Binaural Speech Separation Algorithm Based on Long and Short Time Memory Networks

Speaker separation in complex acoustic environment is one of challenging tasks in speech separation.In practice,speakers are very often unmoving or moving slowly in normal communication.In this case,the spatial features among the consecutive speech frames become highly correlated such that it is helpful for speaker separation by providing additional spatial information.To fully exploit this information,we design a separation system on Recurrent Neural Network(RNN)with long short-term memory(LSTM)which effectively learns the temporal dynamics of spatial features.In detail,a LSTM-based speaker separation algorithm is proposed to extract the spatial features in each time-frequency(TF)unit and form the corresponding feature vector.Then,we treat speaker separation as a supervised learning problem,where a modified ideal ratio mask(IRM)is defined as the training function during LSTM learning.Simulations show that the proposed system achieves attractive separation performance in noisy and reverberant environments.Specifically,during the untrained acoustic test with limited priors,e.g.,unmatched signal to noise ratio(SNR)and reverberation,the proposed LSTM based algorithm can still outperforms the existing DNN based method in the measures of PESQ and STOI.It indicates our method is more robust in untrained conditions.

A Time Series Intrusion Detection Method Based on SSAE,TCN and Bi-LSTM

In the fast-evolving landscape of digital networks,the incidence of network intrusions has escalated alarmingly.Simultaneously,the crucial role of time series data in intrusion detection remains largely underappreciated,with most systems failing to capture the time-bound nuances of network traffic.This leads to compromised detection accuracy and overlooked temporal patterns.Addressing this gap,we introduce a novel SSAE-TCN-BiLSTM(STL)model that integrates time series analysis,significantly enhancing detection capabilities.Our approach reduces feature dimensionalitywith a Stacked Sparse Autoencoder(SSAE)and extracts temporally relevant features through a Temporal Convolutional Network(TCN)and Bidirectional Long Short-term Memory Network(Bi-LSTM).By meticulously adjusting time steps,we underscore the significance of temporal data in bolstering detection accuracy.On the UNSW-NB15 dataset,ourmodel achieved an F1-score of 99.49%,Accuracy of 99.43%,Precision of 99.38%,Recall of 99.60%,and an inference time of 4.24 s.For the CICDS2017 dataset,we recorded an F1-score of 99.53%,Accuracy of 99.62%,Precision of 99.27%,Recall of 99.79%,and an inference time of 5.72 s.These findings not only confirm the STL model’s superior performance but also its operational efficiency,underpinning its significance in real-world cybersecurity scenarios where rapid response is paramount.Our contribution represents a significant advance in cybersecurity,proposing a model that excels in accuracy and adaptability to the dynamic nature of network traffic,setting a new benchmark for intrusion detection systems.

Deep Learning for Financial Time Series Prediction:A State-of-the-Art Review of Standalone and HybridModels

Financial time series prediction,whether for classification or regression,has been a heated research topic over the last decade.While traditional machine learning algorithms have experienced mediocre results,deep learning has largely contributed to the elevation of the prediction performance.Currently,the most up-to-date review of advanced machine learning techniques for financial time series prediction is still lacking,making it challenging for finance domain experts and relevant practitioners to determine which model potentially performs better,what techniques and components are involved,and how themodel can be designed and implemented.This review article provides an overview of techniques,components and frameworks for financial time series prediction,with an emphasis on state-of-the-art deep learning models in the literature from2015 to 2023,including standalonemodels like convolutional neural networks(CNN)that are capable of extracting spatial dependencies within data,and long short-term memory(LSTM)that is designed for handling temporal dependencies;and hybrid models integrating CNN,LSTM,attention mechanism(AM)and other techniques.For illustration and comparison purposes,models proposed in recent studies are mapped to relevant elements of a generalized framework comprised of input,output,feature extraction,prediction,and related processes.Among the state-of-the-artmodels,hybrid models like CNNLSTMand CNN-LSTM-AM in general have been reported superior in performance to stand-alone models like the CNN-only model.Some remaining challenges have been discussed,including non-friendliness for finance domain experts,delayed prediction,domain knowledge negligence,lack of standards,and inability of real-time and highfrequency predictions.The principal contributions of this paper are to provide a one-stop guide for both academia and industry to review,compare and summarize technologies and recent advances in this area,to facilitate smooth and informed implementation,and to highlight future research directions.

