Biomedizinische Technik. Biomedical engineering · 2024
A type-2 fuzzy inference-based approach enables walking speed estimation that adapts to inter-individual gait patterns.
СтатьяНазвание и аннотация: Перевод пока не подготовлен
Обработка статьи · этапы, ошибки и управление
Загрузка состояния…
Ошибки и ограничения
История · было → стало
Состояние обновляется каждые 5 секунд, пока блок открыт. Процент показывается только там, где известен объём работы. Пауза останавливает продолжение этапа; текущий запрос к источнику может завершиться.
Li Linrong, Liao Wenxiang, Yu Hongliu
Аннотация
OBJECTIVES: Individuals change walking speed by regulating step frequency (SF), stride length (SL), or a combination of both (FL combinations). However, existing methods of walking speed estimation ignore this regulatory mechanism. This paper aims to achieve accurate walking speed estimation while enabling adaptation to inter-individual speed regulation strategies.
METHODS: We first extracted thigh features closely related to individual speed regulation based on a single thigh mounted IMU. Next, an interval type-2 fuzzy inference system was used to infer and quantify the individuals' speed regulation intentions, enabling speed estimation independent of inter-individual gait patterns. Experiments with five subjects walking on a treadmill at different speeds and with different gait patterns validated our method.
RESULTS: The overall root mean square error (RMSE) for speed estimation was 0.0704 ± 0.0087 m/s, and the RMSE for different gait patterns was no more than 0.074 ± 0.005 m/s.
CONCLUSIONS: The proposed method provides high-accuracy speed estimation. Moreover, our method can be adapted to different FL combinations without the need for individualised tuning or training of individuals with varying limb lengths and gait habits. We anticipate that the proposed method will help provide more intuitive speed adaptive control for rehabilitation robots, especially intelligent lower limb prostheses.
METHODS: We first extracted thigh features closely related to individual speed regulation based on a single thigh mounted IMU. Next, an interval type-2 fuzzy inference system was used to infer and quantify the individuals' speed regulation intentions, enabling speed estimation independent of inter-individual gait patterns. Experiments with five subjects walking on a treadmill at different speeds and with different gait patterns validated our method.
RESULTS: The overall root mean square error (RMSE) for speed estimation was 0.0704 ± 0.0087 m/s, and the RMSE for different gait patterns was no more than 0.074 ± 0.005 m/s.
CONCLUSIONS: The proposed method provides high-accuracy speed estimation. Moreover, our method can be adapted to different FL combinations without the need for individualised tuning or training of individuals with varying limb lengths and gait habits. We anticipate that the proposed method will help provide more intuitive speed adaptive control for rehabilitation robots, especially intelligent lower limb prostheses.