The micro-expression lasts for a very short time and the intensity is very subtle.Aiming at the problem of its low recognition rate,this paper proposes a new micro-expression recognition algorithm based on a three-dim...The micro-expression lasts for a very short time and the intensity is very subtle.Aiming at the problem of its low recognition rate,this paper proposes a new micro-expression recognition algorithm based on a three-dimensional convolutional neural network(3D-CNN),which can extract two-di-mensional features in spatial domain and one-dimensional features in time domain,simultaneously.The network structure design is based on the deep learning framework Keras,and the discarding method and batch normalization(BN)algorithm are effectively combined with three-dimensional vis-ual geometry group block(3D-VGG-Block)to reduce the risk of overfitting while improving training speed.Aiming at the problem of the lack of samples in the data set,two methods of image flipping and small amplitude flipping are used for data amplification.Finally,the recognition rate on the data set is as high as 69.11%.Compared with the current international average micro-expression recog-nition rate of about 67%,the proposed algorithm has obvious advantages in recognition rate.展开更多
Because behavior recognition is based on video frame sequences,this paper proposes a behavior recognition algorithm that combines 3D residual convolutional neural network(R3D)and long short-term memory(LSTM).First,the...Because behavior recognition is based on video frame sequences,this paper proposes a behavior recognition algorithm that combines 3D residual convolutional neural network(R3D)and long short-term memory(LSTM).First,the residual module is extended to three dimensions,which can extract features in the time and space domain at the same time.Second,by changing the size of the pooling layer window the integrity of the time domain features is preserved,at the same time,in order to overcome the difficulty of network training and over-fitting problems,the batch normalization(BN)layer and the dropout layer are added.After that,because the global average pooling layer(GAP)is affected by the size of the feature map,the network cannot be further deepened,so the convolution layer and maxpool layer are added to the R3D network.Finally,because LSTM has the ability to memorize information and can extract more abstract timing features,the LSTM network is introduced into the R3D network.Experimental results show that the R3D+LSTM network achieves 91%recognition rate on the UCF-101 dataset.展开更多
Objective:To construct a prediction model for three-dimensional(3D)dose distribution of iodine-131 based on SPECT/CT radiomics features.Methods:A multi-scale feature pyramid network(MSFPN)was used to extract heterogen...Objective:To construct a prediction model for three-dimensional(3D)dose distribution of iodine-131 based on SPECT/CT radiomics features.Methods:A multi-scale feature pyramid network(MSFPN)was used to extract heterogeneity features of thyroid tissues before and after iodine-131 treatment.A spatiotemporal modeling framework(MSFPN+CNN+GAT+3D model)integrating convolutional neural network(CNN)and graph attention network(GAT)was established to achieve precise dose distri-bution prediction.Clinical and imaging data from 320 patients at a tertiary hospital were divided into training,validation,and test sets at a 7:2:1 ratio.The models were evaluated for iodine-131 residence time and time-activity curves(TACs)of key target organs.Pre-dictive accuracy was assessed using root mean square error(RMSE),mean absolute error(MAE),and gamma index.Results:The residence time of iodine-131 in the thyroid,bladder,and stomach was longer than that in the bone marrow(P<0.05).Following io-dine-131 treatment,the activity curve of bone marrow showed minimal variation over time.The bladder tissue exhibited an initial increase in activity,reaching its peak at 4 h.followed by a gradual decline.Both the thyroid and gastric tissues demonstrated a de-creasing trend in activity over time,with the gastric tissue displaying even lower dose levels compared to the thyroid.The RMSE and MAE of the MSFPN+CNN+GAT+3D model for the dose distribution of each target organ were lower than those of the MSFPN.ResNet and 3D CNN models,and the γ index was higher than those of the MSFPN,ResNet and 3D CNN models(P<0.05),and there was no statistical significance when compared with the ensemble model(P>0.05).Conclusion:The MSFPN+CNN+GAT+3D model systematically captures deep radiomics features,effectively facilitating the imag-ing evaluation of the accurate dose distribution of multiple organs during radioactive io-dine-131 treatment.展开更多
