Due to the lack of long-range association and spatial location information,fine details and accurate boundaries of complex clothing images cannot always be obtained by using the existing deep learning-based methods.Th...Due to the lack of long-range association and spatial location information,fine details and accurate boundaries of complex clothing images cannot always be obtained by using the existing deep learning-based methods.This paper presents a convolutional structure with multi-scale fusion to optimize the step of clothing feature extraction and a self-attention module to capture long-range association information.The structure enables the self-attention mechanism to directly participate in the process of information exchange through the down-scaling projection operation of the multi-scale framework.In addition,the improved self-attention module introduces the extraction of 2-dimensional relative position information to make up for its lack of ability to extract spatial position features from clothing images.The experimental results based on the colorful fashion parsing dataset(CFPD)show that the proposed network structure achieves 53.68%mean intersection over union(mIoU)and has better performance on the clothing parsing task.展开更多
Fault diagnosis is important for maintaining the safety and effectiveness of chemical process.Considering the multivariate,nonlinear,and dynamic characteristic of chemical process,many time-series-based data-driven fa...Fault diagnosis is important for maintaining the safety and effectiveness of chemical process.Considering the multivariate,nonlinear,and dynamic characteristic of chemical process,many time-series-based data-driven fault diagnosis methods have been developed in recent years.However,the existing methods have the problem of long-term dependency and are difficult to train due to the sequential way of training.To overcome these problems,a novel fault diagnosis method based on time-series and the hierarchical multihead self-attention(HMSAN)is proposed for chemical process.First,a sliding window strategy is adopted to construct the normalized time-series dataset.Second,the HMSAN is developed to extract the time-relevant features from the time-series process data.It improves the basic self-attention model in both width and depth.With the multihead structure,the HMSAN can pay attention to different aspects of the complicated chemical process and obtain the global dynamic features.However,the multiple heads in parallel lead to redundant information,which cannot improve the diagnosis performance.With the hierarchical structure,the redundant information is reduced and the deep local time-related features are further extracted.Besides,a novel many-to-one training strategy is introduced for HMSAN to simplify the training procedure and capture the long-term dependency.Finally,the effectiveness of the proposed method is demonstrated by two chemical cases.The experimental results show that the proposed method achieves a great performance on time-series industrial data and outperforms the state-of-the-art approaches.展开更多
With the development of short video industry,video and bullet screen have become important ways to spread public opinions.Public attitudes can be timely obtained through emotional analysis on bullet screen,which can a...With the development of short video industry,video and bullet screen have become important ways to spread public opinions.Public attitudes can be timely obtained through emotional analysis on bullet screen,which can also reduce difficulties in management of online public opinions.A convolutional neural network model based on multi-head attention is proposed to solve the problem of how to effectively model relations among words and identify key words in emotion classification tasks with short text contents and lack of complete context information.Firstly,encode word positions so that order information of input sequences can be used by the model.Secondly,use a multi-head attention mechanism to obtain semantic expressions in different subspaces,effectively capture internal relevance and enhance dependent relationships among words,as well as highlight emotional weights of key emotional words.Then a dilated convolution is used to increase the receptive field and extract more features.On this basis,the above multi-attention mechanism is combined with a convolutional neural network to model and analyze the seven emotional categories of bullet screens.Testing from perspectives of model and dataset,experimental results can validate effectiveness of our approach.Finally,emotions of bullet screens are visualized to provide data supports for hot event controls and other fields.展开更多
Keyphrase greatly provides summarized and valuable information.This information can help us not only understand text semantics,but also organize and retrieve text content effectively.The task of automatically generati...Keyphrase greatly provides summarized and valuable information.This information can help us not only understand text semantics,but also organize and retrieve text content effectively.The task of automatically generating it has received considerable attention in recent decades.From the previous studies,we can see many workable solutions for obtaining keyphrases.One method is to divide the content to be summarized into multiple blocks of text,then we rank and select the most important content.The disadvantage of this method is that it cannot identify keyphrase that does not include in the text,let alone get the real semantic meaning hidden in the text.Another approach uses recurrent neural networks to generate keyphrases from the semantic aspects of the text,but the inherently sequential nature precludes parallelization within training examples,and distances have limitations on context dependencies.Previous works have demonstrated the benefits of the self-attention mechanism,which can learn global text dependency features and can be parallelized.Inspired by the above observation,we propose a keyphrase generation model,which is based entirely on the self-attention mechanism.It is an encoder-decoder model that can make up the above disadvantage effectively.In addition,we also consider the semantic similarity between keyphrases,and add semantic similarity processing module into the model.This proposed model,which is demonstrated by empirical analysis on five datasets,can achieve competitive performance compared to baseline methods.展开更多
Objective To propose a Light-Atten-Pose-based algorithm for classifying abnormal morphol-ogy in traditional Chinese medicine(TCM)inspection to solve the problem of relying on manual labor or expensive equipment with p...Objective To propose a Light-Atten-Pose-based algorithm for classifying abnormal morphol-ogy in traditional Chinese medicine(TCM)inspection to solve the problem of relying on manual labor or expensive equipment with personal subjectivity or high cost.Methods First,this paper establishes a dataset of abnormal morphology for Chinese medi-cine diagnosis,with images from public resources and labeled with category labels by several Chinese medicine experts,including three categories:normal,shoulder abnormality,and leg abnormality.Second,the key points of human body are extracted by Light-Atten-Pose algo-rithm.Light-Atten-Pose algorithm uses lightweight EfficientNet network and polarized self-attention(PSA)mechanism on the basis of AlphaPose,which reduces the computation amount by using EfficientNet network,and the data is finely processed by using PSA mecha-nism in spatial and channel dimensions.Finally,according to the theory of TCM inspection,the abnormal morphology standard based on the joint angle difference is defined,and the classification of abnormal morphology of Chinese medical diagnosis is realized by calculat-ing the angle between key points.Accuracy,frames per second(FPS),model size,parameter set(Params),and giga floating-point operations per second(GFLOPs)are chosen as the eval-uation indexes for lightweighting.Results Validation of the Light-Atten-Pose algorithm on the dataset showed a classification accuracy of 96.23%,which is close to the original AlphaPose model.However,the FPS of the improved model reaches 41.6 fps from 16.5 fps,the model size is reduced from 155.11 MB to 33.67 MB,the Params decreases from 40.5 M to 8.6 M,and the GFLOPs reduces from 11.93 to 2.10.Conclusion The Light-Atten-Pose algorithm achieves lightweight while maintaining high ro-bustness,resulting in lower complexity and resource consumption and higher classification accuracy,and the experiments prove that the Light-Atten-Pose algorithm has a better overall performance and has practical application in the pose estimation task.展开更多
