The automated interpretation of rock structure can improve the efficiency,accuracy,and consistency of the geological risk assessment of tunnel face.Because of the high uncertainties in the geological images as a resul...The automated interpretation of rock structure can improve the efficiency,accuracy,and consistency of the geological risk assessment of tunnel face.Because of the high uncertainties in the geological images as a result of different regional rock types,as well as in-situ conditions(e.g.,temperature,humidity,and construction procedure),previous automated methods have limited performance in classification of rock structure of tunnel face during construction.This paper presents a framework for classifying multiple rock structures based on the geological images of tunnel face using convolutional neural networks(CNN),namely Inception-ResNet-V2(IRV2).A prototype recognition system is implemented to classify 5 types of rock structures including mosaic,granular,layered,block,and fragmentation structures.The proposed IRV2 network is trained by over 35,000 out of 42,400 images extracted from over 150 sections of tunnel faces and tested by the remaining 7400 images.Furthermore,different hyperparameters of the CNN model are introduced to optimize the most efficient algorithm parameter.Among all the discussed models,i.e.,ResNet-50,ResNet-101,and Inception-v4,Inception-ResNet-V2 exhibits the best performance in terms of various indicators,such as precision,recall,F-score,and testing time per image.Meanwhile,the model trained by a large database can obtain the object features more comprehensively,leading to higher accuracy.Compared with the original image classification method,the sub-image method is closer to the reality considering both the accuracy and the perspective of error divergence.The experimental results reveal that the proposed method is optimal and efficient for automated classification of rock structure using the geological images of the tunnel face.展开更多
Deep neural network-based relational extraction research has made significant progress in recent years,andit provides data support for many natural language processing downstream tasks such as building knowledgegraph,...Deep neural network-based relational extraction research has made significant progress in recent years,andit provides data support for many natural language processing downstream tasks such as building knowledgegraph,sentiment analysis and question-answering systems.However,previous studies ignored much unusedstructural information in sentences that could enhance the performance of the relation extraction task.Moreover,most existing dependency-based models utilize self-attention to distinguish the importance of context,whichhardly deals withmultiple-structure information.To efficiently leverage multiple structure information,this paperproposes a dynamic structure attention mechanism model based on textual structure information,which deeplyintegrates word embedding,named entity recognition labels,part of speech,dependency tree and dependency typeinto a graph convolutional network.Specifically,our model extracts text features of different structures from theinput sentence.Textual Structure information Graph Convolutional Networks employs the dynamic structureattention mechanism to learn multi-structure attention,effectively distinguishing important contextual features invarious structural information.In addition,multi-structure weights are carefully designed as amergingmechanismin the different structure attention to dynamically adjust the final attention.This paper combines these featuresand trains a graph convolutional network for relation extraction.We experiment on supervised relation extractiondatasets including SemEval 2010 Task 8,TACRED,TACREV,and Re-TACED,the result significantly outperformsthe previous.展开更多
Regular detection and repair for lining cracks are necessary to guarantee the safety and stability of tunnels.The development of computer vision has greatly promoted structural health monitoring.This study proposes a ...Regular detection and repair for lining cracks are necessary to guarantee the safety and stability of tunnels.The development of computer vision has greatly promoted structural health monitoring.This study proposes a novel encoder–decoder structure,CrackRecNet,for semantic segmentation of lining segment cracks by integrating improved VGG-19 into the U-Net architecture.An image acquisition equipment is designed based on a camera,3-dimensional printing(3DP)bracket and two laser rangefinders.A tunnel concrete structure crack(TCSC)image data set,containing images collected from a double-shield tunnel boring machines(TBM)tunnel in China,was established.Through data preprocessing operations,such as brightness adjustment,pixel resolution adjustment,flipping,splitting and annotation,2880 image samples with pixel resolution of 448×448 were prepared.The model was implemented by Pytorch in PyCharm processed with 4 NVIDIA TITAN V GPUs.In the experiments,the proposed CrackRecNet showed better prediction performance than U-Net,TernausNet,and ResU-Net.This paper also discusses GPU parallel acceleration effect and the crack maximum width quantification.展开更多
