Pulse pile-up is a problem in nuclear spectroscopy and nuclear reaction studies that occurs when two pulses overlap and distort each other,degrading the quality of energy and timing information.Different methods have ...Pulse pile-up is a problem in nuclear spectroscopy and nuclear reaction studies that occurs when two pulses overlap and distort each other,degrading the quality of energy and timing information.Different methods have been used for pile-up rejection,both digital and analogue,but some pile-up events may contain pulses of interest and need to be reconstructed.The paper proposes a new method for reconstructing pile-up events acquired with a neutron detector array(NEDA)using an one-dimensional convolutional autoencoder(1D-CAE).The datasets for training and testing the 1D-CAE are created from data acquired from the NEDA.The new pile-up signal reconstruction method is evaluated from the point of view of how similar the reconstructed signals are to the original ones.Furthermore,it is analysed considering the result of the neutron-gamma discrimination based on charge comparison,comparing the result obtained from original and reconstructed signals.展开更多
With the rapid development of the Internet,network security and data privacy are increasingly valued.Although classical Network Intrusion Detection System(NIDS)based on Deep Learning(DL)models can provide good detecti...With the rapid development of the Internet,network security and data privacy are increasingly valued.Although classical Network Intrusion Detection System(NIDS)based on Deep Learning(DL)models can provide good detection accuracy,but collecting samples for centralized training brings the huge risk of data privacy leakage.Furthermore,the training of supervised deep learning models requires a large number of labeled samples,which is usually cumbersome.The“black-box”problem also makes the DL models of NIDS untrustworthy.In this paper,we propose a trusted Federated Learning(FL)Traffic IDS method called FL-TIDS to address the above-mentioned problems.In FL-TIDS,we design an unsupervised intrusion detection model based on autoencoders that alleviates the reliance on marked samples.At the same time,we use FL for model training to protect data privacy.In addition,we design an improved SHAP interpretable method based on chi-square test to perform interpretable analysis of the trained model.We conducted several experiments to evaluate the proposed FL-TIDS.We first determine experimentally the structure and the number of neurons of the unsupervised AE model.Secondly,we evaluated the proposed method using the UNSW-NB15 and CICIDS2017 datasets.The exper-imental results show that the unsupervised AE model has better performance than the other 7 intrusion detection models in terms of precision,recall and f1-score.Then,federated learning is used to train the intrusion detection model.The experimental results indicate that the model is more accurate than the local learning model.Finally,we use an improved SHAP explainability method based on Chi-square test to analyze the explainability.The analysis results show that the identification characteristics of the model are consistent with the attack characteristics,and the model is reliable.展开更多
Wayside monitoring is a promising cost-effective alternative to predict damage in the rolling stock. The main goal of this work is to present an unsupervised methodology to identify out-of-roundness(OOR) damage wheels...Wayside monitoring is a promising cost-effective alternative to predict damage in the rolling stock. The main goal of this work is to present an unsupervised methodology to identify out-of-roundness(OOR) damage wheels, such as wheel flats and polygonal wheels. This automatic damage identification algorithm is based on the vertical acceleration evaluated on the rails using a virtual wayside monitoring system and involves the application of a two-step procedure. The first step aims to define a confidence boundary by using(healthy) measurements evaluated on the rail constituting a baseline. The second step of the procedure involves classifying damage of predefined scenarios with different levels of severities. The proposed procedure is based on a machine learning methodology and includes the following stages:(1) data collection,(2) damage-sensitive feature extraction from the acquired responses using a neural network model, i.e., the sparse autoencoder(SAE),(3) data fusion based on the Mahalanobis distance, and(4) unsupervised feature classification by implementing outlier and cluster analysis. This procedure considers baseline responses at different speeds and rail irregularities to train the SAE model. Then, the trained SAE is capable to reconstruct test responses(not trained) allowing to compute the accumulative difference between original and reconstructed signals. The results prove the efficiency of the proposed approach in identifying the two most common types of OOR in railway wheels.展开更多
Network security problems bring many imperceptible threats to the integrity of data and the reliability of device services,so proposing a network intrusion detection model with high reliability is of great research si...Network security problems bring many imperceptible threats to the integrity of data and the reliability of device services,so proposing a network intrusion detection model with high reliability is of great research significance for network security.Due to the strong generalization of invalid features during training process,it is more difficult for single autoencoder intrusion detection model to obtain effective results.A network intrusion detection model based on the Ensemble of Denoising Adversarial Autoencoder(EDAAE)was proposed,which had higher accuracy and reliability compared to the traditional anomaly detection model.Using the adversarial learning idea of Adversarial Autoencoder(AAE),the discriminator module was added to the original model,and the encoder part was used as the generator.The distribution of the hidden space of the data generated by the encoder matched with the distribution of the original data.The generalization of the model to the invalid features was also reduced to improve the detection accuracy.At the same time,the denoising autoencoder and integrated operation was introduced to prevent overfitting in the adversarial learning process.Experiments on the CICIDS2018 traffic dataset showed that the proposed intrusion detection model achieves an Accuracy of 95.23%,which out performs traditional self-encoders and other existing intrusion detection models methods in terms of overall performance.展开更多