Fraud cases have been a risk in society and people’s property security has been greatly threatened.In recent studies,many promising algorithms have been developed for social media offensive text recognition as well a...Fraud cases have been a risk in society and people’s property security has been greatly threatened.In recent studies,many promising algorithms have been developed for social media offensive text recognition as well as sentiment analysis.These algorithms are also suitable for fraudulent phone text recognition.Compared to these tasks,the semantics of fraudulent words are more complex and more difficult to distinguish.Recurrent Neural Networks(RNN),the variants ofRNN,ConvolutionalNeuralNetworks(CNN),and hybrid neural networks to extract text features are used by most text classification research.However,a single network or a simple network combination cannot obtain rich characteristic knowledge of fraudulent phone texts relatively.Therefore,a new model is proposed in this paper.In the fraudulent phone text,the knowledge that can be learned by the model includes the sequence structure of sentences,the correlation between words,the correlation of contextual semantics,the feature of keywords in sentences,etc.The new model combines a bidirectional Long-Short Term Memory Neural Network(BiLSTM)or a bidirectional Gate Recurrent United(BiGRU)and a Multi-Head attention mechanism module with convolution.A normalization layer is added after the output of the final hidden layer.BiLSTM or BiGRU is used to build the encoding and decoding layer.Multi-head attention mechanism module with convolution(MHAC)enhances the ability of the model to learn global interaction information and multi-granularity local interaction information in fraudulent sentences.A fraudulent phone text dataset is produced by us in this paper.The THUCNews data sets and fraudulent phone text data sets are used in experiments.Experiment results show that compared with the baseline model,the proposed model(LMHACL)has the best experiment results in terms of Accuracy,Precision,Recall,and F1 score on the two data sets.And the performance indexes on fraudulent phone text data sets are all above 0.94.展开更多
Automatic extraction of the patient’s health information from the unstructured data concerning the discharge summary remains challenging.Discharge summary related documents contain various aspects of the patient heal...Automatic extraction of the patient’s health information from the unstructured data concerning the discharge summary remains challenging.Discharge summary related documents contain various aspects of the patient health condition to examine the quality of treatment and thereby help improve decision-making in the medical field.Using a sentiment dictionary and feature engineering,the researchers primarily mine semantic text features.However,choosing and designing features requires a lot of manpower.The proposed approach is an unsupervised deep learning model that learns a set of clusters embedded in the latent space.A composite model including Active Learning(AL),Convolutional Neural Network(CNN),BiGRU,and Multi-Attention,called ACBMA in this research,is designed to measure the quality of treatment based on discharge summaries text sentiment detection.CNN is utilized for extracting the set of local features of text vectors.Then BiGRU network was utilized to extract the text’s global features to solve the issues that a single CNN cannot obtain global semantic information and the traditional Recurrent Neural Network(RNN)gradient disappearance.Experiments prove that the ACBMA method can demonstrate the effectiveness of the suggested method,achieve comparable results to state-of-arts methods in sentiment detection,and outperform them with accurate benchmarks.Finally,several algorithm studies ultimately determined that the ACBMA method is more precise for discharge summaries sentiment analysis.展开更多
Nowadays,with the rapid development of industrial Internet technology,on the one hand,advanced industrial control systems(ICS)have improved industrial production efficiency.However,there are more and more cyber-attack...Nowadays,with the rapid development of industrial Internet technology,on the one hand,advanced industrial control systems(ICS)have improved industrial production efficiency.However,there are more and more cyber-attacks targeting industrial control systems.To ensure the security of industrial networks,intrusion detection systems have been widely used in industrial control systems,and deep neural networks have always been an effective method for identifying cyber attacks.Current intrusion detection methods still suffer from low accuracy and a high false alarm rate.Therefore,it is important to build a more efficient intrusion detection model.This paper proposes a hybrid deep learning intrusion detection method based on convolutional neural networks and bidirectional long short-term memory neural networks(CNN-BiLSTM).To address the issue of imbalanced data within the dataset and improve the model’s detection capabilities,the Synthetic Minority Over-sampling Technique-Edited Nearest Neighbors(SMOTE-ENN)algorithm is applied in the preprocessing phase.This algorithm is employed to generate synthetic instances for the minority class,simultaneously mitigating the impact of noise in the majority class.This approach aims to create a more equitable distribution of classes,thereby enhancing the model’s ability to effectively identify patterns in both minority and majority classes.In the experimental phase,the detection performance of the method is verified using two data sets.Experimental results show that the accuracy rate on the CICIDS-2017 data set reaches 97.7%.On the natural gas pipeline dataset collected by Lan Turnipseed from Mississippi State University in the United States,the accuracy rate also reaches 85.5%.展开更多
Due to the closed working environment of shield machines,the construction personnel cannot observe the construction geological environment,which seriously restricts the safety and efficiency of the tunneling process.I...Due to the closed working environment of shield machines,the construction personnel cannot observe the construction geological environment,which seriously restricts the safety and efficiency of the tunneling process.In this study,we present an enhanced multi-head self-attention convolution neural network(EMSACNN)with two-stage feature extraction for geological condition prediction of shield machine.Firstly,we select 30 important parameters according to statistical analysis method and the working principle of the shield machine.Then,we delete the non-working sample data,and combine 10 consecutive data as the input of the model.Thereafter,to deeply mine and extract essential and relevant features,we build a novel model combined with the particularity of the geological type recognition task,in which an enhanced multi-head self-attention block is utilized as the first feature extractor to fully extract the correlation of geological information of adjacent working face of tunnel,and two-dimensional CNN(2dCNN)is utilized as the second feature extractor.The performance and superiority of proposed EMSACNN are verified by the actual data collected by the shield machine used in the construction of a double-track tunnel in Guangzhou,China.The results show that EMSACNN achieves at least 96%accuracy on the test sets of the two tunnels,and all the evaluation indicators of EMSACNN are much better than those of classical AI model and the model that use only the second-stage feature extractor.Therefore,the proposed EMSACNN achieves high accuracy and strong generalization for geological information prediction of shield machine,which is of great guiding significance to engineering practice.展开更多
