In order to solve the problem that the testing cost of the three-dimensional integrated circuit(3D IC)is too high,an optimal stacking order scheme is proposed to reduce the mid-bond test cost.A new testing model is bu...In order to solve the problem that the testing cost of the three-dimensional integrated circuit(3D IC)is too high,an optimal stacking order scheme is proposed to reduce the mid-bond test cost.A new testing model is built with the general consideration of both the test time for automatic test equipment(ATE)and manufacturing failure factors.An algorithm for testing cost and testing order optimization is proposed,and the minimum testing cost and optimized stacking order can be carried out by taking testing bandwidth and testing power as constraints.To prove the influence of the optimal stacking order on testing costs,two baselines stacked in sequential either in pyramid type or in inverted pyramid type are compared.Based on the benchmarks from ITC 02,experimental results show that for a 5-layer 3D IC,under different constraints,the optimal stacking order can reduce the test costs on average by 13%and 62%,respectively,compared to the pyramid type and inverted pyramid type.Furthermore,with the increase of the stack size,the test costs of the optimized stack order can be decreased.展开更多
Objective In tongue diagnosis,the location,color,and distribution of spots can be used to speculate on the viscera and severity of the heat evil.This work focuses on the image analysis method of artificial intelligenc...Objective In tongue diagnosis,the location,color,and distribution of spots can be used to speculate on the viscera and severity of the heat evil.This work focuses on the image analysis method of artificial intelligence(AI)to study the spotted tongue recognition of traditional Chinese medicine(TCM).Methods A model of spotted tongue recognition and extraction is designed,which is based on the principle of image deep learning and instance segmentation.This model includes multiscale feature map generation,region proposal searching,and target region recognition.Firstly,deep convolution network is used to build multiscale low-and high-abstraction feature maps after which,target candidate box generation algorithm and selection strategy are used to select high-quality target candidate regions.Finally,classification network is used for classifying target regions and calculating target region pixels.As a result,the region segmentation of spotted tongue is obtained.Under non-standard illumination conditions,various tongue images were taken by mobile phones,and experiments were conducted.Results The spotted tongue recognition achieved an area under curve(AUC)of 92.40%,an accuracy of 84.30%with a sensitivity of 88.20%,a specificity of 94.19%,a recall of 88.20%,a regional pixel accuracy index pixel accuracy(PA)of 73.00%,a mean pixel accuracy(m PA)of73.00%,an intersection over union(Io U)of 60.00%,and a mean intersection over union(mIo U)of 56.00%.Conclusion The results of the study verify that the model is suitable for the application of the TCM tongue diagnosis system.Spotted tongue recognition via multiscale convolutional neural network(CNN)would help to improve spot classification and the accurate extraction of pixels of spot area as well as provide a practical method for intelligent tongue diagnosis of TCM.展开更多
基金The National Natural Science Foundation of China(No.61674048,61574052,61474036,61371025)the Project of Anhui Institute of Economics and Management(No.YJKT1417T01)
文摘In order to solve the problem that the testing cost of the three-dimensional integrated circuit(3D IC)is too high,an optimal stacking order scheme is proposed to reduce the mid-bond test cost.A new testing model is built with the general consideration of both the test time for automatic test equipment(ATE)and manufacturing failure factors.An algorithm for testing cost and testing order optimization is proposed,and the minimum testing cost and optimized stacking order can be carried out by taking testing bandwidth and testing power as constraints.To prove the influence of the optimal stacking order on testing costs,two baselines stacked in sequential either in pyramid type or in inverted pyramid type are compared.Based on the benchmarks from ITC 02,experimental results show that for a 5-layer 3D IC,under different constraints,the optimal stacking order can reduce the test costs on average by 13%and 62%,respectively,compared to the pyramid type and inverted pyramid type.Furthermore,with the increase of the stack size,the test costs of the optimized stack order can be decreased.
基金Anhui Province College Natural Science Fund Key Project of China(KJ2020ZD77)the Project of Education Department of Anhui Province(KJ2020A0379)。
文摘Objective In tongue diagnosis,the location,color,and distribution of spots can be used to speculate on the viscera and severity of the heat evil.This work focuses on the image analysis method of artificial intelligence(AI)to study the spotted tongue recognition of traditional Chinese medicine(TCM).Methods A model of spotted tongue recognition and extraction is designed,which is based on the principle of image deep learning and instance segmentation.This model includes multiscale feature map generation,region proposal searching,and target region recognition.Firstly,deep convolution network is used to build multiscale low-and high-abstraction feature maps after which,target candidate box generation algorithm and selection strategy are used to select high-quality target candidate regions.Finally,classification network is used for classifying target regions and calculating target region pixels.As a result,the region segmentation of spotted tongue is obtained.Under non-standard illumination conditions,various tongue images were taken by mobile phones,and experiments were conducted.Results The spotted tongue recognition achieved an area under curve(AUC)of 92.40%,an accuracy of 84.30%with a sensitivity of 88.20%,a specificity of 94.19%,a recall of 88.20%,a regional pixel accuracy index pixel accuracy(PA)of 73.00%,a mean pixel accuracy(m PA)of73.00%,an intersection over union(Io U)of 60.00%,and a mean intersection over union(mIo U)of 56.00%.Conclusion The results of the study verify that the model is suitable for the application of the TCM tongue diagnosis system.Spotted tongue recognition via multiscale convolutional neural network(CNN)would help to improve spot classification and the accurate extraction of pixels of spot area as well as provide a practical method for intelligent tongue diagnosis of TCM.
