Activity recognition is a challenging topic in the field of computer vision that has various applications,including surveillance systems,industrial automation,and human-computer interaction.Today,the demand for automa...Activity recognition is a challenging topic in the field of computer vision that has various applications,including surveillance systems,industrial automation,and human-computer interaction.Today,the demand for automation has greatly increased across industries worldwide.Real-time detection requires edge devices with limited computational time.This study proposes a novel hybrid deep learning system for human activity recognition(HAR),aiming to enhance the recognition accuracy and reduce the computational time.The proposed system combines a pretrained image classification model with a sequence analysis model.First,the dataset was divided into a training set(70%),validation set(10%),and test set(20%).Second,all the videos were converted into frames and deep-based features were extracted from each frame using convolutional neural networks(CNNs)with a vision transformer.Following that,bidirectional long short-term memory(BiLSTM)-and temporal convolutional network(TCN)-based models were trained using the training set,and their performances were evaluated using the validation set and test set.Four benchmark datasets(UCF11,UCF50,UCF101,and JHMDB)were used to evaluate the performance of the proposed HAR-based system.The experimental results showed that the combination of ConvNeXt and the TCN-based model achieved a recognition accuracy of 97.73%for UCF11,98.81%for UCF50,98.46%for UCF101,and 83.38%for JHMDB,respectively.This represents improvements in the recognition accuracy of 4%,2.67%,3.67%,and 7.08%for the UCF11,UCF50,UCF101,and JHMDB datasets,respectively,over existing models.Moreover,the proposed HAR-based system obtained superior recognition accuracy,shorter computational times,and minimal memory usage compared to the existing models.展开更多
Dear Editor We read with interest the editorial by Qiu et at about the psychological distress among the general population in China during the COVID-19 pandemic and policy recommendations.The elderly are more vulnerab...Dear Editor We read with interest the editorial by Qiu et at about the psychological distress among the general population in China during the COVID-19 pandemic and policy recommendations.The elderly are more vulnerable to increased mental health problems during COVID-19,which has raised significant challenges for community mental health services.12 Older people with comorbid conditions,including cardiovascular diseases,lung diseases,diabetes and hypertension are more likely to be severely affected and die because of COVID-19,which is caused by SARS-CoV-2.^(3).展开更多
Objective To identify the associated factors affecting the decision regarding institutional delivery for pregnant women in 14 low-and middle-income countries(LMICs).Design A special mixed-method design was used to com...Objective To identify the associated factors affecting the decision regarding institutional delivery for pregnant women in 14 low-and middle-income countries(LMICs).Design A special mixed-method design was used to combine cross-sectional studies for harmonising data from Bangladesh and 13 other countries to obtain extended viewpoints on non-utilisation of institutional healthcare facilities during childbirth.setting Demographic and Health Survey(DHS)data for 14 LMICs were used for the study.Participants There are several kinds of datasets in the DHS.Among them‘Individual Women’s Records’was used as this study is based on all ever-married women.results In the binary logistic and meta-analysis models for Bangladesh,ORs for birth order were 0.57 and 0.51 and for respondents’age were 1.50 and 1.07,respectively.In all 14 LMICs,the most significant factors for not using institutional facilities during childbirth were respondents’age(OR 0.903,95%CI 0.790 to 1.032)and birth order(OR 0.371,95%CI 0.327 to 0.421).Conclusion Birth order and respondents’age were the two most significant factors for non-utilisation of healthcare facilities during childbirth in 14 LMICs.展开更多
基金funded by the Ongoing Research Funding Program(ORF-2025-890),King Saud University,Riyadh,Saudi Arabia.
文摘Activity recognition is a challenging topic in the field of computer vision that has various applications,including surveillance systems,industrial automation,and human-computer interaction.Today,the demand for automation has greatly increased across industries worldwide.Real-time detection requires edge devices with limited computational time.This study proposes a novel hybrid deep learning system for human activity recognition(HAR),aiming to enhance the recognition accuracy and reduce the computational time.The proposed system combines a pretrained image classification model with a sequence analysis model.First,the dataset was divided into a training set(70%),validation set(10%),and test set(20%).Second,all the videos were converted into frames and deep-based features were extracted from each frame using convolutional neural networks(CNNs)with a vision transformer.Following that,bidirectional long short-term memory(BiLSTM)-and temporal convolutional network(TCN)-based models were trained using the training set,and their performances were evaluated using the validation set and test set.Four benchmark datasets(UCF11,UCF50,UCF101,and JHMDB)were used to evaluate the performance of the proposed HAR-based system.The experimental results showed that the combination of ConvNeXt and the TCN-based model achieved a recognition accuracy of 97.73%for UCF11,98.81%for UCF50,98.46%for UCF101,and 83.38%for JHMDB,respectively.This represents improvements in the recognition accuracy of 4%,2.67%,3.67%,and 7.08%for the UCF11,UCF50,UCF101,and JHMDB datasets,respectively,over existing models.Moreover,the proposed HAR-based system obtained superior recognition accuracy,shorter computational times,and minimal memory usage compared to the existing models.
文摘Dear Editor We read with interest the editorial by Qiu et at about the psychological distress among the general population in China during the COVID-19 pandemic and policy recommendations.The elderly are more vulnerable to increased mental health problems during COVID-19,which has raised significant challenges for community mental health services.12 Older people with comorbid conditions,including cardiovascular diseases,lung diseases,diabetes and hypertension are more likely to be severely affected and die because of COVID-19,which is caused by SARS-CoV-2.^(3).
文摘Objective To identify the associated factors affecting the decision regarding institutional delivery for pregnant women in 14 low-and middle-income countries(LMICs).Design A special mixed-method design was used to combine cross-sectional studies for harmonising data from Bangladesh and 13 other countries to obtain extended viewpoints on non-utilisation of institutional healthcare facilities during childbirth.setting Demographic and Health Survey(DHS)data for 14 LMICs were used for the study.Participants There are several kinds of datasets in the DHS.Among them‘Individual Women’s Records’was used as this study is based on all ever-married women.results In the binary logistic and meta-analysis models for Bangladesh,ORs for birth order were 0.57 and 0.51 and for respondents’age were 1.50 and 1.07,respectively.In all 14 LMICs,the most significant factors for not using institutional facilities during childbirth were respondents’age(OR 0.903,95%CI 0.790 to 1.032)and birth order(OR 0.371,95%CI 0.327 to 0.421).Conclusion Birth order and respondents’age were the two most significant factors for non-utilisation of healthcare facilities during childbirth in 14 LMICs.
