• Peerasab Hawaldar
• Girisha Kumar

This paper presents the development of an automated water level detection system using machine learning (ML) algorithms, with MATLAB serving as the primary platform for data analysis and model training. The system integrates ultrasonic sensors and an Arduino microcontroller to capture real-time water level data. The acquired data is then processed and fed into machine learning models, including Decision Trees, Support Vector Machines (SVM), and Neural Networks, to predict water levels and automate water pump operation. Simulations in MATLAB reveal that Neural Networks provide the highest accuracy (96%) but require longer training times, while Decision Trees offer faster response times with moderate accuracy. SVM, particularly with the RBF kernel, strikes a balance between performance and computational efficiency. The research highlights the potential of machine learning to enhance water management by improving accuracy, reducing manual intervention, and ensuring efficient resource usage.

Water level detection, Machine learning, MATLAB, Decision Trees, Support Vector Machines, Neural Networks, Water management, Automation, Ultrasonic sensors, Real-time monitoring

"Automatic water level detector using Machine Learning", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.6, Issue 1, page no.129-133, January-2019, Available :http://www.jetir.org/papers/JETIR1901J22.pdf

"Automatic water level detector using Machine Learning", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.6, Issue 1, page no. pp129-133, January-2019, Available at : http://www.jetir.org/papers/JETIR1901J22.pdf