Audiovisual speech recognition based on a deep convolutional neural network

Audiovisual speech recognition is an emerging research topic.Lipreading is the recognition of what someone is saying using visual information,primarily lip movements.In this study,we created a custom dataset for Indian English linguistics and categorized it into three main categories:(1)audio recognition,(2)visual feature extraction,and(3)combined audio and visual recognition.Audio features were extracted using the mel-frequency cepstral coefficient,and classification was performed using a one-dimension convolutional neural network.Visual feature extraction uses Dlib and then classifies visual speech using a long short-term memory type of recurrent neural networks.Finally,integration was performed using a deep convolutional network.The audio speech of Indian English was successfully recognized with accuracies of 93.67%and 91.53%,respectively,using testing data from 200 epochs.The training accuracy for visual speech recognition using the Indian English dataset was 77.48%and the test accuracy was 76.19%using 60 epochs.After integration,the accuracies of audiovisual speech recognition using the Indian English dataset for training and testing were 94.67%and 91.75%,respectively.

Recurrent Convolutional Neural Network MSER-Based Approach for Payable Document Processing

A tremendous amount of vendor invoices is generated in the corporate sector.To automate the manual data entry in payable documents,highly accurate Optical Character Recognition(OCR)is required.This paper proposes an end-to-end OCR system that does both localization and recognition and serves as a single unit to automate payable document processing such as cheques and cash disbursement.For text localization,the maximally stable extremal region is used,which extracts a word or digit chunk from an invoice.This chunk is later passed to the deep learning model,which performs text recognition.The deep learning model utilizes both convolution neural networks and long short-term memory(LSTM).The convolution layer is used for extracting features,which are fed to the LSTM.The model integrates feature extraction,modeling sequence,and transcription into a unified network.It handles the sequences of unconstrained lengths,independent of the character segmentation or horizontal scale normalization.Furthermore,it applies to both the lexicon-free and lexicon-based text recognition,and finally,it produces a comparatively smaller model,which can be implemented in practical applications.The overall superior performance in the experimental evaluation demonstrates the usefulness of the proposed model.The model is thus generic and can be used for other similar recognition scenarios.

Classification of Arrhythmia Based on Convolutional Neural Networks and Encoder-Decoder Model

As a common and high-risk type of disease,heart disease seriously threatens people’s health.At the same time,in the era of the Internet of Thing(IoT),smart medical device has strong practical significance for medical workers and patients because of its ability to assist in the diagnosis of diseases.Therefore,the research of real-time diagnosis and classification algorithms for arrhythmia can help to improve the diagnostic efficiency of diseases.In this paper,we design an automatic arrhythmia classification algorithm model based on Convolutional Neural Network(CNN)and Encoder-Decoder model.The model uses Long Short-Term Memory(LSTM)to consider the influence of time series features on classification results.Simultaneously,it is trained and tested by the MIT-BIH arrhythmia database.Besides,Generative Adversarial Networks(GAN)is adopted as a method of data equalization for solving data imbalance problem.The simulation results show that for the inter-patient arrhythmia classification,the hybrid model combining CNN and Encoder-Decoder model has the best classification accuracy,of which the accuracy can reach 94.05%.Especially,it has a better advantage for the classification effect of supraventricular ectopic beats(class S)and fusion beats(class F).

基于Convolutional-LSTM的蛋白质亚细胞定位研究

蛋白质亚细胞位置预测研究是目前蛋白质组学和生物信息学研究的重点问题之一。蛋白质的亚细胞定位决定了它的生物学功能,故研究亚细胞定位对了解蛋白质功能非常重要。由于蛋白质结构的序列性,考虑使用序列模型来进行亚细胞定位研究。尝试使用卷积神经网络(convolutional neural network,CNN)、长短期记忆神经网络(long short-term memory,LSTM)两种模型挖掘氨基酸序列所包含的信息,从而进行亚细胞定位的预测。随后构建了基于卷积的长短期记忆网络(Convolutional-LSTM)的集成模型进行亚细胞定位。首先通过卷积神经网络对蛋白质数据进行特征抽取,随后进行特征组合,并将其送入长短期记忆神经网络进行特征表征学习,得到亚细胞定位结果。使用该模型能达到0.816 5的分类准确率,比传统方法有明显提升。