Considering the stealthiness and persistence of Advanced Persistent Threats(APTs),system audit logs are leveraged in recent studies to construct system entity interaction provenance graphs to unveil threats in a host....Considering the stealthiness and persistence of Advanced Persistent Threats(APTs),system audit logs are leveraged in recent studies to construct system entity interaction provenance graphs to unveil threats in a host.Rule-based provenance graph APT detection approaches require elaborate rules and cannot detect unknown attacks,and existing learning-based approaches are limited by the lack of available APT attack samples or generally only perform graph-level anomaly detection,which requires lots of manual efforts to locate attack entities.This paper proposes an APT-exploited process detection approach called ThreatSniffer,which constructs the benign provenance graph from attack-free audit logs,fits normal system entity interactions and then detects APT-exploited processes by predicting the rationality of entity interactions.Firstly,ThreatSniffer understands system entities in terms of their file paths,interaction sequences,and the number distribution of interaction types and uses the multi-head self-attention mechanism to fuse these semantics.Then,based on the insight that APT-exploited processes interact with system entities they should not invoke,ThreatSniffer performs negative sampling on the benign provenance graph to generate non-existent edges,thus characterizing irrational entity interactions without requiring APT attack samples.At last,it employs a heterogeneous graph neural network as the interaction prediction model to aggregate the contextual information of entity interactions,and locate processes exploited by attackers,thereby achieving fine-grained APT detection.Evaluation results demonstrate that anomaly-based detection enables ThreatSniffer to identify all attack activities.Compared to the node-level APT detection method APT-KGL,ThreatSniffer achieves a 6.1%precision improvement because of its comprehensive understanding of entity semantics.展开更多
Long-term urban traffic flow prediction is an important task in the field of intelligent transportation,as it can help optimize traffic management and improve travel efficiency.To improve prediction accuracy,a crucial...Long-term urban traffic flow prediction is an important task in the field of intelligent transportation,as it can help optimize traffic management and improve travel efficiency.To improve prediction accuracy,a crucial issue is how to model spatiotemporal dependency in urban traffic data.In recent years,many studies have adopted spatiotemporal neural networks to extract key information from traffic data.However,most models ignore the semantic spatial similarity between long-distance areas when mining spatial dependency.They also ignore the impact of predicted time steps on the next unpredicted time step for making long-term predictions.Moreover,these models lack a comprehensive data embedding process to represent complex spatiotemporal dependency.This paper proposes a multi-scale persistent spatiotemporal transformer(MSPSTT)model to perform accurate long-term traffic flow prediction in cities.MSPSTT adopts an encoder-decoder structure and incorporates temporal,periodic,and spatial features to fully embed urban traffic data to address these issues.The model consists of a spatiotemporal encoder and a spatiotemporal decoder,which rely on temporal,geospatial,and semantic space multi-head attention modules to dynamically extract temporal,geospatial,and semantic characteristics.The spatiotemporal decoder combines the context information provided by the encoder,integrates the predicted time step information,and is iteratively updated to learn the correlation between different time steps in the broader time range to improve the model’s accuracy for long-term prediction.Experiments on four public transportation datasets demonstrate that MSPSTT outperforms the existing models by up to 9.5%on three common metrics.展开更多
Due to the rapid evolution of Advanced Persistent Threats(APTs)attacks,the emergence of new and rare attack samples,and even those never seen before,make it challenging for traditional rule-based detection methods to ...Due to the rapid evolution of Advanced Persistent Threats(APTs)attacks,the emergence of new and rare attack samples,and even those never seen before,make it challenging for traditional rule-based detection methods to extract universal rules for effective detection.With the progress in techniques such as transfer learning and meta-learning,few-shot network attack detection has progressed.However,challenges in few-shot network attack detection arise from the inability of time sequence flow features to adapt to the fixed length input requirement of deep learning,difficulties in capturing rich information from original flow in the case of insufficient samples,and the challenge of high-level abstract representation.To address these challenges,a few-shot network attack detection based on NFHP(Network Flow Holographic Picture)-RN(ResNet)is proposed.Specifically,leveraging inherent properties of images such as translation invariance,rotation invariance,scale invariance,and illumination invariance,network attack traffic features and contextual relationships are intuitively represented in NFHP.In addition,an improved RN network model is employed for high-level abstract feature extraction,ensuring that the extracted high-level abstract features maintain the detailed characteristics of the original traffic behavior,regardless of changes in background traffic.Finally,a meta-learning model based on the self-attention mechanism is constructed,achieving the detection of novel APT few-shot network attacks through the empirical generalization of high-level abstract feature representations of known-class network attack behaviors.Experimental results demonstrate that the proposed method can learn high-level abstract features of network attacks across different traffic detail granularities.Comparedwith state-of-the-artmethods,it achieves favorable accuracy,precision,recall,and F1 scores for the identification of unknown-class network attacks through cross-validation onmultiple datasets.展开更多
Due to their robust learning and expression ability for complex features,the deep learning(DL)model plays a vital role in bearing fault diagnosis.However,since there are fewer labeled samples in fault diagnosis,the de...Due to their robust learning and expression ability for complex features,the deep learning(DL)model plays a vital role in bearing fault diagnosis.However,since there are fewer labeled samples in fault diagnosis,the depth of DL models in fault diagnosis is generally shallower than that of DL models in other fields,which limits the diagnostic performance.To solve this problem,a novel transfer residual Swin Transformer(RST)is proposed for rolling bearings in this paper.RST has 24 residual self-attention layers,which use the hierarchical design and the shifted window-based residual self-attention.Combined with transfer learning techniques,the transfer RST model uses pre-trained parameters from ImageNet.A new end-to-end method for fault diagnosis based on deep transfer RST is proposed.Firstly,wavelet transform transforms the vibration signal into a wavelet time-frequency diagram.The signal’s time-frequency domain representation can be represented simultaneously.Secondly,the wavelet time-frequency diagram is the input of the RST model to obtain the fault type.Finally,our method is verified on public and self-built datasets.Experimental results show the superior performance of our method by comparing it with a shallow neural network.展开更多