Accurately estimating the ocean subsurface salinity structure(OSSS)is crucial for understanding ocean dynamics and predicting climate variations.We present a convolutional neural network(CNN)model to estimate the OSSS...Accurately estimating the ocean subsurface salinity structure(OSSS)is crucial for understanding ocean dynamics and predicting climate variations.We present a convolutional neural network(CNN)model to estimate the OSSS in the Indian Ocean using satellite data and Argo observations.We evaluated the performance of the CNN model in terms of its vertical and spatial distribution,as well as seasonal variation of OSSS estimation.Results demonstrate that the CNN model accurately estimates the most significant salinity features in the Indian Ocean using sea surface data with no significant differences from Argo-derived OSSS.However,the estimation accuracy of the CNN model varies with depth,with the most challenging depth being approximately 70 m,corresponding to the halocline layer.Validations of the CNN model’s accuracy in estimating OSSS in the Indian Ocean are also conducted by comparing Argo observations and CNN model estimations along two selected sections and four selected boxes.The results show that the CNN model effectively captures the seasonal variability of salinity,demonstrating its high performance in salinity estimation using sea surface data.Our analysis reveals that sea surface salinity has the strongest correlation with OSSS in shallow layers,while sea surface height anomaly plays a more significant role in deeper layers.These preliminary results provide valuable insights into the feasibility of estimating OSSS using satellite observations and have implications for studying upper ocean dynamics using machine learning techniques.展开更多
With the rapid development of the 5G communications,the edge intelligence enables Internet of Vehicles(IoV)to provide traffic forecasting to alleviate traffic congestion and improve quality of experience of users simu...With the rapid development of the 5G communications,the edge intelligence enables Internet of Vehicles(IoV)to provide traffic forecasting to alleviate traffic congestion and improve quality of experience of users simultaneously.To enhance the forecasting performance,a novel edge-enabled probabilistic graph structure learning model(PGSLM)is proposed,which learns the graph structure and parameters by the edge sensing information and discrete probability distribution on the edges of the traffic road network.To obtain the spatio-temporal dependencies of traffic data,the learned dynamic graphs are combined with a predefined static graph to generate the graph convolution part of the recurrent graph convolution module.During the training process,a new graph training loss is introduced,which is composed of the K nearest neighbor(KNN)graph constructed by the traffic feature tensors and the graph structure.Detailed experimental results show that,compared with existing models,the proposed PGSLM improves the traffic prediction performance in terms of average absolute error and root mean square error in IoV.展开更多
Intelligent straw coverage detection plays an important role in agricultural production and the ecological environment.Traditional pattern recognition has some problems,such as low precision and a long processing time...Intelligent straw coverage detection plays an important role in agricultural production and the ecological environment.Traditional pattern recognition has some problems,such as low precision and a long processing time,when segmenting complex farmland,which cannot meet the conditions of embedded equipment deployment.Based on these problems,we proposed a novel deep learning model with high accuracy,small model size and fast running speed named Residual Unet with Attention mechanism using depthwise convolution(RADw–UNet).This algorithm is based on the UNet symmetric codec model.All the feature extraction modules of the network adopt the residual structure,and the whole network only adopts 8 times the downsampling rate to reduce the redundant parameters.To better extract the semantic information of the spatial and channel dimensions,the depthwise convolutional residual block is designed to be used in feature maps with larger depths to reduce the number of parameters while improving the model accuracy.Meanwhile,the multi–level attention mechanism is introduced in the skip connection to effectively integrate the information of the low–level and high–level feature maps.The experimental results showed that the segmentation performance of RADw–UNet outperformed traditional methods and the UNet algorithm.The algorithm achieved an mIoU of 94.9%,the number of trainable parameters was only approximately 0.26 M,and the running time for a single picture was less than 0.03 s.展开更多
In view of the problems of multi-scale changes of segmentation targets,noise interference,rough segmentation results and slow training process faced by medical image semantic segmentation,a multi-scale residual aggreg...In view of the problems of multi-scale changes of segmentation targets,noise interference,rough segmentation results and slow training process faced by medical image semantic segmentation,a multi-scale residual aggregation U-shaped attention network structure of MAAUNet(MultiRes aggregation attention UNet)is proposed based on MultiResUNet.Firstly,aggregate connection is introduced from the original feature aggregation at the same level.Skip connection is redesigned to aggregate features of different semantic scales at the decoder subnet,and the problem of semantic gaps is further solved that may exist between skip connections.Secondly,after the multi-scale convolution module,a convolution block attention module is added to focus and integrate features in the two attention directions of channel and space to adaptively optimize the intermediate feature map.Finally,the original convolution block is improved.The convolution channels are expanded with a series convolution structure to complement each other and extract richer spatial features.Residual connections are retained and the convolution block is turned into a multi-channel convolution block.The model is made to extract multi-scale spatial features.The experimental results show that MAAUNet has strong competitiveness in challenging datasets,and shows good segmentation performance and stability in dealing with multi-scale input and noise interference.展开更多