Dynamic Hand Gesture Recognition Based on Short-Term Sampling Neural Networks

Hand gestures are a natural way for human-robot interaction.Vision based dynamic hand gesture recognition has become a hot research topic due to its various applications.This paper presents a novel deep learning network for hand gesture recognition.The network integrates several well-proved modules together to learn both short-term and long-term features from video inputs and meanwhile avoid intensive computation.To learn short-term features,each video input is segmented into a fixed number of frame groups.A frame is randomly selected from each group and represented as an RGB image as well as an optical flow snapshot.These two entities are fused and fed into a convolutional neural network(Conv Net)for feature extraction.The Conv Nets for all groups share parameters.To learn longterm features,outputs from all Conv Nets are fed into a long short-term memory(LSTM)network,by which a final classification result is predicted.The new model has been tested with two popular hand gesture datasets,namely the Jester dataset and Nvidia dataset.Comparing with other models,our model produced very competitive results.The robustness of the new model has also been proved with an augmented dataset with enhanced diversity of hand gestures.

Leucogranite mapping via convolutional recurrent neural networks and geochemical survey data in the Himalayan orogen

Geochemical survey data analysis is recognized as an implemented and feasible way for lithological mapping to assist mineral exploration.With respect to available approaches,recent methodological advances have focused on deep learning algorithms which provide access to learn and extract information directly from geochemical survey data through multi-level networks and outputting end-to-end classification.Accordingly,this study developed a lithological mapping framework with the joint application of a convolutional neural network(CNN)and a long short-term memory(LSTM).The CNN-LSTM model is dominant in correlation extraction from CNN layers and coupling interaction learning from LSTM layers.This hybrid approach was demonstrated by mapping leucogranites in the Himalayan orogen based on stream sediment geochemical survey data,where the targeted leucogranite was expected to be potential resources of rare metals such as Li,Be,and W mineralization.Three comparative case studies were carried out from both visual and quantitative perspectives to illustrate the superiority of the proposed model.A guided spatial distribution map of leucogranites in the Himalayan orogen,divided into high-,moderate-,and low-potential areas,was delineated by the success rate curve,which further improves the efficiency for identifying unmapped leucogranites through geological mapping.In light of these results,this study provides an alternative solution for lithologic mapping using geochemical survey data at a regional scale and reduces the risk for decision making associated with mineral exploration.

基于注意力机制的CNN-BiLSTM的IGBT剩余使用寿命预测

针对绝缘栅双极型晶体管(IGBT)可靠性问题,提出了一种融合卷积神经网络(CNN)、双向长短期记忆(BiLSTM)网络和注意力机制的剩余使用寿命(RUL)预测模型,可用于IGBT的寿命预测。模型中使用CNN提取特征参数,BiLSTM提取时序信息,注意力机制加权处理特征参数。使用IGBT加速老化数据集对提出的模型进行验证。结果表明,对比自回归差分移动平均(ARIMA)、长短期记忆(LSTM)、多层LSTM(Multi-LSTM)、 BiLSTM预测模型,在均方根误差和决定系数等评价指标方面该模型的性能最优。验证了提出的寿命预测模型对IGBT失效预测是有效的。

基于多源信息融合和WOA-CNN-LSTM的外脚手架隐患分类预警研究

面对施工现场外脚手架隐患信息的多样性,传统的基于传感器监测的单一信号预警研究存在容错力不佳、含有信息有限等问题。针对施工现场外脚手架“图像+监测”数据,提出一种基于数据层和特征层信息融合的脚手架隐患分类预警方法。首先,利用Revit三维建模软件建立外脚手架实体模型,对不同初始隐患下的外脚手架进行有限元分析,划分隐患预警等级;其次,利用无迹卡尔曼滤波算法(Unscented Kalman Filter,UKF)及卷积长短时记忆网络(Convolutional Neural Network-Long Short Term Memory Network,CNN-LSTM)实现脚手架同类信息数据层融合及异类信息特征层融合;最后,通过实时收集西安市某在建项目落地式双排扣件式钢管脚手架隐患信息,对其进行分类预警,并使用鲸鱼优化算法(Whale Optimization Algorithm,WOA)对CNN-LSTM网络进行参数优化,发现隐藏节点个数为30、学习率为0.0072、正则化系数为1×10^(-4)时分类效果最佳,优化后预警精度达到了91.4526%。通过可视化WOA-CNN-LSTM、CNN-LSTM、CNN-SVM(Support Vector Machine,支持向量机)及CNN-GRU(Gate Recurrent Unit,门控循环单元)分类预警结果,证实了优化后的CNN-LSTM网络在脚手架分类预警方面的优越性。

