The infrastructure and construction of roads are crucial for the economic and social development of a region,but traffic-related challenges like accidents and congestion persist.Artificial Intelligence(AI)and Machine ...The infrastructure and construction of roads are crucial for the economic and social development of a region,but traffic-related challenges like accidents and congestion persist.Artificial Intelligence(AI)and Machine Learning(ML)have been used in road infrastructure and construction,particularly with the Internet of Things(IoT)devices.Object detection in Computer Vision also plays a key role in improving road infrastructure and addressing trafficrelated problems.This study aims to use You Only Look Once version 7(YOLOv7),Convolutional Block Attention Module(CBAM),the most optimized object-detection algorithm,to detect and identify traffic signs,and analyze effective combinations of adaptive optimizers like Adaptive Moment estimation(Adam),Root Mean Squared Propagation(RMSprop)and Stochastic Gradient Descent(SGD)with the YOLOv7.Using a portion of German traffic signs for training,the study investigates the feasibility of adopting smaller datasets while maintaining high accuracy.The model proposed in this study not only improves traffic safety by detecting traffic signs but also has the potential to contribute to the rapid development of autonomous vehicle systems.The study results showed an impressive accuracy of 99.7%when using a batch size of 8 and the Adam optimizer.This high level of accuracy demonstrates the effectiveness of the proposed model for the image classification task of traffic sign recognition.展开更多
Aim: To diagnose COVID-19 more efficiently and more correctly, this study proposed a novel attention network forCOVID-19 (ANC). Methods: Two datasets were used in this study. An 18-way data augmentation was proposed t...Aim: To diagnose COVID-19 more efficiently and more correctly, this study proposed a novel attention network forCOVID-19 (ANC). Methods: Two datasets were used in this study. An 18-way data augmentation was proposed toavoid overfitting. Then, convolutional block attention module (CBAM) was integrated to our model, the structureof which is fine-tuned. Finally, Grad-CAM was used to provide an explainable diagnosis. Results: The accuracyof our ANC methods on two datasets are 96.32% ± 1.06%, and 96.00% ± 1.03%, respectively. Conclusions: Thisproposed ANC method is superior to 9 state-of-the-art approaches.展开更多
Deep learning technology is widely used in computer vision.Generally,a large amount of data is used to train the model weights in deep learning,so as to obtain a model with higher accuracy.However,massive data and com...Deep learning technology is widely used in computer vision.Generally,a large amount of data is used to train the model weights in deep learning,so as to obtain a model with higher accuracy.However,massive data and complex model structures require more calculating resources.Since people generally can only carry and use mobile and portable devices in application scenarios,neural networks have limitations in terms of calculating resources,size and power consumption.Therefore,the efficient lightweight model MobileNet is used as the basic network in this study for optimization.First,the accuracy of the MobileNet model is improved by adding methods such as the convolutional block attention module(CBAM)and expansion convolution.Then,the MobileNet model is compressed by using pruning and weight quantization algorithms based on weight size.Afterwards,methods such as Python crawlers and data augmentation are employed to create a garbage classification data set.Based on the above model optimization strategy,the garbage classification mobile terminal application is deployed on mobile phones and raspberry pies,realizing completing the garbage classification task more conveniently.展开更多