Owing to the expansion of the grid interconnection scale,the spatiotemporal distribution characteristics of the frequency response of power systems after the occurrence of disturbances have become increasingly importa...Owing to the expansion of the grid interconnection scale,the spatiotemporal distribution characteristics of the frequency response of power systems after the occurrence of disturbances have become increasingly important.These characteristics can provide effective support in coordinated security control.However,traditional model-based frequencyprediction methods cannot satisfactorily meet the requirements of online applications owing to the long calculation time and accurate power-system models.Therefore,this study presents a rolling frequency-prediction model based on a graph convolutional network(GCN)and a long short-term memory(LSTM)spatiotemporal network and named as STGCN-LSTM.In the proposed method,the measurement data from phasor measurement units after the occurrence of disturbances are used to construct the spatiotemporal input.An improved GCN embedded with topology information is used to extract the spatial features,while the LSTM network is used to extract the temporal features.The spatiotemporal-network-regression model is further trained,and asynchronous-frequency-sequence prediction is realized by utilizing the rolling update of measurement information.The proposed spatiotemporal-network-based prediction model can achieve accurate frequency prediction by considering the spatiotemporal distribution characteristics of the frequency response.The noise immunity and robustness of the proposed method are verified on the IEEE 39-bus and IEEE 118-bus systems.展开更多
The secondary structure of a protein is critical for establishing a link between the protein primary and tertiary structures.For this reason,it is important to design methods for accurate protein secondary structure p...The secondary structure of a protein is critical for establishing a link between the protein primary and tertiary structures.For this reason,it is important to design methods for accurate protein secondary structure prediction.Most of the existing computational techniques for protein structural and functional prediction are based onmachine learning with shallowframeworks.Different deep learning architectures have already been applied to tackle protein secondary structure prediction problem.In this study,deep learning based models,i.e.,convolutional neural network and long short-term memory for protein secondary structure prediction were proposed.The input to proposed models is amino acid sequences which were derived from CulledPDB dataset.Hyperparameter tuning with cross validation was employed to attain best parameters for the proposed models.The proposed models enables effective processing of amino acids and attain approximately 87.05%and 87.47%Q3 accuracy of protein secondary structure prediction for convolutional neural network and long short-term memory models,respectively.展开更多
基金supported by the Natural Science Foundation Committee Program of China(Grant Nos.1538009 and 51778474)Science and Technology Project of Yunnan Provincial Transportation Department(Grant No.25 of 2018)+1 种基金the Fundamental Research Funds for the Central Universities in China(Grant No.0200219129)Key innovation team program of innovation talents promotion plan by MOST of China(Grant No.2016RA4059)。
文摘The automated interpretation of rock structure can improve the efficiency,accuracy,and consistency of the geological risk assessment of tunnel face.Because of the high uncertainties in the geological images as a result of different regional rock types,as well as in-situ conditions(e.g.,temperature,humidity,and construction procedure),previous automated methods have limited performance in classification of rock structure of tunnel face during construction.This paper presents a framework for classifying multiple rock structures based on the geological images of tunnel face using convolutional neural networks(CNN),namely Inception-ResNet-V2(IRV2).A prototype recognition system is implemented to classify 5 types of rock structures including mosaic,granular,layered,block,and fragmentation structures.The proposed IRV2 network is trained by over 35,000 out of 42,400 images extracted from over 150 sections of tunnel faces and tested by the remaining 7400 images.Furthermore,different hyperparameters of the CNN model are introduced to optimize the most efficient algorithm parameter.Among all the discussed models,i.e.,ResNet-50,ResNet-101,and Inception-v4,Inception-ResNet-V2 exhibits the best performance in terms of various indicators,such as precision,recall,F-score,and testing time per image.Meanwhile,the model trained by a large database can obtain the object features more comprehensively,leading to higher accuracy.Compared with the original image classification method,the sub-image method is closer to the reality considering both the accuracy and the perspective of error divergence.The experimental results reveal that the proposed method is optimal and efficient for automated classification of rock structure using the geological images of the tunnel face.