GNSS拒止时基于并行CNN-BiLSTM回归和残差补偿的UAV导航误差校正方法

全球导航卫星系统(GNSS)拒止时,GNSS/惯性导航系统(INS)组合导航系统的性能严重下降,导致无人机集群导航误差快速发散.目前,利用神经网络预测位置与速度代替GNSS导航信息可校正无人机INS误差,但该方法仍存在定位误差较高且在轨迹突变时预测精度急剧下降的问题.因此,提出了一种基于卷积-双向长短时记忆网络联合残差补偿的位置与速度预测方法,用于提高位置与速度预测精度.首先,针对GNSS拒止后GNSS/INS组合导航系统定位误差较高的问题,提出卷积神经网络(CNN)与双向长短时记忆网络(BiLSTM)的融合模型,该模型可建立惯性测量单元(IMU)动力学测量数据与GNSS导航信息之间的关系,实现较准确的位置和速度预测.其次,针对轨迹突变时预测效果急剧下降的问题,提出并行CNNBiLSTM回归架构,在预测位置与速度的同时,挖掘IMU动力学测量数据、预测值与预测残差之间的关系,预测并补偿预测残差,增强模型在轨迹突变时的预测精度.仿真结果表明,所提模型在预测准确性、有效性和稳定性方面都优于CNN-LSTM、LSTM网络模型.

基于双流CNN-BiLSTM的毫米波雷达人体动作识别方法

目前基于雷达的人体动作识别方法,大多是先对人体动作的回波信号进行多维快速傅里叶变换(FFT)得到距离、多普勒和角度等信息,构造各种数据谱图后再输入到神经网络中进行分类识别,数据预处理过程较为复杂。提出了一种双流卷积神经网络(CNN)与双向长短时记忆网络(BiLSTM)串联的毫米波雷达人体动作识别方法。首先对原始的雷达回波信号复数采样数据(I/Q)进行帧差处理,以消除静态干扰,并将其转换为幅度/相位(A/P)的数据格式;然后将帧差后的I/Q和A/P数据分别输入单流的CNN-BiLSTM网络,提取人体动作的空间和时间特征,最后进行双流网络的融合以增强特征的交互性,提高识别准确率。实验结果表明,该方法数据预处理简单,并充分利用了动作数据的帧间相关性,模型收敛快,识别准确率可以达到99%,是一种快速有效的人体动作识别方法。

基于CNN-LSTM和卷复制方法的高可用系统设计方法

针对单机服务器存在的单点故障问题,以及主备双机中存在的逻辑故障导致数据丢失的问题,设计了一种基于卷积和长短期记忆神经网络(CNN-LSTM)和卷复制方法的HA(High Availability)系统。系统至少包含两个节点,一个主节点以及一个或多个备用节点,主节点和备节点之间支持主备切换。每个服务器节点上包含4个模块,分别是负责接收配置信息与读写请求的代理模块;进行磁盘读写操作和重定向读写的磁盘I/O(输入输出)模块;负责主备节点间备份快照、映射表、数据块复制的卷复制模块以及基于CNN-LSTM进行状态检测的高可用模块。实验表明,该系统不仅可以解决单点故障问题,也可以解决主备双机集群中无法解决的逻辑错误问题;同时基于CNN-LSTM方法,自动针对服务器的运行健康状态进行分析和预测,可以根据预测结果自动通知管理员进行处理或自动进行主备切换。

组合模型对管道腐蚀速率预测的效能研究--基于注意力机制增强的CNN与LSTM模型

为评估卷积神经网络(Convolutional Neural Network,CNN)、长短期记忆(Long Short-Term Memory,LSTM)网络及结合的CNN-LSTM模型在管道腐蚀速率预测中的性能表现,特别引入注意力机制,以期提高模型对关键特征的捕捉能力和预测的准确性。分析影响管道腐蚀速率的环境因素作为模型输入,并通过注意力机制优化特征表示。结果表明,结合注意力机制的CNN-LSTM模型在准确性和可靠性上超越了单独的CNN或LSTM模型。这一结果不仅展示了深度学习模型通过技术增强了处理复杂数据的能力,也为实际工业应用中的时间序列预测提供了新的视角,同时证实了利用深度学习技术对管道腐蚀速率进行精确预测的可行性和有效性。