Fault diagnosis of traction systems is important for the safety operation of high-speed trains.Long-term operation of the trains will degrade the performance of systems,which decreases the fault detection accuracy.To ...Fault diagnosis of traction systems is important for the safety operation of high-speed trains.Long-term operation of the trains will degrade the performance of systems,which decreases the fault detection accuracy.To solve this problem,this paper proposes a fault detection method developed by a Generalized Autoencoder(GAE)for systems with performance degradation.The advantage of this method is that it can accurately detect faults when the traction system of high-speed trains is affected by performance degradation.Regardless of the probability distribution,it can handle any data,and the GAE has extremely high sensitivity in anomaly detection.Finally,the effectiveness of this method is verified through the Traction Drive Control System(TDCS)platform.At different performance degradation levels,our method’s experimental results are superior to traditional methods.展开更多
Unmanned surface vehicle(USV)is currently a hot research topic in maritime communication network(MCN),where denoising and semantic segmentation of maritime images taken by USV have been rarely studied.The former has r...Unmanned surface vehicle(USV)is currently a hot research topic in maritime communication network(MCN),where denoising and semantic segmentation of maritime images taken by USV have been rarely studied.The former has recently researched on autoencoder model used for image denoising,but the existed models are too complicated to be suitable for real-time detection of USV.In this paper,we proposed a lightweight autoencoder combined with inception module for maritime image denoising in different noisy environments and explore the effect of different inception modules on the denoising performance.Furthermore,we completed the semantic segmentation task for maritime images taken by USV utilizing the pretrained U-Net model with tuning,and compared them with original U-Net model based on different backbone.Subsequently,we compared the semantic segmentation of noised and denoised maritime images respectively to explore the effect of image noise on semantic segmentation performance.Case studies are provided to prove the feasibility of our proposed denoising and segmentation method.Finally,a simple integrated communication system combining image denoising and segmentation for USV is shown.展开更多
This paper presents an innovative data-integration that uses an iterative-learning method,a deep neural network(DNN)coupled with a stacked autoencoder(SAE)to solve issues encountered with many-objective history matchi...This paper presents an innovative data-integration that uses an iterative-learning method,a deep neural network(DNN)coupled with a stacked autoencoder(SAE)to solve issues encountered with many-objective history matching.The proposed method consists of a DNN-based inverse model with SAE-encoded static data and iterative updates of supervised-learning data are based on distance-based clustering schemes.DNN functions as an inverse model and results in encoded flattened data,while SAE,as a pre-trained neural network,successfully reduces dimensionality and reliably reconstructs geomodels.The iterative-learning method can improve the training data for DNN by showing the error reduction achieved with each iteration step.The proposed workflow shows the small mean absolute percentage error below 4%for all objective functions,while a typical multi-objective evolutionary algorithm fails to significantly reduce the initial population uncertainty.Iterative learning-based manyobjective history matching estimates the trends in water cuts that are not reliably included in dynamicdata matching.This confirms the proposed workflow constructs more plausible geo-models.The workflow would be a reliable alternative to overcome the less-convergent Pareto-based multi-objective evolutionary algorithm in the presence of geological uncertainty and varying objective functions.展开更多
Offline Urdu Nastaleeq text recognition has long been a serious problem due to its very cursive nature. In order to get rid of the character segmentation problems, many researchers are shifting focus towards segmentat...Offline Urdu Nastaleeq text recognition has long been a serious problem due to its very cursive nature. In order to get rid of the character segmentation problems, many researchers are shifting focus towards segmentation free ligature based recognition approaches. Majority of the prevalent ligature based recognition systems heavily rely on hand-engineered feature extraction techniques. However, such techniques are more error prone and may often lead to a loss of useful information that might hardly be captured later by any manual features. Most of the prevalent Urdu Nastaleeq test recognition was trained and tested on small sets. This paper proposes the use of stacked denoising autoencoder for automatic feature extraction directly from raw pixel values of ligature images. Such deep learning networks have not been applied for the recognition of Urdu text thus far. Different stacked denoising autoencoders have been trained on 178573 ligatures with 3732 classes from un-degraded(noise free) UPTI(Urdu Printed Text Image) data set. Subsequently, trained networks are validated and tested on degraded versions of UPTI data set. The experimental results demonstrate accuracies in range of 93% to 96% which are better than the existing Urdu OCR systems for such large dataset of ligatures.展开更多
