In recent years,wearable devices-based Human Activity Recognition(HAR)models have received significant attention.Previously developed HAR models use hand-crafted features to recognize human activities,leading to the e...In recent years,wearable devices-based Human Activity Recognition(HAR)models have received significant attention.Previously developed HAR models use hand-crafted features to recognize human activities,leading to the extraction of basic features.The images captured by wearable sensors contain advanced features,allowing them to be analyzed by deep learning algorithms to enhance the detection and recognition of human actions.Poor lighting and limited sensor capabilities can impact data quality,making the recognition of human actions a challenging task.The unimodal-based HAR approaches are not suitable in a real-time environment.Therefore,an updated HAR model is developed using multiple types of data and an advanced deep-learning approach.Firstly,the required signals and sensor data are accumulated from the standard databases.From these signals,the wave features are retrieved.Then the extracted wave features and sensor data are given as the input to recognize the human activity.An Adaptive Hybrid Deep Attentive Network(AHDAN)is developed by incorporating a“1D Convolutional Neural Network(1DCNN)”with a“Gated Recurrent Unit(GRU)”for the human activity recognition process.Additionally,the Enhanced Archerfish Hunting Optimizer(EAHO)is suggested to fine-tune the network parameters for enhancing the recognition process.An experimental evaluation is performed on various deep learning networks and heuristic algorithms to confirm the effectiveness of the proposed HAR model.The EAHO-based HAR model outperforms traditional deep learning networks with an accuracy of 95.36,95.25 for recall,95.48 for specificity,and 95.47 for precision,respectively.The result proved that the developed model is effective in recognizing human action by taking less time.Additionally,it reduces the computation complexity and overfitting issue through using an optimization approach.展开更多
Research into automatically searching for an optimal neural network(NN)by optimi-sation algorithms is a significant research topic in deep learning and artificial intelligence.However,this is still challenging due to ...Research into automatically searching for an optimal neural network(NN)by optimi-sation algorithms is a significant research topic in deep learning and artificial intelligence.However,this is still challenging due to two issues:Both the hyperparameter and ar-chitecture should be optimised and the optimisation process is computationally expen-sive.To tackle these two issues,this paper focusses on solving the hyperparameter and architecture optimization problem for the NN and proposes a novel light‐weight scale‐adaptive fitness evaluation‐based particle swarm optimisation(SAFE‐PSO)approach.Firstly,the SAFE‐PSO algorithm considers the hyperparameters and architectures together in the optimisation problem and therefore can find their optimal combination for the globally best NN.Secondly,the computational cost can be reduced by using multi‐scale accuracy evaluation methods to evaluate candidates.Thirdly,a stagnation‐based switch strategy is proposed to adaptively switch different evaluation methods to better balance the search performance and computational cost.The SAFE‐PSO algorithm is tested on two widely used datasets:The 10‐category(i.e.,CIFAR10)and the 100−cate-gory(i.e.,CIFAR100).The experimental results show that SAFE‐PSO is very effective and efficient,which can not only find a promising NN automatically but also find a better NN than compared algorithms at the same computational cost.展开更多
Based on high order dynamic neural network, this paper presents the tracking problem for uncertain nonlinear composite system, which contains external disturbance, whose nonlinearities are assumed to be unknown. A smo...Based on high order dynamic neural network, this paper presents the tracking problem for uncertain nonlinear composite system, which contains external disturbance, whose nonlinearities are assumed to be unknown. A smooth controller is designed to guarantee a uniform ultimate boundedness property for the tracking error and all other signals in the dosed loop. Certain measures are utilized to test its performance. No a priori knowledge of an upper bound on the “optimal” weight and modeling error is required; the weights of neural networks are updated on-line. Numerical simulations performed on a simple example illustrate and clarify the approach.展开更多
Cloud computing technology provides flexible,on-demand,and completely controlled computing resources and services are highly desirable.Despite this,with its distributed and dynamic nature and shortcomings in virtualiz...Cloud computing technology provides flexible,on-demand,and completely controlled computing resources and services are highly desirable.Despite this,with its distributed and dynamic nature and shortcomings in virtualization deployment,the cloud environment is exposed to a wide variety of cyber-attacks and security difficulties.The Intrusion Detection System(IDS)is a specialized security tool that network professionals use for the safety and security of the networks against attacks launched from various sources.DDoS attacks are becoming more frequent and powerful,and their attack pathways are continually changing,which requiring the development of new detection methods.Here the purpose of the study is to improve detection accuracy.Feature Selection(FS)is critical.At the same time,the IDS’s computational problem is limited by focusing on the most relevant elements,and its performance and accuracy increase.In this research work,the suggested Adaptive butterfly optimization algorithm(ABOA)framework is used to assess the effectiveness of a reduced feature subset during the feature selection phase,that was motivated by this motive Candidates.Accurate classification is not compromised by using an ABOA technique.The design of Deep Neural Networks(DNN)has simplified the categorization of network traffic into normal and DDoS threat traffic.DNN’s parameters can be finetuned to detect DDoS attacks better using specially built algorithms.Reduced reconstruction error,no exploding or vanishing gradients,and reduced network are all benefits of the changes outlined in this paper.When it comes to performance criteria like accuracy,precision,recall,and F1-Score are the performance measures that show the suggested architecture outperforms the other existing approaches.Hence the proposed ABOA+DNN is an excellent method for obtaining accurate predictions,with an improved accuracy rate of 99.05%compared to other existing approaches.展开更多
