Chinese Journal of Mechanical Engineering

Table 4 Accuracy and loss for training and validation

From: Robust Damage Detection and Localization Under Complex Environmental Conditions Using Singular Value Decomposition-based Feature Extraction and One-dimensional Convolutional Neural Network

Epoch	Loss		Accuracy
Epoch	Training	Validation	Training	Validation
1	1.51	1.39	0.35	0.50
2	1.08	0.50	0.60	0.80
3	0.58	0.46	0.79	0.84
4	0.52	0.28	0.80	0.89
5	0.30	0.25	0.88	0.93
6	0.24	0.16	0.92	0.94
7	0.29	0.17	0.89	0.95
8	0.14	0.18	0.93	0.93
9	0.11	0.23	0.95	0.93
10	0.15	0.18	0.92	0.92
11	0.11	0.07	0.95	0.97
12	0.09	0.07	0.95	0.97
13	0.02	0.16	0.99	0.88
14	0.03	0.02	0.99	0.99
15	0.03	0.27	0.98	0.88
16	0.10	0.15	0.97	0.97
17	0.01	0.02	0.99	0.99
18	0.01	0.01	1.00	1.00
19	0.22	0.16	0.98	0.88
20	0.01	0.01	1.00	1.00

Back to article page