We study the effects of quantization and additive white Gaussian noise(AWGN) in transmitting latent representations of images over a noisy communication channel. The latent representations are obtained using autoencod...We study the effects of quantization and additive white Gaussian noise(AWGN) in transmitting latent representations of images over a noisy communication channel. The latent representations are obtained using autoencoders(AEs). We analyze image reconstruction and classification performance for different channel noise powers, latent vector sizes, and number of quantization bits used for the latent variables as well as AEs’ parameters. The results show that the digital transmission of latent representations using conventional AEs alone is extremely vulnerable to channel noise and quantization effects. We then propose a combination of basic AE and a denoising autoencoder(DAE) to denoise the corrupted latent vectors at the receiver. This approach demonstrates robustness against channel noise and quantization effects and enables a significant improvement in image reconstruction and classification performance particularly in adverse scenarios with high noise powers and significant quantization effects.展开更多
Secure transmission of images over a communication channel, with limited data transfer capacity, possesses compression and encryption schemes. A deep learning based hybrid image compression-encryption scheme is propos...Secure transmission of images over a communication channel, with limited data transfer capacity, possesses compression and encryption schemes. A deep learning based hybrid image compression-encryption scheme is proposed by combining stacked auto-encoder with the logistic map. The proposed structure of stacked autoencoder has seven multiple layers, and back propagation algorithm is intended to extend vector portrayal of information into lower vector space. The randomly generated key is used to set initial conditions and control parameters of logistic map. Subsequently, compressed image is encrypted by substituting and scrambling of pixel sequences using key stream sequences generated from logistic map.The proposed algorithms are experimentally tested over five standard grayscale images. Compression and encryption efficiency of proposed algorithms are evaluated and analyzed based on peak signal to noise ratio(PSNR), mean square error(MSE), structural similarity index metrics(SSIM) and statistical,differential, entropy analysis respectively. Simulation results show that proposed algorithms provide high quality reconstructed images with excellent levels of security during transmission..展开更多
Terahertz wireless communication has been regarded as an emerging technology to satisfy the ever-increasing demand of ultra-high-speed wireless communications.However,affected by the imperfections of cheap and energy-...Terahertz wireless communication has been regarded as an emerging technology to satisfy the ever-increasing demand of ultra-high-speed wireless communications.However,affected by the imperfections of cheap and energy-efficient Terahertz devices,Terahertz signals suffer from serve hybrid distortions,including in-phase/quadrature imbalance,phase noise and nonlinearity,which degrade the demodulation performance significantly.To improve the robustness against these hybrid distortions,an improved autoencoder is proposed,which includes coding the transmitted symbols at the transmitter and decoding the corresponding signals at the receiver.Moreover,due to the lack of information of Terahertz channel during the training of the autoencoder,a fitting network is proposed to approximate the characteristics of Terahertz channel,which provides an approximation of the gradients of loss.Simulation results show that our proposed autoencoder with fitting network can recover the transmitted symbols under serious hybrid distortions,and improves the demodulation performance significantly.展开更多
The spectrum sensing model based on deep learning has achieved satisfying detection per-formence,but its robustness has not been verified.In this paper,we propose primary user adversarial attack(PUAA)to verify the rob...The spectrum sensing model based on deep learning has achieved satisfying detection per-formence,but its robustness has not been verified.In this paper,we propose primary user adversarial attack(PUAA)to verify the robustness of the deep learning based spectrum sensing model.PUAA adds a care-fully manufactured perturbation to the benign primary user signal,which greatly reduces the probability of detection of the spectrum sensing model.We design three PUAA methods in black box scenario.In or-der to defend against PUAA,we propose a defense method based on autoencoder named DeepFilter.We apply the long short-term memory network and the convolutional neural network together to DeepFilter,so that it can extract the temporal and local features of the input signal at the same time to achieve effective defense.Extensive experiments are conducted to eval-uate the attack effect of the designed PUAA method and the defense effect of DeepFilter.Results show that the three PUAA methods designed can greatly reduce the probability of detection of the deep learning-based spectrum sensing model.In addition,the experimen-tal results of the defense effect of DeepFilter show that DeepFilter can effectively defend against PUAA with-out affecting the detection performance of the model.展开更多
Faced with the evolving attacks in recommender systems, many detection features have been proposed by human engineering and used in supervised or unsupervised detection methods. However, the detection features extract...Faced with the evolving attacks in recommender systems, many detection features have been proposed by human engineering and used in supervised or unsupervised detection methods. However, the detection features extracted by human engineering are usually aimed at some specific types of attacks. To further detect other new types of attacks, the traditional methods have to re-extract detection features with high knowledge cost. To address these limitations, the method for automatic extraction of robust features is proposed and then an Adaboost-based detection method is presented. Firstly, to obtain robust representation with prior knowledge, unlike uniform corruption rate in traditional mLDA(marginalized Linear Denoising Autoencoder), different corruption rates for items are calculated according to the ratings’ distribution. Secondly, the ratings sparsity is used to weight the mapping matrix to extract low-dimensional representation. Moreover, the uniform corruption rate is also set to the next layer in mSLDA(marginalized Stacked Linear Denoising Autoencoder) to extract the stable and robust user features. Finally, under the robust feature space, an Adaboost-based detection method is proposed to alleviate the imbalanced classification problem. Experimental results on the Netflix and Amazon review datasets indicate that the proposed method can effectively detect various attacks.展开更多
