Method of Multi-Mode Sensor Data Fusion with an Adaptive Deep Coupling Convolutional Auto-Encoder

To address the difficulties in fusing multi-mode sensor data for complex industrial machinery, an adaptive deep coupling convolutional auto-encoder (ADCCAE) fusion method was proposed. First, the multi-mode features extracted synchronously by the CCAE were stacked and fed to the multi-channel convolution layers for fusion. Then, the fused data was passed to all connection layers for compression and fed to the Softmax module for classification. Finally, the coupling loss function coefficients and the network parameters were optimized through an adaptive approach using the gray wolf optimization (GWO) algorithm. Experimental comparisons showed that the proposed ADCCAE fusion model was superior to existing models for multi-mode data fusion.

Remaining Useful Life Prediction of Rail Based on Improved Pulse Separable Convolution Enhanced Transformer Encoder

In order to prevent possible casualties and economic loss, it is critical to accurate prediction of the Remaining Useful Life (RUL) in rail prognostics health management. However, the traditional neural networks is difficult to capture the long-term dependency relationship of the time series in the modeling of the long time series of rail damage, due to the coupling relationship of multi-channel data from multiple sensors. Here, in this paper, a novel RUL prediction model with an enhanced pulse separable convolution is used to solve this issue. Firstly, a coding module based on the improved pulse separable convolutional network is established to effectively model the relationship between the data. To enhance the network, an alternate gradient back propagation method is implemented. And an efficient channel attention (ECA) mechanism is developed for better emphasizing the useful pulse characteristics. Secondly, an optimized Transformer encoder was designed to serve as the backbone of the model. It has the ability to efficiently understand relationship between the data itself and each other at each time step of long time series with a full life cycle. More importantly, the Transformer encoder is improved by integrating pulse maximum pooling to retain more pulse timing characteristics. Finally, based on the characteristics of the front layer, the final predicted RUL value was provided and served as the end-to-end solution. The empirical findings validate the efficacy of the suggested approach in forecasting the rail RUL, surpassing various existing data-driven prognostication techniques. Meanwhile, the proposed method also shows good generalization performance on PHM2012 bearing data set.

Blind recognition of k/n rate convolutional encoders from noisy observation

Blind recognition of convolutional codes is not only essential for cognitive radio, but also for non-cooperative context. This paper is dedicated to the blind identification of rate k/n convolutional encoders in a noisy context based on Walsh-Hadamard transformation and block matrix (WHT-BM). The proposed algorithm constructs a system of noisy linear equations and utilizes all its coefficients to recover parity check matrix. It is able to make use of fault-tolerant feature of WHT, thus providing more accurate results and achieving better error performance in high raw bit error rate (BER) regions. Moreover, it is more computationally efficient with the use of the block matrix (BM) method. © 2017 Beijing Institute of Aerospace Information.

FPGA Design and Implementation of a Convolutional Encoder and a Viterbi Decoder Based on 802.11a for OFDM

In this paper, a modified FPGA scheme for the convolutional encoder and Viterbi decoder based on the IEEE 802.11a standards of WLAN is presented in OFDM baseband processing systems. The proposed design supports a generic, robust and configurable Viterbi decoder with constraint length of 7, code rate of 1/2 and decoding depth of 36 symbols. The Viterbi decoder uses full-parallel structure to improve computational speed for the add-compare-select (ACS) modules, adopts optimal data storage mechanism to avoid overflow and employs three distributed RAM blocks to complete cyclic trace-back. It includes the core parts, for example, the state path measure computation, the preservation and transfer of the survivor path and trace-back decoding, etc. Compared to the general Viterbi decoder, this design can effectively decrease the 10% of chip logic elements, reduce 5% of power consumption, and increase the encoder and decoder working performance in the hardware implementation. Lastly, relevant simulation results using Verilog HDL language are verified based on a Xinlinx Virtex-II FPGA by ISE 7.1i. It is shown that the Viterbi decoder is capable of decoding (2, 1, 7) convolutional codes accurately with a throughput of 80 Mbps.