Conditional Random Field Tracking Model Based on a Visual Long Short Term Memory Network

In dense pedestrian tracking,frequent object occlusions and close distances between objects cause difficulty when accurately estimating object trajectories.In this study,a conditional random field tracking model is established by using a visual long short term memory network in the three-dimensional(3D)space and the motion estimations jointly performed on object trajectory segments.Object visual field information is added to the long short term memory network to improve the accuracy of the motion related object pair selection and motion estimation.To address the uncertainty of the length and interval of trajectory segments,a multimode long short term memory network is proposed for the object motion estimation.The tracking performance is evaluated using the PETS2009 dataset.The experimental results show that the proposed method achieves better performance than the tracking methods based on the independent motion estimation.

Short-Term Relay Quality Prediction Algorithm Based on Long and Short-Term Memory

The fraction defective of semi-finished products is predicted to optimize the process of relay production lines, by which production quality and productivity are increased, and the costs are decreased. The process parameters of relay production lines are studied based on the long-and-short-term memory network. Then, the Keras deep learning framework is utilized to build up a short-term relay quality prediction algorithm for the semi-finished product. A simulation model is used to study prediction algorithm. The simulation results show that the average prediction absolute error of the fraction is less than 5%. This work displays great application potential in the relay production lines.

State of Health Estimation of Lithium-Ion Batteries Using Support Vector Regression and Long Short-Term Memory

Lithium-ion batteries are the most widely accepted type of battery in the electric vehicle industry because of some of their positive inherent characteristics. However, the safety problems associated with inaccurate estimation and prediction of the state of health of these batteries have attracted wide attention due to the adverse negative effect on vehicle safety. In this paper, both machine and deep learning models were used to estimate the state of health of lithium-ion batteries. The paper introduces the definition of battery health status and its importance in the electric vehicle industry. Based on the data preprocessing and visualization analysis, three features related to actual battery capacity degradation are extracted from the data. Two learning models, SVR and LSTM were employed for the state of health estimation and their respective results are compared in this paper. The mean square error and coefficient of determination were the two metrics for the performance evaluation of the models. The experimental results indicate that both models have high estimation results. However, the metrics indicated that the SVR was the overall best model.

Time Series Forecasting Fusion Network Model Based on Prophet and Improved LSTM

Time series forecasting and analysis are widely used in many fields and application scenarios.Time series historical data reflects the change pattern and trend,which can serve the application and decision in each application scenario to a certain extent.In this paper,we select the time series prediction problem in the atmospheric environment scenario to start the application research.In terms of data support,we obtain the data of nearly 3500 vehicles in some cities in China fromRunwoda Research Institute,focusing on the major pollutant emission data of non-road mobile machinery and high emission vehicles in Beijing and Bozhou,Anhui Province to build the dataset and conduct the time series prediction analysis experiments on them.This paper proposes a P-gLSTNet model,and uses Autoregressive Integrated Moving Average model(ARIMA),long and short-term memory(LSTM),and Prophet to predict and compare the emissions in the future period.The experiments are validated on four public data sets and one self-collected data set,and the mean absolute error(MAE),root mean square error(RMSE),and mean absolute percentage error(MAPE)are selected as the evaluationmetrics.The experimental results show that the proposed P-gLSTNet fusion model predicts less error,outperforms the backbone method,and is more suitable for the prediction of time-series data in this scenario.

Short-TermWind Power Prediction Based on Combinatorial Neural Networks

Wind power volatility not only limits the large-scale grid connection but also poses many challenges to safe grid operation.Accurate wind power prediction can mitigate the adverse effects of wind power volatility on wind power grid connections.For the characteristics of wind power antecedent data and precedent data jointly to determine the prediction accuracy of the prediction model,the short-term prediction of wind power based on a combined neural network is proposed.First,the Bi-directional Long Short Term Memory(BiLSTM)network prediction model is constructed,and the bi-directional nature of the BiLSTM network is used to deeply mine the wind power data information and find the correlation information within the data.Secondly,to avoid the limitation of a single prediction model when the wind power changes abruptly,the Wavelet Transform-Improved Adaptive Genetic Algorithm-Back Propagation(WT-IAGA-BP)neural network based on the combination of the WT-IAGA-BP neural network and BiLSTM network is constructed for the short-term prediction of wind power.Finally,comparing with LSTM,BiLSTM,WT-LSTM,WT-BiLSTM,WT-IAGA-BP,and WT-IAGA-BP&LSTM prediction models,it is verified that the wind power short-term prediction model based on the combination of WT-IAGA-BP neural network and BiLSTM network has higher prediction accuracy.