Weak feature extraction is of great importance for condition monitoring and intelligent diagnosis of aeroengine.Aimed at achieving intelligent diagnosis of aero-engine main shaft bearing,an enhanced sparsity-assisted ...Weak feature extraction is of great importance for condition monitoring and intelligent diagnosis of aeroengine.Aimed at achieving intelligent diagnosis of aero-engine main shaft bearing,an enhanced sparsity-assisted intelligent condition monitoring method is proposed in this paper.Through analyzing the weakness of convex sparse model,i.e.the tradeoff between noise reduction and feature reconstruction,this paper proposes an enhanced-sparsity nonconvex regularized convex model based on Moreau envelope to achieve weak feature extraction.Accordingly,a sparsity-assisted deep convolutional variational autoencoders network is proposed,which achieves the intelligent identification of fault state through training denoised normal data.Finally,the effectiveness of the proposed method is verified through aero-engine bearing run-to-failure experiment.The comparison results show that the proposed method is good at abnormal pattern recognition,showing a good potential for weak fault intelligent diagnosis of aero-engine main shaft bearings.展开更多
The health status of aero engines is very important to the flight safety.However,it is difficult for aero engines to make an effective fault diagnosis due to its complex structure and poor working environment.Therefor...The health status of aero engines is very important to the flight safety.However,it is difficult for aero engines to make an effective fault diagnosis due to its complex structure and poor working environment.Therefore,an effective fault diagnosis method for aero engines based on the gravitational search algorithm and the stack autoencoder(GSA-SAE)is proposed,and the fault diagnosis technology of a turbofan engine is studied.Firstly,the data of 17 parameters,including total inlet air temperature,high-pressure rotor speed,low-pressure rotor speed,turbine pressure ratio,total inlet air temperature of high-pressure compressor and outlet air pressure of high-pressure compressor and so on,are preprocessed,and the fault diagnosis model architecture of SAE is constructed.In order to solve the problem that the best diagnosis effect cannot be obtained due to manually setting the number of neurons in each hidden layer of SAE network,a GSA optimization algorithm for the SAE network is proposed to find and obtain the optimal number of neurons in each hidden layer of SAE network.Furthermore,an optimal fault diagnosis model based on GSA-SAE is established for aero engines.Finally,the effectiveness of the optimal GSA-SAE fault diagnosis model is demonstrated using the practical data of aero engines.The results illustrate that the proposed fault diagnosis method effectively solves the problem of the poor fault diagnosis result because of manually setting the number of neurons in each hidden layer of SAE network,and has good fault diagnosis efficiency.The fault diagnosis accuracy of the GSA-SAE model reaches 98.222%,which is significantly higher than that of SAE,the general regression neural network(GRNN)and the back propagation(BP)network fault diagnosis models.展开更多
Spectrum management and resource allocation(RA)problems are challenging and critical in a vast number of research areas such as wireless communications and computer networks.The traditional approaches for solving such...Spectrum management and resource allocation(RA)problems are challenging and critical in a vast number of research areas such as wireless communications and computer networks.The traditional approaches for solving such problems usually consume time and memory,especially for large-size problems.Recently different machine learning approaches have been considered as potential promising techniques for combinatorial optimization problems,especially the generative model of the deep neural networks.In this work,we propose a resource allocation deep autoencoder network,as one of the promising generative models,for enabling spectrum sharing in underlay device-to-device(D2D)communication by solving linear sum assignment problems(LSAPs).Specifically,we investigate the performance of three different architectures for the conditional variational autoencoders(CVAE).The three proposed architecture are the convolutional neural network(CVAECNN)autoencoder,the feed-forward neural network(CVAE-FNN)autoencoder,and the hybrid(H-CVAE)autoencoder.The simulation results show that the proposed approach could be used as a replacement of the conventional RA techniques,such as the Hungarian algorithm,due to its ability to find solutions of LASPs of different sizes with high accuracy and very fast execution time.Moreover,the simulation results reveal that the accuracy of the proposed hybrid autoencoder architecture outperforms the other proposed architectures and the state-of-the-art DNN techniques.展开更多
基金partially supported by MICIU MCIN/AEI/10.13039/501100011033Spain with grant PID2020-118265GB-C42,-C44,PRTR-C17.I01+1 种基金Generalitat Valenciana,Spain with grant CIPROM/2022/54,ASFAE/2022/031,CIAPOS/2021/114the EU NextGenerationEU,ESF funds,and the National Science Centre (NCN),Poland (grant No.2020/39/D/ST2/00466)
文摘Pulse pile-up is a problem in nuclear spectroscopy and nuclear reaction studies that occurs when two pulses overlap and distort each other,degrading the quality of energy and timing information.Different methods have been used for pile-up rejection,both digital and analogue,but some pile-up events may contain pulses of interest and need to be reconstructed.The paper proposes a new method for reconstructing pile-up events acquired with a neutron detector array(NEDA)using an one-dimensional convolutional autoencoder(1D-CAE).The datasets for training and testing the 1D-CAE are created from data acquired from the NEDA.The new pile-up signal reconstruction method is evaluated from the point of view of how similar the reconstructed signals are to the original ones.Furthermore,it is analysed considering the result of the neutron-gamma discrimination based on charge comparison,comparing the result obtained from original and reconstructed signals.
