Dementias such as Alzheimer disease(AD)and mild cognitive impairment(MCI)lead to problems with memory,language,and daily activities resulting from damage to neurons in the brain.Given the irreversibility of this neuro...Dementias such as Alzheimer disease(AD)and mild cognitive impairment(MCI)lead to problems with memory,language,and daily activities resulting from damage to neurons in the brain.Given the irreversibility of this neuronal damage,it is crucial to find a biomarker to distinguish individuals with these diseases from healthy people.In this study,we construct a brain function network based on electroencephalography data to study changes in AD and MCI patients.Using a graph-theoretical approach,we examine connectivity features and explore their contributions to dementia recognition at edge,node,and network levels.We find that connectivity is reduced in AD and MCI patients compared with healthy controls.We also find that the edge-level features give the best performance when machine learning models are used to recognize dementia.The results of feature selection identify the top 50 ranked edge-level features constituting an optimal subset,which is mainly connected with the frontal nodes.A threshold analysis reveals that the performance of edge-level features is more sensitive to the threshold for the connection strength than that of node-and network-level features.In addition,edge-level features with a threshold of 0 provide the most effective dementia recognition.The K-nearest neighbors(KNN)machine learning model achieves the highest accuracy of 0.978 with the optimal subset when the threshold is 0.Visualization of edge-level features suggests that there are more long connections linking the frontal region with the occipital and parietal regions in AD and MCI patients compared with healthy controls.Our codes are publicly available at https://github.com/Debbie-85/eeg-connectivity.展开更多
Parkinson’s disease(PD)is a debilitating neurological disorder affecting over 10 million people worldwide.PD classification models using voice signals as input are common in the literature.It is believed that using d...Parkinson’s disease(PD)is a debilitating neurological disorder affecting over 10 million people worldwide.PD classification models using voice signals as input are common in the literature.It is believed that using deep learning algorithms further enhances performance;nevertheless,it is challenging due to the nature of small-scale and imbalanced PD datasets.This paper proposed a convolutional neural network-based deep support vector machine(CNN-DSVM)to automate the feature extraction process using CNN and extend the conventional SVM to a DSVM for better classification performance in small-scale PD datasets.A customized kernel function reduces the impact of biased classification towards the majority class(healthy candidates in our consideration).An improved generative adversarial network(IGAN)was designed to generate additional training data to enhance the model’s performance.For performance evaluation,the proposed algorithm achieves a sensitivity of 97.6%and a specificity of 97.3%.The performance comparison is evaluated from five perspectives,including comparisons with different data generation algorithms,feature extraction techniques,kernel functions,and existing works.Results reveal the effectiveness of the IGAN algorithm,which improves the sensitivity and specificity by 4.05%–4.72%and 4.96%–5.86%,respectively;and the effectiveness of the CNN-DSVM algorithm,which improves the sensitivity by 1.24%–57.4%and specificity by 1.04%–163%and reduces biased detection towards the majority class.The ablation experiments confirm the effectiveness of individual components.Two future research directions have also been suggested.展开更多
The information society makes people's lives gradually enter a digital state for living. And the popularity of the Internet has led to the unique phenomenon of network words. What impact will network and the combi...The information society makes people's lives gradually enter a digital state for living. And the popularity of the Internet has led to the unique phenomenon of network words. What impact will network and the combination of language bring about? This article will explore the relation between the phenomenon of network words and social context from the angle of social linguistic through the analysis of network words and grammatical features.展开更多
Sanduao is an important sea-breeding bay in Fujian,South China and holds a high economic status in aquaculture.Quickly and accurately obtaining information including the distribution area,quantity,and aquaculture area...Sanduao is an important sea-breeding bay in Fujian,South China and holds a high economic status in aquaculture.Quickly and accurately obtaining information including the distribution area,quantity,and aquaculture area is important for breeding area planning,production value estimation,ecological survey,and storm surge prevention.However,as the aquaculture area expands,the seawater background becomes increasingly complex and spectral characteristics differ dramatically,making it difficult to determine the aquaculture area.In this study,we used a high-resolution remote-sensing satellite GF-2 image to introduce a deep-learning Richer Convolutional Features(RCF)network model to extract the aquaculture area.Then we used the density of aquaculture as an assessment index to assess the vulnerability of aquaculture areas in Sanduao.The results demonstrate that this method does not require land and water separation of the area in advance,and good extraction can be achieved in the areas with more sediment and waves,with an extraction accuracy>93%,which is suitable for large-scale aquaculture area extraction.Vulnerability assessment results indicate that the density of aquaculture in the eastern part of Sanduao is considerably high,reaching a higher vulnerability level than other parts.展开更多
