How Effective Are Forecasting Models in Predicting Effects of Exoskeletons on Fatigue Progression? DOI Creative Commons
Pranav Madhav Kuber, Abhineet Rajendra Kulkarni, Ehsan Rashedi

и другие.

Sensors, Год журнала: 2024, Номер 24(18), С. 5971 - 5971

Опубликована: Сен. 14, 2024

Forecasting can be utilized to predict future trends in physiological demands, which beneficial for developing effective interventions. This study implemented forecasting models fatigue level progression when performing exoskeleton (EXO)-assisted tasks. Specifically, perceived and muscle activity data were from nine recruited participants who performed 45° trunk flexion tasks intermittently with without assistance until they reached medium-high exertion the low-back region. Two algorithms, Autoregressive Integrated Moving Average (ARIMA) Facebook Prophet, using levels alone, external features of activity. Findings showed that univariate better Prophet model having lowest mean (SD) root squared error (RMSE) across 0.62 (0.24) 0.67 (0.29) EXO-assisted tasks, respectively. Temporal effects BSIE on delaying then evaluated by back up 20 trials. The slope trials was ~48–52% higher vs. assistance. Median benefits 54% 43% observed ARIMA (with features) demonstrates some potential applications workforce health monitoring, intervention assessment, injury prevention.

Язык: Английский

How Effective Are Forecasting Models in Predicting Effects of Exoskeletons on Fatigue Progression? DOI Creative Commons
Pranav Madhav Kuber, Abhineet Rajendra Kulkarni, Ehsan Rashedi

и другие.

Sensors, Год журнала: 2024, Номер 24(18), С. 5971 - 5971

Опубликована: Сен. 14, 2024

Forecasting can be utilized to predict future trends in physiological demands, which beneficial for developing effective interventions. This study implemented forecasting models fatigue level progression when performing exoskeleton (EXO)-assisted tasks. Specifically, perceived and muscle activity data were from nine recruited participants who performed 45° trunk flexion tasks intermittently with without assistance until they reached medium-high exertion the low-back region. Two algorithms, Autoregressive Integrated Moving Average (ARIMA) Facebook Prophet, using levels alone, external features of activity. Findings showed that univariate better Prophet model having lowest mean (SD) root squared error (RMSE) across 0.62 (0.24) 0.67 (0.29) EXO-assisted tasks, respectively. Temporal effects BSIE on delaying then evaluated by back up 20 trials. The slope trials was ~48–52% higher vs. assistance. Median benefits 54% 43% observed ARIMA (with features) demonstrates some potential applications workforce health monitoring, intervention assessment, injury prevention.

Язык: Английский

Процитировано

0