基金supported by National Natural Science Fundation of China under Grant 61972208National Natural Science Fundation(General Program)of China under Grant 61972211+2 种基金National Key Research and Development Project of China under Grant 2020YFB1804700Future Network Innovation Research and Application Projects under Grant No.2021FNA020062021 Jiangsu Postgraduate Research Innovation Plan under Grant No.KYCX210794.
文摘With the rapid development of the Internet,network security and data privacy are increasingly valued.Although classical Network Intrusion Detection System(NIDS)based on Deep Learning(DL)models can provide good detection accuracy,but collecting samples for centralized training brings the huge risk of data privacy leakage.Furthermore,the training of supervised deep learning models requires a large number of labeled samples,which is usually cumbersome.The“black-box”problem also makes the DL models of NIDS untrustworthy.In this paper,we propose a trusted Federated Learning(FL)Traffic IDS method called FL-TIDS to address the above-mentioned problems.In FL-TIDS,we design an unsupervised intrusion detection model based on autoencoders that alleviates the reliance on marked samples.At the same time,we use FL for model training to protect data privacy.In addition,we design an improved SHAP interpretable method based on chi-square test to perform interpretable analysis of the trained model.We conducted several experiments to evaluate the proposed FL-TIDS.We first determine experimentally the structure and the number of neurons of the unsupervised AE model.Secondly,we evaluated the proposed method using the UNSW-NB15 and CICIDS2017 datasets.The exper-imental results show that the unsupervised AE model has better performance than the other 7 intrusion detection models in terms of precision,recall and f1-score.Then,federated learning is used to train the intrusion detection model.The experimental results indicate that the model is more accurate than the local learning model.Finally,we use an improved SHAP explainability method based on Chi-square test to analyze the explainability.The analysis results show that the identification characteristics of the model are consistent with the attack characteristics,and the model is reliable.
基金a result of project WAY4SafeRail—Wayside monitoring system FOR SAFE RAIL transportation, with reference NORTE-01-0247-FEDER-069595co-funded by the European Regional Development Fund (ERDF), through the North Portugal Regional Operational Programme (NORTE2020), under the PORTUGAL 2020 Partnership Agreement+3 种基金financially supported by Base Funding-UIDB/04708/2020Programmatic Funding-UIDP/04708/2020 of the CONSTRUCT—Instituto de Estruturas e Constru??esfunded by national funds through the FCT/ MCTES (PIDDAC)Grant No. 2021.04272. CEECIND from the Stimulus of Scientific Employment, Individual Support (CEECIND) - 4th Edition provided by “FCT – Funda??o para a Ciência, DOI : https:// doi. org/ 10. 54499/ 2021. 04272. CEECI ND/ CP1679/ CT0003”。
文摘Wayside monitoring is a promising cost-effective alternative to predict damage in the rolling stock. The main goal of this work is to present an unsupervised methodology to identify out-of-roundness(OOR) damage wheels, such as wheel flats and polygonal wheels. This automatic damage identification algorithm is based on the vertical acceleration evaluated on the rails using a virtual wayside monitoring system and involves the application of a two-step procedure. The first step aims to define a confidence boundary by using(healthy) measurements evaluated on the rail constituting a baseline. The second step of the procedure involves classifying damage of predefined scenarios with different levels of severities. The proposed procedure is based on a machine learning methodology and includes the following stages:(1) data collection,(2) damage-sensitive feature extraction from the acquired responses using a neural network model, i.e., the sparse autoencoder(SAE),(3) data fusion based on the Mahalanobis distance, and(4) unsupervised feature classification by implementing outlier and cluster analysis. This procedure considers baseline responses at different speeds and rail irregularities to train the SAE model. Then, the trained SAE is capable to reconstruct test responses(not trained) allowing to compute the accumulative difference between original and reconstructed signals. The results prove the efficiency of the proposed approach in identifying the two most common types of OOR in railway wheels.
