Communication behavior recognition is an issue with increasingly importance in the antiterrorism and national defense area.However,the sensing data obtained in actual environment is often not sufficient to accurately ...Communication behavior recognition is an issue with increasingly importance in the antiterrorism and national defense area.However,the sensing data obtained in actual environment is often not sufficient to accurately analyze the communication behavior.Traditional means can hardly utilize the scarce and crude spectrum sensing data captured in a real scene.Thus,communication behavior recognition using raw sensing data under smallsample condition has become a new challenge.In this paper,a data enhanced communication behavior recognition(DECBR)scheme is proposed to meet this challenge.Firstly,a preprocessing method is designed to make the raw spectrum data suitable for the proposed scheme.Then,an adaptive convolutional neural network structure is exploited to carry out communication behavior recognition.Moreover,DCGAN is applied to support data enhancement,which realize communication behavior recognition under small-sample condition.Finally,the scheme is verified by experiments under different data size.The results show that the DECBR scheme can greatly improve the accuracy and efficiency of behavior recognition under smallsample condition.展开更多
To address the shortage of public datasets for customs X-ray images of contraband and the difficulties in deploying trained models in engineering applications,a method has been proposed that employs the Extract-Transf...To address the shortage of public datasets for customs X-ray images of contraband and the difficulties in deploying trained models in engineering applications,a method has been proposed that employs the Extract-Transform-Load(ETL)approach to create an X-ray dataset of contraband items.Initially,X-ray scatter image data is collected and cleaned.Using Kafka message queues and the Elasticsearch(ES)distributed search engine,the data is transmitted in real-time to cloud servers.Subsequently,contraband data is annotated using a combination of neural networks and manual methods to improve annotation efficiency and implemented mean hash algorithm for quick image retrieval.The method of integrating targets with backgrounds has enhanced the X-ray contraband image data,increasing the number of positive samples.Finally,an Airport Customs X-ray dataset(ACXray)compatible with customs business scenarios has been constructed,featuring an increased number of positive contraband samples.Experimental tests using three datasets to train the Mask Region-based Convolutional Neural Network(Mask R-CNN)algorithm and tested on 400 real customs images revealed that the recognition accuracy of algorithms trained with Security Inspection X-ray(SIXray)and Occluded Prohibited Items X-ray(OPIXray)decreased by 16.3%and 15.1%,respectively,while the ACXray dataset trained algorithm’s accuracy was almost unaffected.This indicates that the ACXray dataset-trained algorithm possesses strong generalization capabilities and is more suitable for customs detection scenarios.展开更多
This paper proposes a new network structure,namely the ProNet network.Retinal medical image segmentation can help clinical diagnosis of related eye diseases and is essential for subsequent rational treatment.The basel...This paper proposes a new network structure,namely the ProNet network.Retinal medical image segmentation can help clinical diagnosis of related eye diseases and is essential for subsequent rational treatment.The baseline model of the ProNet network is UperNet(Unified perceptual parsing Network),and the backbone network is ConvNext(Convolutional Network).A network structure based on depth-separable convolution and 1×1 convolution is used,which has good performance and robustness.We further optimise ProNet mainly in two aspects.One is data enhancement using increased noise and slight angle rotation,which can significantly increase the diversity of data and help the model better learn the patterns and features of the data and improve the model’s performance.Meanwhile,it can effectively expand the training data set,reduce the influence of noise and abnormal data in the data set on the model,and improve the accuracy and reliability of the model.Another is the loss function aspect,and we finally use the focal loss function.The focal loss function is well suited for complex tasks such as object detection.The function will penalise the loss carried by samples that the model misclassifies,thus enabling better training of the model to avoid these errors while solving the category imbalance problem as a way to improve image segmentation density and segmentation accuracy.From the experimental results,the evaluation metrics mIoU(mean Intersection over Union)enhanced by 4.47%,and mDice enhanced by 2.92% compared to the baseline network.Better generalization effects and more accurate image segmentation are achieved.展开更多
