MUMBAI, India, July 7 -- Intellectual Property India has published a patent application (202541059950 A) filed by Amrita Vishwa Vidyapeetham on June 23, 2025, for System And Method For Iot-Based Water Demand Prediction Incorporating Spatio-Temporal Multivariate Imputation.
Inventors include Velayudhan, Nibi Kulangara; Devidas, Aryadevi Remanidevi; Ramesh, Maneesha Vinodini; and M, Nitin Kumar.
The application for the patent was published on July 03, 2026, under issue no. 27/2026.
Abstract: The present disclosure relates to a system (100) and method (600) for predicting short-term water demand in a water distribution network (WDN) using real-time multivariate data from a network of IoT-enabled sensors (102). The system (100) includes a processor (108) operatively connected to IoT devices (104) and communicatively linked to a server (120). The processor (108) collects time- series data, identifies missing values, and imputes them using a generative AI model such as a variational autoencoder, generative adversarial network, or diffusion model. Spatial dependencies are modelled using graph-based structures, while temporal dependencies are captured using recurrent neural networks. The imputed data is processed using a deep learning forecasting model based on a deep neural network (DNN) to predict water demand. The system (100) operates in real-time and supports distributed computing through edge, fog, and cloud architecture, enabling accurate and robust water demand forecasting for smart water infrastructure applications.
Disclaimer: Curated by HT Syndication.
