• Mrs Ch Kavitha
• M Sai Uma devi
• M Jahnavi
• Y Karthik
• S Sai Ganesh

Accurate detection of human activities is essential for healthcare, fitness tracking, and rehabilitation. Traditional machine learning models struggle with class imbalances and the high dimensionality of sensor data, leading to reduced classification accuracy. This study presents an Artificial Neural Network (ANN)-based model that integrates the Grey Wolf Optimizer (GWO) for efficient feature selection, enhancing classification performance. The model is trained on the UCI Human Activity Recognition (HAR) dataset, which includes accelerometer and gyroscope readings from smartphones. Comparative analysis with traditional classifiers, such as K-Nearest Neighbors (KNN) and Decision Trees, highlights the ANN's superior ability to handle class imbalances, capture intricate movement patterns, and reduce false positives. Experimental results demonstrate significant improvements in accuracy, precision, recall, and F1-score, making this ANN-based approach a promising solution for real-time activity monitoring applications in wearable health systems

Human Activity Recognition, Artificial Neural Networks, Grey Wolf Optimizer, Deep Learning, Wearable Sensors, Smartphone-Based Activity Detection.

"Revolutionizing Physical Activity Detection Using Artificial Neural Networks", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.12, Issue 3, page no.e38-e45, March-2025, Available :http://www.jetir.org/papers/JETIR2503418.pdf

"Revolutionizing Physical Activity Detection Using Artificial Neural Networks", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.12, Issue 3, page no. ppe38-e45, March-2025, Available at : http://www.jetir.org/papers/JETIR2503418.pdf