Gait based human identification: a comparative analysis

Thanks to gait analysis, many examinations such as person identification, disease detection, and evaluation of neuromusculoskeletal system functions can be performed. In the study, used dataset includes three different parameters obtained from 16 individuals (7 females 9 males) using wearable analysis sensors, here there are 321 for one each person. addition, we classify this data Linear Discriminant, Ensemble Subspace Bagged Trees, Optimizable Ensemble-1, Ensemble-2 classifiers. Two optimization techniques were employed increase performance metrics From results, it is seen that Accuracy (%), Error Sensitivity Specificity Precision F1 Score Matthews Correlation Coefficient (MCC) most successful classifier equal 97.92, 2.08, 99.86, 98.44, 97.86, 0.9790, respectively.