Because stress has such a powerful impact on human health,we must be able to identify it automatically in our everyday lives.The human activity recognition(HAR)system use data from several kinds of sensors to try to r...Because stress has such a powerful impact on human health,we must be able to identify it automatically in our everyday lives.The human activity recognition(HAR)system use data from several kinds of sensors to try to recognize and evaluate human actions automatically recognize and evaluate human actions.Using the multimodal dataset DEAP(Database for Emotion Analysis using Physiological Signals),this paper presents deep learning(DL)technique for effectively detecting human stress.The combination of vision-based and sensor-based approaches for recognizing human stress will help us achieve the increased efficiency of current stress recognition systems and predict probable actions in advance of when fatal.Based on visual and EEG(Electroencephalogram)data,this research aims to enhance the performance and extract the dominating characteristics of stress detection.For the stress identification test,we utilized the DEAP dataset,which included video and EEG data.We also demonstrate that combining video and EEG characteristics may increase overall performance,with the suggested stochastic features providing the most accurate results.In the first step,CNN(Convolutional Neural Network)extracts feature vectors from video frames and EEG data.Feature Level(FL)fusion that combines the features extracted from video and EEG data.We use XGBoost as our classifier model to predict stress,and we put it into action.The stress recognition accuracy of the proposed method is compared to existing methods of Decision Tree(DT),Random Forest(RF),AdaBoost,Linear Discriminant Analysis(LDA),and KNearest Neighborhood(KNN).When we compared our technique to existing state-of-the-art approaches,we found that the suggested DL methodology combining multimodal and heterogeneous inputs may improve stress identification.展开更多
Background Ictal examination based on video-based electroencephalography(EEG)is crucial for locating and lat-eralizing seizures.In this study,we aimed to evaluate the quality of ictal examination in the Comprehensive ...Background Ictal examination based on video-based electroencephalography(EEG)is crucial for locating and lat-eralizing seizures.In this study,we aimed to evaluate the quality of ictal examination in the Comprehensive Epilepsy Center of West China Hospital,Sichuan University,in order to provide information for quality improvement in daily clinical practice.Methods Video recordings of 100 patients with epilepsy were retrospectively reviewed.The performance of the ictal examination was independently reviewed by two epileptologists using an ictal examination protocol.Results In this retrospective analysis,589 seizure episodes from 100 patients with epilepsy were reviewed.The ages of the patients ranged from 3 to 77 years,with a mean age of 25.8±12.8 years.Among the 589 seizure episodes,a majority(93.7%)were focal seizures.For 226(38.4%)seizures,the medical staff arrived at the bedside.Among them,153(153/226,64.7%)seizure episodes,the medical staff arrival at the bedside within 30 s of onset,and 120(120/226,53.1%)seizures were tested by the medical staff.The compliance rates for"safety"and"visibility"reached 80%or higher while"naming","retelling",and“memory testing”only reach less than 3%.Conclusions Our survey identified the main problems in ictal assessments.It is challenging to complete a standard-ized examination for new trainees at Epilepsy Monitoring Units.Regularly strengthening training in ictal examination and understanding of semiology may improve patients’examination ability.However,further study of the implemen-tation of training is necessary.展开更多
文摘Because stress has such a powerful impact on human health,we must be able to identify it automatically in our everyday lives.The human activity recognition(HAR)system use data from several kinds of sensors to try to recognize and evaluate human actions automatically recognize and evaluate human actions.Using the multimodal dataset DEAP(Database for Emotion Analysis using Physiological Signals),this paper presents deep learning(DL)technique for effectively detecting human stress.The combination of vision-based and sensor-based approaches for recognizing human stress will help us achieve the increased efficiency of current stress recognition systems and predict probable actions in advance of when fatal.Based on visual and EEG(Electroencephalogram)data,this research aims to enhance the performance and extract the dominating characteristics of stress detection.For the stress identification test,we utilized the DEAP dataset,which included video and EEG data.We also demonstrate that combining video and EEG characteristics may increase overall performance,with the suggested stochastic features providing the most accurate results.In the first step,CNN(Convolutional Neural Network)extracts feature vectors from video frames and EEG data.Feature Level(FL)fusion that combines the features extracted from video and EEG data.We use XGBoost as our classifier model to predict stress,and we put it into action.The stress recognition accuracy of the proposed method is compared to existing methods of Decision Tree(DT),Random Forest(RF),AdaBoost,Linear Discriminant Analysis(LDA),and KNearest Neighborhood(KNN).When we compared our technique to existing state-of-the-art approaches,we found that the suggested DL methodology combining multimodal and heterogeneous inputs may improve stress identification.
基金supported by the West China Nursing Discipline Development Special Fund Project,Sichuan University(HXHL20004).
文摘Background Ictal examination based on video-based electroencephalography(EEG)is crucial for locating and lat-eralizing seizures.In this study,we aimed to evaluate the quality of ictal examination in the Comprehensive Epilepsy Center of West China Hospital,Sichuan University,in order to provide information for quality improvement in daily clinical practice.Methods Video recordings of 100 patients with epilepsy were retrospectively reviewed.The performance of the ictal examination was independently reviewed by two epileptologists using an ictal examination protocol.Results In this retrospective analysis,589 seizure episodes from 100 patients with epilepsy were reviewed.The ages of the patients ranged from 3 to 77 years,with a mean age of 25.8±12.8 years.Among the 589 seizure episodes,a majority(93.7%)were focal seizures.For 226(38.4%)seizures,the medical staff arrived at the bedside.Among them,153(153/226,64.7%)seizure episodes,the medical staff arrival at the bedside within 30 s of onset,and 120(120/226,53.1%)seizures were tested by the medical staff.The compliance rates for"safety"and"visibility"reached 80%or higher while"naming","retelling",and“memory testing”only reach less than 3%.Conclusions Our survey identified the main problems in ictal assessments.It is challenging to complete a standard-ized examination for new trainees at Epilepsy Monitoring Units.Regularly strengthening training in ictal examination and understanding of semiology may improve patients’examination ability.However,further study of the implemen-tation of training is necessary.