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

Table 11

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

	Brew coffee	Cooking	Use microwave oven	No activity	Take a bath	Dish washing	Hand washing	Teeth brushing	Type II error
Brew coffee	0	0	0	0	0	0	0	0	NA
Cooking	60	35	13	3	130	37	16	25	0.890
Use microwave oven	0	0	0	0	0	0	0	0	NA
No activity	0	0	0	0	0	0	0	0	NA
Take a bath	0	0	0	0	0	0	0	0	NA
Dish washing	0	0	0	0	0	0	0	0	NA
Hand washing	0	0	0	0	0	0	0	0	NA
Teeth brushing	0	0	0	0	0	0	0	0	NA
No activity	0	0	0	0	0	0	0	0	NA
Type I error	1.000	0.000	1.000	1.000	1.000	1.000	1.000	1.000