Accurately predicting fluid forces acting on the sur-face of a structure is crucial in engineering design.However,this task becomes particularly challenging in turbulent flow,due to the complex and irregular changes i...Accurately predicting fluid forces acting on the sur-face of a structure is crucial in engineering design.However,this task becomes particularly challenging in turbulent flow,due to the complex and irregular changes in the flow field.In this study,we propose a novel deep learning method,named mapping net-work-coordinated stacked gated recurrent units(MSU),for pre-dicting pressure on a circular cylinder from velocity data.Specifi-cally,our coordinated learning strategy is designed to extract the most critical velocity point for prediction,a process that has not been explored before.In our experiments,MSU extracts one point from a velocity field containing 121 points and utilizes this point to accurately predict 100 pressure points on the cylinder.This method significantly reduces the workload of data measure-ment in practical engineering applications.Our experimental results demonstrate that MSU predictions are highly similar to the real turbulent data in both spatio-temporal and individual aspects.Furthermore,the comparison results show that MSU predicts more precise results,even outperforming models that use all velocity field points.Compared with state-of-the-art methods,MSU has an average improvement of more than 45%in various indicators such as root mean square error(RMSE).Through comprehensive and authoritative physical verification,we estab-lished that MSU’s prediction results closely align with pressure field data obtained in real turbulence fields.This confirmation underscores the considerable potential of MSU for practical applications in real engineering scenarios.The code is available at https://github.com/zhangzm0128/MSU.展开更多
Quantum error correction is a crucial technology for realizing quantum computers.These computers achieve faulttolerant quantum computing by detecting and correcting errors using decoding algorithms.Quantum error corre...Quantum error correction is a crucial technology for realizing quantum computers.These computers achieve faulttolerant quantum computing by detecting and correcting errors using decoding algorithms.Quantum error correction using neural network-based machine learning methods is a promising approach that is adapted to physical systems without the need to build noise models.In this paper,we use a distributed decoding strategy,which effectively alleviates the problem of exponential growth of the training set required for neural networks as the code distance of quantum error-correcting codes increases.Our decoding algorithm is based on renormalization group decoding and recurrent neural network decoder.The recurrent neural network is trained through the ResNet architecture to improve its decoding accuracy.Then we test the decoding performance of our distributed strategy decoder,recurrent neural network decoder,and the classic minimum weight perfect matching(MWPM)decoder for rotated surface codes with different code distances under the circuit noise model,the thresholds of these three decoders are about 0.0052,0.0051,and 0.0049,respectively.Our results demonstrate that the distributed strategy decoder outperforms the other two decoders,achieving approximately a 5%improvement in decoding efficiency compared to the MWPM decoder and approximately a 2%improvement compared to the recurrent neural network decoder.展开更多
This paper focuses on wireless-powered communication systems,which are increasingly relevant in the Internet of Things(IoT)due to their ability to extend the operational lifetime of devices with limited energy.The mai...This paper focuses on wireless-powered communication systems,which are increasingly relevant in the Internet of Things(IoT)due to their ability to extend the operational lifetime of devices with limited energy.The main contribution of the paper is a novel approach to minimize the secrecy outage probability(SOP)in these systems.Minimizing SOP is crucial for maintaining the confidentiality and integrity of data,especially in situations where the transmission of sensitive data is critical.Our proposed method harnesses the power of an improved biogeography-based optimization(IBBO)to effectively train a recurrent neural network(RNN).The proposed IBBO introduces an innovative migration model.The core advantage of IBBO lies in its adeptness at maintaining equilibrium between exploration and exploitation.This is accomplished by integrating tactics such as advancing towards a random habitat,adopting the crossover operator from genetic algorithms(GA),and utilizing the global best(Gbest)operator from particle swarm optimization(PSO)into the IBBO framework.The IBBO demonstrates its efficacy by enabling the RNN to optimize the system parameters,resulting in significant outage probability reduction.Through comprehensive simulations,we showcase the superiority of the IBBO-RNN over existing approaches,highlighting its capability to achieve remarkable gains in SOP minimization.This paper compares nine methods for predicting outage probability in wireless-powered communications.The IBBO-RNN achieved the highest accuracy rate of 98.92%,showing a significant performance improvement.In contrast,the standard RNN recorded lower accuracy rates of 91.27%.The IBBO-RNN maintains lower SOP values across the entire signal-to-noise ratio(SNR)spectrum tested,suggesting that the method is highly effective at optimizing system parameters for improved secrecy even at lower SNRs.展开更多
Tunnel boring machines(TBMs)have been widely utilised in tunnel construction due to their high efficiency and reliability.Accurately predicting TBM performance can improve project time management,cost control,and risk...Tunnel boring machines(TBMs)have been widely utilised in tunnel construction due to their high efficiency and reliability.Accurately predicting TBM performance can improve project time management,cost control,and risk management.This study aims to use deep learning to develop real-time models for predicting the penetration rate(PR).The models are built using data from the Changsha metro project,and their performances are evaluated using unseen data from the Zhengzhou Metro project.In one-step forecast,the predicted penetration rate follows the trend of the measured penetration rate in both training and testing.The autoregressive integrated moving average(ARIMA)model is compared with the recurrent neural network(RNN)model.The results show that univariate models,which only consider historical penetration rate itself,perform better than multivariate models that take into account multiple geological and operational parameters(GEO and OP).Next,an RNN variant combining time series of penetration rate with the last-step geological and operational parameters is developed,and it performs better than other models.A sensitivity analysis shows that the penetration rate is the most important parameter,while other parameters have a smaller impact on time series forecasting.It is also found that smoothed data are easier to predict with high accuracy.Nevertheless,over-simplified data can lose real characteristics in time series.In conclusion,the RNN variant can accurately predict the next-step penetration rate,and data smoothing is crucial in time series forecasting.This study provides practical guidance for TBM performance forecasting in practical engineering.展开更多