Recently,deep learning has been used to establish the nonlinear and nonintuitive mapping between physical structures and electromagnetic responses of meta-atoms for higher computational efficiency.However,to obtain su...Recently,deep learning has been used to establish the nonlinear and nonintuitive mapping between physical structures and electromagnetic responses of meta-atoms for higher computational efficiency.However,to obtain sufficiently accurate predictions,the conventional deep-learning-based method consumes excessive time to collect the data set,thus hindering its wide application in this interdisciplinary field.We introduce a spectral transfer-learning-based metasurface design method to achieve excellent performance on a small data set with only 1000 samples in the target waveband by utilizing open-source data from another spectral range.We demonstrate three transfer strategies and experimentally quantify their performance,among which the“frozen-none”robustly improves the prediction accuracy by∼26%compared to direct learning.We propose to use a complex-valued deep neural network during the training process to further improve the spectral predicting precision by∼30%compared to its real-valued counterparts.We design several typical teraherz metadevices by employing a hybrid inverse model consolidating this trained target network and a global optimization algorithm.The simulated results successfully validate the capability of our approach.Our work provides a universal methodology for efficient and accurate metasurface design in arbitrary wavebands,which will pave the way toward the automated and mass production of metasurfaces.展开更多
The smart composite structure is introduced, which consists of inorganic and nonmetallic comPOsite and in which resistance strain wire sensor arrays are embedded and shape memory alloys (SMAs) are mounted on the surfa...The smart composite structure is introduced, which consists of inorganic and nonmetallic comPOsite and in which resistance strain wire sensor arrays are embedded and shape memory alloys (SMAs) are mounted on the surface during the manufacturing process. A two dimensional resistance strain wire sensor array can be used to detect changes in the mechanical strain distribution caused by subsequent damage to the structure. Self-adaptive and selfaliagnostic functions are achieved on a microcomputer using high speed parallel processors and neural network software. Results of the modeling and simulation predict a highly robust system with accurate determination of the damage location.展开更多
Organizations are adopting the Bring Your Own Device(BYOD)concept to enhance productivity and reduce expenses.However,this trend introduces security challenges,such as unauthorized access.Traditional access control sy...Organizations are adopting the Bring Your Own Device(BYOD)concept to enhance productivity and reduce expenses.However,this trend introduces security challenges,such as unauthorized access.Traditional access control systems,such as Attribute-Based Access Control(ABAC)and Role-Based Access Control(RBAC),are limited in their ability to enforce access decisions due to the variability and dynamism of attributes related to users and resources.This paper proposes a method for enforcing access decisions that is adaptable and dynamic,based on multilayer hybrid deep learning techniques,particularly the Tabular Deep Neural Network Tabular DNN method.This technique transforms all input attributes in an access request into a binary classification(allow or deny)using multiple layers,ensuring accurate and efficient access decision-making.The proposed solution was evaluated using the Kaggle Amazon access control policy dataset and demonstrated its effectiveness by achieving a 94%accuracy rate.Additionally,the proposed solution enhances the implementation of access decisions based on a variety of resource and user attributes while ensuring privacy through indirect communication with the Policy Administration Point(PAP).This solution significantly improves the flexibility of access control systems,making themmore dynamic and adaptable to the evolving needs ofmodern organizations.Furthermore,it offers a scalable approach to manage the complexities associated with the BYOD environment,providing a robust framework for secure and efficient access management.展开更多
Aiming at the problem of open set voiceprint recognition, this paper proposes an adaptive threshold algorithm based on OTSU and deep learning. The bottleneck technology of open set voiceprint recognition lies in the c...Aiming at the problem of open set voiceprint recognition, this paper proposes an adaptive threshold algorithm based on OTSU and deep learning. The bottleneck technology of open set voiceprint recognition lies in the calculation of similarity values and thresholds of speakers inside and outside the set. This paper combines deep learning and machine learning methods, and uses a Deep Belief Network stacked with three layers of Restricted Boltzmann Machines to extract deep voice features from basic acoustic features. And by training the Gaussian Mixture Model, this paper calculates the similarity value of the feature, and further determines the threshold of the similarity value of the feature through OTSU. After experimental testing, the algorithm in this paper has a false rejection rate of 3.00% for specific speakers, a false acceptance rate of 0.35% for internal speakers, and a false acceptance rate of 0 for external speakers. This improves the accuracy of traditional methods in open set voiceprint recognition. This proves that the method is feasible and good recognition effect.展开更多