The rapid pace of urban development has resulted in the widespread presence of construction equipment andincreasingly complex conditions in transmission corridors. These conditions pose a serious threat to the safeope...The rapid pace of urban development has resulted in the widespread presence of construction equipment andincreasingly complex conditions in transmission corridors. These conditions pose a serious threat to the safeoperation of the power grid.Machine vision technology, particularly object recognition technology, has beenwidelyemployed to identify foreign objects in transmission line images. Despite its wide application, the technique faceslimitations due to the complex environmental background and other auxiliary factors. To address these challenges,this study introduces an improved YOLOv8n. The traditional stepwise convolution and pooling layers are replacedwith a spatial-depth convolution (SPD-Conv) module, aiming to improve the algorithm’s efficacy in recognizinglow-resolution and small-size objects. The algorithm’s feature extraction network is improved by using a LargeSelective Kernel (LSK) attention mechanism, which enhances the ability to extract relevant features. Additionally,the SIoU Loss function is used instead of the Complete Intersection over Union (CIoU) Loss to facilitate fasterconvergence of the algorithm. Through experimental verification, the improved YOLOv8n model achieves adetection accuracy of 88.8% on the test set. The recognition accuracy of cranes is improved by 2.9%, which isa significant enhancement compared to the unimproved algorithm. This improvement effectively enhances theaccuracy of recognizing foreign objects on transmission lines and proves the effectiveness of the new algorithm.展开更多
Encrypted traffic identification pertains to the precise acquisition and categorization of data from traffic datasets containing imbalanced and obscured content.The extraction of encrypted traffic attributes and their...Encrypted traffic identification pertains to the precise acquisition and categorization of data from traffic datasets containing imbalanced and obscured content.The extraction of encrypted traffic attributes and their subsequent identification presents a formidable challenge.The existing models have predominantly relied on direct extraction of encrypted traffic data from imbalanced datasets,with the dataset’s imbalance significantly affecting the model’s performance.In the present study,a new model,referred to as UD-VLD(Unbalanced Dataset-VAE-LSTM-DRN),was proposed to address above problem.The proposed model is an encrypted traffic identification model for handling unbalanced datasets.The encoder of the variational autoencoder(VAE)is combined with the decoder and Long-short term Memory(LSTM)in UD-VLD model to realize the data enhancement processing of the original unbalanced datasets.The enhanced data is processed by transforming the deep residual network(DRN)to address neural network gradient-related issues.Subsequently,the data is classified and recognized.The UD-VLD model integrates the related techniques of deep learning into the encrypted traffic recognition technique,thereby solving the processing problem for unbalanced datasets.The UD-VLD model was tested using the publicly available Tor dataset and VPN dataset.The UD-VLD model is evaluated against other comparative models in terms of accuracy,loss rate,precision,recall,F1-score,total time,and ROC curve.The results reveal that the UD-VLD model exhibits better performance in both binary and multi classification,being higher than other encrypted traffic recognition models that exist for unbalanced datasets.Furthermore,the evaluation performance indicates that the UD-VLD model effectivelymitigates the impact of unbalanced data on traffic classification.and can serve as a novel solution for encrypted traffic identification.展开更多
This paper proposes a real-time detection method to improve the Infrared small target detection CenterNet(ISTD-CenterNet)network for detecting small infrared targets in complex environments.The method eliminates the n...This paper proposes a real-time detection method to improve the Infrared small target detection CenterNet(ISTD-CenterNet)network for detecting small infrared targets in complex environments.The method eliminates the need for an anchor frame,addressing the issues of low accuracy and slow speed.HRNet is used as the framework for feature extraction,and an ECBAM attention module is added to each stage branch for intelligent identification of the positions of small targets and significant objects.A scale enhancement module is also added to obtain a high-level semantic representation and fine-resolution prediction map for the entire