MUMBAI, India, July 7 -- Intellectual Property India has published a patent application (202641079531 A) filed by Dr. Subbulakshmi M; Mrs. C. Swedheetha; Dr. Ancy S; Dr. A. Shakin Banu; Mr. M Sudheer Kumar Reddy; Ms. K. Ragavi; Mr. Krishna Banavathu; and Mr. Sankara Rao Allada on June 28, 2026, for A Machine Learning-Assisted Low-Power Vlsi Framework For Real-Time Embedded System.
Inventors include Dr. Subbulakshmi M; Mrs. C. Swedheetha; Dr. Ancy S; Dr. A. Shakin Banu; Mr. M Sudheer Kumar Reddy; Ms. K. Ragavi; Mr. Krishna Banavathu; and Mr. Sankara Rao Allada.
The application for the patent was published on July 03, 2026, under issue no. 27/2026.
Abstract: As the real-time embedded systems become more and more popular, there is a growing demand for low-power and intelligent hardware platforms or architectures that can process data at high speed and with low power consumption. Proposed is a machine learning-based low power VLSI framework for real-time embedded systems to improve computational efficiency, adaptive processing and intelligent decision making in embedded systems. It combines machine learning algorithms with Very Large-Scale Integration (VLSI) architecture to facilitate real-time data processing, predictive analysis, and autonomous system control with optimization. The objective of the proposed system is to conserve energy, minimize the overall hardware, and shorten processing delay, while achieving high performance and reliability. Machine learning models are used to analyse the system behaviour to optimize resource allocation and to improve the operational efficiency by adaptive learning mechanisms. The architecture facilitates effective signal processing, sensor data analysis, and smart communication in embedded systems. The framework is designed to be used efficiently in energy consumption, so that it can be used for battery-powered and resource-constrained devices. The results of performance evaluation are shown to be better than the processing speed, latency, and power efficiency of any conventional embedded hardware systems. Scalable design enables seamless integration with IoT (Internet of Things), industrial automation, healthcare monitoring, smart devices and edge computing applications. In general, the proposed machine learning aided VLSI structure is an intelligent, dependable, and power efficient approach for next-generation real-time embedded systems.
Disclaimer: Curated by HT Syndication.