Emotional electroencephalography(EEG)signals are a primary means of recording emotional brain activity.Currently,the most effective methods for analyzing emotional EEG signals involve feature engineering and neural ne...Emotional electroencephalography(EEG)signals are a primary means of recording emotional brain activity.Currently,the most effective methods for analyzing emotional EEG signals involve feature engineering and neural networks.However,neural networks possess a strong ability for automatic feature extraction.Is it possible to discard feature engineering and directly employ neural networks for end-to-end recognition?Based on the characteristics of EEG signals,this paper proposes an end-to-end feature extraction and classification method for a dynamic self-attention network(DySAT).The study reveals significant differences in brain activity patterns associated with different emotions across various experimenters and time periods.The results of this experiment can provide insights into the reasons behind these differences.展开更多
In this paper,an artificial-intelligence-based fiber communication receiver model is put forward.With the multi-head attention mechanism it contains,this model can extract crucial patterns and map the transmitted sign...In this paper,an artificial-intelligence-based fiber communication receiver model is put forward.With the multi-head attention mechanism it contains,this model can extract crucial patterns and map the transmitted signals into the bit stream.Once appropriately trained,it can obtain the ability to restore the information from the signals whose transmission distances range from 0 to 100 km,signal-to-noise ratios range from 0 to 20 dB,modulation formats range from OOK to PAM4,and symbol rates range from 10 to 40 GBaud.The validity of the model is numerically demonstrated via MATLAB and Pytorch scenarios and compared with traditional communication receivers.展开更多
To fully make use of information from different representation subspaces,a multi-head attention-based long short-term memory(LSTM)model is proposed in this study for speech emotion recognition(SER).The proposed model ...To fully make use of information from different representation subspaces,a multi-head attention-based long short-term memory(LSTM)model is proposed in this study for speech emotion recognition(SER).The proposed model uses frame-level features and takes the temporal information of emotion speech as the input of the LSTM layer.Here,a multi-head time-dimension attention(MHTA)layer was employed to linearly project the output of the LSTM layer into different subspaces for the reduced-dimension context vectors.To provide relative vital information from other dimensions,the output of MHTA,the output of feature-dimension attention,and the last time-step output of LSTM were utilized to form multiple context vectors as the input of the fully connected layer.To improve the performance of multiple vectors,feature-dimension attention was employed for the all-time output of the first LSTM layer.The proposed model was evaluated on the eNTERFACE and GEMEP corpora,respectively.The results indicate that the proposed model outperforms LSTM by 14.6%and 10.5%for eNTERFACE and GEMEP,respectively,proving the effectiveness of the proposed model in SER tasks.展开更多
False data injection attack(FDIA)can affect the state estimation of the power grid by tampering with the measured value of the power grid data,and then destroying the stable operation of the smart grid.Existing work u...False data injection attack(FDIA)can affect the state estimation of the power grid by tampering with the measured value of the power grid data,and then destroying the stable operation of the smart grid.Existing work usually trains a detection model by fusing the data-driven features from diverse power data streams.Data-driven features,however,cannot effectively capture the differences between noisy data and attack samples.As a result,slight noise disturbances in the power grid may cause a large number of false detections for FDIA attacks.To address this problem,this paper designs a deep collaborative self-attention network to achieve robust FDIA detection,in which the spatio-temporal features of cascaded FDIA attacks are fully integrated.Firstly,a high-order Chebyshev polynomials-based graph convolution module is designed to effectively aggregate the spatio information between grid nodes,and the spatial self-attention mechanism is involved to dynamically assign attention weights to each node,which guides the network to pay more attention to the node information that is conducive to FDIA detection.Furthermore,the bi-directional Long Short-Term Memory(LSTM)network is introduced to conduct time series modeling and long-term dependence analysis for power grid data and utilizes the temporal self-attention mechanism to describe the time correlation of data and assign different weights to different time steps.Our designed deep collaborative network can effectively mine subtle perturbations from spatiotemporal feature information,efficiently distinguish power grid noise from FDIA attacks,and adapt to diverse attack intensities.Extensive experiments demonstrate that our method can obtain an efficient detection performance over actual load data from New York Independent System Operator(NYISO)in IEEE 14,IEEE 39,and IEEE 118 bus systems,and outperforms state-of-the-art FDIA detection schemes in terms of detection accuracy and robustness.展开更多
Circular RNAs(circRNAs)are RNAs with closed circular structure involved in many biological processes by key interactions with RNA binding proteins(RBPs).Existing methods for predicting these interactions have limitati...Circular RNAs(circRNAs)are RNAs with closed circular structure involved in many biological processes by key interactions with RNA binding proteins(RBPs).Existing methods for predicting these interactions have limitations in feature learning.In view of this,we propose a method named circ2CBA,which uses only sequence information of circRNAs to predict circRNA-RBP binding sites.We have constructed a data set which includes eight sub-datasets.First,circ2CBA encodes circRNA sequences using the one-hot method.Next,a two-layer convolutional neural network(CNN)is used to initially extract the features.After CNN,circ2CBA uses a layer of bidirectional long and short-term memory network(BiLSTM)and the self-attention mechanism to learn the features.The AUC value of circ2CBA reaches 0.8987.Comparison of circ2CBA with other three methods on our data set and an ablation experiment confirm that circ2CBA is an effective method to predict the binding sites between circRNAs and RBPs.展开更多
文摘Due to the lack of long-range association and spatial location information,fine details and accurate boundaries of complex clothing images cannot always be obtained by using the existing deep learning-based methods.This paper presents a convolutional structure with multi-scale fusion to optimize the step of clothing feature extraction and a self-attention module to capture long-range association information.The structure enables the self-attention mechanism to directly participate in the process of information exchange through the down-scaling projection operation of the multi-scale framework.In addition,the improved self-attention module introduces the extraction of 2-dimensional relative position information to make up for its lack of ability to extract spatial position features from clothing images.The experimental results based on the colorful fashion parsing dataset(CFPD)show that the proposed network structure achieves 53.68%mean intersection over union(mIoU)and has better performance on the clothing parsing task.
