An Analysis of Audio Features to Develop a Human Activity Recognition Model Using Genetic Algorithms, Random Forests, and Neural Networks

Table 7

Confusion matrix of the NN-based HAR model with 9 features.

	Brew coffee	Cooking	Use microwave oven	No activity	Take a bath	Dish washing	Hand washing	Teeth brushing	Type II error
Brew coffee	45	10	2	0	3	1	0	3	0.297
Cooking	9	22	0	0	2	2	0	1	0.389
Use microwave oven	1	1	10	0	0	0	0	1	0.231
Take a bath	0	1	0	0	119	9	2	3	0.112
Dish washing	3	0	0	0	3	24	0	1	0.226
Hand washing	0	0	0	0	0	1	12	2	0.200
Teeth brushing	0	1	0	0	3	0	2	13	0.316
No activity	2	0	1	3	0	0	0	1	0.571
Type I error	0.250	0.371	0.231	0.000	0.085	0.351	0.250	0.480