的航迹信息是航迹优化、冲突告警等决策工具的输入,而预测准确性取决于模型对航迹序列特征的提取能力。航迹序列数据是具有丰富时空特征的多维时间序列,其中每个变量都呈现出长短期的时间变化模式,并且这些变量之间还存在着相互依赖的空间信息。为了充分提取这种时空特征,本文提出了基于融合时空特征的编码器-解码器(Spatio-Temporal EncoderDecoder,STED)航迹预测模型。在Encoder中使用门控循环单元(Gated Recurrent Unit,GRU)、卷积神经网络(Convolutional Neural Network,CNN)和注意力机制(Attention,AT)构成的双通道网络来分别提取航迹时空特征,Decoder对时空特征进行拼接融合,并利用GRU对融合特征进行学习和递归输出,实现对未来多步航迹信息的预测。利用真实的航迹数据对算法性能进行验证,实验结果表明,所提STED网络模型能够在未来10 min预测范围内进行高精度的短期航迹预测,相比于LSTM、CNN-LSTM和AT-LSTM等数据驱动航迹预测模型具有更高的精度。此外,STED网络模型预测一个航迹点平均耗时为0.002 s,具有良好的实时性。

基于encoder-decoder框架的城镇污水厂出水水质预测

由于污水厂的出水水质指标繁多、污水处理过程中反应复杂、时序非线性程度高,基于机理模型的预测方法无法取得理想效果。针对此问题,提出基于深度学习的污水厂出水水质预测方法,并以吉林省某污水厂监测水质为来源数据,利用多种结合encoder-decoder结构的神经网络预测水质。结果显示,所提结构对LSTM和GRU网络预测能力都有一定提升,对长期预测能力提升更加显著,ED-GRU模型效果最佳,短期预测中的4个出水水质指标均方根误差(RMSE)为0.7551、0.2197、0.0734、0.3146,拟合优度(R2)为0.9013、0.9332、0.9167、0.9532,可以预测出水质局部变化,而长期预测中的4个指标RMSE为1.7204、1.7689、0.4478、0.8316,R2为0.4849、0.5507、0.4502、0.7595,可以预测出水质变化趋势,与顺序结构相比,短期预测RMSE降低10%以上,R2增加2%以上,长期预测RMSE降低25%以上,R2增加15%以上。研究结果表明,基于encoder-decoder结构的神经网络可以对污水厂出水水质进行准确预测,为污水处理工艺改进提供技术支撑。

基于Encoder-Decoder注意力网络的异常驾驶行为在线识别方法

异常驾驶行为是车辆安全运行的重大威胁,其对人员与物资的安全高效投送造成严重危害。以低成本非接触式的手机多传感器数据为基础,通过对驾驶行为特性进行数据分析,提出一种融合Encoder-Decoder深度网络与Attention机制的异常驾驶行为的在线识别方法。该方法由基于LSTM(long short-term memory)的Encoder-Decoder、Attention机制与基于SVM(support vector machine)的分类器3个模块构成。该系统识别方法包括:输入编码、注意力学习、特征解码、序列重构、残差计算与驾驶行为分类等6个步骤。该技术方法利用自然驾驶条件下所采集的手机传感器数据进行实验。实验结果表明:①手机多传感器数据融合方法对驾驶行为识别具备有效性;②异常驾驶行为必然会造成数据异常波动;③Attention机制有助于提升模型学习效果,对所提出模型的识别准确率F1-score为0.717,与经典同类模型比较,准确率得到显著提升;④对于汽车异常驾驶行为来说,SVM比Logistic与随机森林算法具有更优越的识别效果。

