Objective： The aims of this study were to estimate the prevalence of radiographic osteoarthritis （OA） and to assess the association between smoking patterns and OA prevalence in adults aged 50 years or...Objective： The aims of this study were to estimate the prevalence of radiographic osteoarthritis （OA） and to assess the association between smoking patterns and OA prevalence in adults aged 50 years or older belonging to the Shanxi province of China.Methods： A cross-sectional study in the rural regions of the Shanxi province was conducted among 2638 Chinese adults （aged ≥50 years）. Demographic characteristics and behavioral information were collected through epidemiological surveys. All participants with joint pain underwent plain radiographic examination and were diagnosed by a professional orthopedist. Associations between smoking patterns and the prevalence of OA were assessed using binary logistic regression modeling.Results： Among 2638 individuals （men, 50.3% and women, 49.7%; mean age, 61.5 years） included in the analysis, 49.8% had radiographic OA and 27.5% had knee OA. The prevalence of radiographic OA was higher in women than in men （P〈0.001）. After adjusting for potential confounding factors, there was a nonsignificant correlation between smoking and OA prevalence in the muttivariate model. Odds ratios （ORs） for all types of OA and knee OA were higher in active and passive smokers than in nonsmoking individuals after adjustments （OR 1.374; 95% confidence interval [CI] 1.049-1.802; OR 1.440; 95% CI 1.059-1.958, respectively）.Conclusions： This study showed th at smoking may not be an independent risk factor for OA; however, there was a positive correlation between active and passive smoking and OA.展开更多
To improve the performance of the forest fire smoke detection model and achieve a better balance between detection accuracy and speed, an improved YOLOv4 detection model (MoAm-YOLOv4) that combines a lightweight netwo...To improve the performance of the forest fire smoke detection model and achieve a better balance between detection accuracy and speed, an improved YOLOv4 detection model (MoAm-YOLOv4) that combines a lightweight network and attention mechanism was proposed. Based on the YOLOv4 algorithm, the backbone network CSPDarknet53 was replaced with a lightweight network MobilenetV1 to reduce the model’s size. An attention mechanism was added to the three channels before the output to increase its ability to extract forest fire smoke effectively. The algorithm used the K-means clustering algorithm to cluster the smoke dataset, and obtained candidate frames that were close to the smoke images;the dataset was expanded to 2000 images by the random flip expansion method to avoid overfitting in training. The experimental results show that the improved YOLOv4 algorithm has excellent detection effect. Its mAP can reach 93.45%, precision can get 93.28%, and the model size is only 45.58 MB. Compared with YOLOv4 algorithm, MoAm-YOLOv4 improves the accuracy by 1.3% and reduces the model size by 80% while sacrificing only 0.27% mAP, showing reasonable practicability.展开更多
基金supported by the National Natural Science Foundation of China(Nos.81573245 and 81102198)Shanxi Provincial Health and Family Planning Commission Projects(No.2014169)Undergraduate Programs for Innovation and Entrepreneurship of Shanxi Medical University(No.20171050)
文摘Objective： The aims of this study were to estimate the prevalence of radiographic osteoarthritis （OA） and to assess the association between smoking patterns and OA prevalence in adults aged 50 years or older belonging to the Shanxi province of China.Methods： A cross-sectional study in the rural regions of the Shanxi province was conducted among 2638 Chinese adults （aged ≥50 years）. Demographic characteristics and behavioral information were collected through epidemiological surveys. All participants with joint pain underwent plain radiographic examination and were diagnosed by a professional orthopedist. Associations between smoking patterns and the prevalence of OA were assessed using binary logistic regression modeling.Results： Among 2638 individuals （men, 50.3% and women, 49.7%; mean age, 61.5 years） included in the analysis, 49.8% had radiographic OA and 27.5% had knee OA. The prevalence of radiographic OA was higher in women than in men （P〈0.001）. After adjusting for potential confounding factors, there was a nonsignificant correlation between smoking and OA prevalence in the muttivariate model. Odds ratios （ORs） for all types of OA and knee OA were higher in active and passive smokers than in nonsmoking individuals after adjustments （OR 1.374; 95% confidence interval [CI] 1.049-1.802; OR 1.440; 95% CI 1.059-1.958, respectively）.Conclusions： This study showed th at smoking may not be an independent risk factor for OA; however, there was a positive correlation between active and passive smoking and OA.
文摘To improve the performance of the forest fire smoke detection model and achieve a better balance between detection accuracy and speed, an improved YOLOv4 detection model (MoAm-YOLOv4) that combines a lightweight network and attention mechanism was proposed. Based on the YOLOv4 algorithm, the backbone network CSPDarknet53 was replaced with a lightweight network MobilenetV1 to reduce the model’s size. An attention mechanism was added to the three channels before the output to increase its ability to extract forest fire smoke effectively. The algorithm used the K-means clustering algorithm to cluster the smoke dataset, and obtained candidate frames that were close to the smoke images;the dataset was expanded to 2000 images by the random flip expansion method to avoid overfitting in training. The experimental results show that the improved YOLOv4 algorithm has excellent detection effect. Its mAP can reach 93.45%, precision can get 93.28%, and the model size is only 45.58 MB. Compared with YOLOv4 algorithm, MoAm-YOLOv4 improves the accuracy by 1.3% and reduces the model size by 80% while sacrificing only 0.27% mAP, showing reasonable practicability.