infrared image.Besides,an improved sensory field enhancement module is designed to leverage semantic information in low-resolution feature maps,and a convolutional attention mechanism module is used to increase network stability and convergence speed.Comparison experiments conducted on the infrared small target data set ESIRST.The experiments show that compared to the benchmark network CenterNet-HRNet,the proposed ISTD-CenterNet improves the recall by 22.85%and the detection accuracy by 13.36%.Compared to the state-of-the-art YOLOv5small,the ISTD-CenterNet recall is improved by 5.88%,the detection precision is improved by 2.33%,and the detection frame rate is 48.94 frames/sec,which realizes the accurate real-time detection of small infrared targets.展开更多
To improve Asian food image classification accuracy, a method that combined Convolutional Block Attention Module (CBAM) with the Mobile NetV2, VGG16, and ResNet50 was proposed for Asian food image classification. Addi...To improve Asian food image classification accuracy, a method that combined Convolutional Block Attention Module (CBAM) with the Mobile NetV2, VGG16, and ResNet50 was proposed for Asian food image classification. Additionally, we proposed to use a mixed data enhancement algorithm (Mixup) to have a smoother discrimination ability. The effects of introducing the attention mechanism (CBAM) and using the mixed data enhancement algorithm (Mixup) were shown respectively through experimental comparison. The combination of these two and the final test set Top-1 accuracy rate reached 87.33%. Moreover, the information emphasized by CBAM was reflected through the visualization of the heat map. The results confirmed the classification method’s effectiveness and provided new ideas that improved Asian food image classification accuracy.展开更多
Objective A classification and diagnosis model for psoriasis based on deep residual network is proposed in this paper.Which using deep learning technology to classify and diagnose psoriasis can help reduce the burden ...Objective A classification and diagnosis model for psoriasis based on deep residual network is proposed in this paper.Which using deep learning technology to classify and diagnose psoriasis can help reduce the burden of doctors,simplify the diagnosis and treatment process,and improve the quality of diagnosis.Methods Firstly,data enhancement,image resizings,and TFRecord coding are used to preprocess the input of the model,and then a 34-layer deep residual network(ResNet-34)is constructed to extract the characteristics of psoriasis.Finally,we used the Adam algorithm as the optimizer to train ResNet-34,used cross-entropy as the loss function of ResNet-34 in this study to measure the accuracy of the model,and obtained an optimized ResNet-34 model for psoriasis diagnosis.Results The experimental results based on k-fold cross validation show that the proposed model is superior to other diagnostic methods in terms of recall rate,F1-score and ROC curve.Conclusion The ResNet-34 model can achieve accurate diagnosis of psoriasis,and provide technical support for data analysis and intelligent diagnosis and treatment of psoriasis.展开更多
In view of the shortage of traditional life prediction methods for machine tools,such as low accuracy of life prediction and few samples basis attributes,a life prediction model of machine tools combined with machine ...In view of the shortage of traditional life prediction methods for machine tools,such as low accuracy of life prediction and few samples basis attributes,a life prediction model of machine tools combined with machine tool attributes is proposed.The life prediction model of machine tool adopts KL dispersion distribution theory,uses modal superposition method to carry out machine tool life analysis,calculates the theoretical life of machine tool,and then carries on the simulation,obtains the machine tool life prediction value.Compared with the traditional method of machine tool life prediction,the model is based on the application life fatigue damage model,which superimposes the service times and maintenance cycle of the machine tool,derives the influence factor of machine tool life,and obtains the linear relationship between the influence factor of machine tool life and the life of machine tool.The influence factor of machine tool life is introduced as the life prediction parameter of machine tool.The data transformation relationship of HT300 parts is constructed.The original part data is enhanced.The effective training set is obtained.The life prediction model of machine tool based on deep learning is completed.The quantitative analysis of machine tool life is carried out.The experiment of machine tool life prediction using training data set proves the validity of the model.Regression test was carried out on the training data set to reflect the robustness of the model.The prediction accuracy of the model is further verified by Weibull test.展开更多