基金supported by the National Natural Science Foundation of China(62073140,62073141)the Shanghai Rising-Star Program(21QA1401800).
文摘Fault diagnosis is important for maintaining the safety and effectiveness of chemical process.Considering the multivariate,nonlinear,and dynamic characteristic of chemical process,many time-series-based data-driven fault diagnosis methods have been developed in recent years.However,the existing methods have the problem of long-term dependency and are difficult to train due to the sequential way of training.To overcome these problems,a novel fault diagnosis method based on time-series and the hierarchical multihead self-attention(HMSAN)is proposed for chemical process.First,a sliding window strategy is adopted to construct the normalized time-series dataset.Second,the HMSAN is developed to extract the time-relevant features from the time-series process data.It improves the basic self-attention model in both width and depth.With the multihead structure,the HMSAN can pay attention to different aspects of the complicated chemical process and obtain the global dynamic features.However,the multiple heads in parallel lead to redundant information,which cannot improve the diagnosis performance.With the hierarchical structure,the redundant information is reduced and the deep local time-related features are further extracted.Besides,a novel many-to-one training strategy is introduced for HMSAN to simplify the training procedure and capture the long-term dependency.Finally,the effectiveness of the proposed method is demonstrated by two chemical cases.The experimental results show that the proposed method achieves a great performance on time-series industrial data and outperforms the state-of-the-art approaches.
基金National Natural Science Foundation of China(No.61562057)Gansu Science and Technology Plan Project(No.18JR3RA104)。
文摘With the development of short video industry,video and bullet screen have become important ways to spread public opinions.Public attitudes can be timely obtained through emotional analysis on bullet screen,which can also reduce difficulties in management of online public opinions.A convolutional neural network model based on multi-head attention is proposed to solve the problem of how to effectively model relations among words and identify key words in emotion classification tasks with short text contents and lack of complete context information.Firstly,encode word positions so that order information of input sequences can be used by the model.Secondly,use a multi-head attention mechanism to obtain semantic expressions in different subspaces,effectively capture internal relevance and enhance dependent relationships among words,as well as highlight emotional weights of key emotional words.Then a dilated convolution is used to increase the receptive field and extract more features.On this basis,the above multi-attention mechanism is combined with a convolutional neural network to model and analyze the seven emotional categories of bullet screens.Testing from perspectives of model and dataset,experimental results can validate effectiveness of our approach.Finally,emotions of bullet screens are visualized to provide data supports for hot event controls and other fields.
文摘Keyphrase greatly provides summarized and valuable information.This information can help us not only understand text semantics,but also organize and retrieve text content effectively.The task of automatically generating it has received considerable attention in recent decades.From the previous studies,we can see many workable solutions for obtaining keyphrases.One method is to divide the content to be summarized into multiple blocks of text,then we rank and select the most important content.The disadvantage of this method is that it cannot identify keyphrase that does not include in the text,let alone get the real semantic meaning hidden in the text.Another approach uses recurrent neural networks to generate keyphrases from the semantic aspects of the text,but the inherently sequential nature precludes parallelization within training examples,and distances have limitations on context dependencies.Previous works have demonstrated the benefits of the self-attention mechanism,which can learn global text dependency features and can be parallelized.Inspired by the above observation,we propose a keyphrase generation model,which is based entirely on the self-attention mechanism.It is an encoder-decoder model that can make up the above disadvantage effectively.In addition,we also consider the semantic similarity between keyphrases,and add semantic similarity processing module into the model.This proposed model,which is demonstrated by empirical analysis on five datasets,can achieve competitive performance compared to baseline methods.
基金National Key Research and Development Program of China(2022YFC3502302)。
文摘Objective To propose a Light-Atten-Pose-based algorithm for classifying abnormal morphol-ogy in traditional Chinese medicine(TCM)inspection to solve the problem of relying on manual labor or expensive equipment with personal subjectivity or high cost.Methods First,this paper establishes a dataset of abnormal morphology for Chinese medi-cine diagnosis,with images from public resources and labeled with category labels by several Chinese medicine experts,including three categories:normal,shoulder abnormality,and leg abnormality.Second,the key points of human body are extracted by Light-Atten-Pose algo-rithm.Light-Atten-Pose algorithm uses lightweight EfficientNet network and polarized self-attention(PSA)mechanism on the basis of AlphaPose,which reduces the computation amount by using EfficientNet network,and the data is finely processed by using PSA mecha-nism in spatial and channel dimensions.Finally,according to the theory of TCM inspection,the abnormal morphology standard based on the joint angle difference is defined,and the classification of abnormal morphology of Chinese medical diagnosis is realized by calculat-ing the angle between key points.Accuracy,frames per second(FPS),model size,parameter set(Params),and giga floating-point operations per second(GFLOPs)are chosen as the eval-uation indexes for lightweighting.Results Validation of the Light-Atten-Pose algorithm on the dataset showed a classification accuracy of 96.23%,which is close to the original AlphaPose model.However,the FPS of the improved model reaches 41.6 fps from 16.5 fps,the model size is reduced from 155.11 MB to 33.67 MB,the Params decreases from 40.5 M to 8.6 M,and the GFLOPs reduces from 11.93 to 2.10.Conclusion The Light-Atten-Pose algorithm achieves lightweight while maintaining high ro-bustness,resulting in lower complexity and resource consumption and higher classification accuracy,and the experiments prove that the Light-Atten-Pose algorithm has a better overall performance and has practical application in the pose estimation task.
