MUMBAI, India, March 13 -- Intellectual Property India has published a patent application (202641025576 A) filed by Sai Kalyana Deepthi C; and C. Sai Kalyana Deepthi, Guntur, Andhra Pradesh, on March 4, for 'assessing water quality index near industrial regions and aiding in effective water management and controlling pollution level using t5 transformer.'
Inventor(s) include C. Sai Kalyana Deepthi; Gumma Dhana Lakshmi; Bathula Lakshmi Mounika; Shaik Najmabi; and Katakam Srividhya.
The application for the patent was published on March 13, under issue no. 11/2026.
According to the abstract released by the Intellectual Property India: "The current invention reveals an Attribute Similarity based Feature Vector Training (ASbFVT) model of assessing water quality index around industrial areas, which would help in water management and pollution control by using T5 transformer architecture. The technique helps to determine and forecast water quality conditions correctly by deriving and optimizing physical, chemical, and spectral attributes of multi-source sensor networks and remote sensing data. Similarity measures of attributes like cosine similarity, Jaccard index, Euclidean distance and similarity based on correlation are used to produce optimized feature vectors that reflect the inherent environmental associations. A machine learning classifier (such as T5 Transformer, Support Vector machine, Random Forest, Gradient Boosting or Neural Network) is trained to provide a higher accuracy of water quality prediction and pollution events. The system has scalable cloud-based deployment, which enables real-time and parallel processing of heterogeneous data streams of IoT sensors, industrial locations and remote monitoring platforms. The method removes unnecessary and irrelevant elements, which decreases the dimensions, enhances interpretability, and elevates the accuracy in the determination of water quality indexes. The constant updating of model with new environmental and laboratory data improve the flexibility to the changing trends of industrial pollution. Through experimental analysis, it is shown that ASbFVT model performs better than traditional water quality assessment and algorithmic approaches provide low computational requirements to local monitoring hardware and allows controlling the environment and adherence to laws in a timely manner."
Disclaimer: Curated by HT Syndication.