In this paper, Hailin City of Heilongjiang Province, China is taken as the research area. As an important city in Heilongjiang Province, China, the sustainable development of its ecological environment is related to t...In this paper, Hailin City of Heilongjiang Province, China is taken as the research area. As an important city in Heilongjiang Province, China, the sustainable development of its ecological environment is related to the opening up, economic prosperity and social stability of Northeast China. In this paper, the remote sensing ecological index (RSEI) of Hailin City in recent 20 years was calculated by using Landsat 5/8/9 series satellite images, and the temporal and spatial changes of the ecological environment in Hailin City were further analyzed and the influencing factors were discussed. From 2003 to 2023, the mean value of RSEI in Hailin City decreased and increased, and the ecological environment decreased slightly as a whole. RSEI declined most significantly from 2003 to 2008, and it increased from 2008 to 2013, decreased from 2013 to 2018, and increased from 2018 to 2023 again, with higher RSEI value in the south and lower RSEI value in the northwest. It is suggested to appropriately increase vegetation coverage in the northwest to improve ecological quality. As a result, the predicted value of Elman dynamic recurrent neural network model is consistent with the change trend of the mean value, and the prediction error converges quickly, which can accurately predict the ecological environment quality in the future study area.展开更多
This work proposes a recorded recurrent twin delayed deep deterministic(RRTD3)policy gradient algorithm to solve the challenge of constructing guidance laws for intercepting endoatmospheric maneuvering missiles with u...This work proposes a recorded recurrent twin delayed deep deterministic(RRTD3)policy gradient algorithm to solve the challenge of constructing guidance laws for intercepting endoatmospheric maneuvering missiles with uncertainties and observation noise.The attack-defense engagement scenario is modeled as a partially observable Markov decision process(POMDP).Given the benefits of recurrent neural networks(RNNs)in processing sequence information,an RNN layer is incorporated into the agent’s policy network to alleviate the bottleneck of traditional deep reinforcement learning methods while dealing with POMDPs.The measurements from the interceptor’s seeker during each guidance cycle are combined into one sequence as the input to the policy network since the detection frequency of an interceptor is usually higher than its guidance frequency.During training,the hidden states of the RNN layer in the policy network are recorded to overcome the partially observable problem that this RNN layer causes inside the agent.The training curves show that the proposed RRTD3 successfully enhances data efficiency,training speed,and training stability.The test results confirm the advantages of the RRTD3-based guidance laws over some conventional guidance laws.展开更多
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). I...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.展开更多
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 ...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.展开更多
Accurate detection of pipeline leakage is essential to maintain the safety of pipeline transportation.Recently,deep learning(DL)has emerged as a promising tool for pipeline leakage detection(PLD).However,most existing...Accurate detection of pipeline leakage is essential to maintain the safety of pipeline transportation.Recently,deep learning(DL)has emerged as a promising tool for pipeline leakage detection(PLD).However,most existing DL methods have difficulty in achieving good performance in identifying leakage types due to the complex time dynamics of pipeline data.On the other hand,the initial parameter selection in the detection model is generally random,which may lead to unstable recognition performance.For this reason,a hybrid DL framework referred to as parameter-optimized recurrent attention network(PRAN)is presented in this paper to improve the accuracy of PLD.First,a parameter-optimized long short-term memory(LSTM)network is introduced to extract effective and robust features,which exploits a particle swarm optimization(PSO)algorithm with cross-entropy fitness function to search for globally optimal parameters.With this framework,the learning representation capability of the model is improved and the convergence rate is accelerated.Moreover,an anomaly-attention mechanism(AM)is proposed to discover class discriminative information by weighting the hidden states,which contributes to amplifying the normalabnormal distinguishable discrepancy,further improving the accuracy of PLD.After that,the proposed PRAN not only implements the adaptive optimization of network parameters,but also enlarges the contribution of normal-abnormal discrepancy,thereby overcoming the drawbacks of instability and poor generalization.Finally,the experimental results demonstrate the effectiveness and superiority of the proposed PRAN for PLD.展开更多
In social data analytics,Virtual Community(VC)detection is a primary challenge in discovering user relationships and enhancing social recommenda-tions.VC formation is used for personal interaction between communities....In social data analytics,Virtual Community(VC)detection is a primary challenge in discovering user relationships and enhancing social recommenda-tions.VC formation is used for personal interaction between communities.But the usual methods didn’t find the Suspicious Behaviour(SB)needed to make a VC.The Generalized Jaccard Suspicious Behavior Similarity-based Recurrent Deep Neural Network Classification and Ranking(GJSBS-RDNNCR)Model addresses these issues.The GJSBS-RDNNCR model comprises four layers for VC formation in Social Networks(SN).In the GJSBS-RDNNCR model,the SN is given as an input at the input layer.After that,the User’s Behaviors(UB)are extracted in the first Hidden Layer(HL),and the Generalized Jaccard Similarity coefficient calculates the similarity value at the second HL based on the SB.In the third HL,the similarity values are examined,and SB tendency is classified using the Activation Function(AF)in the Output Layer(OL).Finally,the ranking process is performed with classified users in SN and their SB.Results analysis is performed with metrics such as Classification Accuracy(CA),Time Complexity(TC),and False Positive Rate(FPR).The experimental setup consid-ers 250 tweet users from the dataset to identify the SBs of users.展开更多