Depression has become a major health threat around the world,especially for older people,so the effective detection method for depression is a great public health challenge.Electroencephalogram(EEG)can be used as a bi...Depression has become a major health threat around the world,especially for older people,so the effective detection method for depression is a great public health challenge.Electroencephalogram(EEG)can be used as a biomarker to effectively explore depression recognition.Motivated by the studies that multiple smaller scale kernels could increase nonlinear expression compared to a larger kernel,this article proposes a model named the three-dimensional multiscale kernels convolutional neural network model for the depression disorder recognition(3DMKDR),which is a three-dimensional convolutional neural network model with multiscale convolutional kernels for depression recognition based on EEG signals.A three-dimensional structure of the EEG is built by extending one-dimensional feature sequences into a two-dimensional electrode matrix to excavate the related spatiotemporal information among electrodes and the collected electrode matrix.By the major depressive disorder(MDD)and the multi-modal open dataset for mental-disorder analysis(MODMA)datasets,the experiment shows that the accuracies of depression recognition are up to99.86%and 98.01%in the subject-dependent experiment,and 95.80%and 82.27%in the subjectindependent experiment,which are higher than alternative competitive methods.The experimental results demonstrate that the proposed 3DMKDR is potentially useful for depression recognition in older persons in the future.展开更多
Numerical weather prediction of wind speed requires statistical postprocessing of systematic errors to obtain reliable and accurate forecasts.However,use of postprocessing models is often undesirable for extreme weath...Numerical weather prediction of wind speed requires statistical postprocessing of systematic errors to obtain reliable and accurate forecasts.However,use of postprocessing models is often undesirable for extreme weather events such as gales.Here,we propose a postprocessing algorithm based on a gale-aware deep attention network to simultaneously improve wind speed forecasts and gale area warnings.Specifically,the algorithm includes both a galeaware loss function that focuses the model on potential gale areas,and an observation station supervision strategy that alleviates the problem of missing extreme values caused by data gridding.The effectiveness of the proposed model was verified by using data from 235 wind speed observation stations.Experimental results show that our model can produce wind speed forecasts with a root-mean-square error of 1.1547 m s^(-1),and a Hanssen–Kuipers discriminant score of 0.517,performance that is superior to that of the other postprocessing algorithms considered.展开更多
基金Supported by the Shaanxi Province Key Research and Development Project(No.2021GY-280)Shaanxi Province Natural Science Basic Re-search Program Project(No.2021JM-459)+1 种基金the National Natural Science Foundation of China(No.61834005,61772417,61802304,61602377,61634004)the Shaanxi Province International Science and Technology Cooperation Project(No.2018KW-006).
文摘The micro-expression lasts for a very short time and the intensity is very subtle.Aiming at the problem of its low recognition rate,this paper proposes a new micro-expression recognition algorithm based on a three-dimensional convolutional neural network(3D-CNN),which can extract two-di-mensional features in spatial domain and one-dimensional features in time domain,simultaneously.The network structure design is based on the deep learning framework Keras,and the discarding method and batch normalization(BN)algorithm are effectively combined with three-dimensional vis-ual geometry group block(3D-VGG-Block)to reduce the risk of overfitting while improving training speed.Aiming at the problem of the lack of samples in the data set,two methods of image flipping and small amplitude flipping are used for data amplification.Finally,the recognition rate on the data set is as high as 69.11%.Compared with the current international average micro-expression recog-nition rate of about 67%,the proposed algorithm has obvious advantages in recognition rate.
基金Supported by the Shaanxi Province Key Research and Development Project (No. 2021GY-280)Shaanxi Province Natural Science Basic Research Program (No. 2021JM-459)the National Natural Science Foundation of China (No. 61772417)
文摘Because behavior recognition is based on video frame sequences,this paper proposes a behavior recognition algorithm that combines 3D residual convolutional neural network(R3D)and long short-term memory(LSTM).First,the residual module is extended to three dimensions,which can extract features in the time and space domain at the same time.Second,by changing the size of the pooling layer window the integrity of the time domain features is preserved,at the same time,in order to overcome the difficulty of network training and over-fitting problems,the batch normalization(BN)layer and the dropout layer are added.After that,because the global average pooling layer(GAP)is affected by the size of the feature map,the network cannot be further deepened,so the convolution layer and maxpool layer are added to the R3D network.Finally,because LSTM has the ability to memorize information and can extract more abstract timing features,the LSTM network is introduced into the R3D network.Experimental results show that the R3D+LSTM network achieves 91%recognition rate on the UCF-101 dataset.