文摘Network security problems bring many imperceptible threats to the integrity of data and the reliability of device services,so proposing a network intrusion detection model with high reliability is of great research significance for network security.Due to the strong generalization of invalid features during training process,it is more difficult for single autoencoder intrusion detection model to obtain effective results.A network intrusion detection model based on the Ensemble of Denoising Adversarial Autoencoder(EDAAE)was proposed,which had higher accuracy and reliability compared to the traditional anomaly detection model.Using the adversarial learning idea of Adversarial Autoencoder(AAE),the discriminator module was added to the original model,and the encoder part was used as the generator.The distribution of the hidden space of the data generated by the encoder matched with the distribution of the original data.The generalization of the model to the invalid features was also reduced to improve the detection accuracy.At the same time,the denoising autoencoder and integrated operation was introduced to prevent overfitting in the adversarial learning process.Experiments on the CICIDS2018 traffic dataset showed that the proposed intrusion detection model achieves an Accuracy of 95.23%,which out performs traditional self-encoders and other existing intrusion detection models methods in terms of overall performance.
基金supported by the National Natural Science Foundation of China(Grant Nos.U20A20186 and 62372063).
文摘Fault diagnosis of traction systems is important for the safety operation of high-speed trains.Long-term operation of the trains will degrade the performance of systems,which decreases the fault detection accuracy.To solve this problem,this paper proposes a fault detection method developed by a Generalized Autoencoder(GAE)for systems with performance degradation.The advantage of this method is that it can accurately detect faults when the traction system of high-speed trains is affected by performance degradation.Regardless of the probability distribution,it can handle any data,and the GAE has extremely high sensitivity in anomaly detection.Finally,the effectiveness of this method is verified through the Traction Drive Control System(TDCS)platform.At different performance degradation levels,our method’s experimental results are superior to traditional methods.
基金Natural Science Foundation of Fujian Province(No.2019J05026)in part by the Education Scientific Research Project for Young Teachers of Fujian Province(No.JT180053).
文摘Unmanned surface vehicle(USV)is currently a hot research topic in maritime communication network(MCN),where denoising and semantic segmentation of maritime images taken by USV have been rarely studied.The former has recently researched on autoencoder model used for image denoising,but the existed models are too complicated to be suitable for real-time detection of USV.In this paper,we proposed a lightweight autoencoder combined with inception module for maritime image denoising in different noisy environments and explore the effect of different inception modules on the denoising performance.Furthermore,we completed the semantic segmentation task for maritime images taken by USV utilizing the pretrained U-Net model with tuning,and compared them with original U-Net model based on different backbone.Subsequently,we compared the semantic segmentation of noised and denoised maritime images respectively to explore the effect of image noise on semantic segmentation performance.Case studies are provided to prove the feasibility of our proposed denoising and segmentation method.Finally,a simple integrated communication system combining image denoising and segmentation for USV is shown.
基金supported by the basic science research program through the National Research Foundation of Korea(NRF)(2020R1F1A1073395)the basic research project of the Korea Institute of Geoscience and Mineral Resources(KIGAM)(GP2021-011,GP2020-031,21-3117)funded by the Ministry of Science and ICT,Korea。
文摘This paper presents an innovative data-integration that uses an iterative-learning method,a deep neural network(DNN)coupled with a stacked autoencoder(SAE)to solve issues encountered with many-objective history matching.The proposed method consists of a DNN-based inverse model with SAE-encoded static data and iterative updates of supervised-learning data are based on distance-based clustering schemes.DNN functions as an inverse model and results in encoded flattened data,while SAE,as a pre-trained neural network,successfully reduces dimensionality and reliably reconstructs geomodels.The iterative-learning method can improve the training data for DNN by showing the error reduction achieved with each iteration step.The proposed workflow shows the small mean absolute percentage error below 4%for all objective functions,while a typical multi-objective evolutionary algorithm fails to significantly reduce the initial population uncertainty.Iterative learning-based manyobjective history matching estimates the trends in water cuts that are not reliably included in dynamicdata matching.This confirms the proposed workflow constructs more plausible geo-models.The workflow would be a reliable alternative to overcome the less-convergent Pareto-based multi-objective evolutionary algorithm in the presence of geological uncertainty and varying objective functions.
基金National Natural Science Foundation of China (Project No. 61273365)111 Project (No. B08004) are gratefully acknowledged
文摘Offline Urdu Nastaleeq text recognition has long been a serious problem due to its very cursive nature. In order to get rid of the character segmentation problems, many researchers are shifting focus towards segmentation free ligature based recognition approaches. Majority of the prevalent ligature based recognition systems heavily rely on hand-engineered feature extraction techniques. However, such techniques are more error prone and may often lead to a loss of useful information that might hardly be captured later by any manual features. Most of the prevalent Urdu Nastaleeq test recognition was trained and tested on small sets. This paper proposes the use of stacked denoising autoencoder for automatic feature extraction directly from raw pixel values of ligature images. Such deep learning networks have not been applied for the recognition of Urdu text thus far. Different stacked denoising autoencoders have been trained on 178573 ligatures with 3732 classes from un-degraded(noise free) UPTI(Urdu Printed Text Image) data set. Subsequently, trained networks are validated and tested on degraded versions of UPTI data set. The experimental results demonstrate accuracies in range of 93% to 96% which are better than the existing Urdu OCR systems for such large dataset of ligatures.