Data narratives are an emerging form of communication that employs enhanced media for effective knowledge transfer of complex information.Researchers in the fields of data visualization and artificial intelligence hav...Data narratives are an emerging form of communication that employs enhanced media for effective knowledge transfer of complex information.Researchers in the fields of data visualization and artificial intelligence have begun to pioneer new structures of communication to improve the efficiency of construction and the retention of information provided by the knowledge transfer experience.In this paper,we report the results of an empirical study conducted to compare the performance of various narrative communication techniques including frame based narrative visualization,documentary narrative visualization,computer generated text narratives and human generated text narratives.We assess the knowledge transfer performance for each of these data driven narrative structures.Across all conditions,an identical set of knowledge retention questions assessed participants’recall of details from their assigned narrative communication.Statistical analysis on group performance answering the knowledge retention questions revealed that some narrative communication techniques perform better with general audiences.展开更多
Automatic segmentation of ischemic stroke lesions from computed tomography(CT)images is of great significance for identifying and curing this life-threatening condition.However,in addition to the problem of low image ...Automatic segmentation of ischemic stroke lesions from computed tomography(CT)images is of great significance for identifying and curing this life-threatening condition.However,in addition to the problem of low image contrast,it is also challenged by the complex changes in the appearance of the stroke area and the difficulty in obtaining image data.Considering that it is difficult to obtain stroke data and labels,a data enhancement algorithm for one-shot medical image segmentation based on data augmentation using learned transformation was proposed to increase the number of data sets for more accurate segmentation.A deep convolutional neural network based algorithm for stroke lesion segmentation,called structural similarity with light U-structure(USSL)Net,was proposed.We embedded a convolution module that combines switchable normalization,multi-scale convolution and dilated convolution in the network for better segmentation performance.Besides,considering the strong structural similarity between multi-modal stroke CT images,the USSL Net uses the correlation maximized structural similarity loss(SSL)function as the loss function to learn the varying shapes of the lesions.The experimental results show that our framework has achieved results in the following aspects.First,the data obtained by adding our data enhancement algorithm is better than the data directly segmented from the multi-modal image.Second,the performance of our network model is better than that of other models for stroke segmentation tasks.Third,the way SSL functioned as a loss function is more helpful to the improvement of segmentation accuracy than the cross-entropy loss function.展开更多
基金supported by the National Natural Science Foundation of China(No.61971439 and No.61702543)the Natural Science Foundation of the Jiangsu Province of China(No.BK20191329)+1 种基金the China Postdoctoral Science Foundation Project(No.2019T120987)the Startup Foundation for Introducing Talent of NUIST(No.2020r100).
文摘Communication behavior recognition is an issue with increasingly importance in the antiterrorism and national defense area.However,the sensing data obtained in actual environment is often not sufficient to accurately analyze the communication behavior.Traditional means can hardly utilize the scarce and crude spectrum sensing data captured in a real scene.Thus,communication behavior recognition using raw sensing data under smallsample condition has become a new challenge.In this paper,a data enhanced communication behavior recognition(DECBR)scheme is proposed to meet this challenge.Firstly,a preprocessing method is designed to make the raw spectrum data suitable for the proposed scheme.Then,an adaptive convolutional neural network structure is exploited to carry out communication behavior recognition.Moreover,DCGAN is applied to support data enhancement,which realize communication behavior recognition under small-sample condition.Finally,the scheme is verified by experiments under different data size.The results show that the DECBR scheme can greatly improve the accuracy and efficiency of behavior recognition under smallsample condition.
基金supported by the National Natural Science Foundation of China(Grant No.51605069).