Seismic data interpolation,especially irregularly sampled data interpolation,is a critical task for seismic processing and subsequent interpretation.Recently,with the development of machine learning and deep learning,...Seismic data interpolation,especially irregularly sampled data interpolation,is a critical task for seismic processing and subsequent interpretation.Recently,with the development of machine learning and deep learning,convolutional neural networks(CNNs)are applied for interpolating irregularly sampled seismic data.CNN based approaches can address the apparent defects of traditional interpolation methods,such as the low computational efficiency and the difficulty on parameters selection.However,current CNN based methods only consider the temporal and spatial features of irregularly sampled seismic data,which fail to consider the frequency features of seismic data,i.e.,the multi-scale features.To overcome these drawbacks,we propose a wavelet-based convolutional block attention deep learning(W-CBADL)network for irregularly sampled seismic data reconstruction.We firstly introduce the discrete wavelet transform(DWT)and the inverse wavelet transform(IWT)to the commonly used U-Net by considering the multi-scale features of irregularly sampled seismic data.Moreover,we propose to adopt the convolutional block attention module(CBAM)to precisely restore sampled seismic traces,which could apply the attention to both channel and spatial dimensions.Finally,we adopt the proposed W-CBADL model to synthetic and pre-stack field data to evaluate its validity and effectiveness.The results demonstrate that the proposed W-CBADL model could reconstruct irregularly sampled seismic data more effectively and more efficiently than the state-of-the-art contrastive CNN based models.展开更多
Developing an automatic and credible diagnostic system to analyze the type,stage,and level of the liver cancer from Hematoxylin and Eosin(H&E)images is a very challenging and time-consuming endeavor,even for exper...Developing an automatic and credible diagnostic system to analyze the type,stage,and level of the liver cancer from Hematoxylin and Eosin(H&E)images is a very challenging and time-consuming endeavor,even for experienced pathologists,due to the non-uniform illumination and artifacts.Albeit several Machine Learning(ML)and Deep Learning(DL)approaches are employed to increase the performance of automatic liver cancer diagnostic systems,the classi-fication accuracy of these systems still needs significant improvement to satisfy the real-time requirement of the diagnostic situations.In this work,we present a new Ensemble Classifier(hereafter called ECNet)to classify the H&E stained liver histopathology images effectively.The proposed model employs a Dropout Extreme Learning Machine(DrpXLM)and the Enhanced Convolutional Block Attention Modules(ECBAM)based residual network.ECNet applies Voting Mechanism(VM)to integrate the decisions of individual classifiers using the average of probabilities rule.Initially,the nuclei regions in the H&E stain are seg-mented through Super-resolution Convolutional Networks(SrCN),and then these regions are fed into the ensemble DL network for classification.The effectiveness of the proposed model is carefully studied on real-world datasets.The results of our meticulous experiments on the Kasturba Medical College(KMC)liver dataset reveal that the proposed ECNet significantly outperforms other existing classifica-tion networks with better accuracy,sensitivity,specificity,precision,and Jaccard Similarity Score(JSS)of 96.5%,99.4%,89.7%,95.7%,and 95.2%,respectively.We obtain similar results from ECNet when applied to The Cancer Genome Atlas Liver Hepatocellular Carcinoma(TCGA-LIHC)dataset regarding accuracy(96.3%),sensitivity(97.5%),specificity(93.2%),precision(97.5%),and JSS(95.1%).More importantly,the proposed ECNet system consumes only 12.22 s for training and 1.24 s for testing.Also,we carry out the Wilcoxon statistical test to determine whether the ECNet provides a considerable improvement with respect to evaluation metrics or not.From extensive empirical analysis,we can conclude that our ECNet is the better liver cancer diagnostic model related to state-of-the-art classifiers.展开更多
Moving object segmentation (MOS) is one of the essential functions of the vision system of all robots,including medical robots. Deep learning-based MOS methods, especially deep end-to-end MOS methods, are actively inv...Moving object segmentation (MOS) is one of the essential functions of the vision system of all robots,including medical robots. Deep learning-based MOS methods, especially deep end-to-end MOS methods, are actively investigated in this field. Foreground segmentation networks (FgSegNets) are representative deep end-to-endMOS methods proposed recently. This study explores a new mechanism to improve the spatial feature learningcapability of FgSegNets with relatively few brought parameters. Specifically, we propose an enhanced attention(EA) module, a parallel connection of an attention module and a lightweight enhancement module, with sequentialattention and residual attention as special cases. We also propose integrating EA with FgSegNet_v2 by taking thelightweight convolutional block attention module as the attention module and plugging EA module after the twoMaxpooling layers of the encoder. The derived new model is named FgSegNet_v2 EA. The ablation study verifiesthe effectiveness of the proposed EA module and integration strategy. The results on the CDnet2014 dataset,which depicts human activities and vehicles captured in different scenes, show that FgSegNet_v2 EA outperformsFgSegNet_v2 by 0.08% and 14.5% under the settings of scene dependent evaluation and scene independent evaluation, respectively, which indicates the positive effect of EA on improving spatial feature learning capability ofFgSegNet_v2.展开更多