We present a method for solving partial differential equations using artificial neural networks and an adaptive collocation strategy.In this procedure,a coarse grid of training points is used at the initial training s...We present a method for solving partial differential equations using artificial neural networks and an adaptive collocation strategy.In this procedure,a coarse grid of training points is used at the initial training stages,while more points are added at later stages based on the value of the residual at a larger set of evaluation points.This method increases the robustness of the neural network approximation and can result in significant computational savings,particularly when the solution is non-smooth.Numerical results are presented for benchmark problems for scalar-valued PDEs,namely Poisson and Helmholtz equations,as well as for an inverse acoustics problem.展开更多
External disturbances or inaccurate mathematical model built will inevitably impose a disadvantageous effect on the robot system,which generates positioning errors,vibrations,as well as weakening control performances ...External disturbances or inaccurate mathematical model built will inevitably impose a disadvantageous effect on the robot system,which generates positioning errors,vibrations,as well as weakening control performances of the system. The strategy of combining adaptive radial basis function( RBF) neural network control and composite nonlinear feedback( CNF) control is studied,and a robot CNF controller based on RBF neural network compensation is proposed. The core is to use RBF neural network control to approach the uncertainty of the system online,as the compensation term of the CNF controller,and make full use of the advantages of the two control methods to reduce the influence of uncertain factors on the performance of the system. The convergence of closed-loop system is proved. Simulation results demonstrate the effectiveness of this strategy.展开更多
Conventional machine learning(CML)methods have been successfully applied for gas reservoir prediction.Their prediction accuracy largely depends on the quality of the sample data;therefore,feature optimization of the i...Conventional machine learning(CML)methods have been successfully applied for gas reservoir prediction.Their prediction accuracy largely depends on the quality of the sample data;therefore,feature optimization of the input samples is particularly important.Commonly used feature optimization methods increase the interpretability of gas reservoirs;however,their steps are cumbersome,and the selected features cannot sufficiently guide CML models to mine the intrinsic features of sample data efficiently.In contrast to CML methods,deep learning(DL)methods can directly extract the important features of targets from raw data.Therefore,this study proposes a feature optimization and gas-bearing prediction method based on a hybrid fusion model that combines a convolutional neural network(CNN)and an adaptive particle swarm optimization-least squares support vector machine(APSO-LSSVM).This model adopts an end-to-end algorithm structure to directly extract features from sensitive multicomponent seismic attributes,considerably simplifying the feature optimization.A CNN was used for feature optimization to highlight sensitive gas reservoir information.APSO-LSSVM was used to fully learn the relationship between the features extracted by the CNN to obtain the prediction results.The constructed hybrid fusion model improves gas-bearing prediction accuracy through two processes of feature optimization and intelligent prediction,giving full play to the advantages of DL and CML methods.The prediction results obtained are better than those of a single CNN model or APSO-LSSVM model.In the feature optimization process of multicomponent seismic attribute data,CNN has demonstrated better gas reservoir feature extraction capabilities than commonly used attribute optimization methods.In the prediction process,the APSO-LSSVM model can learn the gas reservoir characteristics better than the LSSVM model and has a higher prediction accuracy.The constructed CNN-APSO-LSSVM model had lower errors and a better fit on the test dataset than the other individual models.This method proves the effectiveness of DL technology for the feature extraction of gas reservoirs and provides a feasible way to combine DL and CML technologies to predict gas reservoirs.展开更多
This paper proposes a new Deep Feed-forward Neural Network(DFNN)approach for damage detection in functionally graded carbon nanotube-reinforced composite(FG-CNTRC)plates.In the proposed approach,the DFNN model is deve...This paper proposes a new Deep Feed-forward Neural Network(DFNN)approach for damage detection in functionally graded carbon nanotube-reinforced composite(FG-CNTRC)plates.In the proposed approach,the DFNN model is developed based on a data set containing 20000 samples of damage scenarios,obtained via finite element(FE)simulation,of the FG-CNTRC plates.The elemental modal kinetic energy(MKE)values,calculated from natural frequencies and translational nodal displacements of the structures,are utilized as input of the DFNN model while the damage locations and corresponding severities are considered as output.The state-of-the art Exponential Linear Units(ELU)activation function and the Adamax algorithm are employed to train the DFNN