基金This researchwas funded by the Major Science and Technology Innovation Project of Shandong Province in China(2019JZZY010120).
文摘Fraud cases have been a risk in society and people’s property security has been greatly threatened.In recent studies,many promising algorithms have been developed for social media offensive text recognition as well as sentiment analysis.These algorithms are also suitable for fraudulent phone text recognition.Compared to these tasks,the semantics of fraudulent words are more complex and more difficult to distinguish.Recurrent Neural Networks(RNN),the variants ofRNN,ConvolutionalNeuralNetworks(CNN),and hybrid neural networks to extract text features are used by most text classification research.However,a single network or a simple network combination cannot obtain rich characteristic knowledge of fraudulent phone texts relatively.Therefore,a new model is proposed in this paper.In the fraudulent phone text,the knowledge that can be learned by the model includes the sequence structure of sentences,the correlation between words,the correlation of contextual semantics,the feature of keywords in sentences,etc.The new model combines a bidirectional Long-Short Term Memory Neural Network(BiLSTM)or a bidirectional Gate Recurrent United(BiGRU)and a Multi-Head attention mechanism module with convolution.A normalization layer is added after the output of the final hidden layer.BiLSTM or BiGRU is used to build the encoding and decoding layer.Multi-head attention mechanism module with convolution(MHAC)enhances the ability of the model to learn global interaction information and multi-granularity local interaction information in fraudulent sentences.A fraudulent phone text dataset is produced by us in this paper.The THUCNews data sets and fraudulent phone text data sets are used in experiments.Experiment results show that compared with the baseline model,the proposed model(LMHACL)has the best experiment results in terms of Accuracy,Precision,Recall,and F1 score on the two data sets.And the performance indexes on fraudulent phone text data sets are all above 0.94.
基金This work was supported by the National Natural Science Foundation of China(Grant No.U1811262).
文摘Automatic extraction of the patient’s health information from the unstructured data concerning the discharge summary remains challenging.Discharge summary related documents contain various aspects of the patient health condition to examine the quality of treatment and thereby help improve decision-making in the medical field.Using a sentiment dictionary and feature engineering,the researchers primarily mine semantic text features.However,choosing and designing features requires a lot of manpower.The proposed approach is an unsupervised deep learning model that learns a set of clusters embedded in the latent space.A composite model including Active Learning(AL),Convolutional Neural Network(CNN),BiGRU,and Multi-Attention,called ACBMA in this research,is designed to measure the quality of treatment based on discharge summaries text sentiment detection.CNN is utilized for extracting the set of local features of text vectors.Then BiGRU network was utilized to extract the text’s global features to solve the issues that a single CNN cannot obtain global semantic information and the traditional Recurrent Neural Network(RNN)gradient disappearance.Experiments prove that the ACBMA method can demonstrate the effectiveness of the suggested method,achieve comparable results to state-of-arts methods in sentiment detection,and outperform them with accurate benchmarks.Finally,several algorithm studies ultimately determined that the ACBMA method is more precise for discharge summaries sentiment analysis.
基金support from the Liaoning Province Nature Fund Project(No.2022-MS-291)the Scientific Research Project of Liaoning Province Education Department(LJKMZ20220781,LJKMZ20220783,LJKQZ20222457,JYTMS20231488).
文摘Nowadays,with the rapid development of industrial Internet technology,on the one hand,advanced industrial control systems(ICS)have improved industrial production efficiency.However,there are more and more cyber-attacks targeting industrial control systems.To ensure the security of industrial networks,intrusion detection systems have been widely used in industrial control systems,and deep neural networks have always been an effective method for identifying cyber attacks.Current intrusion detection methods still suffer from low accuracy and a high false alarm rate.Therefore,it is important to build a more efficient intrusion detection model.This paper proposes a hybrid deep learning intrusion detection method based on convolutional neural networks and bidirectional long short-term memory neural networks(CNN-BiLSTM).To address the issue of imbalanced data within the dataset and improve the model’s detection capabilities,the Synthetic Minority Over-sampling Technique-Edited Nearest Neighbors(SMOTE-ENN)algorithm is applied in the preprocessing phase.This algorithm is employed to generate synthetic instances for the minority class,simultaneously mitigating the impact of noise in the majority class.This approach aims to create a more equitable distribution of classes,thereby enhancing the model’s ability to effectively identify patterns in both minority and majority classes.In the experimental phase,the detection performance of the method is verified using two data sets.Experimental results show that the accuracy rate on the CICIDS-2017 data set reaches 97.7%.On the natural gas pipeline dataset collected by Lan Turnipseed from Mississippi State University in the United States,the accuracy rate also reaches 85.5%.
基金supported by the National Key R&D Program of China(Grant No.2019YFB1705203)Shanghai Municipal Science and Technology Major Project(2021SHZDZX0102).
文摘Due to the closed working environment of shield machines,the construction personnel cannot observe the construction geological environment,which seriously restricts the safety and efficiency of the tunneling process.In this study,we present an enhanced multi-head self-attention convolution neural network(EMSACNN)with two-stage feature extraction for geological condition prediction of shield machine.Firstly,we select 30 important parameters according to statistical analysis method and the working principle of the shield machine.Then,we delete the non-working sample data,and combine 10 consecutive data as the input of the model.Thereafter,to deeply mine and extract essential and relevant features,we build a novel model combined with the particularity of the geological type recognition task,in which an enhanced multi-head self-attention block is utilized as the first feature extractor to fully extract the correlation of geological information of adjacent working face of tunnel,and two-dimensional CNN(2dCNN)is utilized as the second feature extractor.The performance and superiority of proposed EMSACNN are verified by the actual data collected by the shield machine used in the construction of a double-track tunnel in Guangzhou,China.The results show that EMSACNN achieves at least 96%accuracy on the test sets of the two tunnels,and all the evaluation indicators of EMSACNN are much better than those of classical AI model and the model that use only the second-stage feature extractor.Therefore,the proposed EMSACNN achieves high accuracy and strong generalization for geological information prediction of shield machine,which is of great guiding significance to engineering practice.