文摘The infrastructure and construction of roads are crucial for the economic and social development of a region,but traffic-related challenges like accidents and congestion persist.Artificial Intelligence(AI)and Machine Learning(ML)have been used in road infrastructure and construction,particularly with the Internet of Things(IoT)devices.Object detection in Computer Vision also plays a key role in improving road infrastructure and addressing trafficrelated problems.This study aims to use You Only Look Once version 7(YOLOv7),Convolutional Block Attention Module(CBAM),the most optimized object-detection algorithm,to detect and identify traffic signs,and analyze effective combinations of adaptive optimizers like Adaptive Moment estimation(Adam),Root Mean Squared Propagation(RMSprop)and Stochastic Gradient Descent(SGD)with the YOLOv7.Using a portion of German traffic signs for training,the study investigates the feasibility of adopting smaller datasets while maintaining high accuracy.The model proposed in this study not only improves traffic safety by detecting traffic signs but also has the potential to contribute to the rapid development of autonomous vehicle systems.The study results showed an impressive accuracy of 99.7%when using a batch size of 8 and the Adam optimizer.This high level of accuracy demonstrates the effectiveness of the proposed model for the image classification task of traffic sign recognition.
基金This paper is partially supported by Open Fund for Jiangsu Key Laboratory of Advanced Manufacturing Technology(HGAMTL-1703)Guangxi Key Laboratory of Trusted Software(kx201901)+5 种基金Fundamental Research Funds for the Central Universities(CDLS-2020-03)Key Laboratory of Child Development and Learning Science(Southeast University),Ministry of EducationRoyal Society International Exchanges Cost Share Award,UK(RP202G0230)Medical Research Council Confidence in Concept Award,UK(MC_PC_17171)Hope Foundation for Cancer Research,UK(RM60G0680)British Heart Foundation Accelerator Award,UK.
文摘Aim: To diagnose COVID-19 more efficiently and more correctly, this study proposed a novel attention network forCOVID-19 (ANC). Methods: Two datasets were used in this study. An 18-way data augmentation was proposed toavoid overfitting. Then, convolutional block attention module (CBAM) was integrated to our model, the structureof which is fine-tuned. Finally, Grad-CAM was used to provide an explainable diagnosis. Results: The accuracyof our ANC methods on two datasets are 96.32% ± 1.06%, and 96.00% ± 1.03%, respectively. Conclusions: Thisproposed ANC method is superior to 9 state-of-the-art approaches.
文摘Deep learning technology is widely used in computer vision.Generally,a large amount of data is used to train the model weights in deep learning,so as to obtain a model with higher accuracy.However,massive data and complex model structures require more calculating resources.Since people generally can only carry and use mobile and portable devices in application scenarios,neural networks have limitations in terms of calculating resources,size and power consumption.Therefore,the efficient lightweight model MobileNet is used as the basic network in this study for optimization.First,the accuracy of the MobileNet model is improved by adding methods such as the convolutional block attention module(CBAM)and expansion convolution.Then,the MobileNet model is compressed by using pruning and weight quantization algorithms based on weight size.Afterwards,methods such as Python crawlers and data augmentation are employed to create a garbage classification data set.Based on the above model optimization strategy,the garbage classification mobile terminal application is deployed on mobile phones and raspberry pies,realizing completing the garbage classification task more conveniently.
基金Supported by the National Natural Science Foundation of China under Grant 42274144 and under Grant 41974137.
