Speech Separation Algorithm Using Gated Recurrent Network Based on Microphone Array

Speech separation is an active research topic that plays an important role in numerous applications,such as speaker recognition,hearing pros-thesis,and autonomous robots.Many algorithms have been put forward to improve separation performance.However,speech separation in reverberant noisy environment is still a challenging task.To address this,a novel speech separation algorithm using gate recurrent unit(GRU)network based on microphone array has been proposed in this paper.The main aim of the proposed algorithm is to improve the separation performance and reduce the computational cost.The proposed algorithm extracts the sub-band steered response power-phase transform(SRP-PHAT)weighted by gammatone filter as the speech separation feature due to its discriminative and robust spatial position in formation.Since the GRU net work has the advantage of processing time series data with faster training speed and fewer training parameters,the GRU model is adopted to process the separation featuresof several sequential frames in the same sub-band to estimate the ideal Ratio Masking(IRM).The proposed algorithm decomposes the mixture signals into time-frequency(TF)units using gammatone filter bank in the frequency domain,and the target speech is reconstructed in the frequency domain by masking the mixture signal according to the estimated IRM.The operations of decomposing the mixture signal and reconstructing the target signal are completed in the frequency domain which can reduce the total computational cost.Experimental results demonstrate that the proposed algorithm realizes omnidirectional speech sep-aration in noisy and reverberant environments,provides good performance in terms of speech quality and intelligibility,and has the generalization capacity to reverberate.

Radar Quantitative Precipitation Estimation Based on the Gated Recurrent Unit Neural Network and Echo-Top Data

The Gated Recurrent Unit(GRU) neural network has great potential in estimating and predicting a variable. In addition to radar reflectivity(Z), radar echo-top height(ET) is also a good indicator of rainfall rate(R). In this study, we propose a new method, GRU_Z-ET, by introducing Z and ET as two independent variables into the GRU neural network to conduct the quantitative single-polarization radar precipitation estimation. The performance of GRU_Z-ET is compared with that of the other three methods in three heavy rainfall cases in China during 2018, namely, the traditional Z-R relationship(Z=300R1.4), the optimal Z-R relationship(Z=79R1.68) and the GRU neural network with only Z as the independent input variable(GRU_Z). The results indicate that the GRU_Z-ET performs the best, while the traditional Z-R relationship performs the worst. The performances of the rest two methods are similar.To further evaluate the performance of the GRU_Z-ET, 200 rainfall events with 21882 total samples during May–July of 2018 are used for statistical analysis. Results demonstrate that the spatial correlation coefficients, threat scores and probability of detection between the observed and estimated precipitation are the largest for the GRU_Z-ET and the smallest for the traditional Z-R relationship, and the root mean square error is just the opposite. In addition, these statistics of GRU_Z are similar to those of optimal Z-R relationship. Thus, it can be concluded that the performance of the GRU_ZET is the best in the four methods for the quantitative precipitation estimation.

A HybridManufacturing ProcessMonitoringMethod Using Stacked Gated Recurrent Unit and Random Forest

This study proposed a new real-time manufacturing process monitoring method to monitor and detect process shifts in manufacturing operations.Since real-time production process monitoring is critical in today’s smart manufacturing.The more robust the monitoring model,the more reliable a process is to be under control.In the past,many researchers have developed real-time monitoring methods to detect process shifts early.However,thesemethods have limitations in detecting process shifts as quickly as possible and handling various data volumes and varieties.In this paper,a robust monitoring model combining Gated Recurrent Unit(GRU)and Random Forest(RF)with Real-Time Contrast(RTC)called GRU-RF-RTC was proposed to detect process shifts rapidly.The effectiveness of the proposed GRU-RF-RTC model is first evaluated using multivariate normal and nonnormal distribution datasets.Then,to prove the applicability of the proposed model in a realmanufacturing setting,the model was evaluated using real-world normal and non-normal problems.The results demonstrate that the proposed GRU-RF-RTC outperforms other methods in detecting process shifts quickly with the lowest average out-of-control run length(ARL1)in all synthesis and real-world problems under normal and non-normal cases.The experiment results on real-world problems highlight the significance of the proposed GRU-RF-RTC model in modern manufacturing process monitoring applications.The result reveals that the proposed method improves the shift detection capability by 42.14%in normal and 43.64%in gamma distribution problems.