BACKGROUND Recurrent hepatocellular carcinoma(rHCC)is a common outcome after curative treatment.Retreatment for rHCC is recommended,but no guidelines exist.AIM To compare curative treatments such as repeated hepatecto...BACKGROUND Recurrent hepatocellular carcinoma(rHCC)is a common outcome after curative treatment.Retreatment for rHCC is recommended,but no guidelines exist.AIM To compare curative treatments such as repeated hepatectomy(RH),radiofrequency ablation(RFA),transarterial chemoembolization(TACE)and liver transplantation(LT)for patients with rHCC after primary hepatectomy by conducting a network meta-analysis(NMA).METHODS From 2011 to 2021,30 articles involving patients with rHCC after primary liver resection were retrieved for this NMA.The Q test was used to assess heterogeneity among studies,and Egger’s test was used to assess publication bias.The efficacy of rHCC treatment was assessed using disease-free survival(DFS)and overall survival(OS).RESULTS From 30 articles,a total of 17,11,8,and 12 arms of RH,RFA,TACE,and LT subgroups were collected for analysis.Forest plot analysis revealed that the LT subgroup had a better cumulative DFS and 1-year OS than the RH subgroup,with an odds ratio(OR)of 0.96(95%CI:0.31-2.96).However,the RH subgroup had a better 3-year and 5-year OS compared to the LT,RFA,and TACE subgroups.Hierarchic step diagram of different subgroups measured by the Wald test yielded the same results as the forest plot analysis.LT had a better 1-year OS(OR:1.04,95%CI:0.34-03.20),and LT was inferior to RH in 3-year OS(OR:10.61,95%CI:0.21-1.73)and 5-year OS(OR:0.95,95%CI:0.39-2.34).According to the predictive P score evaluation,the LT subgroup had a better DFS,and RH had the best OS.However,meta-regression analysis revealed that LT had a better DFS(P<0.001)as well as 3-year OS(P=0.881)and 5-year OS(P=0.188).The differences in superiority between DFS and OS were due to the different testing methods used.CONCLUSION According to this NMA,RH and LT had better DFS and OS for rHCC than RFA and TACE.However,treatment strategies should be determined by the recurrent tumor characteristics,the patient’s general health status,and the care program at each institution.展开更多
Drug-target interactions prediction(DTIP)remains an important requirement in thefield of drug discovery and human medicine.The identification of interaction among the drug compound and target protein plays an essential ...Drug-target interactions prediction(DTIP)remains an important requirement in thefield of drug discovery and human medicine.The identification of interaction among the drug compound and target protein plays an essential pro-cess in the drug discovery process.It is a lengthier and complex process for pre-dicting the drug target interaction(DTI)utilizing experimental approaches.To resolve these issues,computational intelligence based DTIP techniques were developed to offer an efficient predictive model with low cost.The recently devel-oped deep learning(DL)models can be employed for the design of effective pre-dictive approaches for DTIP.With this motivation,this paper presents a new drug target interaction prediction using optimal recurrent neural network(DTIP-ORNN)technique.The goal of the DTIP-ORNN technique is to predict the DTIs in a semi-supervised way,i.e.,inclusion of both labelled and unlabelled instances.Initially,the DTIP-ORNN technique performs data preparation process and also includes class labelling process,where the target interactions from the database are used to determine thefinal label of the unlabelled instances.Besides,drug-to-drug(D-D)and target-to-target(T-T)interactions are used for the weight initia-tion of the RNN based bidirectional long short term memory(BiLSTM)model which is then utilized to the prediction of DTIs.Since hyperparameters signifi-cantly affect the prediction performance of the BiLSTM technique,the Adam optimizer is used which mainly helps to improve the DTI prediction outcomes.In order to ensure the enhanced predictive outcomes of the DTIP-ORNN techni-que,a series of simulations are implemented on four benchmark datasets.The comparative result analysis shows the promising performance of the DTIP-ORNN method on the recent approaches.展开更多
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 fai...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%.展开更多
An accurate vertical wind speed(WS)data estimation is required to determine the potential for wind farm installation.In general,the vertical extrapolation of WS at different heights must consider different parameters ...An accurate vertical wind speed(WS)data estimation is required to determine the potential for wind farm installation.In general,the vertical extrapolation of WS at different heights must consider different parameters fromdifferent locations,such as wind shear coefficient,roughness length,and atmospheric conditions.The novelty presented in this article is the introduction of two steps optimization for the Recurrent Neural Networks(RNN)model to estimate WS at different heights using measurements from lower heights.The first optimization of the RNN is performed to minimize a differentiable cost function,namely,mean squared error(MSE),using the Broyden-Fletcher-Goldfarb-Shanno algorithm.Secondly,the RNN is optimized to reduce a non-differentiable cost function using simulated annealing(RNN-SA),namely mean absolute error(MAE).Estimation ofWS vertically at 50 m height is done by training RNN-SA with the actualWS data a 10–40 m heights.The estimatedWS at height of 50 m and the measured WS at 10–40 heights are further used to train RNN-SA to obtain WS at 60 m height.This procedure is repeated continuously until theWS is estimated at a height of 180 m.The RNN-SA performance is compared with the standard RNN,Multilayer Perceptron(MLP),Support Vector Machine(SVM),and state of the art methods like convolutional neural networks(CNN)and long short-term memory(LSTM)networks to extrapolate theWS vertically.The estimated values are also compared with realWS dataset acquired using LiDAR and tested using four error metrics namely,mean squared error(MSE),mean absolute percentage error(MAPE),mean bias error(MBE),and coefficient of determination(R2).The numerical experimental results show that the MSE values between the estimated and actualWS at 180mheight for the RNN-SA,RNN,MLP,and SVM methods are found to be 2.09,2.12,2.37,and 2.63,respectively.展开更多