利用Encoder-Decoder框架的深度学习网络实现绕射波分离及成像

利用单纯绕射波场实现地下地质异常体的识别具有坚实的理论基础,对应的实施方法得到了广泛研究,且有效地应用于实际勘探。但现有技术在微小尺度异常体成像方面收效甚微,相关研究多数以射线传播理论为基础,对于影响绕射波分离成像精度的因素分析并不完备。相较于反射波,由于存在不连续构造而产生的绕射波能量微弱并且相互干涉,同时环境干扰使得绕射波进一步湮没。因此,更高精度的波场分离及单独成像是现阶段基于绕射波超高分辨率处理、解释的重点研究方向。为此,首先针对地球物理勘探中地质异常体的准确定位,以携带高分辨率信息的绕射波为研究对象,系统分析在不同尺度、不同物性参数的异常体情况下绕射波的能量大小及形态特征,掌握绕射波与其他类型波叠加的具体形式;然后根据相应特征性质提出基于深度学习技术的绕射波分离成像方法,即利用Encoder-Decoder框架的空洞卷积网络捕获绕射波场特征,从而实现绕射波分离,基于速度连续性原则构建单纯绕射波场的偏移速度模型并完成最终成像。数据测试表明,该方法最终可满足微小地质异常体高精度识别的需求。

Unifying Convolution and Transformer Decoder for Textile Fiber Identification

At present,convolutional neural networks(CNNs)and transformers surpass humans in many situations(such as face recognition and object classification),but do not work well in identifying fibers in textile surface images.Hence,this paper proposes an architecture named FiberCT which takes advantages of the feature extraction capability of CNNs and the long-range modeling capability of transformer decoders to adaptively extract multiple types of fiber features.Firstly,the convolution module extracts fiber features from the input textile surface images.Secondly,these features are sent into the transformer decoder module where label embeddings are compared with the features of each type of fibers through multi-head cross-attention and the desired features are pooled adaptively.Finally,an asymmetric loss further purifies the extracted fiber representations.Experiments show that FiberCT can more effectively extract the representations of various types of fibers and improve fiber identification accuracy than state-of-the-art multi-label classification approaches.

A Denoiser for Correlated Noise Channel Decoding: Gated-Neural Network

This letter proposes a sliced-gated-convolutional neural network with belief propagation(SGCNN-BP) architecture for decoding long codes under correlated noise. The basic idea of SGCNNBP is using Neural Networks(NN) to transform the correlated noise into white noise, setting up the optimal condition for a standard BP decoder that takes the output from the NN. A gate-controlled neuron is used to regulate information flow and an optional operation—slicing is adopted to reduce parameters and lower training complexity. Simulation results show that SGCNN-BP has much better performance(with the largest gap being 5dB improvement) than a single BP decoder and achieves a nearly 1dB improvement compared to Fully Convolutional Networks(FCN).

Improved Segmented Belief Propagation List Decoding for Polar Codes with Bit-Flipping

Belief propagation list(BPL) decoding for polar codes has attracted more attention due to its inherent parallel nature. However, a large gap still exists with CRC-aided SCL(CA-SCL) decoding.In this work, an improved segmented belief propagation list decoding based on bit flipping(SBPL-BF) is proposed. On the one hand, the proposed algorithm makes use of the cooperative characteristic in BPL decoding such that the codeword is decoded in different BP decoders. Based on this characteristic, the unreliable bits for flipping could be split into multiple subblocks and could be flipped in different decoders simultaneously. On the other hand, a more flexible and effective processing strategy for the priori information of the unfrozen bits that do not need to be flipped is designed to improve the decoding convergence. In addition, this is the first proposal in BPL decoding which jointly optimizes the bit flipping of the information bits and the code bits. In particular, for bit flipping of the code bits, a H-matrix aided bit-flipping algorithm is designed to enhance the accuracy in identifying erroneous code bits. The simulation results show that the proposed algorithm significantly improves the errorcorrection performance of BPL decoding for medium and long codes. It is more than 0.25 d B better than the state-of-the-art BPL decoding at a block error rate(BLER) of 10^(-5), and outperforms CA-SCL decoding in the low signal-to-noise(SNR) region for(1024, 0.5)polar codes.

