MUMBAI, India, May 1 -- Intellectual Property India has published a patent application (202641048283 A) filed by Madhankumar C; Dr. M. Sarathkumar; Mrs. Dhivya Preethi B; Dr. K. Sebasthirani; Dudhani Rushikesh; Dr. S. Palpandi; and R. Murugan, Pollachi, Tamil Nadu, on April 16, for 'an autonomous fault-resilient embedded communication module using deep learning-based signal diagnostics.'
Inventor(s) include Dr. M. Sarathkumar; Mrs. Dhivya Preethi B; Dr. K. Sebasthirani; Dudhani Rushikesh; Dr. S. Palpandi; and R. Murugan.
The application for the patent was published on May 1, under issue no. 18/2026.
According to the abstract released by the Intellectual Property India: "An Autonomous Fault-Resilient Embedded Communication Module Using Deep Learning-Based Signal Diagnostics Abstract The increasing complexity of embedded communication systems in modern cyber-physical and IoT environments necessitates robust, intelligent, and self healing mechanisms to ensure uninterrupted data transmission. This paper proposes an autonomous fault-resilient embedded communication module leveraging deep learning-based signal diagnostics for real-time anomaly detection and recovery. The system integrates a lightweight embedded processor with advanced neural network architectures to continuously monitor communication signals and identify faults such as noise interference, signal attenuation, packet loss, and hardware-induced distortions. A hybrid deep learning framework combining Convolutional Neural Networks (CNN) and Long Short-Term Memory (LSTM) networks is employed to extract both spatial and temporal features from signal patterns. The model is trained on a diverse dataset of normal and faulty signal conditions to achieve high diagnostic accuracy. Upon detecting anomalies, the module autonomously initiates corrective actions, including adaptive modulation, dynamic rerouting, and error correction protocols, thereby enhancing system reliability without human intervention. Experimental results demonstrate that the proposed system achieves superior fault detection accuracy, reduced latency, and improved communication stability compared to conventional rule-based approaches. The embedded implementation ensures low power consumption and real-time performance, making it suitable for applications in industrial automation, smart grids, autonomous vehicles, and remote sensing systems. This work contributes a scalable and intelligent solution for next-generation resilient communication infrastructures."
Disclaimer: Curated by HT Syndication.