基金This work was supported by the National Natural Science Foundation of China(Nos.U19A2081,62202320)the Fundamental Research Funds for the Central Universities(Nos.2022SCU12116,2023SCU12129,2023SCU12126)+1 种基金the Science and Engineering Connotation Development Project of Sichuan University(No.2020SCUNG129)the Key Laboratory of Data Protection and Intelligent Management(Sichuan University),Ministry of Education.
文摘Considering the stealthiness and persistence of Advanced Persistent Threats(APTs),system audit logs are leveraged in recent studies to construct system entity interaction provenance graphs to unveil threats in a host.Rule-based provenance graph APT detection approaches require elaborate rules and cannot detect unknown attacks,and existing learning-based approaches are limited by the lack of available APT attack samples or generally only perform graph-level anomaly detection,which requires lots of manual efforts to locate attack entities.This paper proposes an APT-exploited process detection approach called ThreatSniffer,which constructs the benign provenance graph from attack-free audit logs,fits normal system entity interactions and then detects APT-exploited processes by predicting the rationality of entity interactions.Firstly,ThreatSniffer understands system entities in terms of their file paths,interaction sequences,and the number distribution of interaction types and uses the multi-head self-attention mechanism to fuse these semantics.Then,based on the insight that APT-exploited processes interact with system entities they should not invoke,ThreatSniffer performs negative sampling on the benign provenance graph to generate non-existent edges,thus characterizing irrational entity interactions without requiring APT attack samples.At last,it employs a heterogeneous graph neural network as the interaction prediction model to aggregate the contextual information of entity interactions,and locate processes exploited by attackers,thereby achieving fine-grained APT detection.Evaluation results demonstrate that anomaly-based detection enables ThreatSniffer to identify all attack activities.Compared to the node-level APT detection method APT-KGL,ThreatSniffer achieves a 6.1%precision improvement because of its comprehensive understanding of entity semantics.
基金the National Natural Science Foundation of China under Grant No.62272087Science and Technology Planning Project of Sichuan Province under Grant No.2023YFG0161.
文摘Long-term urban traffic flow prediction is an important task in the field of intelligent transportation,as it can help optimize traffic management and improve travel efficiency.To improve prediction accuracy,a crucial issue is how to model spatiotemporal dependency in urban traffic data.In recent years,many studies have adopted spatiotemporal neural networks to extract key information from traffic data.However,most models ignore the semantic spatial similarity between long-distance areas when mining spatial dependency.They also ignore the impact of predicted time steps on the next unpredicted time step for making long-term predictions.Moreover,these models lack a comprehensive data embedding process to represent complex spatiotemporal dependency.This paper proposes a multi-scale persistent spatiotemporal transformer(MSPSTT)model to perform accurate long-term traffic flow prediction in cities.MSPSTT adopts an encoder-decoder structure and incorporates temporal,periodic,and spatial features to fully embed urban traffic data to address these issues.The model consists of a spatiotemporal encoder and a spatiotemporal decoder,which rely on temporal,geospatial,and semantic space multi-head attention modules to dynamically extract temporal,geospatial,and semantic characteristics.The spatiotemporal decoder combines the context information provided by the encoder,integrates the predicted time step information,and is iteratively updated to learn the correlation between different time steps in the broader time range to improve the model’s accuracy for long-term prediction.Experiments on four public transportation datasets demonstrate that MSPSTT outperforms the existing models by up to 9.5%on three common metrics.
基金supported by the National Natural Science Foundation of China(Nos.U19A208162202320)+2 种基金the Fundamental Research Funds for the Central Universities(No.SCU2023D008)the Science and Engineering Connotation Development Project of Sichuan University(No.2020SCUNG129)the Key Laboratory of Data Protection and Intelligent Management(Sichuan University),Ministry of Education.
文摘Due to the rapid evolution of Advanced Persistent Threats(APTs)attacks,the emergence of new and rare attack samples,and even those never seen before,make it challenging for traditional rule-based detection methods to extract universal rules for effective detection.With the progress in techniques such as transfer learning and meta-learning,few-shot network attack detection has progressed.However,challenges in few-shot network attack detection arise from the inability of time sequence flow features to adapt to the fixed length input requirement of deep learning,difficulties in capturing rich information from original flow in the case of insufficient samples,and the challenge of high-level abstract representation.To address these challenges,a few-shot network attack detection based on NFHP(Network Flow Holographic Picture)-RN(ResNet)is proposed.Specifically,leveraging inherent properties of images such as translation invariance,rotation invariance,scale invariance,and illumination invariance,network attack traffic features and contextual relationships are intuitively represented in NFHP.In addition,an improved RN network model is employed for high-level abstract feature extraction,ensuring that the extracted high-level abstract features maintain the detailed characteristics of the original traffic behavior,regardless of changes in background traffic.Finally,a meta-learning model based on the self-attention mechanism is constructed,achieving the detection of novel APT few-shot network attacks through the empirical generalization of high-level abstract feature representations of known-class network attack behaviors.Experimental results demonstrate that the proposed method can learn high-level abstract features of network attacks across different traffic detail granularities.Comparedwith state-of-the-artmethods,it achieves favorable accuracy,precision,recall,and F1 scores for the identification of unknown-class network attacks through cross-validation onmultiple datasets.
基金supported in part by the National Natural Science Foundation of China(General Program)under Grants 62073193 and 61873333in part by the National Key Research and Development Project(General Program)under Grant 2020YFE0204900in part by the Key Research and Development Plan of Shandong Province(General Program)under Grant 2021CXGC010204.