In the data retrieval process of the Data recommendation system,the matching prediction and similarity identification take place a major role in the ontology.In that,there are several methods to improve the retrieving...In the data retrieval process of the Data recommendation system,the matching prediction and similarity identification take place a major role in the ontology.In that,there are several methods to improve the retrieving process with improved accuracy and to reduce the searching time.Since,in the data recommendation system,this type of data searching becomes complex to search for the best matching for given query data and fails in the accuracy of the query recommendation process.To improve the performance of data validation,this paper proposed a novel model of data similarity estimation and clustering method to retrieve the relevant data with the best matching in the big data processing.In this paper advanced model of the Logarithmic Directionality Texture Pattern(LDTP)method with a Metaheuristic Pattern Searching(MPS)system was used to estimate the similarity between the query data in the entire database.The overall work was implemented for the application of the data recommendation process.These are all indexed and grouped as a cluster to form a paged format of database structure which can reduce the computation time while at the searching period.Also,with the help of a neural network,the relevancies of feature attributes in the database are predicted,and the matching index was sorted to provide the recommended data for given query data.This was achieved by using the Distributional Recurrent Neural Network(DRNN).This is an enhanced model of Neural Network technology to find the relevancy based on the correlation factor of the feature set.The training process of the DRNN classifier was carried out by estimating the correlation factor of the attributes of the dataset.These are formed as clusters and paged with proper indexing based on the MPS parameter of similarity metric.The overall performance of the proposed work can be evaluated by varying the size of the training database by 60%,70%,and 80%.The parameters that are considered for performance analysis are Precision,Recall,F1-score and the accuracy of data retrieval,the query recommendation output,and comparison with other state-of-art methods.展开更多
In this paper,a recurrent neural network(RNN)is used to estimate uncertainties and implement feedback control for nonlinear dynamic systems.The neural network approximates the uncertainties related to unmodeled dynami...In this paper,a recurrent neural network(RNN)is used to estimate uncertainties and implement feedback control for nonlinear dynamic systems.The neural network approximates the uncertainties related to unmodeled dynamics,parametric variations,and external disturbances.The RNN has a single hidden layer and uses the tracking error and the output as feedback to estimate the disturbance.The RNN weights are online adapted,and the adaptation laws are developed from the stability analysis of the controlled system with the RNN estimation.The used activation function,at the hidden layer,has an expression that simplifies the adaptation laws from the stability analysis.It is found that the adaptive RNN enhances the tracking performance of the feedback controller at the transient and steady state responses.The proposed RNN based feedback control is applied to a DC–DC converter for current regulation.Simulation and experimental results are provided to show its effectiveness.Compared to the feedforward neural network and the conventional feedback control,the RNN based feedback control provides good tracking performance.展开更多
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 improv...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.展开更多
Knowledge of pore-water pressure(PWP)variation is fundamental for slope stability.A precise prediction of PWP is difficult due to complex physical mechanisms and in situ natural variability.To explore the applicabilit...Knowledge of pore-water pressure(PWP)variation is fundamental for slope stability.A precise prediction of PWP is difficult due to complex physical mechanisms and in situ natural variability.To explore the applicability and advantages of recurrent neural networks(RNNs)on PWP prediction,three variants of RNNs,i.e.,standard RNN,long short-term memory(LSTM)and gated recurrent unit(GRU)are adopted and compared with a traditional static artificial neural network(ANN),i.e.,multi-layer perceptron(MLP).Measurements of rainfall and PWP of representative piezometers from a fully instrumented natural slope in Hong Kong are used to establish the prediction models.The coefficient of determination(R^2)and root mean square error(RMSE)are used for model evaluations.The influence of input time series length on the model performance is investigated.The results reveal that MLP can provide acceptable performance but is not robust.The uncertainty bounds of RMSE of the MLP model range from 0.24 kPa to 1.12 k Pa for the selected two piezometers.The standard RNN can perform better but the robustness is slightly affected when there are significant time lags between PWP changes and rainfall.The GRU and LSTM models can provide more precise and robust predictions than the standard RNN.The effects of the hidden layer structure and the dropout technique are investigated.The single-layer GRU is accurate enough for PWP prediction,whereas a double-layer GRU brings extra time cost with little accuracy improvement.The dropout technique is essential to overfitting prevention and improvement of accuracy.展开更多
This paper proposes a co-evolutionary recurrent neural network (CERNN) for the multi-step-prediction of chaotic time series, it estimates the proper parameters of phase space reconstruction and optimizes the structu...This paper proposes a co-evolutionary recurrent neural network (CERNN) for the multi-step-prediction of chaotic time series, it estimates the proper parameters of phase space reconstruction and optimizes the structure of recurrent neural networks by coevolutionary strategy. The searching space was separated into two subspaces and the individuals are trained in a parallel computational procedure. It can dynamically combine the embedding method with the capability of recurrent neural network to incorporate past experience due to internal recurrence. The effectiveness of CERNN is evaluated by using three benchmark chaotic time series data sets: the Lorenz series, Mackey-Glass series and real-world sun spot series. The simulation results show that CERNN improves the performances of multi-step-prediction of chaotic time series.展开更多
In view of the failure of GNSS signals,this paper proposes an INS/GNSS integrated navigation method based on the recurrent neural network(RNN).This proposed method utilizes the calculation principle of INS and the mem...In view of the failure of GNSS signals,this paper proposes an INS/GNSS integrated navigation method based on the recurrent neural network(RNN).This proposed method utilizes the calculation principle of INS and the memory function of the RNN to estimate the errors of the INS,thereby obtaining a continuous,reliable and high-precision navigation solution.The performance of the proposed method is firstly demonstrated using an INS/GNSS simulation environment.Subsequently,an experimental test on boat is also conducted to validate the performance of the method.The results show a promising application prospect for RNN in the field of positioning for INS/GNSS integrated navigation in the absence of GNSS signal,as it outperforms extreme learning machine(ELM)and EKF by approximately 30%and 60%,respectively.展开更多