model.Additionally,in order to enhance the performance of the DFNN model,the mini-batch and early-stopping techniques are applied to the training process.A trial-and-error procedure is implemented to determine suitable parameters of the network such as the number of hidden layers and the number of neurons in each layer.The accuracy and capability of the proposed DFNN model are illustrated through two distinct configurations of the CNT-fibers constituting the FG-CNTRC plates including uniform distribution(UD)and functionally graded-V distribution(FG-VD).Furthermore,the performance and stability of the DFNN model with the consideration of noise effects on the input data are also investigated.Obtained results indicate that the proposed DFNN model is able to give sufficiently accurate damage detection outcomes for the FG-CNTRC plates for both cases of noise-free and noise-influenced data.展开更多
The variations in gas path parameter deviations can fully reflect the healthy state of aeroengine gas path components and units;therefore,airlines usually take them as key parameters for monitoring the aero-engine gas...The variations in gas path parameter deviations can fully reflect the healthy state of aeroengine gas path components and units;therefore,airlines usually take them as key parameters for monitoring the aero-engine gas path performance state and conducting fault diagnosis.In the past,the airlines could not obtain deviations autonomously.At present,a data-driven method based on an aero-engine dataset with a large sample size can be utilized to obtain the deviations.However,it is still difficult to utilize aero-engine datasets with small sample sizes to establish regression models for deviations based on deep neural networks.To obtain monitoring autonomy of each aero-engine model,it is crucial to transfer and reuse the relevant knowledge of deviation modelling learned from different aero-engine models.This paper adopts the Residual-Back Propagation Neural Network(Res-BPNN)to deeply extract high-level features and stacks multi-layer Multi-Kernel Maximum Mean Discrepancy(MK-MMD)adaptation layers to map the extracted high-level features to the Reproduce Kernel Hilbert Space(RKHS)for discrepancy measurement.To further reduce the distribution discrepancy of each aero-engine model,the method of maximizing domain-confusion loss based on an adversarial mechanism is introduced to make the features learned from different domains as close as possible,and then the learned features can be confused.Through the above methods,domain-invariant features can be extracted,and the optimal adaptation effect can be achieved.Finally,the effectiveness of the proposed method is verified by using cruise data from different civil aero-engine models and compared with other transfer learning algorithms.展开更多
In this paper,we summarize recent progresses made in deep learning based acoustic models and the motivation and insights behind the surveyed techniques.We first discuss models such as recurrent neural networks(RNNs) a...In this paper,we summarize recent progresses made in deep learning based acoustic models and the motivation and insights behind the surveyed techniques.We first discuss models such as recurrent neural networks(RNNs) and convolutional neural networks(CNNs) that can effectively exploit variablelength contextual information,and their various combination with other models.We then describe models that are optimized end-to-end and emphasize on feature representations learned jointly with the rest of the system,the connectionist temporal classification(CTC) criterion,and the attention-based sequenceto-sequence translation model.We further illustrate robustness issues in speech recognition systems,and discuss acoustic model adaptation,speech enhancement and separation,and robust training strategies.We also cover modeling techniques that lead to more efficient decoding and discuss possible future directions in acoustic model research.展开更多
Alzheimer’s Disease(AD)is a progressive neurological disease.Early diagnosis of this illness using conventional methods is very challenging.Deep Learning(DL)is one of the finest solutions for improving diagnostic pro...Alzheimer’s Disease(AD)is a progressive neurological disease.Early diagnosis of this illness using conventional methods is very challenging.Deep Learning(DL)is one of the finest solutions for improving diagnostic procedures’performance and forecast accuracy.The disease’s widespread distribution and elevated mortality rate demonstrate its significance in the older-onset and younger-onset age groups.In light of research investigations,it is vital to consider age as one of the key criteria when choosing the subjects.The younger subjects are more susceptible to the perishable side than the older onset.The proposed investigation concentrated on the younger onset.The research used deep learning models and neuroimages to diagnose and categorize the disease at its early stages automatically.The proposed work is executed in three steps.The 3D input images must first undergo image pre-processing using Weiner filtering and Contrast Limited Adaptive Histogram Equalization(CLAHE)methods.The Transfer Learning(TL)models extract features,which are subsequently compressed using cascaded Auto Encoders(AE).The final phase entails using a Deep Neural Network(DNN)to classify the phases of AD.The model was trained and tested to classify the five stages of AD.The ensemble ResNet-18 and sparse autoencoder with DNN model achieved an accuracy of 98.54%.The method is compared to state-of-the-art approaches to validate its efficacy and performance.展开更多