基金supported by Hong Kong Government general research fund (GRF) under project number PolyU152757/16ENational Natural Science Foundation China under project numbers 61435006 and 61401020
文摘We study the effects of quantization and additive white Gaussian noise(AWGN) in transmitting latent representations of images over a noisy communication channel. The latent representations are obtained using autoencoders(AEs). We analyze image reconstruction and classification performance for different channel noise powers, latent vector sizes, and number of quantization bits used for the latent variables as well as AEs’ parameters. The results show that the digital transmission of latent representations using conventional AEs alone is extremely vulnerable to channel noise and quantization effects. We then propose a combination of basic AE and a denoising autoencoder(DAE) to denoise the corrupted latent vectors at the receiver. This approach demonstrates robustness against channel noise and quantization effects and enables a significant improvement in image reconstruction and classification performance particularly in adverse scenarios with high noise powers and significant quantization effects.
文摘Secure transmission of images over a communication channel, with limited data transfer capacity, possesses compression and encryption schemes. A deep learning based hybrid image compression-encryption scheme is proposed by combining stacked auto-encoder with the logistic map. The proposed structure of stacked autoencoder has seven multiple layers, and back propagation algorithm is intended to extend vector portrayal of information into lower vector space. The randomly generated key is used to set initial conditions and control parameters of logistic map. Subsequently, compressed image is encrypted by substituting and scrambling of pixel sequences using key stream sequences generated from logistic map.The proposed algorithms are experimentally tested over five standard grayscale images. Compression and encryption efficiency of proposed algorithms are evaluated and analyzed based on peak signal to noise ratio(PSNR), mean square error(MSE), structural similarity index metrics(SSIM) and statistical,differential, entropy analysis respectively. Simulation results show that proposed algorithms provide high quality reconstructed images with excellent levels of security during transmission..
基金supported in part by the National Natural Science Foundation of China(Grant 62101306)in part by the National Key R&D Program of China(Grant 2018YFB1801501)+2 种基金in part by Shenzhen Special Projects for the Development of Strategic Emerging Industries(201806081439290640)in part by Shenzhen Wireless over VLC Technology Engineering Lab Promotionin part by Postdoctoral Science Foundation of China(Grant 2020M670332)。
文摘Terahertz wireless communication has been regarded as an emerging technology to satisfy the ever-increasing demand of ultra-high-speed wireless communications.However,affected by the imperfections of cheap and energy-efficient Terahertz devices,Terahertz signals suffer from serve hybrid distortions,including in-phase/quadrature imbalance,phase noise and nonlinearity,which degrade the demodulation performance significantly.To improve the robustness against these hybrid distortions,an improved autoencoder is proposed,which includes coding the transmitted symbols at the transmitter and decoding the corresponding signals at the receiver.Moreover,due to the lack of information of Terahertz channel during the training of the autoencoder,a fitting network is proposed to approximate the characteristics of Terahertz channel,which provides an approximation of the gradients of loss.Simulation results show that our proposed autoencoder with fitting network can recover the transmitted symbols under serious hybrid distortions,and improves the demodulation performance significantly.
基金the National Nat-ural Science Foundation of China under Grant No.62072406,No.U19B2016,No.U20B2038 and No.61871398the Natural Science Foundation of Zhejiang Province under Grant No.LY19F020025the Major Special Funding for“Science and Tech-nology Innovation 2025”in Ningbo under Grant No.2018B10063.
文摘The spectrum sensing model based on deep learning has achieved satisfying detection per-formence,but its robustness has not been verified.In this paper,we propose primary user adversarial attack(PUAA)to verify the robustness of the deep learning based spectrum sensing model.PUAA adds a care-fully manufactured perturbation to the benign primary user signal,which greatly reduces the probability of detection of the spectrum sensing model.We design three PUAA methods in black box scenario.In or-der to defend against PUAA,we propose a defense method based on autoencoder named DeepFilter.We apply the long short-term memory network and the convolutional neural network together to DeepFilter,so that it can extract the temporal and local features of the input signal at the same time to achieve effective defense.Extensive experiments are conducted to eval-uate the attack effect of the designed PUAA method and the defense effect of DeepFilter.Results show that the three PUAA methods designed can greatly reduce the probability of detection of the deep learning-based spectrum sensing model.In addition,the experimen-tal results of the defense effect of DeepFilter show that DeepFilter can effectively defend against PUAA with-out affecting the detection performance of the model.
