Atlantic Meridional Overturning Circulation(AMOC)plays a central role in long-term climate variations through its heat and freshwater transports,which can collapse under a rapid increase of greenhouse gas forcing in c...Atlantic Meridional Overturning Circulation(AMOC)plays a central role in long-term climate variations through its heat and freshwater transports,which can collapse under a rapid increase of greenhouse gas forcing in climate models.Previous studies have suggested that the deviation of model parameters is one of the major factors in inducing inaccurate AMOC simulations.In this work,with a low-resolution earth system model,the authors try to explore whether a reasonable adjustment of the key model parameter can help to re-establish the AMOC after its collapse.Through a new optimization strategy,the extra freshwater flux(FWF)parameter is determined to be the dominant one affecting the AMOC’s variability.The traditional ensemble optimal interpolation(EnOI)data assimilation and new machine learning methods are adopted to optimize the FWF parameter in an abrupt 4×CO_(2) forcing experiment to improve the adaptability of model parameters and accelerate the recovery of AMOC.The results show that,under an abrupt 4×CO_(2) forcing in millennial simulations,the AMOC will first collapse and then re-establish by the default FWF parameter slowly.However,during the parameter adjustment process,the saltier and colder sea water over the North Atlantic region are the dominant factors in usefully improving the adaptability of the FWF parameter and accelerating the recovery of AMOC,according to their physical relationship with FWF on the interdecadal timescale.展开更多
Human Interaction Recognition(HIR)was one of the challenging issues in computer vision research due to the involvement of multiple individuals and their mutual interactions within video frames generated from their mov...Human Interaction Recognition(HIR)was one of the challenging issues in computer vision research due to the involvement of multiple individuals and their mutual interactions within video frames generated from their movements.HIR requires more sophisticated analysis than Human Action Recognition(HAR)since HAR focuses solely on individual activities like walking or running,while HIR involves the interactions between people.This research aims to develop a robust system for recognizing five common human interactions,such as hugging,kicking,pushing,pointing,and no interaction,from video sequences using multiple cameras.In this study,a hybrid Deep Learning(DL)and Machine Learning(ML)model was employed to improve classification accuracy and generalizability.The dataset was collected in an indoor environment with four-channel cameras capturing the five types of interactions among 13 participants.The data was processed using a DL model with a fine-tuned ResNet(Residual Networks)architecture based on 2D Convolutional Neural Network(CNN)layers for feature extraction.Subsequently,machine learning models were trained and utilized for interaction classification using six commonly used ML algorithms,including SVM,KNN,RF,DT,NB,and XGBoost.The results demonstrate a high accuracy of 95.45%in classifying human interactions.The hybrid approach enabled effective learning,resulting in highly accurate performance across different interaction types.Future work will explore more complex scenarios involving multiple individuals based on the application of this architecture.展开更多
Condition monitoring ensures the safety of freight railroad operations. With the development of machine vision technology, visual inspection has become a principal means of condition monitoring. The brake shoe key （...Condition monitoring ensures the safety of freight railroad operations. With the development of machine vision technology, visual inspection has become a principal means of condition monitoring. The brake shoe key （BSK） is an important component in the brake system, and its absence will lead to serious accidents. This paper presents a novel method for automated visual inspection of the BSK condition in freight cars. BSK images are first acquired by hardware devices. The subsequent in- spection process is divided into three stages： first, the region-of-interest （ROI） is segmented from the source image by an im- proved spatial pyramid matching scheme based on multi-scale census transform （MSCT）. To localize the BSK in the ROI, cen- sus transform （CT） on gradient images is developed in the second stage. Then gradient encoding histogram （GEH） features and linear support vector machines （SVMs） are used to generate a BSK localization classifier. In the last stage, a condition classifier is trained by SVM, but the features are extracted from gray images. Finally, the ROI, BSK localization, and condition classifiers are cascaded to realize a completely automated inspection system. Experimental results show that the system achieves a correct inspection rate of 99.2% and a speed of 5 frames/s, which represents a good real-time performance and high recognition accuracy.展开更多
