Human Gait Analysis: A Sequential Framework of Lightweight Deep Learning and Improved Moth-Flame Optimization Algorithm

Table 2

Proposed classification results of human gait recognition on the TUM GAID dataset.

Classifier	Class-based accuracy (%)			Mean accuracy (%)
	Normal walk	Walk with a bag	Walk with shoes
LightweightDeep-ELM	99.64	98.52	97.65	98.60
LightweightDeep-SVM	98.58	96.92	96.25	97.25
LightweightDeep-FKNN	98.63	96.21	95.37	96.73
LightweightDeep-EBT	98.12	96.82	95.80	96.91
LightweightDeep-DT	97.52	96.03	95.24	96.26

Bold values indicate the best values.