MUMBAI, India, April 17 -- Intellectual Property India has published a patent application (202641043170 A) filed by Anwar Bhasha Pattan; and Bvrit Hyderabad College Of Engineering For Women, Hyderabad, Telangana, on April 4, for 'intelligent water quality monitoring device using esp32-cam with on-device cnn inference.'
Inventor(s) include Dr. Anwar Bhasha Pattan; Banka Sujatha; Vadla Shivathmika; Vempati Harshini; and Dr. L. Bhargava Kumar.
The application for the patent was published on April 17, under issue no. 16/2026.
According to the abstract released by the Intellectual Property India: "The present invention relates to a hybrid drinking water hygiene monitoring system based on embedded systems and Edge Artificial Intelligence (Edge AI) for real-time water quality assessment. The system is designed to provide a cost-effective, portable, and efficient solution for detecting whether water is clean or contaminated without relying on conventional laboratory testing methods or internet connectivity. The proposed system utilizes an ESP32-CAM module equipped with an integrated camera to capture real-time images of water samples. These images are processed using a convolutional neural network (CNN)-based machine learning model trained on labelled datasets of clean and contaminated water. The trained model is deployed on the device using tiny ML techniques, enabling on-device inference and eliminating the need for cloud-based processing. In addition to image-based analysis, the system incorporates a Total Dissolved Solids (TDS) sensor to measure the concentration of dissolved impurities present in the water. This hybrid approach combines visual analysis and quantitative sensor data to improve the accuracy and reliability of water quality detection compared to single-method systems. The ESP32 microcontroller processes both the captured image data and sensor readings, and a decision-making mechanism determines the water quality status. Based on the classification result, the system provides immediate feedback through LED indicators, where a green LED indicates clean water and a red LED indicates contaminated water. The entire system operates offline, making it highly suitable for deployment in rural, remote, and resource-constrained environments. The design is compact, energy-efficient, and scalable, allowing future integration with additional sensors or communication modules. Overall, the present invention offers an intelligent, automated, and user-friendly solution for real-time water hygiene monitoring, contributing to improved public health and environmental safety."
Disclaimer: Curated by HT Syndication.
