• Sayan Das
• Swagatam Ghosh
• Kana Biswas
• Avinaba Das
• Dr. Sandhya Pattanayak

Path loss is all about how a signal becomes weaker as it travels from the transmitter to the receiver. Traditional methods like the Okumura and Hata models use fixed formulas to calculate this weakening, but these methods are not flexible or accurate in every situation. To improve this, a machine learning approach using a Random Forest Regression model was used. This model was trained on data that included factors like frequency, antenna heights, distance, and environment types. The machine learning model turned out to be better than traditional methods because it learned the complex relationships between these factors and gave more accurate predictions. It also showed which factors, such as distance and environment, are most important in predicting path loss. This makes planning wireless networks smarter and more effective.

"Predicting Pathloss using Machine Learning", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.12, Issue 5, page no.g696-g699, May-2025, Available :http://www.jetir.org/papers/JETIR2505772.pdf

"Predicting Pathloss using Machine Learning", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.12, Issue 5, page no. ppg696-g699, May-2025, Available at : http://www.jetir.org/papers/JETIR2505772.pdf