Long Short-Term Memory Recurrent Neural Network-Based Acoustic Model Using Connectionist Temporal Classification on a Large-Scale Training Corpus

A Long Short-Term Memory(LSTM) Recurrent Neural Network(RNN) has driven tremendous improvements on an acoustic model based on Gaussian Mixture Model(GMM). However, these models based on a hybrid method require a forced aligned Hidden Markov Model(HMM) state sequence obtained from the GMM-based acoustic model. Therefore, it requires a long computation time for training both the GMM-based acoustic model and a deep learning-based acoustic model. In order to solve this problem, an acoustic model using CTC algorithm is proposed. CTC algorithm does not require the GMM-based acoustic model because it does not use the forced aligned HMM state sequence. However, previous works on a LSTM RNN-based acoustic model using CTC used a small-scale training corpus. In this paper, the LSTM RNN-based acoustic model using CTC is trained on a large-scale training corpus and its performance is evaluated. The implemented acoustic model has a performance of 6.18% and 15.01% in terms of Word Error Rate(WER) for clean speech and noisy speech, respectively. This is similar to a performance of the acoustic model based on the hybrid method.

Bitcoin Candlestick Prediction with Deep Neural Networks Based on Real Time Data

Currently,Bitcoin is the world’s most popular cryptocurrency.The price of Bitcoin is extremely volatile,which can be described as high-benefit and high-risk.To minimize the risk involved,a means of more accurately predicting the Bitcoin price is required.Most of the existing studies of Bitcoin prediction are based on historical(i.e.,benchmark)data,without considering the real-time(i.e.,live)data.To mitigate the issue of price volatility and achieve more precise outcomes,this study suggests using historical and real-time data to predict the Bitcoin candlestick—or open,high,low,and close(OHLC)—prices.Seeking a better prediction model,the present study proposes time series-based deep learning models.In particular,two deep learning algorithms were applied,namely,long short-term memory(LSTM)and gated recurrent unit(GRU).Using real-time data,the Bitcoin candlesticks were predicted for three intervals:the next 4 h,the next 12 h,and the next 24 h.The results showed that the best-performing model was the LSTM-based model with the 4-h interval.In particular,this model achieved a stellar performance with a mean absolute percentage error(MAPE)of 0.63,a root mean square error(RMSE)of 0.0009,a mean square error(MSE)of 9e-07,a mean absolute error(MAE)of 0.0005,and an R-squared coefficient(R2)of 0.994.With these results,the proposed prediction model has demonstrated its efficiency over the models proposed in previous studies.The findings of this study have considerable implications in the business field,as the proposed model can assist investors and traders in precisely identifying Bitcoin sales and buying opportunities.

Classification of Short Time Series in Early Parkinson’s Disease With Deep Learning of Fuzzy Recurrence Plots

There are many techniques using sensors and wearable devices for detecting and monitoring patients with Parkinson’s disease(PD).A recent development is the utilization of human interaction with computer keyboards for analyzing and identifying motor signs in the early stages of the disease.Current designs for classification of time series of computer-key hold durations recorded from healthy control and PD subjects require the time series of length to be considerably long.With an attempt to avoid discomfort to participants in performing long physical tasks for data recording,this paper introduces the use of fuzzy recurrence plots of very short time series as input data for the machine training and classification with long short-term memory(LSTM)neural networks.Being an original approach that is able to both significantly increase the feature dimensions and provides the property of deterministic dynamical systems of very short time series for information processing carried out by an LSTM layer architecture,fuzzy recurrence plots provide promising results and outperform the direct input of the time series for the classification of healthy control and early PD subjects.

A Novel MegaBAT Optimized Intelligent Intrusion Detection System in Wireless Sensor Networks