SBAS-InSAR技术融合CNN-LSTM模型的矿区开采沉陷监测与预测

针对传统矿区开采沉陷监测方法耗费人力财力和预测预警模型较少的问题,研究提出一种基于短基线集合成孔径雷达干涉测量(Small Baseline Subset-Interferometry Synthetic Aperture Radar,SBAS-InSAR)技术和卷积神经网络(Convolutional Neural Networks,CNN)与长短期记忆网络(Long Short-Term Memory,LSTM)相结合的矿区开采沉陷监测预测方法。首先,利用SBAS-InSAR技术对建新煤矿进行矿区开采沉陷监测,获取了该矿区的年平均沉降速率和累计沉降值。用GNSS监测数据与SBAS-InSAR结果进行对比验证,其拟合效果较好。其次,在此基础上利用CNN-LSTM模型预测后6期沉降数据,其结果与CNN和LSTM预测结果进行对比。研究显示,CNN-LSTM模型的平均绝对误差(S_(MAE))和均方根误差(S_(RMSE))比单一的CNN和LSTM分别至少降低了44.8%和40.6%,其决定系数均高于98%。最后,进一步预测前6期和中6期沉降数据,验证了CNN-LSTM预测模型在时间上的一致性。因此,SBAS-InSAR融合CNN-LSTM模型在类似矿山开采沉陷监测和预测中有较好的应用前景。

融合CNN与BiLSTM模型的短期电能负荷预测

针对卷积神经网络(CNN)在捕捉预测序列间历史相关性方面的不足以及在变量复杂情况下出现的无法精准提取预测关键信息的问题,提出一种将双向长短期记忆网络(BiLSTM)与卷积神经网络结合的CNN-BiLSTM模型.首先,采用数据预处理方法保证数据的正确性和完整性,并对数据进行分析以探究多变量之间的相关性;其次,通过CNN与L1正则化对多维输入特征进行特征筛选,选取与预测相关的重要性特征向量;最后,使用BiLSTM对CNN输出的关键特征信息进行保存,形成向量与预测序列,并通过分析时序特征的潜在特点,提取用户的内在消费模式.实验比较了该模型与其他时序模型在不同时间分辨率下的预测效果,实验结果表明,CNN-BiLSTM模型在不同的回望时间间隔下表现出了最佳的预测性能,能够实现更好的短期负荷预测.

基于CNN-BiLSTM的油田注水流量预测

针对深度学习中的RNN(Recurrent Neural Networks)常用于时间序列预测,但其存在难以对历史序列进行特征提取、以及无法突出关键信息的影响且时间序列过长时早期信息易丢失等问题,提出一种基于双重注意力机制CNN(Convolutional Neural Networks)-BiLSTM(Bi-directional Long Short-Term Memory)的油田注水流量预测方法。该方法以油田历史注水数据为输入,利用CNN层提取历史注水数据特征,并引入特征注意力机制层,通过计算权重值的方式为特征赋予相应权重,使关键特征更容易得到较大权重,进而对预测结果产生影响;BiLSTM层对数据进行时序建模,并引入时间步注意力机制,通过选取关键时间步并突出该时间步的隐藏状态表达,使早期隐藏状态不会随时间消失,能提升模型对长时间序列的预测效果,最后完成流量预测。以公开数据集和中国南部某地区油田注水数据为算例,并与MLP(Multilayer Perceptron)、GRU(Gate Recurrent Unit)、LSTM(Long Short-Term Memory)、BiLSTM,CNN进行对比,证明该方法在油田注水流量预测中精度更高,可帮助油田制定生产计划、减少资源浪费以及提高注采率,具有一定的实际工程应用价值。

基于BERT+CNN_BiLSTM的列控车载设备故障诊断

列控车载设备作为列车运行控制系统核心设备,在高速列车运行过程中发挥着重要作用。目前,其故障诊断仅依赖于现场作业人员经验,诊断效率相对较低。为了实现列控车载设备故障自动诊断并提高诊断效率,提出了BERT+CNN_BiLSTM故障诊断模型。首先,使用来自变换器的双向编码器表征量(Bidirectional encoder representations from transformers,BERT)模型将应用事件日志(Application event log,AElog)转换为计算机能够识别的可以挖掘语义信息的文本向量表示。其次,分别利用卷积神经网络(Convolutional neural network,CNN)和双向长短时记忆网络(Bidirectional long short-term memory,BiLSTM)提取故障特征并进行组合,从而增强空间和时序能力。最后,利用Softmax实现列控车载设备的故障分类与诊断。实验中,选取一列实际运行的列车为研究对象,以运行过程中产生的AElog日志作为实验数据来验证BERT+CNN_BiLSTM模型的性能。与传统机器学习算法、BERT+BiLSTM模型和BERT+CNN模型相比,BERT+CNN_BiLSTM模型的准确率、召回率和F1分别为92.27%、91.03%和91.64%,表明该模型在高速列车控制系统故障诊断中性能优良。

