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

Table 8

Confusion matrix of the RF-based HAR model with all features.

	Brew coffee	Cooking	Use microwave oven	No activity	Take a bath	Dish washing	Hand washing	Teeth brushing	Type II error
Brew coffee	232	0	0	1	0	8	2	2	0.053
Cooking	50	77	0	0	5	0	0	0	0.417
Use microwave oven	9	0	33	0	0	0	0	0	0.214
Take a bath	4	5	0	1	399	9	0	10	0.068
Dish washing	4	7	0	0	11	106	2	4	0.209
Hand washing	0	0	0	1	3	3	60	3	0.143
Teeth brushing	4	5	0	0	15	0	1	99	0.202
No activity	1	0	0	13	0	0	0	2	0.188
Type I error	0.237	0.181	0.000	0.188	0.079	0.159	0.077	0.175