基金supported by the Japan Society for the Promotion of Science(JSPS)KAKENHI(JP22H03643)Japan Science and Technology Agency(JST)Support for Pioneering Research Initiated by the Next Generation(SPRING)(JPMJSP2145)+2 种基金JST Through the Establishment of University Fellowships Towards the Creation of Science Technology Innovation(JPMJFS2115)the National Natural Science Foundation of China(52078382)the State Key Laboratory of Disaster Reduction in Civil Engineering(CE19-A-01)。
文摘Accurately predicting fluid forces acting on the sur-face of a structure is crucial in engineering design.However,this task becomes particularly challenging in turbulent flow,due to the complex and irregular changes in the flow field.In this study,we propose a novel deep learning method,named mapping net-work-coordinated stacked gated recurrent units(MSU),for pre-dicting pressure on a circular cylinder from velocity data.Specifi-cally,our coordinated learning strategy is designed to extract the most critical velocity point for prediction,a process that has not been explored before.In our experiments,MSU extracts one point from a velocity field containing 121 points and utilizes this point to accurately predict 100 pressure points on the cylinder.This method significantly reduces the workload of data measure-ment in practical engineering applications.Our experimental results demonstrate that MSU predictions are highly similar to the real turbulent data in both spatio-temporal and individual aspects.Furthermore,the comparison results show that MSU predicts more precise results,even outperforming models that use all velocity field points.Compared with state-of-the-art methods,MSU has an average improvement of more than 45%in various indicators such as root mean square error(RMSE).Through comprehensive and authoritative physical verification,we estab-lished that MSU’s prediction results closely align with pressure field data obtained in real turbulence fields.This confirmation underscores the considerable potential of MSU for practical applications in real engineering scenarios.The code is available at https://github.com/zhangzm0128/MSU.
基金Project supported by Natural Science Foundation of Shandong Province,China (Grant Nos.ZR2021MF049,ZR2022LLZ012,and ZR2021LLZ001)。
文摘Quantum error correction is a crucial technology for realizing quantum computers.These computers achieve faulttolerant quantum computing by detecting and correcting errors using decoding algorithms.Quantum error correction using neural network-based machine learning methods is a promising approach that is adapted to physical systems without the need to build noise models.In this paper,we use a distributed decoding strategy,which effectively alleviates the problem of exponential growth of the training set required for neural networks as the code distance of quantum error-correcting codes increases.Our decoding algorithm is based on renormalization group decoding and recurrent neural network decoder.The recurrent neural network is trained through the ResNet architecture to improve its decoding accuracy.Then we test the decoding performance of our distributed strategy decoder,recurrent neural network decoder,and the classic minimum weight perfect matching(MWPM)decoder for rotated surface codes with different code distances under the circuit noise model,the thresholds of these three decoders are about 0.0052,0.0051,and 0.0049,respectively.Our results demonstrate that the distributed strategy decoder outperforms the other two decoders,achieving approximately a 5%improvement in decoding efficiency compared to the MWPM decoder and approximately a 2%improvement compared to the recurrent neural network decoder.
文摘This paper focuses on wireless-powered communication systems,which are increasingly relevant in the Internet of Things(IoT)due to their ability to extend the operational lifetime of devices with limited energy.The main contribution of the paper is a novel approach to minimize the secrecy outage probability(SOP)in these systems.Minimizing SOP is crucial for maintaining the confidentiality and integrity of data,especially in situations where the transmission of sensitive data is critical.Our proposed method harnesses the power of an improved biogeography-based optimization(IBBO)to effectively train a recurrent neural network(RNN).The proposed IBBO introduces an innovative migration model.The core advantage of IBBO lies in its adeptness at maintaining equilibrium between exploration and exploitation.This is accomplished by integrating tactics such as advancing towards a random habitat,adopting the crossover operator from genetic algorithms(GA),and utilizing the global best(Gbest)operator from particle swarm optimization(PSO)into the IBBO framework.The IBBO demonstrates its efficacy by enabling the RNN to optimize the system parameters,resulting in significant outage probability reduction.Through comprehensive simulations,we showcase the superiority of the IBBO-RNN over existing approaches,highlighting its capability to achieve remarkable gains in SOP minimization.This paper compares nine methods for predicting outage probability in wireless-powered communications.The IBBO-RNN achieved the highest accuracy rate of 98.92%,showing a significant performance improvement.In contrast,the standard RNN recorded lower accuracy rates of 91.27%.The IBBO-RNN maintains lower SOP values across the entire signal-to-noise ratio(SNR)spectrum tested,suggesting that the method is highly effective at optimizing system parameters for improved secrecy even at lower SNRs.
文摘Tunnel boring machines(TBMs)have been widely utilised in tunnel construction due to their high efficiency and reliability.Accurately predicting TBM performance can improve project time management,cost control,and risk management.This study aims to use deep learning to develop real-time models for predicting the penetration rate(PR).The models are built using data from the Changsha metro project,and their performances are evaluated using unseen data from the Zhengzhou Metro project.In one-step forecast,the predicted penetration rate follows the trend of the measured penetration rate in both training and testing.The autoregressive integrated moving average(ARIMA)model is compared with the recurrent neural network(RNN)model.The results show that univariate models,which only consider historical penetration rate itself,perform better than multivariate models that take into account multiple geological and operational parameters(GEO and OP).Next,an RNN variant combining time series of penetration rate with the last-step geological and operational parameters is developed,and it performs better than other models.A sensitivity analysis shows that the penetration rate is the most important parameter,while other parameters have a smaller impact on time series forecasting.It is also found that smoothed data are easier to predict with high accuracy.Nevertheless,over-simplified data can lose real characteristics in time series.In conclusion,the RNN variant can accurately predict the next-step penetration rate,and data smoothing is crucial in time series forecasting.This study provides practical guidance for TBM performance forecasting in practical engineering.