With the large-scale commercial launch of fifth generation(5G)mobile network,the development of new services and applications catering to the year 2030,along with the deep convergence of information,communication,and ...With the large-scale commercial launch of fifth generation(5G)mobile network,the development of new services and applications catering to the year 2030,along with the deep convergence of information,communication,and data technologies(ICDT),and the lessons and experiences from 5G practice will drive the evolution of the next generation of mobile networks.This article surveys the history and driving forces of the evolution of the mobile network architecture and proposes a logical function architecture for sixth generation(6G)mobile network.The proposed 6G network architecture is termed SOLIDS(related to the following basic features:soft,on-demand fulfillment,lite,native intelligence,digital twin,and native security),which can support self-generation,self-healing,self-evolution,and self-immunity without human involvement and address the primary issues in the legacy 5G network(e.g.,high cost,high power consumption,and highly complicated operation and maintenance),significantly well.展开更多
A better understanding of previous accidents is an effective way to reduce the occurrence of similar accidents in the future. In this paper, a complex network approach is adopted to construct a directed weighted hazar...A better understanding of previous accidents is an effective way to reduce the occurrence of similar accidents in the future. In this paper, a complex network approach is adopted to construct a directed weighted hazard network(DWHN) to analyze topological features and evolution of accidents in the subway construction. The nodes are hazards and accidents, the edges are multiple relationships of these nodes and the weight of edges are occurrence times of repetitive relationships. The results indicate that the DWHN possesses the property of small-world with small average path length and large clustering coefficient, indicating that hazards have better connectivity and will spread widely and quickly in the network. Moreover,the DWHN has the property of scale-free network for the cumulative degree distribution follows a power-law distribution.It makes DWHN more vulnerable to target attacks. Controlling key nodes with higher degree, strength and betweenness centrality will destroy the connectivity of DWHN and mitigate the spreading of accidents in the network. This study is helpful for discovering inner relationships and evolutionary features of hazards and accidents in the subway construction.展开更多
As a well-known urban landscape concept to describe urban space quality,urban street vitality is a subjective human perception of the urban environment but difficult to evaluate directly from the physical space.The st...As a well-known urban landscape concept to describe urban space quality,urban street vitality is a subjective human perception of the urban environment but difficult to evaluate directly from the physical space.The study utilized a modern machine learning computer vision algorithm in the urban build environment to simulate the process,which starts with the visual perception of the urban street landscape and ends with the human reaction to street vitality.By analyzing the optimized trained model,we tried to identify urban street vitality’s visual features and evaluate their importance.A region around the Mochou Lake in Nanjing,China,was set as our study area.Seven investigators surveyed the area,recorded their evaluation score on each site’s vitality level with a corresponding picture taken on site.A total of 370 pictures and recorded score pairs from 231 valid survey sites were used to train a convolutional neural network.After optimization,a deep neural network model with 43 layers,including 11 convolutional ones,was created.Heat maps were then used to identify the features which lead to high vitality score outputs.The spatial distributions of different types of feature entities were also analyzed to help identify the spatial effects.The study found that visual features,including human,construction site,shop front,and roadside/walking pavement,are vital ones that correspond to the vitality of the urban street.The consistency of these critical features with traditional urban vitality features indicates the model had learned useful knowledge from the training process.Applying the trained model in urban planning practices can help to improve the city environment for better attraction of residents’activities and communications.展开更多
Dissolved oxygen(DO)content is an important index of river water quality.Water quality sensors have been used in China for urban river water monitoring and DO content prediction.However,water quality sensors are expen...Dissolved oxygen(DO)content is an important index of river water quality.Water quality sensors have been used in China for urban river water monitoring and DO content prediction.However,water quality sensors are expensive and difficult to maintain,and have a short operation period and difficult to maintain.This study developed a scientific and accurate method for prediction of DO content changes using fish school features.The behavioral features of the Carassius auratus fish school were described using two-dimensional fish school images.The degree of DO content decline was graded into five levels,and the corresponding numerical ranges of cluster characteristic parameters were determined by considering the opinions of ichthyologists.Finally,the variation of DO content was predicted using the characteristic parameters of the fish school and the multiple-input single-output Takagi-Sugeno fuzzy neural network.The prediction results were basically consistent with the actual variations of DO content.Therefore,it is feasible to use the behavioral features of the fish school to dynamically predict the level of DO content in water,and this method is especially suitable for prediction of sharp decline of DO content in a relatively short time.展开更多