基于GRU Encoder-decoder和注意力机制的RUL预测方法

深度学习模型可直接建立机械设备的状态与剩余使用寿命(RUL)之间的映射关系,从而避免人工提取特征和建立健康指标的过程。文中基于深度学习理论,提出一种基于注意力机制和时序编码解码器(Encoder-decoder)相结合的RUL预测方法。首先,基于门控循环神经网络(GRU)构建一个时序编码解码器以实现输入序列的重构,其中GRU-Encoder对输入的多元时间序列进行编码;再引入注意力机制对GRU-Encoder在每个时刻的输出向量进行加权融合,以融合后的向量作为编码结果,并将其输入到GRU-Decoder中实现输入序列的重构,同时将编码结果映射为输入样本的RUL。采用CMAPSS数据集对所提方法的有效性进行验证,结果表明,该方法预测精度较高,可行且有效。

基于Encoder-Decoder-ILSTM模型的瓦斯浓度预测研究

近年来,神经网络在各领域均发挥了巨大作用,同样在煤矿瓦斯浓度预测当中也有应用。为了提高模型的预测精度和实时性,结合Encoder-Decoder结构、长短期记忆形成、蛇优化算法提出了一种新的神经网络,为促进煤矿安全生产提供了技术支持。

Viterbi Decoder ACS单元中路径度量值存储空间的优化

ACS单元的设计及路径度量(PM)值的存储是Viterbi Decoder硬件实现的重要部分之一。介绍了一种码率为1/2的硬判决Viterbi Decoder的ACS部分的硬件实现方法。采用了一种全新的设计与存储方式,即原位运算旋转地址的方式,极大地节省了在ACS运算过程中用以存储路径度量值的RAM空间,大量的实验证明,设计的译码器在资源消耗上有较大优势。

Lowering the Error Floor of ADMM Penalized Decoder for LDPC Codes

Decoding by alternating direction method of multipliers(ADMM) is a promising linear programming decoder for low-density parity-check(LDPC) codes. In this paper, we propose a two-step scheme to lower the error floor of LDPC codes with ADMM penalized decoder.For the undetected errors that cannot be avoided at the decoder side, we modify the code structure slightly to eliminate low-weight code words. For the detected errors induced by small error-prone structures, we propose a post-processing method for the ADMM penalized decoder. Simulation results show that the error floor can be reduced significantly over three illustrated LDPC codes by the proposed two-step scheme.

Improved List Sphere Decoder for Multiple Antenna Systems

An improved list sphere decoder （ILSD） is proposed based on the conventional list sphere decoder （LSD） and the reduced- complexity maximum likelihood sphere-decoding algorithm. Unlike the conventional LSD with fixed initial radius, the ILSD adopts an adaptive radius to accelerate the list cdnstruction. Characterized by low-complexity and radius-insensitivity, the proposed algorithm makes iterative joint detection and decoding more realizable in multiple-antenna systems. Simulation results show that computational savings of ILSD over LSD are more apparent with more transmit antennas or larger constellations, and with no performance degradation. Because the complexity of the ILSD algorithm almost keeps invariant with the increasing of initial radius, the BER performance can be improved by selecting a sufficiently large radius.

Efficient VLSI architecture of CAVLC decoder with power optimized

This paper presents an efficient VLSI architecture of the contest-based adaptive variable length code （CAVLC） decoder with power optimized for the H.264/advanced video coding （AVC） standard. In the proposed design, according to the regularity of the codewords, the first one detector is used to solve the low efficiency and high power dissipation problem within the traditional method of table-searching. Considering the relevance of the data used in the process of runbefore＇s decoding, arithmetic operation is combined with finite state machine （FSM）, which achieves higher decoding efficiency. According to the CAVLC decoding flow, clock gating is employed in the module level and the register level respectively, which reduces 43% of the overall dynamic power dissipation. The proposed design can decode every syntax element in one clock cycle. When the proposed design is synthesized at the clock constraint of 100 MHz, the synthesis result shows that the design costs 11 300 gates under a 0.25 μm CMOS technology, which meets the demand of real time decoding in the H.264/AVC standard.