文摘In this paper, Hailin City of Heilongjiang Province, China is taken as the research area. As an important city in Heilongjiang Province, China, the sustainable development of its ecological environment is related to the opening up, economic prosperity and social stability of Northeast China. In this paper, the remote sensing ecological index (RSEI) of Hailin City in recent 20 years was calculated by using Landsat 5/8/9 series satellite images, and the temporal and spatial changes of the ecological environment in Hailin City were further analyzed and the influencing factors were discussed. From 2003 to 2023, the mean value of RSEI in Hailin City decreased and increased, and the ecological environment decreased slightly as a whole. RSEI declined most significantly from 2003 to 2008, and it increased from 2008 to 2013, decreased from 2013 to 2018, and increased from 2018 to 2023 again, with higher RSEI value in the south and lower RSEI value in the northwest. It is suggested to appropriately increase vegetation coverage in the northwest to improve ecological quality. As a result, the predicted value of Elman dynamic recurrent neural network model is consistent with the change trend of the mean value, and the prediction error converges quickly, which can accurately predict the ecological environment quality in the future study area.
基金supported by the National Natural Science Foundation of China(Grant No.12072090)。
文摘This work proposes a recorded recurrent twin delayed deep deterministic(RRTD3)policy gradient algorithm to solve the challenge of constructing guidance laws for intercepting endoatmospheric maneuvering missiles with uncertainties and observation noise.The attack-defense engagement scenario is modeled as a partially observable Markov decision process(POMDP).Given the benefits of recurrent neural networks(RNNs)in processing sequence information,an RNN layer is incorporated into the agent’s policy network to alleviate the bottleneck of traditional deep reinforcement learning methods while dealing with POMDPs.The measurements from the interceptor’s seeker during each guidance cycle are combined into one sequence as the input to the policy network since the detection frequency of an interceptor is usually higher than its guidance frequency.During training,the hidden states of the RNN layer in the policy network are recorded to overcome the partially observable problem that this RNN layer causes inside the agent.The training curves show that the proposed RRTD3 successfully enhances data efficiency,training speed,and training stability.The test results confirm the advantages of the RRTD3-based guidance laws over some conventional guidance laws.
基金jointly supported by the National Science Foundation of China (Grant Nos. 42275007 and 41865003)Jiangxi Provincial Department of science and technology project (Grant No. 20171BBG70004)。
文摘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.
基金support from the National Science and Technology Council of Taiwan(Contract Nos.111-2221 E-011081 and 111-2622-E-011019)the support from Intelligent Manufacturing Innovation Center(IMIC),National Taiwan University of Science and Technology(NTUST),Taipei,Taiwan,which is a Featured Areas Research Center in Higher Education Sprout Project of Ministry of Education(MOE),Taiwan(since 2023)was appreciatedWe also thank Wang Jhan Yang Charitable Trust Fund(Contract No.WJY 2020-HR-01)for its financial support.
文摘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.
基金This work was supported in part by the National Natural Science Foundation of China(U21A2019,61873058),Hainan Province Science and Technology Special Fund of China(ZDYF2022SHFZ105)the Alexander von Humboldt Foundation of Germany.
文摘Accurate detection of pipeline leakage is essential to maintain the safety of pipeline transportation.Recently,deep learning(DL)has emerged as a promising tool for pipeline leakage detection(PLD).However,most existing DL methods have difficulty in achieving good performance in identifying leakage types due to the complex time dynamics of pipeline data.On the other hand,the initial parameter selection in the detection model is generally random,which may lead to unstable recognition performance.For this reason,a hybrid DL framework referred to as parameter-optimized recurrent attention network(PRAN)is presented in this paper to improve the accuracy of PLD.First,a parameter-optimized long short-term memory(LSTM)network is introduced to extract effective and robust features,which exploits a particle swarm optimization(PSO)algorithm with cross-entropy fitness function to search for globally optimal parameters.With this framework,the learning representation capability of the model is improved and the convergence rate is accelerated.Moreover,an anomaly-attention mechanism(AM)is proposed to discover class discriminative information by weighting the hidden states,which contributes to amplifying the normalabnormal distinguishable discrepancy,further improving the accuracy of PLD.After that,the proposed PRAN not only implements the adaptive optimization of network parameters,but also enlarges the contribution of normal-abnormal discrepancy,thereby overcoming the drawbacks of instability and poor generalization.Finally,the experimental results demonstrate the effectiveness and superiority of the proposed PRAN for PLD.
文摘In social data analytics,Virtual Community(VC)detection is a primary challenge in discovering user relationships and enhancing social recommenda-tions.VC formation is used for personal interaction between communities.But the usual methods didn’t find the Suspicious Behaviour(SB)needed to make a VC.The Generalized Jaccard Suspicious Behavior Similarity-based Recurrent Deep Neural Network Classification and Ranking(GJSBS-RDNNCR)Model addresses these issues.The GJSBS-RDNNCR model comprises four layers for VC formation in Social Networks(SN).In the GJSBS-RDNNCR model,the SN is given as an input at the input layer.After that,the User’s Behaviors(UB)are extracted in the first Hidden Layer(HL),and the Generalized Jaccard Similarity coefficient calculates the similarity value at the second HL based on the SB.In the third HL,the similarity values are examined,and SB tendency is classified using the Activation Function(AF)in the Output Layer(OL).Finally,the ranking process is performed with classified users in SN and their SB.Results analysis is performed with metrics such as Classification Accuracy(CA),Time Complexity(TC),and False Positive Rate(FPR).The experimental setup consid-ers 250 tweet users from the dataset to identify the SBs of users.