一种融合AutoEncoder与CNN的混合算法用于图像特征提取

深度学习方法在图像的特征提取方面具有优势。针对传统特征提取方法需要先验知识的不足,提出一种自动编码器(Auto Encoder)与卷积神经网络(convolutional neural network,CNN)相结合的深度学习特征提取方法。该方法给Auto Encoder加入快速稀疏性控制,据此对图像训练出基本构件,并初始化CNN的卷积核;同时,给CNN加入了滤波机制,使输出特征保持稀疏性。实验结果表明,在Minist手写数字库和Yale人脸库的识别效果上,提出的特征提取方法均取得了较好的结果,实验进一步通过交叉验证T检验指出,引入滤波机制的特征提取模型优于没有采用滤波机制的模型。

基于Auto Encoder的智能监控指纹识别系统

针对目前已有的嵌入式指纹识别系统往往采用手工提取,不能自动学习并提取识别所需的特征及识别正确率仍然不高的缺点,提出一种基于自动编码器(Auto Encoder)和LSSVM的指纹识别系统。首先,提出采用FPS200作为指纹传感器采集指纹数据,然后将采集的数据经过滤波和二值化等预处理,通过比较差异算法获得Auto Encoder中的权值和偏置等参数,从而得到训练好的Auto Encoder用于指纹图像特征提取。最后,将自动提取的特征进行训练和分类,将投票最多的分类作为指纹识别的结果。通过测试表明,系统能较精确地实现指纹识别,具有收敛速度快、正确识别率高和匹配时间短的优点。

基于AutoEncoder的油气管道控制系统异常状态监测方法

压缩机控制电路的健康状态管理在管道运输中至关重要。通常油气管道压缩机系统部署地点远离城市,环境恶劣,且负荷高、工作时间长,因此故障频发。构建可靠的健康状态检测模型通常需要大量的故障样本,然而在实际数据中,故障样本相对稀缺。采用一种基于自编码器(auto encoder,AE)的单分类方法对油气管道控制系统的异常状态进行辨识。该模型仅需对系统的正常工作状态进行学习,通过编码器可实现特征的自适应提取,从而对数据进行抽象表示,并获得较好的非线性映射能力;当数据分布异常时,系统可区分其与正常信号间的差异,并进行预警。实验部分采用西部输油管道控制系统中实地获取的通信解码信号以及电源信号进行验证,并以单分类支持向量机方法作对比实验,表明了所提出方法的有效性。

Position Encoding Based Convolutional Neural Networks for Machine Remaining Useful Life Prediction

Accurate remaining useful life(RUL)prediction is important in industrial systems.It prevents machines from working under failure conditions,and ensures that the industrial system works reliably and efficiently.Recently,many deep learning based methods have been proposed to predict RUL.Among these methods,recurrent neural network(RNN)based approaches show a strong capability of capturing sequential information.This allows RNN based methods to perform better than convolutional neural network(CNN)based approaches on the RUL prediction task.In this paper,we question this common paradigm and argue that existing CNN based approaches are not designed according to the classic principles of CNN,which reduces their performances.Additionally,the capacity of capturing sequential information is highly affected by the receptive field of CNN,which is neglected by existing CNN based methods.To solve these problems,we propose a series of new CNNs,which show competitive results to RNN based methods.Compared with RNN,CNN processes the input signals in parallel so that the temporal sequence is not easily determined.To alleviate this issue,a position encoding scheme is developed to enhance the sequential information encoded by a CNN.Hence,our proposed position encoding based CNN called PE-Net is further improved and even performs better than RNN based methods.Extensive experiments are conducted on the C-MAPSS dataset,where our PE-Net shows state-of-the-art performance.

A Lightweight Network with Dual Encoder and Cross Feature Fusion for Cement Pavement Crack Detection

Automatic crack detection of cement pavement chiefly benefits from the rapid development of deep learning,with convolutional neural networks(CNN)playing an important role in this field.However,as the performance of crack detection in cement pavement improves,the depth and width of the network structure are significantly increased,which necessitates more computing power and storage space.This limitation hampers the practical implementation of crack detection models on various platforms,particularly portable devices like small mobile devices.To solve these problems,we propose a dual-encoder-based network architecture that focuses on extracting more comprehensive fracture feature information and combines cross-fusion modules and coordinated attention mechanisms formore efficient feature fusion.Firstly,we use small channel convolution to construct shallow feature extractionmodule(SFEM)to extract low-level feature information of cracks in cement pavement images,in order to obtainmore information about cracks in the shallowfeatures of images.In addition,we construct large kernel atrous convolution(LKAC)to enhance crack information,which incorporates coordination attention mechanism for non-crack information filtering,and large kernel atrous convolution with different cores,using different receptive fields to extract more detailed edge and context information.Finally,the three-stage feature map outputs from the shallow feature extraction module is cross-fused with the two-stage feature map outputs from the large kernel atrous convolution module,and the shallow feature and detailed edge feature are fully fused to obtain the final crack prediction map.We evaluate our method on three public crack datasets:DeepCrack,CFD,and Crack500.Experimental results on theDeepCrack dataset demonstrate the effectiveness of our proposed method compared to state-of-the-art crack detection methods,which achieves Precision(P)87.2%,Recall(R)87.7%,and F-score(F1)87.4%.Thanks to our lightweight crack detectionmodel,the parameter count of the model in real-world detection scenarios has been significantly reduced to less than 2M.This advancement also facilitates technical support for portable scene detection.

