http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
Thays Falcari,Osamu Saotome,Ricardo Pires,Alexandre Brincalepe Campo 대한의용생체공학회 2020 Biomedical Engineering Letters (BMEL) Vol.10 No.2
One-vs-One (OVO) and One-vs-All (OVA) are decomposition methods for multi-class strategies used to allow binarySupport-Vector Machines (SVM) to transform a given k-class problem into pairwise small problems. In this context, thepresent work proposes the analysis of these two decomposition methods applied to the hand posture recognition problem inwhich the sEMG data of eight participants were collected by means of an 8-channel armband bracelet located on the forearm. Linear, Polynomial and Radial Basis Function kernels functions and its adjustments level were implemented combined tothe strategies OVO and OVA to compare the performance of the SVM when mapping posture data into the classifi cationspaces spanned by the studied kernels. Acquired sEMG signals were segmented considering 0.16 s e 0.32 s time windows. Root Mean Square (RMS) feature was extracted from each time window of each posture and used for SVM training. Thepresent work focused in investigating the relationship between the multi-class strategies combined to kernels adjustmentslevels and SVM classifi cation performance. Promising results were observed using OVA strategy which presents a reducednumber of binary SVM implementation achieved a mean accuracy of 97.63%.