文摘Due to their robust learning and expression ability for complex features,the deep learning(DL)model plays a vital role in bearing fault diagnosis.However,since there are fewer labeled samples in fault diagnosis,the depth of DL models in fault diagnosis is generally shallower than that of DL models in other fields,which limits the diagnostic performance.To solve this problem,a novel transfer residual Swin Transformer(RST)is proposed for rolling bearings in this paper.RST has 24 residual self-attention layers,which use the hierarchical design and the shifted window-based residual self-attention.Combined with transfer learning techniques,the transfer RST model uses pre-trained parameters from ImageNet.A new end-to-end method for fault diagnosis based on deep transfer RST is proposed.Firstly,wavelet transform transforms the vibration signal into a wavelet time-frequency diagram.The signal’s time-frequency domain representation can be represented simultaneously.Secondly,the wavelet time-frequency diagram is the input of the RST model to obtain the fault type.Finally,our method is verified on public and self-built datasets.Experimental results show the superior performance of our method by comparing it with a shallow neural network.
文摘Emotional electroencephalography(EEG)signals are a primary means of recording emotional brain activity.Currently,the most effective methods for analyzing emotional EEG signals involve feature engineering and neural networks.However,neural networks possess a strong ability for automatic feature extraction.Is it possible to discard feature engineering and directly employ neural networks for end-to-end recognition?Based on the characteristics of EEG signals,this paper proposes an end-to-end feature extraction and classification method for a dynamic self-attention network(DySAT).The study reveals significant differences in brain activity patterns associated with different emotions across various experimenters and time periods.The results of this experiment can provide insights into the reasons behind these differences.
基金supported by the National Key Research and Development Program of China(No.2019YFB1803501)the National Natural Science Foundation of China(No.62135009)。
文摘In this paper,an artificial-intelligence-based fiber communication receiver model is put forward.With the multi-head attention mechanism it contains,this model can extract crucial patterns and map the transmitted signals into the bit stream.Once appropriately trained,it can obtain the ability to restore the information from the signals whose transmission distances range from 0 to 100 km,signal-to-noise ratios range from 0 to 20 dB,modulation formats range from OOK to PAM4,and symbol rates range from 10 to 40 GBaud.The validity of the model is numerically demonstrated via MATLAB and Pytorch scenarios and compared with traditional communication receivers.
基金The National Natural Science Foundation of China(No.61571106,61633013,61673108,81871444).
文摘To fully make use of information from different representation subspaces,a multi-head attention-based long short-term memory(LSTM)model is proposed in this study for speech emotion recognition(SER).The proposed model uses frame-level features and takes the temporal information of emotion speech as the input of the LSTM layer.Here,a multi-head time-dimension attention(MHTA)layer was employed to linearly project the output of the LSTM layer into different subspaces for the reduced-dimension context vectors.To provide relative vital information from other dimensions,the output of MHTA,the output of feature-dimension attention,and the last time-step output of LSTM were utilized to form multiple context vectors as the input of the fully connected layer.To improve the performance of multiple vectors,feature-dimension attention was employed for the all-time output of the first LSTM layer.The proposed model was evaluated on the eNTERFACE and GEMEP corpora,respectively.The results indicate that the proposed model outperforms LSTM by 14.6%and 10.5%for eNTERFACE and GEMEP,respectively,proving the effectiveness of the proposed model in SER tasks.
基金supported in part by the Research Fund of Guangxi Key Lab of Multi-Source Information Mining&Security(MIMS21-M-02).
文摘False data injection attack(FDIA)can affect the state estimation of the power grid by tampering with the measured value of the power grid data,and then destroying the stable operation of the smart grid.Existing work usually trains a detection model by fusing the data-driven features from diverse power data streams.Data-driven features,however,cannot effectively capture the differences between noisy data and attack samples.As a result,slight noise disturbances in the power grid may cause a large number of false detections for FDIA attacks.To address this problem,this paper designs a deep collaborative self-attention network to achieve robust FDIA detection,in which the spatio-temporal features of cascaded FDIA attacks are fully integrated.Firstly,a high-order Chebyshev polynomials-based graph convolution module is designed to effectively aggregate the spatio information between grid nodes,and the spatial self-attention mechanism is involved to dynamically assign attention weights to each node,which guides the network to pay more attention to the node information that is conducive to FDIA detection.Furthermore,the bi-directional Long Short-Term Memory(LSTM)network is introduced to conduct time series modeling and long-term dependence analysis for power grid data and utilizes the temporal self-attention mechanism to describe the time correlation of data and assign different weights to different time steps.Our designed deep collaborative network can effectively mine subtle perturbations from spatiotemporal feature information,efficiently distinguish power grid noise from FDIA attacks,and adapt to diverse attack intensities.Extensive experiments demonstrate that our method can obtain an efficient detection performance over actual load data from New York Independent System Operator(NYISO)in IEEE 14,IEEE 39,and IEEE 118 bus systems,and outperforms state-of-the-art FDIA detection schemes in terms of detection accuracy and robustness.
基金supported by the National Natural Science Foundation of China(Grant Nos.61972451,61902230)the Fundamental Research Funds for the Central Universities,Shaanxi Normal University(GK202103091)。
文摘Circular RNAs(circRNAs)are RNAs with closed circular structure involved in many biological processes by key interactions with RNA binding proteins(RBPs).Existing methods for predicting these interactions have limitations in feature learning.In view of this,we propose a method named circ2CBA,which uses only sequence information of circRNAs to predict circRNA-RBP binding sites.We have constructed a data set which includes eight sub-datasets.First,circ2CBA encodes circRNA sequences using the one-hot method.Next,a two-layer convolutional neural network(CNN)is used to initially extract the features.After CNN,circ2CBA uses a layer of bidirectional long and short-term memory network(BiLSTM)and the self-attention mechanism to learn the features.The AUC value of circ2CBA reaches 0.8987.Comparison of circ2CBA with other three methods on our data set and an ablation experiment confirm that circ2CBA is an effective method to predict the binding sites between circRNAs and RBPs.