基金Supported by the Research Fund from E-Da Hospital,No.EDAHS110012.
文摘BACKGROUND Recurrent hepatocellular carcinoma(rHCC)is a common outcome after curative treatment.Retreatment for rHCC is recommended,but no guidelines exist.AIM To compare curative treatments such as repeated hepatectomy(RH),radiofrequency ablation(RFA),transarterial chemoembolization(TACE)and liver transplantation(LT)for patients with rHCC after primary hepatectomy by conducting a network meta-analysis(NMA).METHODS From 2011 to 2021,30 articles involving patients with rHCC after primary liver resection were retrieved for this NMA.The Q test was used to assess heterogeneity among studies,and Egger’s test was used to assess publication bias.The efficacy of rHCC treatment was assessed using disease-free survival(DFS)and overall survival(OS).RESULTS From 30 articles,a total of 17,11,8,and 12 arms of RH,RFA,TACE,and LT subgroups were collected for analysis.Forest plot analysis revealed that the LT subgroup had a better cumulative DFS and 1-year OS than the RH subgroup,with an odds ratio(OR)of 0.96(95%CI:0.31-2.96).However,the RH subgroup had a better 3-year and 5-year OS compared to the LT,RFA,and TACE subgroups.Hierarchic step diagram of different subgroups measured by the Wald test yielded the same results as the forest plot analysis.LT had a better 1-year OS(OR:1.04,95%CI:0.34-03.20),and LT was inferior to RH in 3-year OS(OR:10.61,95%CI:0.21-1.73)and 5-year OS(OR:0.95,95%CI:0.39-2.34).According to the predictive P score evaluation,the LT subgroup had a better DFS,and RH had the best OS.However,meta-regression analysis revealed that LT had a better DFS(P<0.001)as well as 3-year OS(P=0.881)and 5-year OS(P=0.188).The differences in superiority between DFS and OS were due to the different testing methods used.CONCLUSION According to this NMA,RH and LT had better DFS and OS for rHCC than RFA and TACE.However,treatment strategies should be determined by the recurrent tumor characteristics,the patient’s general health status,and the care program at each institution.
文摘Drug-target interactions prediction(DTIP)remains an important requirement in thefield of drug discovery and human medicine.The identification of interaction among the drug compound and target protein plays an essential pro-cess in the drug discovery process.It is a lengthier and complex process for pre-dicting the drug target interaction(DTI)utilizing experimental approaches.To resolve these issues,computational intelligence based DTIP techniques were developed to offer an efficient predictive model with low cost.The recently devel-oped deep learning(DL)models can be employed for the design of effective pre-dictive approaches for DTIP.With this motivation,this paper presents a new drug target interaction prediction using optimal recurrent neural network(DTIP-ORNN)technique.The goal of the DTIP-ORNN technique is to predict the DTIs in a semi-supervised way,i.e.,inclusion of both labelled and unlabelled instances.Initially,the DTIP-ORNN technique performs data preparation process and also includes class labelling process,where the target interactions from the database are used to determine thefinal label of the unlabelled instances.Besides,drug-to-drug(D-D)and target-to-target(T-T)interactions are used for the weight initia-tion of the RNN based bidirectional long short term memory(BiLSTM)model which is then utilized to the prediction of DTIs.Since hyperparameters signifi-cantly affect the prediction performance of the BiLSTM technique,the Adam optimizer is used which mainly helps to improve the DTI prediction outcomes.In order to ensure the enhanced predictive outcomes of the DTIP-ORNN techni-que,a series of simulations are implemented on four benchmark datasets.The comparative result analysis shows the promising performance of the DTIP-ORNN method on the recent approaches.
文摘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%.
文摘An accurate vertical wind speed(WS)data estimation is required to determine the potential for wind farm installation.In general,the vertical extrapolation of WS at different heights must consider different parameters fromdifferent locations,such as wind shear coefficient,roughness length,and atmospheric conditions.The novelty presented in this article is the introduction of two steps optimization for the Recurrent Neural Networks(RNN)model to estimate WS at different heights using measurements from lower heights.The first optimization of the RNN is performed to minimize a differentiable cost function,namely,mean squared error(MSE),using the Broyden-Fletcher-Goldfarb-Shanno algorithm.Secondly,the RNN is optimized to reduce a non-differentiable cost function using simulated annealing(RNN-SA),namely mean absolute error(MAE).Estimation ofWS vertically at 50 m height is done by training RNN-SA with the actualWS data a 10–40 m heights.The estimatedWS at height of 50 m and the measured WS at 10–40 heights are further used to train RNN-SA to obtain WS at 60 m height.This procedure is repeated continuously until theWS is estimated at a height of 180 m.The RNN-SA performance is compared with the standard RNN,Multilayer Perceptron(MLP),Support Vector Machine(SVM),and state of the art methods like convolutional neural networks(CNN)and long short-term memory(LSTM)networks to extrapolate theWS vertically.The estimated values are also compared with realWS dataset acquired using LiDAR and tested using four error metrics namely,mean squared error(MSE),mean absolute percentage error(MAPE),mean bias error(MBE),and coefficient of determination(R2).The numerical experimental results show that the MSE values between the estimated and actualWS at 180mheight for the RNN-SA,RNN,MLP,and SVM methods are found to be 2.09,2.12,2.37,and 2.63,respectively.