The continual growth of the use of technological appliances during the COVID-19 pandemic has resulted in a massive volume of data flow on the Internet,as many employees have transitioned to working from home.Furthermo...The continual growth of the use of technological appliances during the COVID-19 pandemic has resulted in a massive volume of data flow on the Internet,as many employees have transitioned to working from home.Furthermore,with the increase in the adoption of encrypted data transmission by many people who tend to use a Virtual Private Network(VPN)or Tor Browser(dark web)to keep their data privacy and hidden,network traffic encryption is rapidly becoming a universal approach.This affects and complicates the quality of service(QoS),traffic monitoring,and network security provided by Internet Service Providers(ISPs),particularly for analysis and anomaly detection approaches based on the network traffic’s nature.The method of categorizing encrypted traffic is one of the most challenging issues introduced by a VPN as a way to bypass censorship as well as gain access to geo-locked services.Therefore,an efficient approach is especially needed that enables the identification of encrypted network traffic data to extract and select valuable features which improve the quality of service and network management as well as to oversee the overall performance.In this paper,the classification of network traffic data in terms of VPN and non-VPN traffic is studied based on the efficiency of time-based features extracted from network packets.Therefore,this paper suggests two machine learning models that categorize network traffic into encrypted and non-encrypted traffic.The proposed models utilize statistical features(SF),Pearson Correlation(PC),and a Genetic Algorithm(GA),preprocessing the traffic samples into net flow traffic to accomplish the experiment’s objectives.The GA-based method utilizes a stochastic method based on natural genetics and biological evolution to extract essential features.The PC-based method performs well in removing different features of network traffic.With a microsecond perpacket prediction time,the best model achieved an accuracy of more than 95.02 percent in the most demanding traffic classification task,a drop in accuracy of only 2.37 percent in comparison to the entire statistical-based machine learning approach.This is extremely promising for the development of real-time traffic analyzers.展开更多
In order to explore the structural features of neural networks and the ap-proaches to local interconnection,the geometrical structural information is introduced tothe Hopfield neural network model which is applied to ...In order to explore the structural features of neural networks and the ap-proaches to local interconnection,the geometrical structural information is introduced tothe Hopfield neural network model which is applied to associative memory.The dynamicsof the recalling is studied theoretically and cxpcrimcntally.The rcsults show that the geo-metrical structural information is helpless to the associative memory of monolayeredneural networks,furthermore,it makes the error probability increased.If the geometricalstructural information of the stored patterns is necessary to be introduced,somc new ap-proaches have to be explored.展开更多
Sepsis poses a serious threat to health of children in pediatric intensive care unit.The mortality from pediatric sepsis can be effectively reduced through in-time diagnosis and therapeutic intervention.The bacillicul...Sepsis poses a serious threat to health of children in pediatric intensive care unit.The mortality from pediatric sepsis can be effectively reduced through in-time diagnosis and therapeutic intervention.The bacilliculture detection method is too time-consuming to receive timely treatment.In this research,we propose a new framework:a deep encoding network with cross features(CF-DEN)that enables accurate early detection of sepsis.Cross features are automatically constructed via the gradient boosting decision tree and distilled into the deep encoding network(DEN)we designed.The DEN is aimed at learning sufficiently effective representation from clinical test data.Each layer of the DEN fltrates the features involved in computation at current layer via attention mechanism and outputs the current prediction which is additive layer by layer to obtain the embedding feature at last layer.The framework takes the advantage of tree-based method and neural network method to extract effective representation from small clinical dataset and obtain accurate prediction in order to prompt patient to get timely treatment.We evaluate the performance of the framework on the dataset collected from Shanghai Children's Medical Center.Compared with common machine learning methods,our method achieves the increase on F1-score by 16.06%on the test set.展开更多
Human gait recognition(HGR)is the process of identifying a sub-ject(human)based on their walking pattern.Each subject is a unique walking pattern and cannot be simulated by other subjects.But,gait recognition is not e...Human gait recognition(HGR)is the process of identifying a sub-ject(human)based on their walking pattern.Each subject is a unique walking pattern and cannot be simulated by other subjects.But,gait recognition is not easy and makes the system difficult if any object is carried by a subject,such as a bag or coat.This article proposes an automated architecture based on deep features optimization for HGR.To our knowledge,it is the first architecture in which features are fused using multiset canonical correlation analysis(MCCA).In the proposed method,original video frames are processed for all 11 selected angles of the CASIA B dataset and utilized to train two fine-tuned deep learning models such as Squeezenet and Efficientnet.Deep transfer learning was used to train both fine-tuned models on selected angles,yielding two new targeted models that were later used for feature engineering.Features are extracted from the deep layer of both fine-tuned models and fused into one vector using MCCA.An improved manta ray foraging optimization algorithm is also proposed to select the best features from the fused feature matrix and classified using a narrow neural network classifier.The experimental process was conducted on all 11 angles of the large multi-view gait dataset(CASIA B)dataset and obtained improved accuracy than the state-of-the-art techniques.Moreover,a detailed confidence interval based analysis also shows the effectiveness of the proposed architecture for HGR.展开更多
In order to improve the models capability in expressing features during few-shot learning,a multi-scale features prototypical network(MS-PN)algorithm is proposed.The metric learning algo-rithm is employed to extract i...In order to improve the models capability in expressing features during few-shot learning,a multi-scale features prototypical network(MS-PN)algorithm is proposed.The metric learning algo-rithm is employed to extract image features and project them into a feature space,thus evaluating the similarity between samples based on their relative distances within the metric space.To sufficiently extract feature information from limited sample data and mitigate the impact of constrained data vol-ume,a multi-scale feature extraction network is presented to capture data features at various scales during the process of image feature extraction.Additionally,the position of the prototype is fine-tuned by assigning weights to data points to mitigate the influence of outliers on the experiment.The loss function integrates contrastive loss and label-smoothing to bring similar data points closer and separate dissimilar data points within the metric space.Experimental evaluations are conducted on small-sample datasets mini-ImageNet and CUB200-2011.The method in this paper can achieve higher classification accuracy.Specifically,in the 5-way 1-shot experiment,classification accuracy reaches 50.13%and 66.79%respectively on these two datasets.Moreover,in the 5-way 5-shot ex-periment,accuracy of 66.79%and 85.91%are observed,respectively.展开更多