文摘Deep neural network-based relational extraction research has made significant progress in recent years,andit provides data support for many natural language processing downstream tasks such as building knowledgegraph,sentiment analysis and question-answering systems.However,previous studies ignored much unusedstructural information in sentences that could enhance the performance of the relation extraction task.Moreover,most existing dependency-based models utilize self-attention to distinguish the importance of context,whichhardly deals withmultiple-structure information.To efficiently leverage multiple structure information,this paperproposes a dynamic structure attention mechanism model based on textual structure information,which deeplyintegrates word embedding,named entity recognition labels,part of speech,dependency tree and dependency typeinto a graph convolutional network.Specifically,our model extracts text features of different structures from theinput sentence.Textual Structure information Graph Convolutional Networks employs the dynamic structureattention mechanism to learn multi-structure attention,effectively distinguishing important contextual features invarious structural information.In addition,multi-structure weights are carefully designed as amergingmechanismin the different structure attention to dynamically adjust the final attention.This paper combines these featuresand trains a graph convolutional network for relation extraction.We experiment on supervised relation extractiondatasets including SemEval 2010 Task 8,TACRED,TACREV,and Re-TACED,the result significantly outperformsthe previous.
基金This work was supported by the National Natural Science Foundation of China(Grant Nos.52179105 and 41941019)Science and Technology Innovation Project of Quanmutang Engineering.
文摘Regular detection and repair for lining cracks are necessary to guarantee the safety and stability of tunnels.The development of computer vision has greatly promoted structural health monitoring.This study proposes a novel encoder–decoder structure,CrackRecNet,for semantic segmentation of lining segment cracks by integrating improved VGG-19 into the U-Net architecture.An image acquisition equipment is designed based on a camera,3-dimensional printing(3DP)bracket and two laser rangefinders.A tunnel concrete structure crack(TCSC)image data set,containing images collected from a double-shield tunnel boring machines(TBM)tunnel in China,was established.Through data preprocessing operations,such as brightness adjustment,pixel resolution adjustment,flipping,splitting and annotation,2880 image samples with pixel resolution of 448×448 were prepared.The model was implemented by Pytorch in PyCharm processed with 4 NVIDIA TITAN V GPUs.In the experiments,the proposed CrackRecNet showed better prediction performance than U-Net,TernausNet,and ResU-Net.This paper also discusses GPU parallel acceleration effect and the crack maximum width quantification.
基金Supported by the National Key Research and Development Program of China(No.2022YFF0801400)the National Natural Science Foundation of China(No.42176010)the Natural Science Foundation of Shandong Province,China(No.ZR2021MD022)。
文摘Accurately estimating the ocean subsurface salinity structure(OSSS)is crucial for understanding ocean dynamics and predicting climate variations.We present a convolutional neural network(CNN)model to estimate the OSSS in the Indian Ocean using satellite data and Argo observations.We evaluated the performance of the CNN model in terms of its vertical and spatial distribution,as well as seasonal variation of OSSS estimation.Results demonstrate that the CNN model accurately estimates the most significant salinity features in the Indian Ocean using sea surface data with no significant differences from Argo-derived OSSS.However,the estimation accuracy of the CNN model varies with depth,with the most challenging depth being approximately 70 m,corresponding to the halocline layer.Validations of the CNN model’s accuracy in estimating OSSS in the Indian Ocean are also conducted by comparing Argo observations and CNN model estimations along two selected sections and four selected boxes.The results show that the CNN model effectively captures the seasonal variability of salinity,demonstrating its high performance in salinity estimation using sea surface data.Our analysis reveals that sea surface salinity has the strongest correlation with OSSS in shallow layers,while sea surface height anomaly plays a more significant role in deeper layers.These preliminary results provide valuable insights into the feasibility of estimating OSSS using satellite observations and have implications for studying upper ocean dynamics using machine learning techniques.
基金supported by the project of the National Natural Science Foundation of China(No.61772562)the Knowledge Innovation Program of Wuhan-Basic Research(No.2022010801010225)the Fundamental Research Funds for the Central Universities(No.2662022YJ012)。
文摘With the rapid development of the 5G communications,the edge intelligence enables Internet of Vehicles(IoV)to provide traffic forecasting to alleviate traffic congestion and improve quality of experience of users simultaneously.To enhance the forecasting performance,a novel edge-enabled probabilistic graph structure learning model(PGSLM)is proposed,which learns the graph structure and parameters by the edge sensing information and discrete probability distribution on the edges of the traffic road network.To obtain the spatio-temporal dependencies of traffic data,the learned dynamic graphs are combined with a predefined static graph to generate the graph convolution part of the recurrent graph convolution module.During the training process,a new graph training loss is introduced,which is composed of the K nearest neighbor(KNN)graph constructed by the traffic feature tensors and the graph structure.Detailed experimental results show that,compared with existing models,the proposed PGSLM improves the traffic prediction performance in terms of average absolute error and root mean square error in IoV.
基金National Natural Science Foundation of China,grant number 42001256key science and technology projects of science and technology department of Jilin province,Grant Number 20180201014NY+1 种基金science and technology project of education department of Jilin province,Grant Number JJKH20190927KJinnovation fund project of Jilin provincial development and reform commission,Grant Number 2019C054.