文摘Objective:To construct a prediction model for three-dimensional(3D)dose distribution of iodine-131 based on SPECT/CT radiomics features.Methods:A multi-scale feature pyramid network(MSFPN)was used to extract heterogeneity features of thyroid tissues before and after iodine-131 treatment.A spatiotemporal modeling framework(MSFPN+CNN+GAT+3D model)integrating convolutional neural network(CNN)and graph attention network(GAT)was established to achieve precise dose distri-bution prediction.Clinical and imaging data from 320 patients at a tertiary hospital were divided into training,validation,and test sets at a 7:2:1 ratio.The models were evaluated for iodine-131 residence time and time-activity curves(TACs)of key target organs.Pre-dictive accuracy was assessed using root mean square error(RMSE),mean absolute error(MAE),and gamma index.Results:The residence time of iodine-131 in the thyroid,bladder,and stomach was longer than that in the bone marrow(P<0.05).Following io-dine-131 treatment,the activity curve of bone marrow showed minimal variation over time.The bladder tissue exhibited an initial increase in activity,reaching its peak at 4 h.followed by a gradual decline.Both the thyroid and gastric tissues demonstrated a de-creasing trend in activity over time,with the gastric tissue displaying even lower dose levels compared to the thyroid.The RMSE and MAE of the MSFPN+CNN+GAT+3D model for the dose distribution of each target organ were lower than those of the MSFPN.ResNet and 3D CNN models,and the γ index was higher than those of the MSFPN,ResNet and 3D CNN models(P<0.05),and there was no statistical significance when compared with the ensemble model(P>0.05).Conclusion:The MSFPN+CNN+GAT+3D model systematically captures deep radiomics features,effectively facilitating the imag-ing evaluation of the accurate dose distribution of multiple organs during radioactive io-dine-131 treatment.
基金supported by the National Natural Science Foundation of China(Nos.61862058,61962034,and 8226070356)in part by the Gansu Provincial Science&Technology Department(No.20JR10RA076)。
文摘Depression has become a major health threat around the world,especially for older people,so the effective detection method for depression is a great public health challenge.Electroencephalogram(EEG)can be used as a biomarker to effectively explore depression recognition.Motivated by the studies that multiple smaller scale kernels could increase nonlinear expression compared to a larger kernel,this article proposes a model named the three-dimensional multiscale kernels convolutional neural network model for the depression disorder recognition(3DMKDR),which is a three-dimensional convolutional neural network model with multiscale convolutional kernels for depression recognition based on EEG signals.A three-dimensional structure of the EEG is built by extending one-dimensional feature sequences into a two-dimensional electrode matrix to excavate the related spatiotemporal information among electrodes and the collected electrode matrix.By the major depressive disorder(MDD)and the multi-modal open dataset for mental-disorder analysis(MODMA)datasets,the experiment shows that the accuracies of depression recognition are up to99.86%and 98.01%in the subject-dependent experiment,and 95.80%and 82.27%in the subjectindependent experiment,which are higher than alternative competitive methods.The experimental results demonstrate that the proposed 3DMKDR is potentially useful for depression recognition in older persons in the future.
基金Supported by the National Natural Science Foundation of China (62106169)。
文摘Numerical weather prediction of wind speed requires statistical postprocessing of systematic errors to obtain reliable and accurate forecasts.However,use of postprocessing models is often undesirable for extreme weather events such as gales.Here,we propose a postprocessing algorithm based on a gale-aware deep attention network to simultaneously improve wind speed forecasts and gale area warnings.Specifically,the algorithm includes both a galeaware loss function that focuses the model on potential gale areas,and an observation station supervision strategy that alleviates the problem of missing extreme values caused by data gridding.The effectiveness of the proposed model was verified by using data from 235 wind speed observation stations.Experimental results show that our model can produce wind speed forecasts with a root-mean-square error of 1.1547 m s^(-1),and a Hanssen–Kuipers discriminant score of 0.517,performance that is superior to that of the other postprocessing algorithms considered.