Accurate performance prediction of Grid workflow activities can help Grid schedulers map activitiesto appropriate Grid sites.This paper describes an approach based on features-ranked RBF neural networkto predict the p...Accurate performance prediction of Grid workflow activities can help Grid schedulers map activitiesto appropriate Grid sites.This paper describes an approach based on features-ranked RBF neural networkto predict the performance of Grid workflow activities.Experimental results for two kinds of real worldGrid workflow activities are presented to show effectiveness of our approach.展开更多
Audio-visual scene classification(AVSC)poses a formidable challenge owing to the intricate spatial-temporal relationships exhibited by audio-visual signals,coupled with the complex spatial patterns of objects and text...Audio-visual scene classification(AVSC)poses a formidable challenge owing to the intricate spatial-temporal relationships exhibited by audio-visual signals,coupled with the complex spatial patterns of objects and textures found in visual images.The focus of recent studies has predominantly revolved around extracting features from diverse neural network structures,inadvertently neglecting the acquisition of semantically meaningful regions and crucial components within audio-visual data.The authors present a feature pyramid attention network(FPANet)for audio-visual scene understanding,which extracts semantically significant characteristics from audio-visual data.The authors’approach builds multi-scale hierarchical features of sound spectrograms and visual images using a feature pyramid representation and localises the semantically relevant regions with a feature pyramid attention module(FPAM).A dimension alignment(DA)strategy is employed to align feature maps from multiple layers,a pyramid spatial attention(PSA)to spatially locate essential regions,and a pyramid channel attention(PCA)to pinpoint significant temporal frames.Experiments on visual scene classification(VSC),audio scene classification(ASC),and AVSC tasks demonstrate that FPANet achieves performance on par with state-of-the-art(SOTA)approaches,with a 95.9 F1-score on the ADVANCE dataset and a relative improvement of 28.8%.Visualisation results show that FPANet can prioritise semantically meaningful areas in audio-visual signals.展开更多
In this paper,we propose hierarchical attention dual network(DNet)for fine-grained image classification.The DNet can randomly select pairs of inputs from the dataset and compare the differences between them through hi...In this paper,we propose hierarchical attention dual network(DNet)for fine-grained image classification.The DNet can randomly select pairs of inputs from the dataset and compare the differences between them through hierarchical attention feature learning,which are used simultaneously to remove noise and retain salient features.In the loss function,it considers the losses of difference in paired images according to the intra-variance and inter-variance.In addition,we also collect the disaster scene dataset from remote sensing images and apply the proposed method to disaster scene classification,which contains complex scenes and multiple types of disasters.Compared to other methods,experimental results show that the DNet with hierarchical attention is robust to different datasets and performs better.展开更多
Remote sensing image classification is the basis of remote sensing image analysis and understanding.It aims to assign each pixel an object class label.To achieve satisfactory classification accuracy,single feature is ...Remote sensing image classification is the basis of remote sensing image analysis and understanding.It aims to assign each pixel an object class label.To achieve satisfactory classification accuracy,single feature is not enough.Multiple features are usually integrated in remote sensing image classification.In this paper,a method based on neural network to combine multiple features was proposed.A single network was used to perform the task instead of ensemble of neural networks.A special architecture of network was designed to fit the task.The method effectively avoids the problems in direct conjunction of multiple features.Experiments on Indian93 data set show that the method has obvious advantages over conjunction of features on both recognition rate and training time.展开更多
Hyperspectral image(HSI)classification is crucial for numerous remote sensing applications.Traditional deep learning methods may miss pixel relationships and context,leading to inefficiencies.This paper introduces the...Hyperspectral image(HSI)classification is crucial for numerous remote sensing applications.Traditional deep learning methods may miss pixel relationships and context,leading to inefficiencies.This paper introduces the spectral band graph convolutional and attention-enhanced CNN joint network(SGCCN),a novel approach that harnesses the power of spectral band graph convolutions for capturing long-range relationships,utilizes local perception of attention-enhanced multi-level convolutions for local spatial feature and employs a dynamic attention mechanism to enhance feature extraction.The SGCCN integrates spectral and spatial features through a self-attention fusion network,significantly improving classification accuracy and efficiency.The proposed method outperforms existing techniques,demonstrating its effectiveness in handling the challenges associated with HSI data.展开更多
基金supported by the National Natural Science Foundation of China(Grant Nos.62071451,62331025,and U21A20447)the National Key Research and Development Project(Grant No.2021YFC3002204)the CAMS Innovation Fund for Medical Sciences(Grant No.2019-I2M-5-019).