文摘To address the shortage of public datasets for customs X-ray images of contraband and the difficulties in deploying trained models in engineering applications,a method has been proposed that employs the Extract-Transform-Load(ETL)approach to create an X-ray dataset of contraband items.Initially,X-ray scatter image data is collected and cleaned.Using Kafka message queues and the Elasticsearch(ES)distributed search engine,the data is transmitted in real-time to cloud servers.Subsequently,contraband data is annotated using a combination of neural networks and manual methods to improve annotation efficiency and implemented mean hash algorithm for quick image retrieval.The method of integrating targets with backgrounds has enhanced the X-ray contraband image data,increasing the number of positive samples.Finally,an Airport Customs X-ray dataset(ACXray)compatible with customs business scenarios has been constructed,featuring an increased number of positive contraband samples.Experimental tests using three datasets to train the Mask Region-based Convolutional Neural Network(Mask R-CNN)algorithm and tested on 400 real customs images revealed that the recognition accuracy of algorithms trained with Security Inspection X-ray(SIXray)and Occluded Prohibited Items X-ray(OPIXray)decreased by 16.3%and 15.1%,respectively,while the ACXray dataset trained algorithm’s accuracy was almost unaffected.This indicates that the ACXray dataset-trained algorithm possesses strong generalization capabilities and is more suitable for customs detection scenarios.
文摘This paper proposes a new network structure,namely the ProNet network.Retinal medical image segmentation can help clinical diagnosis of related eye diseases and is essential for subsequent rational treatment.The baseline model of the ProNet network is UperNet(Unified perceptual parsing Network),and the backbone network is ConvNext(Convolutional Network).A network structure based on depth-separable convolution and 1×1 convolution is used,which has good performance and robustness.We further optimise ProNet mainly in two aspects.One is data enhancement using increased noise and slight angle rotation,which can significantly increase the diversity of data and help the model better learn the patterns and features of the data and improve the model’s performance.Meanwhile,it can effectively expand the training data set,reduce the influence of noise and abnormal data in the data set on the model,and improve the accuracy and reliability of the model.Another is the loss function aspect,and we finally use the focal loss function.The focal loss function is well suited for complex tasks such as object detection.The function will penalise the loss carried by samples that the model misclassifies,thus enabling better training of the model to avoid these errors while solving the category imbalance problem as a way to improve image segmentation density and segmentation accuracy.From the experimental results,the evaluation metrics mIoU(mean Intersection over Union)enhanced by 4.47%,and mDice enhanced by 2.92% compared to the baseline network.Better generalization effects and more accurate image segmentation are achieved.
基金the Natural Science Foundation of Shandong Province(ZR2021QE289)State Key Laboratory of Electrical Insulation and Power Equipment(EIPE22201).
文摘The rapid pace of urban development has resulted in the widespread presence of construction equipment andincreasingly complex conditions in transmission corridors. These conditions pose a serious threat to the safeoperation of the power grid.Machine vision technology, particularly object recognition technology, has beenwidelyemployed to identify foreign objects in transmission line images. Despite its wide application, the technique faceslimitations due to the complex environmental background and other auxiliary factors. To address these challenges,this study introduces an improved YOLOv8n. The traditional stepwise convolution and pooling layers are replacedwith a spatial-depth convolution (SPD-Conv) module, aiming to improve the algorithm’s efficacy in recognizinglow-resolution and small-size objects. The algorithm’s feature extraction network is improved by using a LargeSelective Kernel (LSK) attention mechanism, which enhances the ability to extract relevant features. Additionally,the SIoU Loss function is used instead of the Complete Intersection over Union (CIoU) Loss to facilitate fasterconvergence of the algorithm. Through experimental verification, the improved YOLOv8n model achieves adetection accuracy of 88.8% on the test set. The recognition accuracy of cranes is improved by 2.9%, which isa significant enhancement compared to the unimproved algorithm. This improvement effectively enhances theaccuracy of recognizing foreign objects on transmission lines and proves the effectiveness of the new algorithm.
基金supported by the Fundamental Research Funds for Higher Education Institutions of Heilongjiang Province(145209126)the Heilongjiang Province Higher Education Teaching Reform Project under Grant No.SJGY20200770.