文摘In the data retrieval process of the Data recommendation system,the matching prediction and similarity identification take place a major role in the ontology.In that,there are several methods to improve the retrieving process with improved accuracy and to reduce the searching time.Since,in the data recommendation system,this type of data searching becomes complex to search for the best matching for given query data and fails in the accuracy of the query recommendation process.To improve the performance of data validation,this paper proposed a novel model of data similarity estimation and clustering method to retrieve the relevant data with the best matching in the big data processing.In this paper advanced model of the Logarithmic Directionality Texture Pattern(LDTP)method with a Metaheuristic Pattern Searching(MPS)system was used to estimate the similarity between the query data in the entire database.The overall work was implemented for the application of the data recommendation process.These are all indexed and grouped as a cluster to form a paged format of database structure which can reduce the computation time while at the searching period.Also,with the help of a neural network,the relevancies of feature attributes in the database are predicted,and the matching index was sorted to provide the recommended data for given query data.This was achieved by using the Distributional Recurrent Neural Network(DRNN).This is an enhanced model of Neural Network technology to find the relevancy based on the correlation factor of the feature set.The training process of the DRNN classifier was carried out by estimating the correlation factor of the attributes of the dataset.These are formed as clusters and paged with proper indexing based on the MPS parameter of similarity metric.The overall performance of the proposed work can be evaluated by varying the size of the training database by 60%,70%,and 80%.The parameters that are considered for performance analysis are Precision,Recall,F1-score and the accuracy of data retrieval,the query recommendation output,and comparison with other state-of-art methods.
基金supported in part by Khalifa University of Science and Technology (KUST),United Arab Emirates under Award CIRA-2020-013.
文摘In this paper,a recurrent neural network(RNN)is used to estimate uncertainties and implement feedback control for nonlinear dynamic systems.The neural network approximates the uncertainties related to unmodeled dynamics,parametric variations,and external disturbances.The RNN has a single hidden layer and uses the tracking error and the output as feedback to estimate the disturbance.The RNN weights are online adapted,and the adaptation laws are developed from the stability analysis of the controlled system with the RNN estimation.The used activation function,at the hidden layer,has an expression that simplifies the adaptation laws from the stability analysis.It is found that the adaptive RNN enhances the tracking performance of the feedback controller at the transient and steady state responses.The proposed RNN based feedback control is applied to a DC–DC converter for current regulation.Simulation and experimental results are provided to show its effectiveness.Compared to the feedforward neural network and the conventional feedback control,the RNN based feedback control provides good tracking performance.
基金This work is supported by Nanjing Institute of Technology(NIT)fund for Research Startup Projects of Introduced talents under Grant No.YKJ202019Nature Sci-ence Research Project of Higher Education Institutions in Jiangsu Province under Grant No.21KJB510018+1 种基金National Nature Science Foundation of China(NSFC)under Grant No.62001215NIT fund for Doctoral Research Projects under Grant No.ZKJ2020003.
文摘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.
基金supported by the Natural Science Foundation of China(Grant Nos.51979158,51639008,51679135,and 51422905)the Program of Shanghai Academic Research Leader by Science and Technology Commission of Shanghai Municipality(Project No.19XD1421900)。
文摘Knowledge of pore-water pressure(PWP)variation is fundamental for slope stability.A precise prediction of PWP is difficult due to complex physical mechanisms and in situ natural variability.To explore the applicability and advantages of recurrent neural networks(RNNs)on PWP prediction,three variants of RNNs,i.e.,standard RNN,long short-term memory(LSTM)and gated recurrent unit(GRU)are adopted and compared with a traditional static artificial neural network(ANN),i.e.,multi-layer perceptron(MLP).Measurements of rainfall and PWP of representative piezometers from a fully instrumented natural slope in Hong Kong are used to establish the prediction models.The coefficient of determination(R^2)and root mean square error(RMSE)are used for model evaluations.The influence of input time series length on the model performance is investigated.The results reveal that MLP can provide acceptable performance but is not robust.The uncertainty bounds of RMSE of the MLP model range from 0.24 kPa to 1.12 k Pa for the selected two piezometers.The standard RNN can perform better but the robustness is slightly affected when there are significant time lags between PWP changes and rainfall.The GRU and LSTM models can provide more precise and robust predictions than the standard RNN.The effects of the hidden layer structure and the dropout technique are investigated.The single-layer GRU is accurate enough for PWP prediction,whereas a double-layer GRU brings extra time cost with little accuracy improvement.The dropout technique is essential to overfitting prevention and improvement of accuracy.
基金Project supported by the State Key Program of National Natural Science of China (Grant No 30230350)the Natural Science Foundation of Guangdong Province,China (Grant No 07006474)
文摘This paper proposes a co-evolutionary recurrent neural network (CERNN) for the multi-step-prediction of chaotic time series, it estimates the proper parameters of phase space reconstruction and optimizes the structure of recurrent neural networks by coevolutionary strategy. The searching space was separated into two subspaces and the individuals are trained in a parallel computational procedure. It can dynamically combine the embedding method with the capability of recurrent neural network to incorporate past experience due to internal recurrence. The effectiveness of CERNN is evaluated by using three benchmark chaotic time series data sets: the Lorenz series, Mackey-Glass series and real-world sun spot series. The simulation results show that CERNN improves the performances of multi-step-prediction of chaotic time series.
基金supported in part by the National Natural Science Foundation of China(No.41876222)。
文摘In view of the failure of GNSS signals,this paper proposes an INS/GNSS integrated navigation method based on the recurrent neural network(RNN).This proposed method utilizes the calculation principle of INS and the memory function of the RNN to estimate the errors of the INS,thereby obtaining a continuous,reliable and high-precision navigation solution.The performance of the proposed method is firstly demonstrated using an INS/GNSS simulation environment.Subsequently,an experimental test on boat is also conducted to validate the performance of the method.The results show a promising application prospect for RNN in the field of positioning for INS/GNSS integrated navigation in the absence of GNSS signal,as it outperforms extreme learning machine(ELM)and EKF by approximately 30%and 60%,respectively.