文摘Dementias such as Alzheimer disease(AD)and mild cognitive impairment(MCI)lead to problems with memory,language,and daily activities resulting from damage to neurons in the brain.Given the irreversibility of this neuronal damage,it is crucial to find a biomarker to distinguish individuals with these diseases from healthy people.In this study,we construct a brain function network based on electroencephalography data to study changes in AD and MCI patients.Using a graph-theoretical approach,we examine connectivity features and explore their contributions to dementia recognition at edge,node,and network levels.We find that connectivity is reduced in AD and MCI patients compared with healthy controls.We also find that the edge-level features give the best performance when machine learning models are used to recognize dementia.The results of feature selection identify the top 50 ranked edge-level features constituting an optimal subset,which is mainly connected with the frontal nodes.A threshold analysis reveals that the performance of edge-level features is more sensitive to the threshold for the connection strength than that of node-and network-level features.In addition,edge-level features with a threshold of 0 provide the most effective dementia recognition.The K-nearest neighbors(KNN)machine learning model achieves the highest accuracy of 0.978 with the optimal subset when the threshold is 0.Visualization of edge-level features suggests that there are more long connections linking the frontal region with the occipital and parietal regions in AD and MCI patients compared with healthy controls.Our codes are publicly available at https://github.com/Debbie-85/eeg-connectivity.
基金The work described in this paper was fully supported by a grant from Hong Kong Metropolitan University(RIF/2021/05).
文摘Parkinson’s disease(PD)is a debilitating neurological disorder affecting over 10 million people worldwide.PD classification models using voice signals as input are common in the literature.It is believed that using deep learning algorithms further enhances performance;nevertheless,it is challenging due to the nature of small-scale and imbalanced PD datasets.This paper proposed a convolutional neural network-based deep support vector machine(CNN-DSVM)to automate the feature extraction process using CNN and extend the conventional SVM to a DSVM for better classification performance in small-scale PD datasets.A customized kernel function reduces the impact of biased classification towards the majority class(healthy candidates in our consideration).An improved generative adversarial network(IGAN)was designed to generate additional training data to enhance the model’s performance.For performance evaluation,the proposed algorithm achieves a sensitivity of 97.6%and a specificity of 97.3%.The performance comparison is evaluated from five perspectives,including comparisons with different data generation algorithms,feature extraction techniques,kernel functions,and existing works.Results reveal the effectiveness of the IGAN algorithm,which improves the sensitivity and specificity by 4.05%–4.72%and 4.96%–5.86%,respectively;and the effectiveness of the CNN-DSVM algorithm,which improves the sensitivity by 1.24%–57.4%and specificity by 1.04%–163%and reduces biased detection towards the majority class.The ablation experiments confirm the effectiveness of individual components.Two future research directions have also been suggested.
文摘The information society makes people's lives gradually enter a digital state for living. And the popularity of the Internet has led to the unique phenomenon of network words. What impact will network and the combination of language bring about? This article will explore the relation between the phenomenon of network words and social context from the angle of social linguistic through the analysis of network words and grammatical features.
基金Supported by the National Key Research and Development Program of China(No.2016YFC1402003)the National Natural Science Foundation of China(No.41671436)the Innovation Project of LREIS(No.O88RAA01YA)
文摘Sanduao is an important sea-breeding bay in Fujian,South China and holds a high economic status in aquaculture.Quickly and accurately obtaining information including the distribution area,quantity,and aquaculture area is important for breeding area planning,production value estimation,ecological survey,and storm surge prevention.However,as the aquaculture area expands,the seawater background becomes increasingly complex and spectral characteristics differ dramatically,making it difficult to determine the aquaculture area.In this study,we used a high-resolution remote-sensing satellite GF-2 image to introduce a deep-learning Richer Convolutional Features(RCF)network model to extract the aquaculture area.Then we used the density of aquaculture as an assessment index to assess the vulnerability of aquaculture areas in Sanduao.The results demonstrate that this method does not require land and water separation of the area in advance,and good extraction can be achieved in the areas with more sediment and waves,with an extraction accuracy>93%,which is suitable for large-scale aquaculture area extraction.Vulnerability assessment results indicate that the density of aquaculture in the eastern part of Sanduao is considerably high,reaching a higher vulnerability level than other parts.
基金the National Key Research and Development Program of China(2020YFB1806800).
