{"title":"基于层析触觉传感器的手指运动分析系统,用于识别抓握手指的数量,以评估精细运动技能","authors":"Ryunosuke Asahi, Shunsuke Yoshimoto, Hiroki Sato","doi":"10.1109/MeMeA57477.2023.10171917","DOIUrl":null,"url":null,"abstract":"Finger movements are closely related to development disabilities such as autism spectrum disorder (ASD). These results suggest that a quantitative evaluation of finger movements may be applied to the early diagnosis of cognitive decline and autism in infants and young children. Therefore, we developed a novel automatic finger motion analysis system based on a tomographic tactile sensor by-using coupled conductors with a continuous sensing surface and conductive material with a high degree of freedom (DOF) of shape. Further, we developed two cylindrical sensors, with diameters of 25 and 50 mm, utilizing the high DOF of geometry. To evaluate the developed sensors, we conducted two validations-60-segment cross-validation and holdout validation–to identify the number of fingers engaged in grasping by adults. AlexNet was used for identification of the used reconstruction image; k-nearest neighbors (KNN) and Support vector machine (SVM) were used for the measurement of the voltage vector. According to the results, these accuracies exceeding the chance level was obtained for all participants of both validations. In addition, an average accuracy of approximately 90% was acquired using the measured voltage vector. In conclusion, the study findings indicate that the proposed device could be used for early diagnosis of ASD in infants and cognitive decline in older adults.","PeriodicalId":191927,"journal":{"name":"2023 IEEE International Symposium on Medical Measurements and Applications (MeMeA)","volume":"279 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2023-06-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Tomographic tactile sensor-based finger motion analysis system to identify number of grasping fingers for evaluating fine motor skills\",\"authors\":\"Ryunosuke Asahi, Shunsuke Yoshimoto, Hiroki Sato\",\"doi\":\"10.1109/MeMeA57477.2023.10171917\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Finger movements are closely related to development disabilities such as autism spectrum disorder (ASD). These results suggest that a quantitative evaluation of finger movements may be applied to the early diagnosis of cognitive decline and autism in infants and young children. Therefore, we developed a novel automatic finger motion analysis system based on a tomographic tactile sensor by-using coupled conductors with a continuous sensing surface and conductive material with a high degree of freedom (DOF) of shape. Further, we developed two cylindrical sensors, with diameters of 25 and 50 mm, utilizing the high DOF of geometry. To evaluate the developed sensors, we conducted two validations-60-segment cross-validation and holdout validation–to identify the number of fingers engaged in grasping by adults. AlexNet was used for identification of the used reconstruction image; k-nearest neighbors (KNN) and Support vector machine (SVM) were used for the measurement of the voltage vector. According to the results, these accuracies exceeding the chance level was obtained for all participants of both validations. In addition, an average accuracy of approximately 90% was acquired using the measured voltage vector. In conclusion, the study findings indicate that the proposed device could be used for early diagnosis of ASD in infants and cognitive decline in older adults.\",\"PeriodicalId\":191927,\"journal\":{\"name\":\"2023 IEEE International Symposium on Medical Measurements and Applications (MeMeA)\",\"volume\":\"279 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2023-06-14\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2023 IEEE International Symposium on Medical Measurements and Applications (MeMeA)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/MeMeA57477.2023.10171917\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2023 IEEE International Symposium on Medical Measurements and Applications (MeMeA)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/MeMeA57477.2023.10171917","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Tomographic tactile sensor-based finger motion analysis system to identify number of grasping fingers for evaluating fine motor skills
Finger movements are closely related to development disabilities such as autism spectrum disorder (ASD). These results suggest that a quantitative evaluation of finger movements may be applied to the early diagnosis of cognitive decline and autism in infants and young children. Therefore, we developed a novel automatic finger motion analysis system based on a tomographic tactile sensor by-using coupled conductors with a continuous sensing surface and conductive material with a high degree of freedom (DOF) of shape. Further, we developed two cylindrical sensors, with diameters of 25 and 50 mm, utilizing the high DOF of geometry. To evaluate the developed sensors, we conducted two validations-60-segment cross-validation and holdout validation–to identify the number of fingers engaged in grasping by adults. AlexNet was used for identification of the used reconstruction image; k-nearest neighbors (KNN) and Support vector machine (SVM) were used for the measurement of the voltage vector. According to the results, these accuracies exceeding the chance level was obtained for all participants of both validations. In addition, an average accuracy of approximately 90% was acquired using the measured voltage vector. In conclusion, the study findings indicate that the proposed device could be used for early diagnosis of ASD in infants and cognitive decline in older adults.