Metaheuristic-Driven Feature Selection for Human Activity Recognition on KU-HAR Dataset Using XGBoost Classifier

Human activity recognition (HAR) is an automated technique for identifying human activities using images and sensor data. Although numerous studies exist, most of the models proposed are highly complex and rely on deep learning. This research utilized two novel frameworks based on the Extreme Gradient Boosting (XGB) classifier, also known as the XGBoost classifier, enhanced with metaheuristic algorithms: Golden Jackal Optimization (GJO) and War Strategy Optimization (WARSO). This study utilized the KU-HAR dataset, which was collected from smartphone accelerometer and gyroscope sensors. We extracted 48 mathematical features to convey the HAR information. GJO-XGB achieved a mean accuracy in 10-fold cross-validation of 93.55% using only 23 out of 48 features. However, WARSO-XGB outperformed GJO-XGB and other traditional classifiers, achieving a mean accuracy, F-score, precision, and recall of 94.04%, 92.88%, 93.47%, and 92.40%, respectively. GJO-XGB has shown lower standard deviations on the test set (accuracy: 0.200; F-score: 0.285; precision: 0.388; recall: 0.336) compared to WARSO-XGB, indicating a more stable performance. WARSO-XGB exhibited lower time complexity, with average training and testing times of 30.84 s and 0.51 s, compared to 39.40 s and 0.81 s for GJO-XGB. After performing 10-fold cross-validation using various external random seeds, GJO-XGB and WARSO-XGB achieved accuracies of 93.80% and 94.19%, respectively, with a random seed = 20. SHAP identified that range_gyro_x, max_acc_z, mean_gyro_x, and some other features are the most informative features for HAR. The SHAP analysis also involved a discussion of the individual predictions, including the misclassifications.