Detection and recognition of a stairway as upstairs,downstairs and negative(e.g.,ladder,level ground)are the fundamentals of assisting the visually impaired to travel independently in unfamiliar environments.Previous ...Detection and recognition of a stairway as upstairs,downstairs and negative(e.g.,ladder,level ground)are the fundamentals of assisting the visually impaired to travel independently in unfamiliar environments.Previous studies have focused on using massive amounts of RGB-D scene data to train traditional machine learning(ML)-based models to detect and recognize stationary stairway and escalator stairway separately.Nevertheless,none of them consider jointly training these two similar but different datasets to achieve better performance.This paper applies an adversarial learning algorithm on the indicated unsupervised domain adaptation scenario to transfer knowledge learned from the labeled RGB-D escalator stairway dataset to the unlabeled RGB-D stationary dataset.By utilizing the developed method,a feedforward convolutional neural network(CNN)-based feature extractor with five convolution layers can achieve 100%classification accuracy on testing the labeled escalator stairway data distributions and 80.6%classification accuracy on testing the unlabeled stationary data distributions.The success of the developed approach is demonstrated for classifying stairway on these two domains with a limited amount of data.To further demonstrate the effectiveness of the proposed method,the same CNN model is evaluated without domain adaptation and the results are compared with those of the presented architecture.展开更多
文摘In recent years,wearable devices-based Human Activity Recognition(HAR)models have received significant attention.Previously developed HAR models use hand-crafted features to recognize human activities,leading to the extraction of basic features.The images captured by wearable sensors contain advanced features,allowing them to be analyzed by deep learning algorithms to enhance the detection and recognition of human actions.Poor lighting and limited sensor capabilities can impact data quality,making the recognition of human actions a challenging task.The unimodal-based HAR approaches are not suitable in a real-time environment.Therefore,an updated HAR model is developed using multiple types of data and an advanced deep-learning approach.Firstly,the required signals and sensor data are accumulated from the standard databases.From these signals,the wave features are retrieved.Then the extracted wave features and sensor data are given as the input to recognize the human activity.An Adaptive Hybrid Deep Attentive Network(AHDAN)is developed by incorporating a“1D Convolutional Neural Network(1DCNN)”with a“Gated Recurrent Unit(GRU)”for the human activity recognition process.Additionally,the Enhanced Archerfish Hunting Optimizer(EAHO)is suggested to fine-tune the network parameters for enhancing the recognition process.An experimental evaluation is performed on various deep learning networks and heuristic algorithms to confirm the effectiveness of the proposed HAR model.The EAHO-based HAR model outperforms traditional deep learning networks with an accuracy of 95.36,95.25 for recall,95.48 for specificity,and 95.47 for precision,respectively.The result proved that the developed model is effective in recognizing human action by taking less time.Additionally,it reduces the computation complexity and overfitting issue through using an optimization approach.
基金supported in part by the National Key Research and Development Program of China under Grant 2019YFB2102102in part by the National Natural Science Foundations of China under Grant 62176094 and Grant 61873097+2 种基金in part by the Key‐Area Research and Development of Guangdong Province under Grant 2020B010166002in part by the Guangdong Natural Science Foundation Research Team under Grant 2018B030312003in part by the Guangdong‐Hong Kong Joint Innovation Platform under Grant 2018B050502006.
文摘Research into automatically searching for an optimal neural network(NN)by optimi-sation algorithms is a significant research topic in deep learning and artificial intelligence.However,this is still challenging due to two issues:Both the hyperparameter and ar-chitecture should be optimised and the optimisation process is computationally expen-sive.To tackle these two issues,this paper focusses on solving the hyperparameter and architecture optimization problem for the NN and proposes a novel light‐weight scale‐adaptive fitness evaluation‐based particle swarm optimisation(SAFE‐PSO)approach.Firstly,the SAFE‐PSO algorithm considers the hyperparameters and architectures together in the optimisation problem and therefore can find their optimal combination for the globally best NN.Secondly,the computational cost can be reduced by using multi‐scale accuracy evaluation methods to evaluate candidates.Thirdly,a stagnation‐based switch strategy is proposed to adaptively switch different evaluation methods to better balance the search performance and computational cost.The SAFE‐PSO algorithm is tested on two widely used datasets:The 10‐category(i.e.,CIFAR10)and the 100−cate-gory(i.e.,CIFAR100).The experimental results show that SAFE‐PSO is very effective and efficient,which can not only find a promising NN automatically but also find a better NN than compared algorithms at the same computational cost.
基金This work was supported by the National Natural Science Foundation of China(No.60274009)and Specialized Research Fundfor the Doctoral Program of Higher Education(No.20020145007).
文摘Based on high order dynamic neural network, this paper presents the tracking problem for uncertain nonlinear composite system, which contains external disturbance, whose nonlinearities are assumed to be unknown. A smooth controller is designed to guarantee a uniform ultimate boundedness property for the tracking error and all other signals in the dosed loop. Certain measures are utilized to test its performance. No a priori knowledge of an upper bound on the “optimal” weight and modeling error is required; the weights of neural networks are updated on-line. Numerical simulations performed on a simple example illustrate and clarify the approach.