Wireless Sensor Network(WSN),whichfinds as one of the major components of modern electronic and wireless systems.A WSN consists of numerous sensor nodes for the discovery of sensor networks to leverage features like data sensing,data processing,and communication.In thefield of medical health care,these network plays a very vital role in transmitting highly sensitive data from different geographic regions and collecting this information by the respective network.But the fear of different attacks on health care data typically increases day by day.In a very short period,these attacks may cause adversarial effects to the WSN nodes.Furthermore,the existing Intrusion Detection System(IDS)suffers from the drawbacks of limited resources,low detection rate,and high computational overhead and also increases the false alarm rates in detecting the different attacks.Given the above-mentioned problems,this paper proposes the novel MegaBAT optimized Long Short Term Memory(MBOLT)-IDS for WSNs for the effective detection of different attacks.In the proposed framework,hyperpara-meters of deep Long Short-Term Memory(LSTM)were optimized by the meta-heuristic megabat algorithm to obtain a low computational overhead and high performance.The experimentations have been carried out using(Wireless Sensor NetworkDetection System)WSN-DS datasets and performance metrics such as accuracy,recall,precision,specificity,and F1-score are calculated and compared with the other existing intelligent IDS.The proposed framework provides outstanding results in detecting the black hole,gray hole,scheduling,flooding attacks and significantly reduces the time complexity,which makes this system suitable for resource-constraint WSNs.

基于改进麻雀搜索算法优化LSTM的滚动轴承故障诊断

为了对滚动轴承的工作状态及故障类别进行准确的诊断,本文采用长短时记忆(LSTM)神经网络作为分类器对滚动轴承数据集进行分类诊断。首先,从滚动轴承原始运行振动信号中提取时域和频域特征参数,组成具有高维特征参数的数据集;使用核主成分分析(KPCA)方法对高维特征集进行降维处理,选取重要性程度高的特征构成输入特征向量。然后,针对LSTM神经网络在滚动轴承故障诊断中存在的超参数难以确定的问题,提出一种基于自适应t分布策略的麻雀搜索算法优化LSTM神经网络的故障诊断方法(tSSA–LSTM)。最后,使用凯斯西储大学滚动轴承数据中心的数据进行故障诊断精度测试、泛化性能测试及噪声环境下故障诊断性能测试等多个仿真实验,并将本文提出的诊断模型与麻雀搜索算法优化长短时记忆神经网络(SSA–LSTM)、遗传算法优化长短时记忆神经网络(GA–LSTM)、粒子群算法优化长短时记忆神经网络(PSO–LSTM)及传统LSTM诊断模型进行对比。结果表明:tSSA可以更有效地对LSTM的隐含层神经元数量、周期次数、学习率等超参数进行合理优化;所提方法的平均诊断准确率达到98.86%,交叉验证平均诊断结果为98.57%;所提方法在噪声干扰下的故障诊断准确率也优于对比方法。因此,本文提出的tSSA–LSTM模型不仅可以更精准地诊断滚动轴承故障状态,而且具有更强的泛化能力及抗干扰能力,有效地提高了滚动轴承故障诊断的性能。

基于CEEMD-SE的CNN&LSTM-GRU短期风电功率预测

为进一步提升短期风电功率的预测精度,提出了一种基于互补集合经验模态分解-样本熵(complementary ensemble empirical mode decomposition-sample entropy,CEEMD-SE)的卷积神经网络(convolutional neural network,CNN)和长短期记忆-门控循环单元(longshorttermmemory-gatedrecurrentunit,LSTM-GRU)的短期风电功率预测模型。首先,利用互补集合经验模态分解将原始风电功率序列分解为若干本征模态函数(intrinsic mode function,IMF)分量和一个残差(residual,RES)分量,利用样本熵算法将相近的分量进行重构;其次,搭建卷积神经网络和长短期记忆网络的并行网络结构,提取数据的局部特征和时序特征,并将特征融合后输入门控循环单元网络中进行学习预测;最后,通过算例进行验证,结果表明采用该模型后预测精度得到了有效提升,其均方根误差降低了15.06%、平均绝对误差降低了15.22%、决定系数提高了1.91%。

User Station Security Protection Method Based on Random Domain Name Detection and Active Defense

The power monitoring system is the most important production management system in the power industry. As an important part of the power monitoring system, the user station that lacks grid binding will become an important target of network attacks. In order to perceive the network attack events on the user station side in time, a method combining real-time detection and active defense of random domain names on the user station side was proposed. Capsule network (CapsNet) combined with long short-term memory network (LSTM) was used to classify the domain names extracted from the traffic data. When a random domain name is detected, it sent instructions to routers and switched to update their security policies through the remote terminal protocol (Telnet), or shut down the service interfaces of routers and switched to block network attacks. The experimental results showed that the use of CapsNet combined with LSTM classification algorithm can achieve 99.16% accuracy and 98% recall rate in random domain name detection. Through the Telnet protocol, routers and switches can be linked to make active defense without interrupting services.