Stacking Ensemble Learning-Based Convolutional Gated Recurrent Neural Network for Diabetes Miletus

Diabetes mellitus is a metabolic disease in which blood glucose levels rise as a result of pancreatic insulin production failure.It causes hyperglycemia and chronic multiorgan dysfunction,including blindness,renal failure,and cardi-ovascular disease,if left untreated.One of the essential checks that are needed to be performed frequently in Type 1 Diabetes Mellitus is a blood test,this procedure involves extracting blood quite frequently,which leads to subject discomfort increasing the possibility of infection when the procedure is often recurring.Exist-ing methods used for diabetes classification have less classification accuracy and suffer from vanishing gradient problems,to overcome these issues,we proposed stacking ensemble learning-based convolutional gated recurrent neural network(CGRNN)Metamodel algorithm.Our proposed method initially performs outlier detection to remove outlier data,using the Gaussian distribution method,and the Box-cox method is used to correctly order the dataset.After the outliers’detec-tion,the missing values are replaced by the data’s mean rather than their elimina-tion.In the stacking ensemble base model,multiple machine learning algorithms like Naïve Bayes,Bagging with random forest,and Adaboost Decision tree have been employed.CGRNN Meta model uses two hidden layers Long-Short-Time Memory(LSTM)and Gated Recurrent Unit(GRU)to calculate the weight matrix for diabetes prediction.Finally,the calculated weight matrix is passed to the soft-max function in the output layer to produce the diabetes prediction results.By using LSTM-based CG-RNN,the mean square error(MSE)value is 0.016 and the obtained accuracy is 91.33%.

Real-time analysis and prediction of shield cutterhead torque using optimized gated recurrent unit neural network

An accurate prediction of earth pressure balance(EPB)shield moving performance is important to ensure the safety tunnel excavation.A hybrid model is developed based on the particle swarm optimization(PSO)and gated recurrent unit(GRU)neural network.PSO is utilized to assign the optimal hyperparameters of GRU neural network.There are mainly four steps:data collection and processing,hybrid model establishment,model performance evaluation and correlation analysis.The developed model provides an alternative to tackle with time-series data of tunnel project.Apart from that,a novel framework about model application is performed to provide guidelines in practice.A tunnel project is utilized to evaluate the performance of proposed hybrid model.Results indicate that geological and construction variables are significant to the model performance.Correlation analysis shows that construction variables(main thrust and foam liquid volume)display the highest correlation with the cutterhead torque(CHT).This work provides a feasible and applicable alternative way to estimate the performance of shield tunneling.

Adaptive Learning Video Streaming with QoE in Multi-Home Heterogeneous Networks

In recent years,real-time video streaming has grown in popularity.The growing popularity of the Internet of Things(IoT)and other wireless heterogeneous networks mandates that network resources be carefully apportioned among versatile users in order to achieve the best Quality of Experience(QoE)and performance objectives.Most researchers focused on Forward Error Correction(FEC)techniques when attempting to strike a balance between QoE and performance.However,as network capacity increases,the performance degrades,impacting the live visual experience.Recently,Deep Learning(DL)algorithms have been successfully integrated with FEC to stream videos across multiple heterogeneous networks.But these algorithms need to be changed to make the experience better without sacrificing packet loss and delay time.To address the previous challenge,this paper proposes a novel intelligent algorithm that streams video in multi-home heterogeneous networks based on network-centric characteristics.The proposed framework contains modules such as Intelligent Content Extraction Module(ICEM),Channel Status Monitor(CSM),and Adaptive FEC(AFEC).This framework adopts the Cognitive Learning-based Scheduling(CLS)Module,which works on the deep Reinforced Gated Recurrent Networks(RGRN)principle and embeds them along with the FEC to achieve better performances.The complete framework was developed using the Objective Modular Network Testbed in C++(OMNET++),Internet networking(INET),and Python 3.10,with Keras as the front end and Tensorflow 2.10 as the back end.With extensive experimentation,the proposed model outperforms the other existing intelligentmodels in terms of improving the QoE,minimizing the End-to-End Delay(EED),and maintaining the highest accuracy(98%)and a lower Root Mean Square Error(RMSE)value of 0.001.

Ensembling Neural Networks for User’s Indoor Localization Using Magnetic Field Data from Smartphones

Predominantly the localization accuracy of the magnetic field-based localization approaches is severed by two limiting factors:Smartphone heterogeneity and smaller data lengths.The use of multifarioussmartphones cripples the performance of such approaches owing to the variability of the magnetic field data.In the same vein,smaller lengths of magnetic field data decrease the localization accuracy substantially.The current study proposes the use of multiple neural networks like deep neural network(DNN),long short term memory network(LSTM),and gated recurrent unit network(GRN)to perform indoor localization based on the embedded magnetic sensor of the smartphone.A voting scheme is introduced that takes predictions from neural networks into consideration to estimate the current location of the user.Contrary to conventional magnetic field-based localization approaches that rely on the magnetic field data intensity,this study utilizes the normalized magnetic field data for this purpose.Training of neural networks is carried out using Galaxy S8 data while the testing is performed with three devices,i.e.,LG G7,Galaxy S8,and LG Q6.Experiments are performed during different times of the day to analyze the impact of time variability.Results indicate that the proposed approach minimizes the impact of smartphone variability and elevates the localization accuracy.Performance comparison with three approaches reveals that the proposed approach outperforms them in mean,50%,and 75%error even using a lesser amount of magnetic field data than those of other approaches.