Low-loss belief propagation decoder with Tanner graph in quantum error-correction codes

Quantum error-correction codes are immeasurable resources for quantum computing and quantum communication.However,the existing decoders are generally incapable of checking node duplication of belief propagation(BP)on quantum low-density parity check(QLDPC)codes.Based on the probability theory in the machine learning,mathematical statistics and topological structure,a GF(4)(the Galois field is abbreviated as GF)augmented model BP decoder with Tanner graph is designed.The problem of repeated check nodes can be solved by this decoder.In simulation,when the random perturbation strength p=0.0115-0.0116 and number of attempts N=60-70,the highest decoding efficiency of the augmented model BP decoder is obtained,and the low-loss frame error rate(FER)decreases to 7.1975×10^(-5).Hence,we design a novel augmented model decoder to compare the relationship between GF(2)and GF(4)for quantum code[[450,200]]on the depolarization channel.It can be verified that the proposed decoder provides the widely application range,and the decoding performance is better in QLDPC codes.

基于Encoder-Decoder网络的遥感影像道路提取方法

针对道路目标特点,设计实现了用于遥感影像道路提取的Encoder-Decoder深度语义分割网络。首先,针对道路目标局部特征丰富、语义特征较为简单的特点,设计了较浅深度、分辨率较高的Encoder-Decoder网络结构,提高了分割网络的细节表示能力。其次,针对遥感影像中道路目标所占像素比例较小的特点,改进了二分类交叉熵损失函数,解决了网络训练中正负样本严重失衡的问题。在大型道路提取数据集上的试验表明,所提方法召回率、精度和F1-score指标分别达到了83.9%、82.5%及82.9%,能够完整准确地提取遥感影像中的道路目标。所设计的Encoder-Decoder网络性能优良,且不需人工设计提取特征,因而具有良好的应用前景。

Determination of quantum toric error correction code threshold using convolutional neural network decoders

Quantum error correction technology is an important solution to solve the noise interference generated during the operation of quantum computers.In order to find the best syndrome of the stabilizer code in quantum error correction,we need to find a fast and close to the optimal threshold decoder.In this work,we build a convolutional neural network(CNN)decoder to correct errors in the toric code based on the system research of machine learning.We analyze and optimize various conditions that affect CNN,and use the RestNet network architecture to reduce the running time.It is shortened by 30%-40%,and we finally design an optimized algorithm for CNN decoder.In this way,the threshold accuracy of the neural network decoder is made to reach 10.8%,which is closer to the optimal threshold of about 11%.The previous threshold of 8.9%-10.3%has been slightly improved,and there is no need to verify the basic noise.

3G移动通信系统中信道编码Turbo Decoder解码器实现简介

介绍了在第三代移动通信系统中信道编解码使用的 Turbo- codes和 TurboDecoder解码器的原理算法和实现方案。

基于长短时记忆网络的Encoder-Decoder多步交通流预测模型

交通流序列多为单步预测。为实现交通流序列的多步预测,提出一种基于编码器解码器(encoder-decoder,ED)框架的长短期记忆网络(long short-term memory,LSTM)模型,即ED LSTM模型。将自回归滑动平均、支持向量回归机、XGBOOST、循环神经网络、卷积神经网络、LSTM作为对照组进行实验验证。实验结果表明,当预测时间步长增加时,ED框架能够减缓模型性能的下降趋势,LSTM能够充分挖掘时间序列中的非线性关系。除此之外,在单变量输入的情况下,在PEMS-04数据集上,当预测时间步长为t+1到t+12的12个时间步时,ED LSTM模型的均方根误差(root mean squard error,RMSE)及平均绝对误差(mean absolute error,MAE)分别下降0.210~5.422、0.061~0.191。相较于单因素输入,多因素输入的ED LSTM模型在12个预测时间步长下,RMSE、MAE分别下降0.840、0.136。实验证明了ED LSTM模型能够有效地用于交通流序列的多步及单因素、多因素预测任务。

基于Encoder-Decoder LSTM的电梯制动滑移量预测方法研究

电梯曳引系统的可靠性是电梯安全性能评估中的重要部分,紧急制动滑移量是其重要反映指标,对滑移量进行时序预测能有利保证电梯安全,具有重要意义。采用结合Encoder-Decoder的LSTM模型学习电梯紧急制动滑移量的增长过程,进行多步预测来获得未来区间内滑移预测数据。通过与RNN和LSTM模型预测结果的对比,表明Encoder-Decoder LSTM模型针对电梯紧急制动滑移量的预测具有较好的精度,可以作为电梯曳引能力评估的重要手段。