文摘Cloud computing technology provides flexible,on-demand,and completely controlled computing resources and services are highly desirable.Despite this,with its distributed and dynamic nature and shortcomings in virtualization deployment,the cloud environment is exposed to a wide variety of cyber-attacks and security difficulties.The Intrusion Detection System(IDS)is a specialized security tool that network professionals use for the safety and security of the networks against attacks launched from various sources.DDoS attacks are becoming more frequent and powerful,and their attack pathways are continually changing,which requiring the development of new detection methods.Here the purpose of the study is to improve detection accuracy.Feature Selection(FS)is critical.At the same time,the IDS’s computational problem is limited by focusing on the most relevant elements,and its performance and accuracy increase.In this research work,the suggested Adaptive butterfly optimization algorithm(ABOA)framework is used to assess the effectiveness of a reduced feature subset during the feature selection phase,that was motivated by this motive Candidates.Accurate classification is not compromised by using an ABOA technique.The design of Deep Neural Networks(DNN)has simplified the categorization of network traffic into normal and DDoS threat traffic.DNN’s parameters can be finetuned to detect DDoS attacks better using specially built algorithms.Reduced reconstruction error,no exploding or vanishing gradients,and reduced network are all benefits of the changes outlined in this paper.When it comes to performance criteria like accuracy,precision,recall,and F1-Score are the performance measures that show the suggested architecture outperforms the other existing approaches.Hence the proposed ABOA+DNN is an excellent method for obtaining accurate predictions,with an improved accuracy rate of 99.05%compared to other existing approaches.
基金support from the National Natural Science Foundation of China (Grant Nos.62027820,61975143,61735012,and 62205380).
文摘Recently,deep learning has been used to establish the nonlinear and nonintuitive mapping between physical structures and electromagnetic responses of meta-atoms for higher computational efficiency.However,to obtain sufficiently accurate predictions,the conventional deep-learning-based method consumes excessive time to collect the data set,thus hindering its wide application in this interdisciplinary field.We introduce a spectral transfer-learning-based metasurface design method to achieve excellent performance on a small data set with only 1000 samples in the target waveband by utilizing open-source data from another spectral range.We demonstrate three transfer strategies and experimentally quantify their performance,among which the“frozen-none”robustly improves the prediction accuracy by∼26%compared to direct learning.We propose to use a complex-valued deep neural network during the training process to further improve the spectral predicting precision by∼30%compared to its real-valued counterparts.We design several typical teraherz metadevices by employing a hybrid inverse model consolidating this trained target network and a global optimization algorithm.The simulated results successfully validate the capability of our approach.Our work provides a universal methodology for efficient and accurate metasurface design in arbitrary wavebands,which will pave the way toward the automated and mass production of metasurfaces.
文摘The smart composite structure is introduced, which consists of inorganic and nonmetallic comPOsite and in which resistance strain wire sensor arrays are embedded and shape memory alloys (SMAs) are mounted on the surface during the manufacturing process. A two dimensional resistance strain wire sensor array can be used to detect changes in the mechanical strain distribution caused by subsequent damage to the structure. Self-adaptive and selfaliagnostic functions are achieved on a microcomputer using high speed parallel processors and neural network software. Results of the modeling and simulation predict a highly robust system with accurate determination of the damage location.
基金partly supported by the University of Malaya Impact Oriented Interdisci-plinary Research Grant under Grant IIRG008(A,B,C)-19IISS.
文摘Organizations are adopting the Bring Your Own Device(BYOD)concept to enhance productivity and reduce expenses.However,this trend introduces security challenges,such as unauthorized access.Traditional access control systems,such as Attribute-Based Access Control(ABAC)and Role-Based Access Control(RBAC),are limited in their ability to enforce access decisions due to the variability and dynamism of attributes related to users and resources.This paper proposes a method for enforcing access decisions that is adaptable and dynamic,based on multilayer hybrid deep learning techniques,particularly the Tabular Deep Neural Network Tabular DNN method.This technique transforms all input attributes in an access request into a binary classification(allow or deny)using multiple layers,ensuring accurate and efficient access decision-making.The proposed solution was evaluated using the Kaggle Amazon access control policy dataset and demonstrated its effectiveness by achieving a 94%accuracy rate.Additionally,the proposed solution enhances the implementation of access decisions based on a variety of resource and user attributes while ensuring privacy through indirect communication with the Policy Administration Point(PAP).This solution significantly improves the flexibility of access control systems,making themmore dynamic and adaptable to the evolving needs ofmodern organizations.Furthermore,it offers a scalable approach to manage the complexities associated with the BYOD environment,providing a robust framework for secure and efficient access management.
文摘Aiming at the problem of open set voiceprint recognition, this paper proposes an adaptive threshold algorithm based on OTSU and deep learning. The bottleneck technology of open set voiceprint recognition lies in the calculation of similarity values and thresholds of speakers inside and outside the set. This paper combines deep learning and machine learning methods, and uses a Deep Belief Network stacked with three layers of Restricted Boltzmann Machines to extract deep voice features from basic acoustic features. And by training the Gaussian Mixture Model, this paper calculates the similarity value of the feature, and further determines the threshold of the similarity value of the feature through OTSU. After experimental testing, the algorithm in this paper has a false rejection rate of 3.00% for specific speakers, a false acceptance rate of 0.35% for internal speakers, and a false acceptance rate of 0 for external speakers. This improves the accuracy of traditional methods in open set voiceprint recognition. This proves that the method is feasible and good recognition effect.