STABC-IR:An air target intention recognition method based on bidirectional gated recurrent unit and conditional random field with space-time attention mechanism

The battlefield environment is changing rapidly,and fast and accurate identification of the tactical intention of enemy targets is an important condition for gaining a decision-making advantage.The current Intention Recognition(IR)method for air targets has shortcomings in temporality,interpretability and back-and-forth dependency of intentions.To address these problems,this paper designs a novel air target intention recognition method named STABC-IR,which is based on Bidirectional Gated Recurrent Unit(Bi GRU)and Conditional Random Field(CRF)with Space-Time Attention mechanism(STA).First,the problem of intention recognition of air targets is described and analyzed in detail.Then,a temporal network based on Bi GRU is constructed to achieve the temporal requirement.Subsequently,STA is proposed to focus on the key parts of the features and timing information to meet certain interpretability requirements while strengthening the timing requirements.Finally,an intention transformation network based on CRF is proposed to solve the back-and-forth dependency and transformation problem by jointly modeling the tactical intention of the target at each moment.The experimental results show that the recognition accuracy of the jointly trained STABC-IR model can reach 95.7%,which is higher than other latest intention recognition methods.STABC-IR solves the problem of intention transformation for the first time and considers both temporality and interpretability,which is important for improving the tactical intention recognition capability and has reference value for the construction of command and control auxiliary decision-making system.

Deep Learning Applied to Computational Mechanics:A Comprehensive Review,State of the Art,and the Classics

Three recent breakthroughs due to AI in arts and science serve as motivation:An award winning digital image,protein folding,fast matrix multiplication.Many recent developments in artificial neural networks,particularly deep learning(DL),applied and relevant to computational mechanics(solid,fluids,finite-element technology)are reviewed in detail.Both hybrid and pure machine learning(ML)methods are discussed.Hybrid methods combine traditional PDE discretizations with ML methods either(1)to help model complex nonlinear constitutive relations,(2)to nonlinearly reduce the model order for efficient simulation(turbulence),or(3)to accelerate the simulation by predicting certain components in the traditional integration methods.Here,methods(1)and(2)relied on Long-Short-Term Memory(LSTM)architecture,with method(3)relying on convolutional neural networks.Pure ML methods to solve(nonlinear)PDEs are represented by Physics-Informed Neural network(PINN)methods,which could be combined with attention mechanism to address discontinuous solutions.Both LSTM and attention architectures,together with modern and generalized classic optimizers to include stochasticity for DL networks,are extensively reviewed.Kernel machines,including Gaussian processes,are provided to sufficient depth for more advanced works such as shallow networks with infinite width.Not only addressing experts,readers are assumed familiar with computational mechanics,but not with DL,whose concepts and applications are built up from the basics,aiming at bringing first-time learners quickly to the forefront of research.History and limitations of AI are recounted and discussed,with particular attention at pointing out misstatements or misconceptions of the classics,even in well-known references.Positioning and pointing control of a large-deformable beam is given as an example.

Application of LiDAR Data for Deep Learning Based Near Crash Prediction at Signalized Intersection

Near crash events are often regarded as an excellent surrogate measure for traffic safety research because they include abrupt changes in vehicle kinematics that can lead to deadly accident scenarios. In this paper, we introduced machine learning and deep learning algorithms for predicting near crash events using LiDAR data at a signalized intersection. To predict a near crash occurrence, we used essential vehicle kinematic variables such as lateral and longitudinal velocity, yaw, tracking status of LiDAR, etc. A deep learning hybrid model Convolutional Gated Recurrent Neural Network (CNN + GRU) was introduced, and comparative performances were evaluated with multiple machine learning classification models such as Logistic Regression, K Nearest Neighbor, Decision Tree, Random Forest, Adaptive Boost, and deep learning models like Long Short-Term Memory (LSTM). As vehicle kinematics changes occur after sudden brake, we considered average deceleration and kinematic energy drop as thresholds to identify near crashes after vehicle braking time . We looked at the next 3 seconds of this braking time as our prediction horizon. All models work best in the next 1-second prediction horizon to braking time. The results also reveal that our hybrid model gathers the greatest near crash information while working flawlessly. In comparison to existing models for near crash prediction, our hybrid Convolutional Gated Recurrent Neural Network model has 100% recall, 100% precision, and 100% F1-score: accurately capturing all near crashes. This prediction performance outperforms previous baseline models in forecasting near crash events and provides opportunities for improving traffic safety via Intelligent Transportation Systems (ITS).