Brain Functional Network Generation Using Distribution-Regularized Adversarial Graph Autoencoder with Transformer for Dementia Diagnosis

The topological connectivity information derived from the brain functional network can bring new insights for diagnosing and analyzing dementia disorders.The brain functional network is suitable to bridge the correlation between abnormal connectivities and dementia disorders.However,it is challenging to access considerable amounts of brain functional network data,which hinders the widespread application of data-driven models in dementia diagnosis.In this study,a novel distribution-regularized adversarial graph auto-Encoder(DAGAE)with transformer is proposed to generate new fake brain functional networks to augment the brain functional network dataset,improving the dementia diagnosis accuracy of data-driven models.Specifically,the label distribution is estimated to regularize the latent space learned by the graph encoder,which canmake the learning process stable and the learned representation robust.Also,the transformer generator is devised to map the node representations into node-to-node connections by exploring the long-term dependence of highly-correlated distant brain regions.The typical topological properties and discriminative features can be preserved entirely.Furthermore,the generated brain functional networks improve the prediction performance using different classifiers,which can be applied to analyze other cognitive diseases.Attempts on the Alzheimer’s Disease Neuroimaging Initiative(ADNI)dataset demonstrate that the proposed model can generate good brain functional networks.The classification results show adding generated data can achieve the best accuracy value of 85.33%,sensitivity value of 84.00%,specificity value of 86.67%.The proposed model also achieves superior performance compared with other related augmentedmodels.Overall,the proposedmodel effectively improves cognitive disease diagnosis by generating diverse brain functional networks.

Application of deep autoencoder model for structural condition monitoring

Damage detection in structures is performed via vibra-tion based structural identification. Modal information, such as fre-quencies and mode shapes, are widely used for structural dama-ge detection to indicate the health conditions of civil structures.The deep learning algorithm that works on a multiple layer neuralnetwork model termed as deep autoencoder is proposed to learnthe relationship between the modal information and structural stiff-ness parameters. This is achieved via dimension reduction of themodal information feature and a non-linear regression against thestructural stiffness parameters. Numerical tests on a symmetri-cal steel frame model are conducted to generate the data for thetraining and validation, and to demonstrate the efficiency of theproposed approach for vibration based structural damage detec-tion.

Application of Improved Deep Auto-Encoder Network in Rolling Bearing Fault Diagnosis

Since the effectiveness of extracting fault features is not high under traditional bearing fault diagnosis method, a bearing fault diagnosis method based on Deep Auto-encoder Network (DAEN) optimized by Cloud Adaptive Particle Swarm Optimization (CAPSO) was proposed. On the basis of analyzing CAPSO and DAEN, the CAPSO-DAEN fault diagnosis model is built. The model uses the randomness and stability of CAPSO algorithm to optimize the connection weight of DAEN, to reduce the constraints on the weights and extract fault features adaptively. Finally, efficient and accurate fault diagnosis can be implemented with the Softmax classifier. The results of test show that the proposed method has higher diagnostic accuracy and more stable diagnosis results than those based on the DAEN, Support Vector Machine (SVM) and the Back Propagation algorithm (BP) under appropriate parameters.

