Table 2 Summary of the performance of the algorithms for all participants group, considering Input 1 as training data.

From: On the prediction of tibiofemoral contact forces for healthy individuals and osteoarthritis patients during gait: a comparative study of regression methods

Function	1st Knee contact peak (N/body weight)								2nd Knee contact peak (N/body weight)
Function	MAE	RPE	RMSE	R	R2	MDF	LCI	UCI	MAE	RPE	RMSE	R	R2	MDF	LCI	UCI
(1) Ensemble trees (bagging)	0.25	8.67	0.32	0.64	0.41	\(-\) 0.15	\(-\) 0.25	\(-\) 0.06	0.46	13.14	0.63	0.15	0.02	\(-\) 0.25	\(-\) 0.44	\(-\) 0.05
(2) Ensemble trees (LSBoost)	0.36	12.59	0.42	0.49	0.24	\(-\) 0.02	\(-\) 0.16	0.13	0.46	14.09	0.63	0.34	0.11	\(-\) 0.09	\(-\) 0.30	0.13
(3) Linear SVR	0.29	10.32	0.35	0.78	0.61	0.23	0.14	0.32	0.58	17.69	0.69	0.16	0.02	\(-\) 0.18	\(-\) 0.41	0.05
(4) Quadratic SVR	0.39	13.60	0.51	0.44	0.19	\(-\) 0.27	\(-\) 0.42	\(-\) 0.13	0.59	17.81	0.69	0.01	0.00	\(-\) 0.14	\(-\) 0.38	0.09
(5) Cubic SVR	0.32	11.20	0.39	0.55	0.30	\(-\) 0.24	\(-\) 0.35	\(-\) 0.13	0.91	30.08	1.49	0.36	0.13	\(-\) 0.48	\(-\) 0.96	0.01
(6) Gaussian SVR	0.19	6.79	0.23	0.88	0.77	\(-\) 0.16	\(-\) 0.21	\(-\) 0.11	0.48	14.68	0.53	0.02	0.00	0.04	\(-\) 0.14	0.22
(7) Linear regression	0.20	7.43	0.25	0.77	0.59	0.13	0.05	0.20	0.59	17.49	0.75	0.25	0.07	\(-\) 0.21	\(-\) 0.46	0.03
(8) Lasso regression	0.21	7.74	0.27	0.71	0.50	0.10	0.02	0.19	0.58	17.26	0.70	0.07	0.01	\(-\) 0.20	\(-\) 0.43	0.03
(9) Ridge regression	0.28	10.60	0.39	0.59	0.35	0.19	0.08	0.31	0.60	18.40	0.69	0.06	0.00	\(-\) 0.09	\(-\) 0.32	0.14
(10) Binary decision tree	0.31	11.06	0.39	0.64	0.41	\(-\) 0.24	\(-\) 0.34	\(-\) 0.13	0.48	14.24	0.58	0.14	0.02	\(-\) 0.09	\(-\) 0.28	0.11
(11) GR (K.-exponential)	0.17	5.94	0.21	0.88	0.77	\(-\) 0.12	\(-\) 0.18	\(-\) 0.07	0.47	14.10	0.56	0.19	0.04	\(-\) 0.02	\(-\) 0.22	0.17
(12) GR (K.-squared exponential)	0.22	7.68	0.25	0.86	0.74	\(-\) 0.19	\(-\) 0.25	\(-\) 0.13	0.46	13.97	0.52	0.05	0.00	0.03	\(-\) 0.15	0.20
(13) GR (K.-matern 32)	0.17	6.58	0.22	0.75	0.56	\(-\) 0.01	\(-\) 0.09	0.06	0.47	14.41	0.54	0.10	0.01	0.01	\(-\) 0.17	0.20
(14) GR (K.-matern 52)	0.20	7.06	0.23	0.89	0.79	\(-\) 0.17	\(-\) 0.23	\(-\) 0.12	0.47	14.36	0.53	0.06	0.00	0.02	\(-\) 0.16	0.20
(15) GR (K.-rational quadratic)	0.20	6.94	0.23	0.89	0.79	\(-\) 0.17	\(-\) 0.22	\(-\) 0.12	0.46	14.17	0.53	0.02	0.00	0.02	\(-\) 0.16	0.20
(16) ETSVR-Kernel linear	0.35	12.62	0.47	0.63	0.40	0.26	0.12	0.39	0.57	17.49	0.69	0.05	0.00	\(-\) 0.17	\(-\) 0.40	0.06
(17) Kernel ridge regression	0.37	13.16	0.49	0.65	0.42	0.28	0.14	0.41	0.62	19.04	0.72	0.00	0.00	\(-\) 0.10	\(-\) 0.35	0.14
(18) Nyström Ridge Regression	0.44	15.53	0.60	0.61	0.37	0.34	0.17	0.51	0.62	19.02	0.71	0.02	0.00	\(-\) 0.09	\(-\) 0.33	0.16
(19) DNNE	0.41	14.58	0.49	0.73	0.54	\(-\) 0.07	\(-\) 0.23	0.10	0.28	9.05	0.38	0.68	0.46	0.03	\(-\) 0.10	0.16
(20) kNN weighted mean	0.49	16.93	0.58	0.53	0.28	\(-\) 0.49	\(-\) 0.60	\(-\) 0.38	0.46	13.23	0.61	0.02	0.00	\(-\) 0.25	\(-\) 0.44	\(-\) 0.06
(21) RKNNWTSVR	0.31	11.39	0.42	0.68	0.46	0.23	0.11	0.35	0.57	17.25	0.70	0.03	0.00	\(-\) 0.21	\(-\) 0.43	0.02
(22) LTSVR	0.38	13.74	0.53	0.55	0.31	0.28	0.13	0.44	0.56	17.46	0.65	0.12	0.01	\(-\) 0.05	\(-\) 0.28	0.17
(23) Stepwise glm	0.21	7.57	0.26	0.66	0.44	\(-\) 0.06	\(-\) 0.15	0.02	0.48	14.46	0.60	0.24	0.06	\(-\) 0.21	\(-\) 0.40	\(-\) 0.02
(24) Neural networks	0.25	9.24	0.30	0.68	0.46	0.03	\(-\) 0.08	0.13	0.76	22.45	0.92	0.48	0.23	\(-\) 0.11	\(-\) 0.43	0.20

Best results (i.e. highest accuracy) are in bold.
RMSE root mean squared error, R Pearson correlation coefficient, (R\(^2\)) the coefficient of determination, MDF mean delta force, LCI lower confidence interval, UPF upper confidence interval, GR Gaussian regression, K Kernel.

Back to article page

Table 2 Summary of the performance of the algorithms for all participants group, considering Input 1 as training data.

Search

Quick links