文摘Encrypted traffic identification pertains to the precise acquisition and categorization of data from traffic datasets containing imbalanced and obscured content.The extraction of encrypted traffic attributes and their subsequent identification presents a formidable challenge.The existing models have predominantly relied on direct extraction of encrypted traffic data from imbalanced datasets,with the dataset’s imbalance significantly affecting the model’s performance.In the present study,a new model,referred to as UD-VLD(Unbalanced Dataset-VAE-LSTM-DRN),was proposed to address above problem.The proposed model is an encrypted traffic identification model for handling unbalanced datasets.The encoder of the variational autoencoder(VAE)is combined with the decoder and Long-short term Memory(LSTM)in UD-VLD model to realize the data enhancement processing of the original unbalanced datasets.The enhanced data is processed by transforming the deep residual network(DRN)to address neural network gradient-related issues.Subsequently,the data is classified and recognized.The UD-VLD model integrates the related techniques of deep learning into the encrypted traffic recognition technique,thereby solving the processing problem for unbalanced datasets.The UD-VLD model was tested using the publicly available Tor dataset and VPN dataset.The UD-VLD model is evaluated against other comparative models in terms of accuracy,loss rate,precision,recall,F1-score,total time,and ROC curve.The results reveal that the UD-VLD model exhibits better performance in both binary and multi classification,being higher than other encrypted traffic recognition models that exist for unbalanced datasets.Furthermore,the evaluation performance indicates that the UD-VLD model effectivelymitigates the impact of unbalanced data on traffic classification.and can serve as a novel solution for encrypted traffic identification.
基金funded by National Natural Science Foundation of China,Fund Number 61703424.
文摘This paper proposes a real-time detection method to improve the Infrared small target detection CenterNet(ISTD-CenterNet)network for detecting small infrared targets in complex environments.The method eliminates the need for an anchor frame,addressing the issues of low accuracy and slow speed.HRNet is used as the framework for feature extraction,and an ECBAM attention module is added to each stage branch for intelligent identification of the positions of small targets and significant objects.A scale enhancement module is also added to obtain a high-level semantic representation and fine-resolution prediction map for the entire infrared image.Besides,an improved sensory field enhancement module is designed to leverage semantic information in low-resolution feature maps,and a convolutional attention mechanism module is used to increase network stability and convergence speed.Comparison experiments conducted on the infrared small target data set ESIRST.The experiments show that compared to the benchmark network CenterNet-HRNet,the proposed ISTD-CenterNet improves the recall by 22.85%and the detection accuracy by 13.36%.Compared to the state-of-the-art YOLOv5small,the ISTD-CenterNet recall is improved by 5.88%,the detection precision is improved by 2.33%,and the detection frame rate is 48.94 frames/sec,which realizes the accurate real-time detection of small infrared targets.
文摘To improve Asian food image classification accuracy, a method that combined Convolutional Block Attention Module (CBAM) with the Mobile NetV2, VGG16, and ResNet50 was proposed for Asian food image classification. Additionally, we proposed to use a mixed data enhancement algorithm (Mixup) to have a smoother discrimination ability. The effects of introducing the attention mechanism (CBAM) and using the mixed data enhancement algorithm (Mixup) were shown respectively through experimental comparison. The combination of these two and the final test set Top-1 accuracy rate reached 87.33%. Moreover, the information emphasized by CBAM was reflected through the visualization of the heat map. The results confirmed the classification method’s effectiveness and provided new ideas that improved Asian food image classification accuracy.
基金We thank for the funding support from the Key Research and Development Plan of China(No.2017YFC1703306)Youth Project of Natural Science Foundation of Hunan Province(No.2019JJ50453)+2 种基金Project of Hunan Health Commission(No.202112072217)Open Fund Project of Hunan University of Traditional Chinese Medicine(No.2018JK02)General Project of Education Department of Hunan Province(No.19C1318).