Feature Enhanced Stacked Auto Encoder for Diseases Detection in Brain MRI

The detection of brain disease is an essential issue in medical and research areas.Deep learning techniques have shown promising results in detecting and diagnosing brain diseases using magnetic resonance imaging(MRI)images.These techniques involve training neural networks on large datasets of MRI images,allowing the networks to learn patterns and features indicative of different brain diseases.However,several challenges and limitations still need to be addressed further to improve the accuracy and effectiveness of these techniques.This paper implements a Feature Enhanced Stacked Auto Encoder(FESAE)model to detect brain diseases.The standard stack auto encoder’s results are trivial and not robust enough to boost the system’s accuracy.Therefore,the standard Stack Auto Encoder(SAE)is replaced with a Stacked Feature Enhanced Auto Encoder with a feature enhancement function to efficiently and effectively get non-trivial features with less activation energy froman image.The proposed model consists of four stages.First,pre-processing is performed to remove noise,and the greyscale image is converted to Red,Green,and Blue(RGB)to enhance feature details for discriminative feature extraction.Second,feature Extraction is performed to extract significant features for classification using DiscreteWavelet Transform(DWT)and Channelization.Third,classification is performed to classify MRI images into four major classes:Normal,Tumor,Brain Stroke,and Alzheimer’s.Finally,the FESAE model outperforms the state-of-theart,machine learning,and deep learning methods such as Artificial Neural Network(ANN),SAE,Random Forest(RF),and Logistic Regression(LR)by achieving a high accuracy of 98.61% on a dataset of 2000 MRI images.The proposed model has significant potential for assisting radiologists in diagnosing brain diseases more accurately and improving patient outcomes.

Fault Diagnosis for Rolling Bearings with Stacked Denoising Auto-encoder of Information Aggregation

Rolling bearings are important central components in rotating machines, whose fault diagnosis is crucial in condition-based maintenance to reduce the complexity of different kinds of faults. To classify various rolling bearing faults, a prognostic algorithm consisting of four phases was proposed. Since stacked denoising auto-encoder can be filtered, noise of large numbers of mechanical vibration signals was used for deep learning structure to extract the characteristics of the noise. Unsupervised pre-training method, which can greatly simplify the traditional manual extraction approach, was utilized to process the depth of the data automatically. Furthermore, the aggregation layer of stacked denoising auto-encoder(SDA) was proposed to get rid of gradient disappearance in deeper layers of network, mix superficial nodes’ expression with deeper layers, and avoid the insufficient express ability in deeper layers. Principal component analysis(PCA) was adopted to extract different features for classification. According to the experimental data of this method and from the comparison results, the proposed method of rolling bearing fault classification reached 97.02% of correct rate, suggesting a better performance than other algorithms.

Self-Encoded Multiple Access Multiuser Convolutional Codes in Uplink and Downlink Cellular Systems

Self-encoded spread spectrum eliminates the need for traditional pseudo noise (PN) code generators. In a self-encoded multiple access (SEMA) system, the number of users is not limited by the number of available sequences, unlike code division multiple access (CDMA) systems that employ PN codes such as m-, Gold or Kassami sequences. SEMA provides a convenient way of supporting multi-rate, multi-level grades of service in multimedia communications and prioritized heterogeneous networking systems. In this paper, we propose multiuser convolutional channel coding in SEMA that provides fewer cross-correlations among users and thereby reducing multiple access interference (MAI). We analyze SEMA multiuser convolutional coding in additive white Gaussian noise (AWGN) channels as well as fading channels. Our analysis includes downlink synchronous system as well as asynchronous system such as uplink mobile-to-base station communication.

基于Encoder-CNN的土壤氮含量光谱预测模型研究

基于光谱的土壤氮含量预测模型泛化能力弱是制约其推广应用的瓶颈。鉴于特征提取及非线性表达能力方面的优势,深度学习模型具有较强的泛化能力。提出一种融合自动编码器和卷积神经网络(Encoder-CNN)的土壤氮含量光谱预测模型,探索模型结构和参数对模型性能的影响。根据以往研究成果和相关性分析,获得180个与氮含量强相关的波长,将其作为Encoder-CNN模型输入,而将土壤氮含量作为模型输出。Encoder-CNN模型利用自动编码器的编码部分进行光谱数据降维,然后输入到卷积神经网络进行土壤氮含量预测。设计2种网络结构,每种网络结构包含2种不同参数设置,共4个模型,用以探索Encoder-CNN土壤氮含量光谱预测模型结构和参数对模型性能的影响。利用公开数据集LUCAS对模型进行训练。按3σ原则对公开数据集LUCAS进行异常值检测与处理,获得20791个数据,其中18711个样本作为训练集,2080个样本作为测试集,对Encoder-CNN模型进行训练。结果表明:对于自动编码器,在相同隐含层数下,最后的隐含层神经元个数为30时,复现效果最优。增加隐含层数,会提升复现效果。增加卷积核数量,特别是尺寸为1×1卷积核,能够提高模型的预测性能与可靠性。增加池化层的网络结构,模型预测精度提升至0.90以上。增加全连接层神经元数量也会提升模型性能。利用自采集的黑龙江黑土实时光谱数据集进行模型迁移,观察模型泛化能力。当模型迭代100次后,在黑龙江数据集上的预测精度即可达到0.90以上;当迭代次数为900时,模型在训练集和测试集上的预测精度可以达到0.98。结果表明,所构建的Encoder-CNN土壤氮含量光谱预测模型具有较好的泛化能力。