文摘Intelligent straw coverage detection plays an important role in agricultural production and the ecological environment.Traditional pattern recognition has some problems,such as low precision and a long processing time,when segmenting complex farmland,which cannot meet the conditions of embedded equipment deployment.Based on these problems,we proposed a novel deep learning model with high accuracy,small model size and fast running speed named Residual Unet with Attention mechanism using depthwise convolution(RADw–UNet).This algorithm is based on the UNet symmetric codec model.All the feature extraction modules of the network adopt the residual structure,and the whole network only adopts 8 times the downsampling rate to reduce the redundant parameters.To better extract the semantic information of the spatial and channel dimensions,the depthwise convolutional residual block is designed to be used in feature maps with larger depths to reduce the number of parameters while improving the model accuracy.Meanwhile,the multi–level attention mechanism is introduced in the skip connection to effectively integrate the information of the low–level and high–level feature maps.The experimental results showed that the segmentation performance of RADw–UNet outperformed traditional methods and the UNet algorithm.The algorithm achieved an mIoU of 94.9%,the number of trainable parameters was only approximately 0.26 M,and the running time for a single picture was less than 0.03 s.
基金National Natural Science Foundation of China(No.61806006)Jiangsu University Superior Discipline Construction Project。
文摘In view of the problems of multi-scale changes of segmentation targets,noise interference,rough segmentation results and slow training process faced by medical image semantic segmentation,a multi-scale residual aggregation U-shaped attention network structure of MAAUNet(MultiRes aggregation attention UNet)is proposed based on MultiResUNet.Firstly,aggregate connection is introduced from the original feature aggregation at the same level.Skip connection is redesigned to aggregate features of different semantic scales at the decoder subnet,and the problem of semantic gaps is further solved that may exist between skip connections.Secondly,after the multi-scale convolution module,a convolution block attention module is added to focus and integrate features in the two attention directions of channel and space to adaptively optimize the intermediate feature map.Finally,the original convolution block is improved.The convolution channels are expanded with a series convolution structure to complement each other and extract richer spatial features.Residual connections are retained and the convolution block is turned into a multi-channel convolution block.The model is made to extract multi-scale spatial features.The experimental results show that MAAUNet has strong competitiveness in challenging datasets,and shows good segmentation performance and stability in dealing with multi-scale input and noise interference.
基金supported by the National Natural Science Foundation of China(Grant Nos.51627811,51725702)the Science and Technology Project of State Grid Corporation of Beijing(Grant No.SGBJDK00DWJS2100164).
文摘Owing to the expansion of the grid interconnection scale,the spatiotemporal distribution characteristics of the frequency response of power systems after the occurrence of disturbances have become increasingly important.These characteristics can provide effective support in coordinated security control.However,traditional model-based frequencyprediction methods cannot satisfactorily meet the requirements of online applications owing to the long calculation time and accurate power-system models.Therefore,this study presents a rolling frequency-prediction model based on a graph convolutional network(GCN)and a long short-term memory(LSTM)spatiotemporal network and named as STGCN-LSTM.In the proposed method,the measurement data from phasor measurement units after the occurrence of disturbances are used to construct the spatiotemporal input.An improved GCN embedded with topology information is used to extract the spatial features,while the LSTM network is used to extract the temporal features.The spatiotemporal-network-regression model is further trained,and asynchronous-frequency-sequence prediction is realized by utilizing the rolling update of measurement information.The proposed spatiotemporal-network-based prediction model can achieve accurate frequency prediction by considering the spatiotemporal distribution characteristics of the frequency response.The noise immunity and robustness of the proposed method are verified on the IEEE 39-bus and IEEE 118-bus systems.
文摘The secondary structure of a protein is critical for establishing a link between the protein primary and tertiary structures.For this reason,it is important to design methods for accurate protein secondary structure prediction.Most of the existing computational techniques for protein structural and functional prediction are based onmachine learning with shallowframeworks.Different deep learning architectures have already been applied to tackle protein secondary structure prediction problem.In this study,deep learning based models,i.e.,convolutional neural network and long short-term memory for protein secondary structure prediction were proposed.The input to proposed models is amino acid sequences which were derived from CulledPDB dataset.Hyperparameter tuning with cross validation was employed to attain best parameters for the proposed models.The proposed models enables effective processing of amino acids and attain approximately 87.05%and 87.47%Q3 accuracy of protein secondary structure prediction for convolutional neural network and long short-term memory models,respectively.