基金supported by the National Key R&D Program of China [grant number 2023YFF0805202]the National Natural Science Foun-dation of China [grant number 42175045]the Strategic Priority Research Program of the Chinese Academy of Sciences [grant number XDB42000000]。
文摘Atlantic Meridional Overturning Circulation(AMOC)plays a central role in long-term climate variations through its heat and freshwater transports,which can collapse under a rapid increase of greenhouse gas forcing in climate models.Previous studies have suggested that the deviation of model parameters is one of the major factors in inducing inaccurate AMOC simulations.In this work,with a low-resolution earth system model,the authors try to explore whether a reasonable adjustment of the key model parameter can help to re-establish the AMOC after its collapse.Through a new optimization strategy,the extra freshwater flux(FWF)parameter is determined to be the dominant one affecting the AMOC’s variability.The traditional ensemble optimal interpolation(EnOI)data assimilation and new machine learning methods are adopted to optimize the FWF parameter in an abrupt 4×CO_(2) forcing experiment to improve the adaptability of model parameters and accelerate the recovery of AMOC.The results show that,under an abrupt 4×CO_(2) forcing in millennial simulations,the AMOC will first collapse and then re-establish by the default FWF parameter slowly.However,during the parameter adjustment process,the saltier and colder sea water over the North Atlantic region are the dominant factors in usefully improving the adaptability of the FWF parameter and accelerating the recovery of AMOC,according to their physical relationship with FWF on the interdecadal timescale.
基金supported by the National Research Foundation of Korea(NRF)grant funded by the Korea government(MSIT)(No.RS-2023-00218176)and the Soonchunhyang University Research Fund.
文摘Human Interaction Recognition(HIR)was one of the challenging issues in computer vision research due to the involvement of multiple individuals and their mutual interactions within video frames generated from their movements.HIR requires more sophisticated analysis than Human Action Recognition(HAR)since HAR focuses solely on individual activities like walking or running,while HIR involves the interactions between people.This research aims to develop a robust system for recognizing five common human interactions,such as hugging,kicking,pushing,pointing,and no interaction,from video sequences using multiple cameras.In this study,a hybrid Deep Learning(DL)and Machine Learning(ML)model was employed to improve classification accuracy and generalizability.The dataset was collected in an indoor environment with four-channel cameras capturing the five types of interactions among 13 participants.The data was processed using a DL model with a fine-tuned ResNet(Residual Networks)architecture based on 2D Convolutional Neural Network(CNN)layers for feature extraction.Subsequently,machine learning models were trained and utilized for interaction classification using six commonly used ML algorithms,including SVM,KNN,RF,DT,NB,and XGBoost.The results demonstrate a high accuracy of 95.45%in classifying human interactions.The hybrid approach enabled effective learning,resulting in highly accurate performance across different interaction types.Future work will explore more complex scenarios involving multiple individuals based on the application of this architecture.
基金supported by the Special-Funded Programme on National Key Scientific Instruments and Equipment Development(No.2012YQ140032)the National Natural Science Foundation of China(No.51179076)+2 种基金the Jiangsu Province Postdoctoral Research Funding Plan(No.1402012B)the Scientific Research Foundation of Jiangsu University for Senior Personnel(No.14JDG134)the Jiangsu Province Science and Technology Support Plan(Industrial)(No.BE2012149)
文摘Condition monitoring ensures the safety of freight railroad operations. With the development of machine vision technology, visual inspection has become a principal means of condition monitoring. The brake shoe key （BSK） is an important component in the brake system, and its absence will lead to serious accidents. This paper presents a novel method for automated visual inspection of the BSK condition in freight cars. BSK images are first acquired by hardware devices. The subsequent in- spection process is divided into three stages： first, the region-of-interest （ROI） is segmented from the source image by an im- proved spatial pyramid matching scheme based on multi-scale census transform （MSCT）. To localize the BSK in the ROI, cen- sus transform （CT） on gradient images is developed in the second stage. Then gradient encoding histogram （GEH） features and linear support vector machines （SVMs） are used to generate a BSK localization classifier. In the last stage, a condition classifier is trained by SVM, but the features are extracted from gray images. Finally, the ROI, BSK localization, and condition classifiers are cascaded to realize a completely automated inspection system. Experimental results show that the system achieves a correct inspection rate of 99.2% and a speed of 5 frames/s, which represents a good real-time performance and high recognition accuracy.