文摘With the large-scale commercial launch of fifth generation(5G)mobile network,the development of new services and applications catering to the year 2030,along with the deep convergence of information,communication,and data technologies(ICDT),and the lessons and experiences from 5G practice will drive the evolution of the next generation of mobile networks.This article surveys the history and driving forces of the evolution of the mobile network architecture and proposes a logical function architecture for sixth generation(6G)mobile network.The proposed 6G network architecture is termed SOLIDS(related to the following basic features:soft,on-demand fulfillment,lite,native intelligence,digital twin,and native security),which can support self-generation,self-healing,self-evolution,and self-immunity without human involvement and address the primary issues in the legacy 5G network(e.g.,high cost,high power consumption,and highly complicated operation and maintenance),significantly well.
基金supported by the Co-Funding of National Natural Science Foundation of China and Shenhua Group Corporation Ltd(Grant No.U1261212)the Program of Major Achievements Transformation and Industrialization of Beijing Education Commission,China(Grant No.ZDZH20141141301)
文摘A better understanding of previous accidents is an effective way to reduce the occurrence of similar accidents in the future. In this paper, a complex network approach is adopted to construct a directed weighted hazard network(DWHN) to analyze topological features and evolution of accidents in the subway construction. The nodes are hazards and accidents, the edges are multiple relationships of these nodes and the weight of edges are occurrence times of repetitive relationships. The results indicate that the DWHN possesses the property of small-world with small average path length and large clustering coefficient, indicating that hazards have better connectivity and will spread widely and quickly in the network. Moreover,the DWHN has the property of scale-free network for the cumulative degree distribution follows a power-law distribution.It makes DWHN more vulnerable to target attacks. Controlling key nodes with higher degree, strength and betweenness centrality will destroy the connectivity of DWHN and mitigate the spreading of accidents in the network. This study is helpful for discovering inner relationships and evolutionary features of hazards and accidents in the subway construction.
基金This work was supported by the China Scholarship Council[grant number 201706195004]the National Natural Science Foundation of China[grant numbers 41001093 and 51778278]the Social Science Foundation of Jiangsu Province,China[grant number 18GLB014].
文摘As a well-known urban landscape concept to describe urban space quality,urban street vitality is a subjective human perception of the urban environment but difficult to evaluate directly from the physical space.The study utilized a modern machine learning computer vision algorithm in the urban build environment to simulate the process,which starts with the visual perception of the urban street landscape and ends with the human reaction to street vitality.By analyzing the optimized trained model,we tried to identify urban street vitality’s visual features and evaluate their importance.A region around the Mochou Lake in Nanjing,China,was set as our study area.Seven investigators surveyed the area,recorded their evaluation score on each site’s vitality level with a corresponding picture taken on site.A total of 370 pictures and recorded score pairs from 231 valid survey sites were used to train a convolutional neural network.After optimization,a deep neural network model with 43 layers,including 11 convolutional ones,was created.Heat maps were then used to identify the features which lead to high vitality score outputs.The spatial distributions of different types of feature entities were also analyzed to help identify the spatial effects.The study found that visual features,including human,construction site,shop front,and roadside/walking pavement,are vital ones that correspond to the vitality of the urban street.The consistency of these critical features with traditional urban vitality features indicates the model had learned useful knowledge from the training process.Applying the trained model in urban planning practices can help to improve the city environment for better attraction of residents’activities and communications.
基金supported by the Natural Science Foundation of Changzhou City,China(Grants No.CE20195026 and CE20205031)the Teaching Steering Committee of Electronics Information Specialty in Colleges and Universities of the Ministry of Education(Grant No.2020-YB-42)the Jiangsu Overseas Visiting Scholar Program for University Prominent Young and Middle Aged Teachers and Presidents.
文摘Dissolved oxygen(DO)content is an important index of river water quality.Water quality sensors have been used in China for urban river water monitoring and DO content prediction.However,water quality sensors are expensive and difficult to maintain,and have a short operation period and difficult to maintain.This study developed a scientific and accurate method for prediction of DO content changes using fish school features.The behavioral features of the Carassius auratus fish school were described using two-dimensional fish school images.The degree of DO content decline was graded into five levels,and the corresponding numerical ranges of cluster characteristic parameters were determined by considering the opinions of ichthyologists.Finally,the variation of DO content was predicted using the characteristic parameters of the fish school and the multiple-input single-output Takagi-Sugeno fuzzy neural network.The prediction results were basically consistent with the actual variations of DO content.Therefore,it is feasible to use the behavioral features of the fish school to dynamically predict the level of DO content in water,and this method is especially suitable for prediction of sharp decline of DO content in a relatively short time.
