کد مقاله | کد نشریه | سال انتشار | مقاله انگلیسی | نسخه تمام متن |
---|---|---|---|---|
10432569 | 910252 | 2013 | 9 صفحه PDF | دانلود رایگان |
عنوان انگلیسی مقاله ISI
Relative performances of artificial neural network and regression mapping tools in evaluation of spinal loads and muscle forces during static lifting
ترجمه فارسی عنوان
عملکرد نسبی شبکه های عصبی مصنوعی و ابزار نقشه برداری رگرسیون در ارزیابی بارهای ستون فقرات و نیروهای عضلانی در طول بلند کردن استاتیک
دانلود مقاله + سفارش ترجمه
دانلود مقاله ISI انگلیسی
رایگان برای ایرانیان
کلمات کلیدی
بلند کردن استاتیک، نیروهای عضلانی، بارهای ستون فقرات، مدل ها، پسرفت، شبکه های عصبی مصنوعی،
موضوعات مرتبط
مهندسی و علوم پایه
سایر رشته های مهندسی
مهندسی پزشکی
چکیده انگلیسی
Two artificial neural networks (ANNs) are constructed, trained, and tested to map inputs of a complex trunk finite element (FE) model to its outputs for spinal loads and muscle forces. Five input variables (thorax flexion angle, load magnitude, its anterior and lateral positions, load handling technique, i.e., one- or two-handed static lifting) and four model outputs (L4-L5 and L5-S1 disc compression and anterior-posterior shear forces) for spinal loads and 76 model outputs (forces in individual trunk muscles) are considered. Moreover, full quadratic regression equations mapping input-outputs of the model developed here for muscle forces and previously for spine loads are used to compare the relative accuracy of these two mapping tools (ANN and regression equations). Results indicate that the ANNs are more accurate in mapping input-output relationships of the FE model (RMSE= 20.7Â N for spinal loads and RMSE= 4.7Â N for muscle forces) as compared to regression equations (RMSE= 120.4Â N for spinal loads and RMSE=43.2Â N for muscle forces). Quadratic regression equations map up to second order variations of outputs with inputs while ANNs capture higher order variations too. Despite satisfactory achievement in estimating overall muscle forces by the ANN, some inadequacies are noted including assigning force to antagonistic muscles with no activity in the optimization algorithm of the FE model or predicting slightly different forces in bilateral pair muscles in symmetric lifting activities. Using these user-friendly tools spine loads and trunk muscle forces during symmetric and asymmetric static lifts can be easily estimated.
ناشر
Database: Elsevier - ScienceDirect (ساینس دایرکت)
Journal: Journal of Biomechanics - Volume 46, Issue 8, 31 May 2013, Pages 1454-1462
Journal: Journal of Biomechanics - Volume 46, Issue 8, 31 May 2013, Pages 1454-1462
نویسندگان
N. Arjmand, O. Ekrami, A. Shirazi-Adl, A. Plamondon, M. Parnianpour,