As an important part of railway lines, the healthy service status of track fasteners was very important to ensure the safety of trains. The application of deep learning algorithms was becoming an important method to r...As an important part of railway lines, the healthy service status of track fasteners was very important to ensure the safety of trains. The application of deep learning algorithms was becoming an important method to realize its state detection. However, there was often a deficiency that the detection accuracy and calculation speed of model were difficult to balance, when the traditional deep learning model is used to detect the service state of track fasteners. Targeting this issue, an improved Yolov4 model for detecting the service status of track fasteners was proposed. Firstly, the Mixup data augmentation technology was introduced into Yolov4 model to enhance the generalization ability of model. Secondly, the MobileNet-V2 lightweight network was employed in lieu of the CSPDarknet53 network as the backbone, thereby reducing the number of algorithm parameters and improving the model’s computational efficiency. Finally, the SE attention mechanism was incorporated to boost the importance of rail fastener identification by emphasizing relevant image features, ensuring that the network’s focus was primarily on the fasteners being inspected. The algorithm achieved both high precision and high speed operation of the rail fastener service state detection, while realizing the lightweight of model. The experimental results revealed that, the MAP value of the rail fastener service state detection algorithm based on the improved Yolov4 model reaches 83.2%, which is 2.83% higher than that of the traditional Yolov4 model, and the calculation speed was improved by 67.39%. Compared with the traditional Yolov4 model, the proposed method achieved the collaborative optimization of detection accuracy and calculation speed.展开更多
More than 87000 dams have been built in China,and about one third of them are risky projects.A number of high and ultra-high dams are being constructed in China's western region.The current dam construction practi...More than 87000 dams have been built in China,and about one third of them are risky projects.A number of high and ultra-high dams are being constructed in China's western region.The current dam construction practice tends to focus on socio-economic benefits and neglect the environment and ecology.Furthermore,periodic examinations are intended to ensure the structural safety of dams.This paper proposes a general evaluation principle for dam service.This principle stipulates that dam projects should have maximum socio-economic benefits and minimum negative effects on the environment and ecology.To satisfy the general principle of mutual harmony,socio-economic benefits,dam safety,environment,and ecology are analyzed,and the evaluation methods for dam service status are discussed.Then,a fusion algorithm of interlayer assessment is proposed on the basis of evidence theory and the fuzzy comprehensive analysis method.Finally,a comprehensive evaluation model is established.Example analysis shows that the proposed theories and methods can fulfill scientific assessment of the service status of dams.展开更多
Objective:This study investigated and discussed the current status of community mental health service in three northern areas of China(Beijing,Harbin,and Karamay)in an effort to improve the community mental health ser...Objective:This study investigated and discussed the current status of community mental health service in three northern areas of China(Beijing,Harbin,and Karamay)in an effort to improve the community mental health services in China.Methods:In this study 176 residents from communities of the three northern areas of China were involved and divided into 18 groups.The study was conducted according to a self-prepared structured interview outline.Results:The analysis was conducted based on the following four perspectives:1.commu-nity residents’understanding of the mental health problems and how they treated psychiatric patients;2.community residents’access to and application of mental health information;3.com-munity residents’attitude to accept mental health services and the factors influencing community residents to seek help from mental health services;and 4.community residents’attitude and will-ingness to participate in the activities of community mental health services.Conclusion:Based on the investigation and analysis regarding the current status of the com-munity mental health services in three northern areas of China,it is concluded that the residents do not have s clear and complete understanding of mental health.The characteristics of mental health services had a regional correlation.Currently,the mental health services do not work effectively,and the residents are somewhat passive in obtaining information about mental health.Community mental health services should be offered according to different individual needs of the residents and the actual situations of each region.展开更多
文摘As an important part of railway lines, the healthy service status of track fasteners was very important to ensure the safety of trains. The application of deep learning algorithms was becoming an important method to realize its state detection. However, there was often a deficiency that the detection accuracy and calculation speed of model were difficult to balance, when the traditional deep learning model is used to detect the service state of track fasteners. Targeting this issue, an improved Yolov4 model for detecting the service status of track fasteners was proposed. Firstly, the Mixup data augmentation technology was introduced into Yolov4 model to enhance the generalization ability of model. Secondly, the MobileNet-V2 lightweight network was employed in lieu of the CSPDarknet53 network as the backbone, thereby reducing the number of algorithm parameters and improving the model’s computational efficiency. Finally, the SE attention mechanism was incorporated to boost the importance of rail fastener identification by emphasizing relevant image features, ensuring that the network’s focus was primarily on the fasteners being inspected. The algorithm achieved both high precision and high speed operation of the rail fastener service state detection, while realizing the lightweight of model. The experimental results revealed that, the MAP value of the rail fastener service state detection algorithm based on the improved Yolov4 model reaches 83.2%, which is 2.83% higher than that of the traditional Yolov4 model, and the calculation speed was improved by 67.39%. Compared with the traditional Yolov4 model, the proposed method achieved the collaborative optimization of detection accuracy and calculation speed.
基金supported by the National Natural Science Foundation of China (Grant Nos. 51139001,51179066,51079046,50909041)the Program for New Century Excellent Talents in University (Grant No. NCET-10-0359)+1 种基金Jiangsu Province "333 High-Level Personnel Training Project" (Grant No. 2017-B08037)the Ministry of Water Resources Public Welfare Industry Research Special Fund Project (Grant No. 201201038)
文摘More than 87000 dams have been built in China,and about one third of them are risky projects.A number of high and ultra-high dams are being constructed in China's western region.The current dam construction practice tends to focus on socio-economic benefits and neglect the environment and ecology.Furthermore,periodic examinations are intended to ensure the structural safety of dams.This paper proposes a general evaluation principle for dam service.This principle stipulates that dam projects should have maximum socio-economic benefits and minimum negative effects on the environment and ecology.To satisfy the general principle of mutual harmony,socio-economic benefits,dam safety,environment,and ecology are analyzed,and the evaluation methods for dam service status are discussed.Then,a fusion algorithm of interlayer assessment is proposed on the basis of evidence theory and the fuzzy comprehensive analysis method.Finally,a comprehensive evaluation model is established.Example analysis shows that the proposed theories and methods can fulfill scientific assessment of the service status of dams.
基金National Science and Technology Support Program:applied in the propaganda,education,intervention and demonstration of community mental health against the mental illness prevention and treatment[2009BA177B08].
文摘Objective:This study investigated and discussed the current status of community mental health service in three northern areas of China(Beijing,Harbin,and Karamay)in an effort to improve the community mental health services in China.Methods:In this study 176 residents from communities of the three northern areas of China were involved and divided into 18 groups.The study was conducted according to a self-prepared structured interview outline.Results:The analysis was conducted based on the following four perspectives:1.commu-nity residents’understanding of the mental health problems and how they treated psychiatric patients;2.community residents’access to and application of mental health information;3.com-munity residents’attitude to accept mental health services and the factors influencing community residents to seek help from mental health services;and 4.community residents’attitude and will-ingness to participate in the activities of community mental health services.Conclusion:Based on the investigation and analysis regarding the current status of the com-munity mental health services in three northern areas of China,it is concluded that the residents do not have s clear and complete understanding of mental health.The characteristics of mental health services had a regional correlation.Currently,the mental health services do not work effectively,and the residents are somewhat passive in obtaining information about mental health.Community mental health services should be offered according to different individual needs of the residents and the actual situations of each region.