文摘The continual growth of the use of technological appliances during the COVID-19 pandemic has resulted in a massive volume of data flow on the Internet,as many employees have transitioned to working from home.Furthermore,with the increase in the adoption of encrypted data transmission by many people who tend to use a Virtual Private Network(VPN)or Tor Browser(dark web)to keep their data privacy and hidden,network traffic encryption is rapidly becoming a universal approach.This affects and complicates the quality of service(QoS),traffic monitoring,and network security provided by Internet Service Providers(ISPs),particularly for analysis and anomaly detection approaches based on the network traffic’s nature.The method of categorizing encrypted traffic is one of the most challenging issues introduced by a VPN as a way to bypass censorship as well as gain access to geo-locked services.Therefore,an efficient approach is especially needed that enables the identification of encrypted network traffic data to extract and select valuable features which improve the quality of service and network management as well as to oversee the overall performance.In this paper,the classification of network traffic data in terms of VPN and non-VPN traffic is studied based on the efficiency of time-based features extracted from network packets.Therefore,this paper suggests two machine learning models that categorize network traffic into encrypted and non-encrypted traffic.The proposed models utilize statistical features(SF),Pearson Correlation(PC),and a Genetic Algorithm(GA),preprocessing the traffic samples into net flow traffic to accomplish the experiment’s objectives.The GA-based method utilizes a stochastic method based on natural genetics and biological evolution to extract essential features.The PC-based method performs well in removing different features of network traffic.With a microsecond perpacket prediction time,the best model achieved an accuracy of more than 95.02 percent in the most demanding traffic classification task,a drop in accuracy of only 2.37 percent in comparison to the entire statistical-based machine learning approach.This is extremely promising for the development of real-time traffic analyzers.
文摘In order to explore the structural features of neural networks and the ap-proaches to local interconnection,the geometrical structural information is introduced tothe Hopfield neural network model which is applied to associative memory.The dynamicsof the recalling is studied theoretically and cxpcrimcntally.The rcsults show that the geo-metrical structural information is helpless to the associative memory of monolayeredneural networks,furthermore,it makes the error probability increased.If the geometricalstructural information of the stored patterns is necessary to be introduced,somc new ap-proaches have to be explored.
文摘Sepsis poses a serious threat to health of children in pediatric intensive care unit.The mortality from pediatric sepsis can be effectively reduced through in-time diagnosis and therapeutic intervention.The bacilliculture detection method is too time-consuming to receive timely treatment.In this research,we propose a new framework:a deep encoding network with cross features(CF-DEN)that enables accurate early detection of sepsis.Cross features are automatically constructed via the gradient boosting decision tree and distilled into the deep encoding network(DEN)we designed.The DEN is aimed at learning sufficiently effective representation from clinical test data.Each layer of the DEN fltrates the features involved in computation at current layer via attention mechanism and outputs the current prediction which is additive layer by layer to obtain the embedding feature at last layer.The framework takes the advantage of tree-based method and neural network method to extract effective representation from small clinical dataset and obtain accurate prediction in order to prompt patient to get timely treatment.We evaluate the performance of the framework on the dataset collected from Shanghai Children's Medical Center.Compared with common machine learning methods,our method achieves the increase on F1-score by 16.06%on the test set.
基金supported by the MSIT(Ministry of Science and ICT),Korea,under the ICAN(ICT Challenge and Advanced Network of HRD)program(IITP-2022-2020-0-01832)supervised by the IITP(Institute of Information&Communications Technology Planning&Evaluation)and the Soonchunhyang University Research Fund.
文摘Human gait recognition(HGR)is the process of identifying a sub-ject(human)based on their walking pattern.Each subject is a unique walking pattern and cannot be simulated by other subjects.But,gait recognition is not easy and makes the system difficult if any object is carried by a subject,such as a bag or coat.This article proposes an automated architecture based on deep features optimization for HGR.To our knowledge,it is the first architecture in which features are fused using multiset canonical correlation analysis(MCCA).In the proposed method,original video frames are processed for all 11 selected angles of the CASIA B dataset and utilized to train two fine-tuned deep learning models such as Squeezenet and Efficientnet.Deep transfer learning was used to train both fine-tuned models on selected angles,yielding two new targeted models that were later used for feature engineering.Features are extracted from the deep layer of both fine-tuned models and fused into one vector using MCCA.An improved manta ray foraging optimization algorithm is also proposed to select the best features from the fused feature matrix and classified using a narrow neural network classifier.The experimental process was conducted on all 11 angles of the large multi-view gait dataset(CASIA B)dataset and obtained improved accuracy than the state-of-the-art techniques.Moreover,a detailed confidence interval based analysis also shows the effectiveness of the proposed architecture for HGR.
基金the Scientific Research Foundation of Liaoning Provincial Department of Education(No.LJKZ0139)the Program for Liaoning Excellent Talents in University(No.LR15045).