文摘We present a method for solving partial differential equations using artificial neural networks and an adaptive collocation strategy.In this procedure,a coarse grid of training points is used at the initial training stages,while more points are added at later stages based on the value of the residual at a larger set of evaluation points.This method increases the robustness of the neural network approximation and can result in significant computational savings,particularly when the solution is non-smooth.Numerical results are presented for benchmark problems for scalar-valued PDEs,namely Poisson and Helmholtz equations,as well as for an inverse acoustics problem.
基金National Natural Science Foundation of China(Nos.61663030,61663032)Natural Science Foundation of Jiangxi Province,China(No.20142BAB207021)+3 种基金the Foundation of Jiangxi Educational Committee,China(No.GJJ150753)the Innovation Fund Designated for Graduate Students of Nanchang Hangkong University,China(Nos.YC2017027,2018YBXG014)the Open Fund of Key Laboratory of Image Processing and Pattern Recognition of Jiangxi Province(Nanchang Hangkong University),China(No.TX201404003)Key Laboratory of Nondestructive Testing(Nanchang Hangkong University),Ministry of Education,China(No.ZD29529005)
文摘External disturbances or inaccurate mathematical model built will inevitably impose a disadvantageous effect on the robot system,which generates positioning errors,vibrations,as well as weakening control performances of the system. The strategy of combining adaptive radial basis function( RBF) neural network control and composite nonlinear feedback( CNF) control is studied,and a robot CNF controller based on RBF neural network compensation is proposed. The core is to use RBF neural network control to approach the uncertainty of the system online,as the compensation term of the CNF controller,and make full use of the advantages of the two control methods to reduce the influence of uncertain factors on the performance of the system. The convergence of closed-loop system is proved. Simulation results demonstrate the effectiveness of this strategy.
基金funded by the Natural Science Foundation of Shandong Province (ZR2021MD061ZR2023QD025)+3 种基金China Postdoctoral Science Foundation (2022M721972)National Natural Science Foundation of China (41174098)Young Talents Foundation of Inner Mongolia University (10000-23112101/055)Qingdao Postdoctoral Science Foundation (QDBSH20230102094)。
文摘Conventional machine learning(CML)methods have been successfully applied for gas reservoir prediction.Their prediction accuracy largely depends on the quality of the sample data;therefore,feature optimization of the input samples is particularly important.Commonly used feature optimization methods increase the interpretability of gas reservoirs;however,their steps are cumbersome,and the selected features cannot sufficiently guide CML models to mine the intrinsic features of sample data efficiently.In contrast to CML methods,deep learning(DL)methods can directly extract the important features of targets from raw data.Therefore,this study proposes a feature optimization and gas-bearing prediction method based on a hybrid fusion model that combines a convolutional neural network(CNN)and an adaptive particle swarm optimization-least squares support vector machine(APSO-LSSVM).This model adopts an end-to-end algorithm structure to directly extract features from sensitive multicomponent seismic attributes,considerably simplifying the feature optimization.A CNN was used for feature optimization to highlight sensitive gas reservoir information.APSO-LSSVM was used to fully learn the relationship between the features extracted by the CNN to obtain the prediction results.The constructed hybrid fusion model improves gas-bearing prediction accuracy through two processes of feature optimization and intelligent prediction,giving full play to the advantages of DL and CML methods.The prediction results obtained are better than those of a single CNN model or APSO-LSSVM model.In the feature optimization process of multicomponent seismic attribute data,CNN has demonstrated better gas reservoir feature extraction capabilities than commonly used attribute optimization methods.In the prediction process,the APSO-LSSVM model can learn the gas reservoir characteristics better than the LSSVM model and has a higher prediction accuracy.The constructed CNN-APSO-LSSVM model had lower errors and a better fit on the test dataset than the other individual models.This method proves the effectiveness of DL technology for the feature extraction of gas reservoirs and provides a feasible way to combine DL and CML technologies to predict gas reservoirs.
基金This research was funded by Vietnam National Foundation for Science and Technology Development(NAFOSTED)under No.107.02-2019.330.
文摘This paper proposes a new Deep Feed-forward Neural Network(DFNN)approach for damage detection in functionally graded carbon nanotube-reinforced composite(FG-CNTRC)plates.In the proposed approach,the DFNN model is developed based on a data set containing 20000 samples of damage scenarios,obtained via finite element(FE)simulation,of the FG-CNTRC plates.The elemental modal kinetic energy(MKE)values,calculated from natural frequencies and translational nodal displacements of the structures,are utilized as input of the DFNN model while the damage locations and corresponding severities are considered as output.The state-of-the art Exponential Linear Units(ELU)activation function and the Adamax algorithm are employed to train the DFNN model.Additionally,in order to enhance the performance of the DFNN model,the mini-batch and early-stopping techniques are applied to the training process.A trial-and-error procedure is implemented to determine suitable parameters of the network such as the number of hidden layers and the number of neurons in each layer.The accuracy and capability of the proposed DFNN model are illustrated through two distinct configurations of the CNT-fibers constituting the FG-CNTRC plates including uniform distribution(UD)and functionally graded-V distribution(FG-VD).Furthermore,the performance and stability of the DFNN model with the consideration of noise effects on the input data are also investigated.Obtained results indicate that the proposed DFNN model is able to give sufficiently accurate damage detection outcomes for the FG-CNTRC plates for both cases of noise-free and noise-influenced data.