基于CNN-ATT-ConvLSTM的行人属性识别

针对现有行人属性识别方法忽视行人属性的互相关性和空间信息导致识别性能较低的问题,将任务视为时空序列多标签图像分类问题,提出基于卷积神经网络(CNN)和卷积长短期记忆网络(ConvLSTM)并融合通道注意力机制的模型。用CNN和通道注意力提取行人属性的显著性和相关性视觉特征;用ConvLSTM进一步提取视觉特征的空间信息和属性相关性;以优化序列对行人属性进行预测。在两个常用行人属性数据集PETA和RAP上进行大量实验,取得了最佳性能,证明了该方法的优越性和有效性。

A hybrid deep neural network based on multi-time window convolutional bidirectional LSTM for civil aircraft APU hazard identification

Safety is one of the important topics in the field of civil aviation. Auxiliary Power Unit(APU) is one of important components in aircraft, which provides electrical power and compressed air for aircraft. The hazards in APU are prone to cause economic losses and even casualties. So,actively identifying the hazards in APU before an accident occurs is necessary. In this paper, a Hybrid Deep Neural Network(HDNN) based on multi-time window convolutional neural network-Bidirectional Long Short-Term Memory(CNN-Bi LSTM) neural network is proposed for active hazard identification of APU in civil aircraft. In order to identify the risks caused by different types of failures, the proposed HDNN simultaneously integrates three CNN-Bi LSTM basic models with different time window sizes in parallel by using a fully connected neural network. The CNN-Bi LSTM basic model can automatically extract features representing the system state from the input data and learn the time information of irregular trends in the time series data. Nine benchmark models are compared with the proposed HDNN. The comparison results show that the proposed HDNN has the highest identification accuracy. The HDNN has the most stable identification performance for data with imbalanced samples.

基于注意力机制和CNN-LSTM融合模型的锂电池SOC预测

为提高锂电池荷电状态SOC(state-of-charge)预测精度,提出1种基于注意力机制和卷积神经网络-长短时记忆CNN-LSTM(convolution neural network-long short-term memory)融合模型的锂电池荷电状态预测方法。该模型采用一维CNN和LSTM神经网络学习得到SOC与锂电池放电数据的非线性关系,以及SOC序列存在的长期依赖性。同时,该模型采用“多对一”的结构,将当前时刻的锂电池SOC与多个历史时刻的放电数据建立映射关系,并通过注意力机制关注到对当前时刻SOC影响较大的历史放电数据,进一步提升SOC的预测准确度。动态工况下的锂电池SOC预测实验表明,该方法在不同温度条件下的平均预测误差为0.89%,与SVM、GRU和XGBoost相比,分别降低了81.2%、66.7%和56.5%,且优于未融合注意力机制的LSTM和CNN-LSTM,具有较高的预测精度和应用价值。

基于WT-CNN-BiLSTM模型的日前光伏功率预测

光伏功率的准确预测对于电网的安全稳定和经济运行具有重大意义。为此,提出了一种日前光伏功率预测方法,利用小波变换(wavelet transform,WT)将数值天气预报数据(numerical weather prediction,NWP)和光伏功率数据分解为具有时间信息的频率数据,消除数据信息中随机性和波动性对预测精度的影响,利用卷积神经网络(convolutional neural network,CNN)模型深度挖掘输入数据的季节性特征和空间关联特性,利用双向长短期记忆网络(bi-directional long-short term memory,BiLSTM)模型获取输入数据序列的时间相关性,构建基于WT-CNN-BiLSTM的日前光伏功率预测模型。以某一光伏电站为计算对象,在不同季节和气候条件下对比分析WT-CNN-BiLSTM模型、CNN-BiLSTM模型、LSTM(long-short term memory)模型、GRU(gated recurrent unit)模型以及PSO-BP(particle swarm optimization-back propagation)模型的预测结果,计算结果表明WT-CNN-BiLSTM模型的预测精度高于其他模型的预测精度。