Attention-based spatio-temporal graph convolutional network considering external factors for multi-step traffic flow prediction

Traffic flow prediction is an important part of the intelligent transportation system. Accurate multi-step traffic flow prediction plays an important role in improving the operational efficiency of the traffic network. Since traffic flow data has complex spatio-temporal correlation and non-linearity, existing prediction methods are mainly accomplished through a combination of a Graph Convolutional Network (GCN) and a recurrent neural network. The combination strategy has an excellent performance in traffic prediction tasks. However, multi-step prediction error accumulates with the predicted step size. Some scholars use multiple sampling sequences to achieve more accurate prediction results. But it requires high hardware conditions and multiplied training time. Considering the spatiotemporal correlation of traffic flow and influence of external factors, we propose an Attention Based Spatio-Temporal Graph Convolutional Network considering External Factors (ABSTGCN-EF) for multi-step traffic flow prediction. This model models the traffic flow as diffusion on a digraph and extracts the spatial characteristics of traffic flow through GCN. We add meaningful time-slots attention to the encoder-decoder to form an Attention Encoder Network (AEN) to handle temporal correlation. The attention vector is used as a competitive choice to draw the correlation between predicted states and historical states. We considered the impact of three external factors (daytime, weekdays, and traffic accident markers) on the traffic flow prediction tasks. Experiments on two public data sets show that it makes sense to consider external factors. The prediction performance of our ABSTGCN-EF model achieves 7.2%–8.7% higher than the state-of-the-art baselines.

Ensemble of High Performance Structured Binary Convolutional LDPC Codes with Moderate Rates

An algebraic construction methodology is proposed to design binary time-invariant convolutional low-density parity-check(LDPC)codes.Assisted by a proposed partial search algorithm,the polynomialform parity-check matrix of the time-invariant convolutional LDPC code is derived by combining some special codewords of an(n,2,n−1)code.The achieved convolutional LDPC codes possess the characteristics of comparatively large girth and given syndrome former memory.The objective of our design is to enable the time-invariant convolutional LDPC codes the advantages of excellent error performance and fast encoding.In particular,the error performance of the proposed convolutional LDPC code with small constraint length is superior to most existing convolutional LDPC codes.

A New Speech Encoder Based on Dynamic Framing Approach

Latent information is difficult to get from the text in speech synthesis.Studies show that features from speech can get more information to help text encoding.In the field of speech encoding,a lot of work has been conducted on two aspects.The first aspect is to encode speech frame by frame.The second aspect is to encode the whole speech to a vector.But the scale in these aspects is fixed.So,encoding speech with an adjustable scale for more latent information is worthy of investigation.But current alignment approaches only support frame-by-frame encoding and speech-to-vector encoding.It remains a challenge to propose a new alignment approach to support adjustable scale speech encoding.This paper presents the dynamic speech encoder with a new alignment approach in conjunction with frame-by-frame encoding and speech-to-vector encoding.The speech feature fromourmodel achieves three functions.First,the speech feature can reconstruct the origin speech while the length of the speech feature is equal to the text length.Second,our model can get text embedding fromspeech,and the encoded speech feature is similar to the text embedding result.Finally,it can transfer the style of synthesis speech and make it more similar to the given reference speech.

Adaptive Binary Coding for Scene Classification Based on Convolutional Networks

With the rapid development of computer technology,millions of images are produced everyday by different sources.How to efficiently process these images and accurately discern the scene in them becomes an important but tough task.In this paper,we propose a novel supervised learning framework based on proposed adaptive binary coding for scene classification.Specifically,we first extract some high-level features of images under consideration based on available models trained on public datasets.Then,we further design a binary encoding method called one-hot encoding to make the feature representation more efficient.Benefiting from the proposed adaptive binary coding,our method is free of time to train or fine-tune the deep network and can effectively handle different applications.Experimental results on three public datasets,i.e.,UIUC sports event dataset,MIT Indoor dataset,and UC Merced dataset in terms of three different classifiers,demonstrate that our method is superior to the state-of-the-art methods with large margins.