Prediction of landslide displacement with dynamic features using intelligent approaches

Landslide displacement prediction can enhance the efficacy of landslide monitoring system,and the prediction of the periodic displacement is particularly challenging.In the previous studies,static regression models(e.g.,support vector machine(SVM))were mostly used for predicting the periodic displacement.These models may have bad performances,when the dynamic features of landslide triggers are incorporated.This paper proposes a method for predicting the landslide displacement in a dynamic manner,based on the gated recurrent unit(GRU)neural network and complete ensemble empirical decomposition with adaptive noise(CEEMDAN).The CEEMDAN is used to decompose the training data,and the GRU is subsequently used for predicting the periodic displacement.Implementation procedures of the proposed method were illustrated by a case study in the Caojiatuo landslide area,and SVM was also adopted for the periodic displacement prediction.This case study shows that the predictors obtained by SVM are inaccurate,as the landslide displacement is in a pronouncedly step-wise manner.By contrast,the accuracy can be significantly improved using the dynamic predictive method.This paper reveals the significance of capturing the dynamic features of the inputs in the training process,when the machine learning models are adopted to predict the landslide displacement.

Deep Scalogram Representations for Acoustic Scene Classification

Spectrogram representations of acoustic scenes have achieved competitive performance for acoustic scene classification. Yet, the spectrogram alone does not take into account a substantial amount of time-frequency information. In this study, we present an approach for exploring the benefits of deep scalogram representations, extracted in segments from an audio stream. The approach presented firstly transforms the segmented acoustic scenes into bump and morse scalograms, as well as spectrograms; secondly, the spectrograms or scalograms are sent into pre-trained convolutional neural networks; thirdly,the features extracted from a subsequent fully connected layer are fed into(bidirectional) gated recurrent neural networks, which are followed by a single highway layer and a softmax layer;finally, predictions from these three systems are fused by a margin sampling value strategy. We then evaluate the proposed approach using the acoustic scene classification data set of 2017 IEEE AASP Challenge on Detection and Classification of Acoustic Scenes and Events(DCASE). On the evaluation set, an accuracy of 64.0 % from bidirectional gated recurrent neural networks is obtained when fusing the spectrogram and the bump scalogram, which is an improvement on the 61.0 % baseline result provided by the DCASE 2017 organisers. This result shows that extracted bump scalograms are capable of improving the classification accuracy,when fusing with a spectrogram-based system.

基于BGRU-CapsNet的情感分析算法研究

提出了一种基于双向门控循环神经网络(bidirectional gated recurrent neural network,BGRU)和胶囊网络(capsule network,CapsNet)的混合神经网络情感分析模型。其目的是对内在的部分-整体关系进行编码,探索语法和句法特征,全面丰富表征。每个句子的语义由BGRU表示,缩短了相互依赖特征之间的距离。设计了基于动态路由的CapsNet来提取更丰富的文本信息,提高了文本的表达能力。实验证明,将BGRU和CapsNet相结合可以提高情感分析的性能。

A computational method for the load spectra of large-scale structures with a data-driven learning algorithm

For complex engineering systems, such as trains, planes, and offshore oil platforms, load spectra are cornerstone of their safety designs and fault diagnoses. We demonstrate in this study that well-orchestrated machine learning modeling, in combination with limited experimental data, can effectively reproduce the high-fidelity, history-dependent load spectra in critical sites of complex engineering systems, such as high-speed trains. To meet the need for in-service monitoring, we propose a segmentation and randomization strategy for long-duration historical data processing to improve the accuracy of our data-driven model for longterm load-time history prediction. Results showed the existence of an optimal length of subsequence, which is associated with the characteristic dissipation time of the dynamic system. Moreover, the data-driven model exhibits an excellent generalization capability to accurately predict the load spectra for different levels of passenger-dedicated lines. In brief, we pave the way, from data preprocessing, hyperparameter selection, to learning strategy, on how to capture the nonlinear responses of such a dynamic system, which may then provide a unifying framework that could enable the synergy of computation and in-field experiments to save orders of magnitude of expenses for the load spectrum monitoring of complex engineering structures in service and prevent catastrophic fatigue and fracture in those solids.