文摘In order to improve the models capability in expressing features during few-shot learning,a multi-scale features prototypical network(MS-PN)algorithm is proposed.The metric learning algo-rithm is employed to extract image features and project them into a feature space,thus evaluating the similarity between samples based on their relative distances within the metric space.To sufficiently extract feature information from limited sample data and mitigate the impact of constrained data vol-ume,a multi-scale feature extraction network is presented to capture data features at various scales during the process of image feature extraction.Additionally,the position of the prototype is fine-tuned by assigning weights to data points to mitigate the influence of outliers on the experiment.The loss function integrates contrastive loss and label-smoothing to bring similar data points closer and separate dissimilar data points within the metric space.Experimental evaluations are conducted on small-sample datasets mini-ImageNet and CUB200-2011.The method in this paper can achieve higher classification accuracy.Specifically,in the 5-way 1-shot experiment,classification accuracy reaches 50.13%and 66.79%respectively on these two datasets.Moreover,in the 5-way 5-shot ex-periment,accuracy of 66.79%and 85.91%are observed,respectively.
基金Supported by the European Union through the IST-034601 edutain@grid project
文摘Accurate performance prediction of Grid workflow activities can help Grid schedulers map activitiesto appropriate Grid sites.This paper describes an approach based on features-ranked RBF neural networkto predict the performance of Grid workflow activities.Experimental results for two kinds of real worldGrid workflow activities are presented to show effectiveness of our approach.
基金Shenzhen Institute of Artificial Intelligence and Robotics for Society,Grant/Award Number:AC01202201003-02GuangDong Basic and Applied Basic Research Foundation,Grant/Award Number:2024A1515010252Longgang District Shenzhen's“Ten Action Plan”for Supporting Innovation Projects,Grant/Award Number:LGKCSDPT2024002。
文摘Audio-visual scene classification(AVSC)poses a formidable challenge owing to the intricate spatial-temporal relationships exhibited by audio-visual signals,coupled with the complex spatial patterns of objects and textures found in visual images.The focus of recent studies has predominantly revolved around extracting features from diverse neural network structures,inadvertently neglecting the acquisition of semantically meaningful regions and crucial components within audio-visual data.The authors present a feature pyramid attention network(FPANet)for audio-visual scene understanding,which extracts semantically significant characteristics from audio-visual data.The authors’approach builds multi-scale hierarchical features of sound spectrograms and visual images using a feature pyramid representation and localises the semantically relevant regions with a feature pyramid attention module(FPAM).A dimension alignment(DA)strategy is employed to align feature maps from multiple layers,a pyramid spatial attention(PSA)to spatially locate essential regions,and a pyramid channel attention(PCA)to pinpoint significant temporal frames.Experiments on visual scene classification(VSC),audio scene classification(ASC),and AVSC tasks demonstrate that FPANet achieves performance on par with state-of-the-art(SOTA)approaches,with a 95.9 F1-score on the ADVANCE dataset and a relative improvement of 28.8%.Visualisation results show that FPANet can prioritise semantically meaningful areas in audio-visual signals.
基金Supported by the National Natural Science Foundation of China(61601176)。
文摘In this paper,we propose hierarchical attention dual network(DNet)for fine-grained image classification.The DNet can randomly select pairs of inputs from the dataset and compare the differences between them through hierarchical attention feature learning,which are used simultaneously to remove noise and retain salient features.In the loss function,it considers the losses of difference in paired images according to the intra-variance and inter-variance.In addition,we also collect the disaster scene dataset from remote sensing images and apply the proposed method to disaster scene classification,which contains complex scenes and multiple types of disasters.Compared to other methods,experimental results show that the DNet with hierarchical attention is robust to different datasets and performs better.
基金National Natural Science Foundation of China(No.61101202)
文摘Remote sensing image classification is the basis of remote sensing image analysis and understanding.It aims to assign each pixel an object class label.To achieve satisfactory classification accuracy,single feature is not enough.Multiple features are usually integrated in remote sensing image classification.In this paper,a method based on neural network to combine multiple features was proposed.A single network was used to perform the task instead of ensemble of neural networks.A special architecture of network was designed to fit the task.The method effectively avoids the problems in direct conjunction of multiple features.Experiments on Indian93 data set show that the method has obvious advantages over conjunction of features on both recognition rate and training time.
基金supported in part by the National Natural Science Foundations of China(No.61801214)the Postgraduate Research Practice Innovation Program of NUAA(No.xcxjh20231504)。
文摘Hyperspectral image(HSI)classification is crucial for numerous remote sensing applications.Traditional deep learning methods may miss pixel relationships and context,leading to inefficiencies.This paper introduces the spectral band graph convolutional and attention-enhanced CNN joint network(SGCCN),a novel approach that harnesses the power of spectral band graph convolutions for capturing long-range relationships,utilizes local perception of attention-enhanced multi-level convolutions for local spatial feature and employs a dynamic attention mechanism to enhance feature extraction.The SGCCN integrates spectral and spatial features through a self-attention fusion network,significantly improving classification accuracy and efficiency.The proposed method outperforms existing techniques,demonstrating its effectiveness in handling the challenges associated with HSI data.
