Neural network committees for finger joint angle estimation from surface EMG signals
- Тип контента: Научная статья
- Номер документа: 6241
- Название документа: Neural network committees for finger joint angle estimation from surface EMG signals
- Номер (DOI, IBSN, Патент): 10.1186/1475-925X-8-2
- Изобретатель/автор: Nikhil A Shrirao, Narender P Reddy, Durga R Kosuri
- Правопреемник/учебное заведение: University of Akron
- Дата публикации документа: 2009-01-20
- Страна опубликовавшая документ: США
- Язык документа: Английский
- Наименование изделия: Не заполнено
- Источник: BioMedical Engineering OnLine
- Вложения: Да
- Аналитик: Глаголева Елена
Background: In virtual reality (VR) systems, the user’s finger and hand positions are sensed and used to control the virtual envi-ronments. Direct biocontrol of VR environments using surface electromyography (SEMG) signals may be more synergistic and uncons-training to the user. The purpose of the present investigation was to develop a technique to predict the finger joint angle from the surface EMG measurements of the extensor muscle using neural network models.
Methodology: SEMG together with the actual joint angle measurements were obtained while the subject was performing flexion-exten-sion rotation of the index finger at three speeds. Several neural networks were trained to predict the joint angle from the para-meters extracted from the SEMG signals. The best networks were selected to form six committees. The neural network committees were evaluated using data from new subjects.
Results: There was hysteresis in the measured SMEG signals during the flexion-extension cycle. However, neural network committees were able to predict the joint angle with reasonable accuracy. RMS errors ranged from 0.085 ± 0.036 for fast speed finger-extension to 0.147 ± 0.026 for slow speed finger extension, and from 0.098 ± 0.023 for the fast speed finger flexion to 0.163 ± 0.054 for slow speed finger flexion.
Conclusion: Although hysteresis was observed in the measured SEMG signals, the committees of neural networks were able to predict the finger joint angle from SEMG signals.
Категория: Научные статьи | Нет комментариев »
Комментарии
Статистика
Категорий: 179
Статей всего: 2,003
По типу:
Видео: 36
Выдержка с форума: 1
Контактные данные: 12
Научная статья: 1388
Не заполнено: 5
Новостная статья: 317
Обзор технологии: 42
Патент: 219
Тех.подробности: 34
Тип: 1
Комментариев: 6,634
Изображений: 3,005
Подробней...
ТОР 10 аналитиков
-
Глаголева Елена - 591
Дмитрий Соловьев - 459
Helix - 218
Ридна Украина))) - 85
Наталья Черкасова - 81
max-orduan - 29
Елена Токай - 15
Роман Михайлов - 9
Мансур Жигануров - 4
Дуванова Татьяна - 3
Календарь
Авторизация
Ошибка в тексте?
Выдели её мышкой!
И нажми Ctrl+Enter