基于集群辨识和卷积神经网络-双向长短期记忆-时序模式注意力机制的区域级短期负荷预测

为了解决区域级短期电力负荷预测时输入特征过多和负荷时序性较强的问题,提出一种基于集群辨识和卷积神经网络(convolutional neural networks,CNN)-双向长短期记忆网络(bi-directional long short-term memory,BiLSTM)-时序模式注意力机制(temporal pattern attention,TPA)的预测方法。首先,将用电模式和天气作为影响因素,基于二阶聚类算法对区域内的负荷节点进行集群辨识,再从每个集群中挑选代表特征作为深度学习模型的输入,这样既能减少输入特征维度,降低计算复杂度,又能综合考虑预测区域的整体特征,提升预测精度。然后,针对区域电力负荷时序性的特点,用CNN-BiLSTM-TPA模型完成训练和预测,该模型能提取输入数据的双向信息生成隐状态矩阵,并对隐状态矩阵的重要特征加权,从多时间步上捕获双向时序信息用于预测。最后,在美国加利福尼亚州实例上分析验证了所提方法的有效性。

基于ResNet-LSTM的航空发动机性能异常检测方法

为了实现数据驱动的航空发动机性能异常的智能检测,提出了一种基于残差网络(ResNet)-长短期记忆网络(LSTM)的发动机性能异常检测方法。采用发动机性能数据图像化方法,在数据降维的同时,完备保留数据的关联特征和时序特征;以残差单元构建发动机性能异常检测模型,在加深网络结构的同时,消除深层网络梯度消失问题,提高发动机性能图像空间关联特征的提取能力。同时,引入LSTM,提出基于ResNet-LSTM的发动机性能异常检测模型,通过ResNet与LSTM的融合,强化异常检测模型对时序特征的提取,提升发动机性能异常检测的准确率;通过发动机运行数据进行验证。结果表明:在训练集上,该方法的异常检测准确率为94.95%,比基于ResNet18、ResNet34、ResNet50异常检测模型的分别提高10.87%、8.00%、3.23%;在测试集上,该方法的异常检测准确率为92.15%,比基于ResNet18、ResNet34、ResNet50异常检测模型的分别提高11.81%、9.45%、3.78%。

基于奇异谱分析和辛几何模态分解的短期碳排放预测模型

在短时期内对碳排放水平进行评估和规划,对制定精准的减排目标和有效的政策措施可以起到辅助作用。将奇异谱分析分解法(Singular spectrum analysis decomposition,SSAD)和辛几何模态分解(Symplectic geometry mode decomposition,SGMD)组合成新型的二次信号分解法,并应用于每日碳排放量预测。在对原始序列进行二次分解之后,利用快速傅里叶变换对子序列进行重构,并应用偏自相关函数来选择合适的输入变量。最后,利用麻雀搜索算法(Sparrow search algorithm,SSA)对长短期记忆网络(Long short-term memory network,LSTM)进行优化,建立了SSAD-SGMD-SSA-LSTM模型。通过与其他模型进行对比实验,发现SSAD-SGMD二次分解更加适合碳排放时间序列预处理,并且可以进一步提高预测精度。SSAD-SGMD模型与集成经验模态分解和变分模态分解相结合的二次分解模型相比,模型的可决系数R2提高了1.83%,平均绝对百分比误差(Mean absolute percentage error,MAPE)有所降低,均方根误差(Root mean square error,RMSE)降低了43.16%。此外,经过SSA优化后的LSTM模型,R2提高了1.49%,MAPE有所降低,RMSE降低了38.64%。所提出的模型能够有效提升短期碳排放预测的准确性。

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。

基于CNN-LSTM的机床滚动轴承性能退化趋势和寿命预测

滚动轴承作为机床主轴的关键部件,其剩余寿命预测直接决定着整机设备的剩余寿命。若不能及时地预知滚动轴承的健康状态或损伤情况,不仅会影响维修策略的制定,还会造成级联故障,易造成机床灾难性的事故。针对大数据下滚动轴承振动信号的自适应故障特征提取和智能诊断问题,构建卷积神经网络和长短期记忆网络(CNN-LSTM)相结合的寿命预测模型,它可以避免人工参与的影响,实现网络的互补优势。对滚动轴承的退化状态以及剩余寿命进行预测,并与卷积神经网络(CNN)、长短时记忆神经网络(LSTM)进行对比实验。结果表明:所提方法CNN-LSTM有着较高的预测准确度。