A novel method to infer the finger flexing motions of various arm postures is proposed. From the gyroscope signal, the authors recognized forearm posture using K-means clustering method. Then finger motion inferred. F...A novel method to infer the finger flexing motions of various arm postures is proposed. From the gyroscope signal, the authors recognized forearm posture using K-means clustering method. Then finger motion inferred. For finger motion inference, Gaussian model of information entropy and maximum likelibood method was utilized. Experimentally it is obtained that the average recognition rate with the forearm posture inference is much higher than those without the inference by 30.7%.展开更多
ms paper proposes a set of objective and quantitative human motion evaluation indices, among Which the index of difficulty and index of performance are introduced as the general indices for the quality measure of 2-D ...ms paper proposes a set of objective and quantitative human motion evaluation indices, among Which the index of difficulty and index of performance are introduced as the general indices for the quality measure of 2-D target-to-talget movement. As an example, the target-reaching movement of index finger, which is a basic functional action of index finger in the daily life of hUman beings, were experimentally investigated. In the experiment five healthy male subjects were asked to perform three target-reaching movement tasks Which have different indices of difficulty. All movements were recorded by a 3-D motion analysis system. Later, their motion qualities were measured with these evaluation metrics. The results showed that these indices are reasonable and have potential applications to biomedical engineering.展开更多
基金supported by the MKE(The Ministry of Knowledge Economy),Koreathe ITRC(Information Technology Research Center)support program(NIPA-2010-C1090-1021-0010)
文摘A novel method to infer the finger flexing motions of various arm postures is proposed. From the gyroscope signal, the authors recognized forearm posture using K-means clustering method. Then finger motion inferred. For finger motion inference, Gaussian model of information entropy and maximum likelibood method was utilized. Experimentally it is obtained that the average recognition rate with the forearm posture inference is much higher than those without the inference by 30.7%.
文摘ms paper proposes a set of objective and quantitative human motion evaluation indices, among Which the index of difficulty and index of performance are introduced as the general indices for the quality measure of 2-D target-to-talget movement. As an example, the target-reaching movement of index finger, which is a basic functional action of index finger in the daily life of hUman beings, were experimentally investigated. In the experiment five healthy male subjects were asked to perform three target-reaching movement tasks Which have different indices of difficulty. All movements were recorded by a 3-D motion analysis system. Later, their motion qualities were measured with these evaluation metrics. The results showed that these indices are reasonable and have potential applications to biomedical engineering.