文摘Objective A classification and diagnosis model for psoriasis based on deep residual network is proposed in this paper.Which using deep learning technology to classify and diagnose psoriasis can help reduce the burden of doctors,simplify the diagnosis and treatment process,and improve the quality of diagnosis.Methods Firstly,data enhancement,image resizings,and TFRecord coding are used to preprocess the input of the model,and then a 34-layer deep residual network(ResNet-34)is constructed to extract the characteristics of psoriasis.Finally,we used the Adam algorithm as the optimizer to train ResNet-34,used cross-entropy as the loss function of ResNet-34 in this study to measure the accuracy of the model,and obtained an optimized ResNet-34 model for psoriasis diagnosis.Results The experimental results based on k-fold cross validation show that the proposed model is superior to other diagnostic methods in terms of recall rate,F1-score and ROC curve.Conclusion The ResNet-34 model can achieve accurate diagnosis of psoriasis,and provide technical support for data analysis and intelligent diagnosis and treatment of psoriasis.
文摘In view of the shortage of traditional life prediction methods for machine tools,such as low accuracy of life prediction and few samples basis attributes,a life prediction model of machine tools combined with machine tool attributes is proposed.The life prediction model of machine tool adopts KL dispersion distribution theory,uses modal superposition method to carry out machine tool life analysis,calculates the theoretical life of machine tool,and then carries on the simulation,obtains the machine tool life prediction value.Compared with the traditional method of machine tool life prediction,the model is based on the application life fatigue damage model,which superimposes the service times and maintenance cycle of the machine tool,derives the influence factor of machine tool life,and obtains the linear relationship between the influence factor of machine tool life and the life of machine tool.The influence factor of machine tool life is introduced as the life prediction parameter of machine tool.The data transformation relationship of HT300 parts is constructed.The original part data is enhanced.The effective training set is obtained.The life prediction model of machine tool based on deep learning is completed.The quantitative analysis of machine tool life is carried out.The experiment of machine tool life prediction using training data set proves the validity of the model.Regression test was carried out on the training data set to reflect the robustness of the model.The prediction accuracy of the model is further verified by Weibull test.
文摘Data narratives are an emerging form of communication that employs enhanced media for effective knowledge transfer of complex information.Researchers in the fields of data visualization and artificial intelligence have begun to pioneer new structures of communication to improve the efficiency of construction and the retention of information provided by the knowledge transfer experience.In this paper,we report the results of an empirical study conducted to compare the performance of various narrative communication techniques including frame based narrative visualization,documentary narrative visualization,computer generated text narratives and human generated text narratives.We assess the knowledge transfer performance for each of these data driven narrative structures.Across all conditions,an identical set of knowledge retention questions assessed participants’recall of details from their assigned narrative communication.Statistical analysis on group performance answering the knowledge retention questions revealed that some narrative communication techniques perform better with general audiences.
基金the National Natural Science Foundation of China(No.61976091)。
文摘Automatic segmentation of ischemic stroke lesions from computed tomography(CT)images is of great significance for identifying and curing this life-threatening condition.However,in addition to the problem of low image contrast,it is also challenged by the complex changes in the appearance of the stroke area and the difficulty in obtaining image data.Considering that it is difficult to obtain stroke data and labels,a data enhancement algorithm for one-shot medical image segmentation based on data augmentation using learned transformation was proposed to increase the number of data sets for more accurate segmentation.A deep convolutional neural network based algorithm for stroke lesion segmentation,called structural similarity with light U-structure(USSL)Net,was proposed.We embedded a convolution module that combines switchable normalization,multi-scale convolution and dilated convolution in the network for better segmentation performance.Besides,considering the strong structural similarity between multi-modal stroke CT images,the USSL Net uses the correlation maximized structural similarity loss(SSL)function as the loss function to learn the varying shapes of the lesions.The experimental results show that our framework has achieved results in the following aspects.First,the data obtained by adding our data enhancement algorithm is better than the data directly segmented from the multi-modal image.Second,the performance of our network model is better than that of other models for stroke segmentation tasks.Third,the way SSL functioned as a loss function is more helpful to the improvement of segmentation accuracy than the cross-entropy loss function.