基金supported by the Shandong Provincial Natural Science Foundation(No.ZR2019MEE096)the Key National Natural Science Foundation of China(No.U1733201)。
文摘The variations in gas path parameter deviations can fully reflect the healthy state of aeroengine gas path components and units;therefore,airlines usually take them as key parameters for monitoring the aero-engine gas path performance state and conducting fault diagnosis.In the past,the airlines could not obtain deviations autonomously.At present,a data-driven method based on an aero-engine dataset with a large sample size can be utilized to obtain the deviations.However,it is still difficult to utilize aero-engine datasets with small sample sizes to establish regression models for deviations based on deep neural networks.To obtain monitoring autonomy of each aero-engine model,it is crucial to transfer and reuse the relevant knowledge of deviation modelling learned from different aero-engine models.This paper adopts the Residual-Back Propagation Neural Network(Res-BPNN)to deeply extract high-level features and stacks multi-layer Multi-Kernel Maximum Mean Discrepancy(MK-MMD)adaptation layers to map the extracted high-level features to the Reproduce Kernel Hilbert Space(RKHS)for discrepancy measurement.To further reduce the distribution discrepancy of each aero-engine model,the method of maximizing domain-confusion loss based on an adversarial mechanism is introduced to make the features learned from different domains as close as possible,and then the learned features can be confused.Through the above methods,domain-invariant features can be extracted,and the optimal adaptation effect can be achieved.Finally,the effectiveness of the proposed method is verified by using cruise data from different civil aero-engine models and compared with other transfer learning algorithms.
文摘In this paper,we summarize recent progresses made in deep learning based acoustic models and the motivation and insights behind the surveyed techniques.We first discuss models such as recurrent neural networks(RNNs) and convolutional neural networks(CNNs) that can effectively exploit variablelength contextual information,and their various combination with other models.We then describe models that are optimized end-to-end and emphasize on feature representations learned jointly with the rest of the system,the connectionist temporal classification(CTC) criterion,and the attention-based sequenceto-sequence translation model.We further illustrate robustness issues in speech recognition systems,and discuss acoustic model adaptation,speech enhancement and separation,and robust training strategies.We also cover modeling techniques that lead to more efficient decoding and discuss possible future directions in acoustic model research.
文摘Alzheimer’s Disease(AD)is a progressive neurological disease.Early diagnosis of this illness using conventional methods is very challenging.Deep Learning(DL)is one of the finest solutions for improving diagnostic procedures’performance and forecast accuracy.The disease’s widespread distribution and elevated mortality rate demonstrate its significance in the older-onset and younger-onset age groups.In light of research investigations,it is vital to consider age as one of the key criteria when choosing the subjects.The younger subjects are more susceptible to the perishable side than the older onset.The proposed investigation concentrated on the younger onset.The research used deep learning models and neuroimages to diagnose and categorize the disease at its early stages automatically.The proposed work is executed in three steps.The 3D input images must first undergo image pre-processing using Weiner filtering and Contrast Limited Adaptive Histogram Equalization(CLAHE)methods.The Transfer Learning(TL)models extract features,which are subsequently compressed using cascaded Auto Encoders(AE).The final phase entails using a Deep Neural Network(DNN)to classify the phases of AD.The model was trained and tested to classify the five stages of AD.The ensemble ResNet-18 and sparse autoencoder with DNN model achieved an accuracy of 98.54%.The method is compared to state-of-the-art approaches to validate its efficacy and performance.
文摘Detection and recognition of a stairway as upstairs,downstairs and negative(e.g.,ladder,level ground)are the fundamentals of assisting the visually impaired to travel independently in unfamiliar environments.Previous studies have focused on using massive amounts of RGB-D scene data to train traditional machine learning(ML)-based models to detect and recognize stationary stairway and escalator stairway separately.Nevertheless,none of them consider jointly training these two similar but different datasets to achieve better performance.This paper applies an adversarial learning algorithm on the indicated unsupervised domain adaptation scenario to transfer knowledge learned from the labeled RGB-D escalator stairway dataset to the unlabeled RGB-D stationary dataset.By utilizing the developed method,a feedforward convolutional neural network(CNN)-based feature extractor with five convolution layers can achieve 100%classification accuracy on testing the labeled escalator stairway data distributions and 80.6%classification accuracy on testing the unlabeled stationary data distributions.The success of the developed approach is demonstrated for classifying stairway on these two domains with a limited amount of data.To further demonstrate the effectiveness of the proposed method,the same CNN model is evaluated without domain adaptation and the results are compared with those of the presented architecture.