文摘Seismic data interpolation,especially irregularly sampled data interpolation,is a critical task for seismic processing and subsequent interpretation.Recently,with the development of machine learning and deep learning,convolutional neural networks(CNNs)are applied for interpolating irregularly sampled seismic data.CNN based approaches can address the apparent defects of traditional interpolation methods,such as the low computational efficiency and the difficulty on parameters selection.However,current CNN based methods only consider the temporal and spatial features of irregularly sampled seismic data,which fail to consider the frequency features of seismic data,i.e.,the multi-scale features.To overcome these drawbacks,we propose a wavelet-based convolutional block attention deep learning(W-CBADL)network for irregularly sampled seismic data reconstruction.We firstly introduce the discrete wavelet transform(DWT)and the inverse wavelet transform(IWT)to the commonly used U-Net by considering the multi-scale features of irregularly sampled seismic data.Moreover,we propose to adopt the convolutional block attention module(CBAM)to precisely restore sampled seismic traces,which could apply the attention to both channel and spatial dimensions.Finally,we adopt the proposed W-CBADL model to synthetic and pre-stack field data to evaluate its validity and effectiveness.The results demonstrate that the proposed W-CBADL model could reconstruct irregularly sampled seismic data more effectively and more efficiently than the state-of-the-art contrastive CNN based models.
文摘Developing an automatic and credible diagnostic system to analyze the type,stage,and level of the liver cancer from Hematoxylin and Eosin(H&E)images is a very challenging and time-consuming endeavor,even for experienced pathologists,due to the non-uniform illumination and artifacts.Albeit several Machine Learning(ML)and Deep Learning(DL)approaches are employed to increase the performance of automatic liver cancer diagnostic systems,the classi-fication accuracy of these systems still needs significant improvement to satisfy the real-time requirement of the diagnostic situations.In this work,we present a new Ensemble Classifier(hereafter called ECNet)to classify the H&E stained liver histopathology images effectively.The proposed model employs a Dropout Extreme Learning Machine(DrpXLM)and the Enhanced Convolutional Block Attention Modules(ECBAM)based residual network.ECNet applies Voting Mechanism(VM)to integrate the decisions of individual classifiers using the average of probabilities rule.Initially,the nuclei regions in the H&E stain are seg-mented through Super-resolution Convolutional Networks(SrCN),and then these regions are fed into the ensemble DL network for classification.The effectiveness of the proposed model is carefully studied on real-world datasets.The results of our meticulous experiments on the Kasturba Medical College(KMC)liver dataset reveal that the proposed ECNet significantly outperforms other existing classifica-tion networks with better accuracy,sensitivity,specificity,precision,and Jaccard Similarity Score(JSS)of 96.5%,99.4%,89.7%,95.7%,and 95.2%,respectively.We obtain similar results from ECNet when applied to The Cancer Genome Atlas Liver Hepatocellular Carcinoma(TCGA-LIHC)dataset regarding accuracy(96.3%),sensitivity(97.5%),specificity(93.2%),precision(97.5%),and JSS(95.1%).More importantly,the proposed ECNet system consumes only 12.22 s for training and 1.24 s for testing.Also,we carry out the Wilcoxon statistical test to determine whether the ECNet provides a considerable improvement with respect to evaluation metrics or not.From extensive empirical analysis,we can conclude that our ECNet is the better liver cancer diagnostic model related to state-of-the-art classifiers.
基金the National Natural Science Foundation of China(No.61702323)。
文摘Moving object segmentation (MOS) is one of the essential functions of the vision system of all robots,including medical robots. Deep learning-based MOS methods, especially deep end-to-end MOS methods, are actively investigated in this field. Foreground segmentation networks (FgSegNets) are representative deep end-to-endMOS methods proposed recently. This study explores a new mechanism to improve the spatial feature learningcapability of FgSegNets with relatively few brought parameters. Specifically, we propose an enhanced attention(EA) module, a parallel connection of an attention module and a lightweight enhancement module, with sequentialattention and residual attention as special cases. We also propose integrating EA with FgSegNet_v2 by taking thelightweight convolutional block attention module as the attention module and plugging EA module after the twoMaxpooling layers of the encoder. The derived new model is named FgSegNet_v2 EA. The ablation study verifiesthe effectiveness of the proposed EA module and integration strategy. The results on the CDnet2014 dataset,which depicts human activities and vehicles captured in different scenes, show that FgSegNet_v2 EA outperformsFgSegNet_v2 by 0.08% and 14.5% under the settings of scene dependent evaluation and scene independent evaluation, respectively, which indicates the positive effect of EA on improving spatial feature learning capability ofFgSegNet_v2.