C. Amici, Martina Mosso, F. Vérité, M. Tiboni, A. Borboni, S. Negrini
{"title":"用FDA分析躯干运动:对健康受试者的探索性研究","authors":"C. Amici, Martina Mosso, F. Vérité, M. Tiboni, A. Borboni, S. Negrini","doi":"10.1109/MESA55290.2022.10004476","DOIUrl":null,"url":null,"abstract":"In this work, 48 acquisitions of trunk flexion-extension in healthy subjects are evaluated with the Functional Data Analysis (FDA) approach. Signals are registered with different strategies: i) assigning to the registering function two and three landmark points, and ii) aligning signals to a target profile externally imposed. The results are compared, and the normality profile for the analyzed sample is computed, revealing that the registration with three landmark points represents the best compromise between accuracy and computational burden for the current dataset. The reliability of FDA for the current purpose is investigated with the Leave-One-Out method, and the obtained results suggest the suitability of FDA for the analysis of this kind of data, although further studies should be performed increasing the original dataset in quantity and quality to extend the reliability of the normality profile to the whole healthy population.","PeriodicalId":410029,"journal":{"name":"2022 18th IEEE/ASME International Conference on Mechatronic and Embedded Systems and Applications (MESA)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2022-11-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Trunk Movement Analysis with FDA: Exploratory Study for the Healthy Subject\",\"authors\":\"C. Amici, Martina Mosso, F. Vérité, M. Tiboni, A. Borboni, S. Negrini\",\"doi\":\"10.1109/MESA55290.2022.10004476\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"In this work, 48 acquisitions of trunk flexion-extension in healthy subjects are evaluated with the Functional Data Analysis (FDA) approach. Signals are registered with different strategies: i) assigning to the registering function two and three landmark points, and ii) aligning signals to a target profile externally imposed. The results are compared, and the normality profile for the analyzed sample is computed, revealing that the registration with three landmark points represents the best compromise between accuracy and computational burden for the current dataset. The reliability of FDA for the current purpose is investigated with the Leave-One-Out method, and the obtained results suggest the suitability of FDA for the analysis of this kind of data, although further studies should be performed increasing the original dataset in quantity and quality to extend the reliability of the normality profile to the whole healthy population.\",\"PeriodicalId\":410029,\"journal\":{\"name\":\"2022 18th IEEE/ASME International Conference on Mechatronic and Embedded Systems and Applications (MESA)\",\"volume\":\"1 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2022-11-28\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2022 18th IEEE/ASME International Conference on Mechatronic and Embedded Systems and Applications (MESA)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/MESA55290.2022.10004476\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2022 18th IEEE/ASME International Conference on Mechatronic and Embedded Systems and Applications (MESA)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/MESA55290.2022.10004476","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Trunk Movement Analysis with FDA: Exploratory Study for the Healthy Subject
In this work, 48 acquisitions of trunk flexion-extension in healthy subjects are evaluated with the Functional Data Analysis (FDA) approach. Signals are registered with different strategies: i) assigning to the registering function two and three landmark points, and ii) aligning signals to a target profile externally imposed. The results are compared, and the normality profile for the analyzed sample is computed, revealing that the registration with three landmark points represents the best compromise between accuracy and computational burden for the current dataset. The reliability of FDA for the current purpose is investigated with the Leave-One-Out method, and the obtained results suggest the suitability of FDA for the analysis of this kind of data, although further studies should be performed increasing the original dataset in quantity and quality to extend the reliability of the normality profile to the whole healthy population.