基金supported by the National Natural Science Foundation of China [Nos. 61772452, 61379116]the Scientific and Technological Innovation Programs of Higher Education Institutions in Shanxi [No.2019L0847]the Natural Science Foundation of Hebei Province, China [No. F2015203046]
文摘Faced with the evolving attacks in recommender systems, many detection features have been proposed by human engineering and used in supervised or unsupervised detection methods. However, the detection features extracted by human engineering are usually aimed at some specific types of attacks. To further detect other new types of attacks, the traditional methods have to re-extract detection features with high knowledge cost. To address these limitations, the method for automatic extraction of robust features is proposed and then an Adaboost-based detection method is presented. Firstly, to obtain robust representation with prior knowledge, unlike uniform corruption rate in traditional mLDA(marginalized Linear Denoising Autoencoder), different corruption rates for items are calculated according to the ratings’ distribution. Secondly, the ratings sparsity is used to weight the mapping matrix to extract low-dimensional representation. Moreover, the uniform corruption rate is also set to the next layer in mSLDA(marginalized Stacked Linear Denoising Autoencoder) to extract the stable and robust user features. Finally, under the robust feature space, an Adaboost-based detection method is proposed to alleviate the imbalanced classification problem. Experimental results on the Netflix and Amazon review datasets indicate that the proposed method can effectively detect various attacks.
基金the National Natural Science Foundations of China(Nos.91860125,51705398)the National Key Basic Research Program of China(No.2015CB057400)the Shaanxi Province 2020 Natural Science Basic Research Plan(No.2020JQ-042).
文摘Weak feature extraction is of great importance for condition monitoring and intelligent diagnosis of aeroengine.Aimed at achieving intelligent diagnosis of aero-engine main shaft bearing,an enhanced sparsity-assisted intelligent condition monitoring method is proposed in this paper.Through analyzing the weakness of convex sparse model,i.e.the tradeoff between noise reduction and feature reconstruction,this paper proposes an enhanced-sparsity nonconvex regularized convex model based on Moreau envelope to achieve weak feature extraction.Accordingly,a sparsity-assisted deep convolutional variational autoencoders network is proposed,which achieves the intelligent identification of fault state through training denoised normal data.Finally,the effectiveness of the proposed method is verified through aero-engine bearing run-to-failure experiment.The comparison results show that the proposed method is good at abnormal pattern recognition,showing a good potential for weak fault intelligent diagnosis of aero-engine main shaft bearings.
基金supported by the National Natural Science Foundation of China(No.51605309)the Aeronautical Science Foundation of China(Nos.201933054002,20163354004)。
文摘The health status of aero engines is very important to the flight safety.However,it is difficult for aero engines to make an effective fault diagnosis due to its complex structure and poor working environment.Therefore,an effective fault diagnosis method for aero engines based on the gravitational search algorithm and the stack autoencoder(GSA-SAE)is proposed,and the fault diagnosis technology of a turbofan engine is studied.Firstly,the data of 17 parameters,including total inlet air temperature,high-pressure rotor speed,low-pressure rotor speed,turbine pressure ratio,total inlet air temperature of high-pressure compressor and outlet air pressure of high-pressure compressor and so on,are preprocessed,and the fault diagnosis model architecture of SAE is constructed.In order to solve the problem that the best diagnosis effect cannot be obtained due to manually setting the number of neurons in each hidden layer of SAE network,a GSA optimization algorithm for the SAE network is proposed to find and obtain the optimal number of neurons in each hidden layer of SAE network.Furthermore,an optimal fault diagnosis model based on GSA-SAE is established for aero engines.Finally,the effectiveness of the optimal GSA-SAE fault diagnosis model is demonstrated using the practical data of aero engines.The results illustrate that the proposed fault diagnosis method effectively solves the problem of the poor fault diagnosis result because of manually setting the number of neurons in each hidden layer of SAE network,and has good fault diagnosis efficiency.The fault diagnosis accuracy of the GSA-SAE model reaches 98.222%,which is significantly higher than that of SAE,the general regression neural network(GRNN)and the back propagation(BP)network fault diagnosis models.
基金supported in part by the China NSFC Grant 61872248Guangdong NSF 2017A030312008+1 种基金Fok Ying-Tong Education Foundation for Young Teachers in the Higher Education Institutions of China (Grant No.161064)GDUPS (2015)
文摘Spectrum management and resource allocation(RA)problems are challenging and critical in a vast number of research areas such as wireless communications and computer networks.The traditional approaches for solving such problems usually consume time and memory,especially for large-size problems.Recently different machine learning approaches have been considered as potential promising techniques for combinatorial optimization problems,especially the generative model of the deep neural networks.In this work,we propose a resource allocation deep autoencoder network,as one of the promising generative models,for enabling spectrum sharing in underlay device-to-device(D2D)communication by solving linear sum assignment problems(LSAPs).Specifically,we investigate the performance of three different architectures for the conditional variational autoencoders(CVAE).The three proposed architecture are the convolutional neural network(CVAECNN)autoencoder,the feed-forward neural network(CVAE-FNN)autoencoder,and the hybrid(H-CVAE)autoencoder.The simulation results show that the proposed approach could be used as a replacement of the conventional RA techniques,such as the Hungarian algorithm,due to its ability to find solutions of LASPs of different sizes with high accuracy and very fast execution time.Moreover,the simulation results reveal that the accuracy of the proposed hybrid autoencoder architecture outperforms the other proposed architectures and the state-of-the-art DNN techniques.
