Stroke patients experience varying degrees of upper limb functional impairment.Although bilateral arm training can help stroke patients recover movement after stroke,little is known about the way in which the brain an...Stroke patients experience varying degrees of upper limb functional impairment.Although bilateral arm training can help stroke patients recover movement after stroke,little is known about the way in which the brain and muscles work together during this type of training.To address this,we conducted a cross-sectional study at The Seventh Affiliated Hospital,Sun Yat-sen University in China,where we observed the connection between brain and muscle activity during bilateral upper limb training in 21 stroke patients and 17 healthy controls.We used functional near-infrared spectroscopy and surface electromyography to measure changes in cerebral cortex oxygenation and upper limb muscle contraction signals,respectively.The results showed that,compared with the healthy control group,stroke patients had reduced functional connectivity and more irregular muscle activity in the affected flexor muscle during bilateral upper limb training.Moreover,we found a significant correlation between the surface electromyographic signal characteristics of upper limb muscles and cerebral oxygenation indicators of multiple brain regions in stroke patients.These findings indicate that bilateral upper limb training is an effective rehabilitation method that improves upper limb motor function in stroke patients by promoting brain functional connectivity and improving muscle activity patterns.展开更多
To support the process of grasping objects on a tabletop for the blind or robotic arm,it is necessary to address fundamental computer vision tasks,such as detecting,recognizing,and locating objects in space,and determ...To support the process of grasping objects on a tabletop for the blind or robotic arm,it is necessary to address fundamental computer vision tasks,such as detecting,recognizing,and locating objects in space,and determining the position of the grasping information.These results can then be used to guide the visually impaired or to execute grasping tasks with a robotic arm.In this paper,we collected,annotated,and published the benchmark TQUGraspingObject dataset for testing,validation,and evaluation of deep learning(DL)models for detecting,recognizing,and localizing grasping objects in 2D and 3D space,especially 3D point cloud data.Our dataset is collected in a shared room,with common everyday objects placed on the tabletop in jumbled positions by Intel RealSense D435(IR-D435).This dataset includes more than 63k RGB-D pairs and related data such as normalized 3D object point cloud,3D object point cloud segmented,coordinate system normalizationmatrix,3D object point cloud normalized,and hand pose for grasping each object.At the same time,we also conducted experiments on fourDL networks with the best performance:SSD-MobileNetV3,ResNet50-Transformer,ResNet101-Transformer,and YOLOv12.The results present that YOLOv12 has the most suitable results in detecting and recognizing objects in images.All data,annotations,toolkit,source code,point cloud data,and results are publicly available on our project website:https://github.com/HuaTThanhIT2327Tqu/datasetv2.展开更多
文摘Stroke patients experience varying degrees of upper limb functional impairment.Although bilateral arm training can help stroke patients recover movement after stroke,little is known about the way in which the brain and muscles work together during this type of training.To address this,we conducted a cross-sectional study at The Seventh Affiliated Hospital,Sun Yat-sen University in China,where we observed the connection between brain and muscle activity during bilateral upper limb training in 21 stroke patients and 17 healthy controls.We used functional near-infrared spectroscopy and surface electromyography to measure changes in cerebral cortex oxygenation and upper limb muscle contraction signals,respectively.The results showed that,compared with the healthy control group,stroke patients had reduced functional connectivity and more irregular muscle activity in the affected flexor muscle during bilateral upper limb training.Moreover,we found a significant correlation between the surface electromyographic signal characteristics of upper limb muscles and cerebral oxygenation indicators of multiple brain regions in stroke patients.These findings indicate that bilateral upper limb training is an effective rehabilitation method that improves upper limb motor function in stroke patients by promoting brain functional connectivity and improving muscle activity patterns.
文摘To support the process of grasping objects on a tabletop for the blind or robotic arm,it is necessary to address fundamental computer vision tasks,such as detecting,recognizing,and locating objects in space,and determining the position of the grasping information.These results can then be used to guide the visually impaired or to execute grasping tasks with a robotic arm.In this paper,we collected,annotated,and published the benchmark TQUGraspingObject dataset for testing,validation,and evaluation of deep learning(DL)models for detecting,recognizing,and localizing grasping objects in 2D and 3D space,especially 3D point cloud data.Our dataset is collected in a shared room,with common everyday objects placed on the tabletop in jumbled positions by Intel RealSense D435(IR-D435).This dataset includes more than 63k RGB-D pairs and related data such as normalized 3D object point cloud,3D object point cloud segmented,coordinate system normalizationmatrix,3D object point cloud normalized,and hand pose for grasping each object.At the same time,we also conducted experiments on fourDL networks with the best performance:SSD-MobileNetV3,ResNet50-Transformer,ResNet101-Transformer,and YOLOv12.The results present that YOLOv12 has the most suitable results in detecting and recognizing objects in images.All data,annotations,toolkit,source code,point cloud data,and results are publicly available on our project website:https://github.com/HuaTThanhIT2327Tqu/datasetv2.
