Intellectual Property India Publishes Patent Application for 'VLSI-Based Abnormal Heartbeat Detection Via Knowledge-Infused Dynamic Spiking Graph Neural Network Optimized With Wader Hunt Algorithm' Filed by Dr. Aditya Mandloi; Mr. Kush Soni; Dr. Vinita Tomar; Smt. Gosavi Shweta Vishnu; Prasad Nitin Varade; and Mr. Pradeep Kumar Mahapatro

MUMBAI, India, Jan. 9 -- Intellectual Property India has published a patent application (202521110356 A) filed by Dr. Aditya Mandloi; Mr. Kush Soni; Dr. Vinita Tomar; Smt. Gosavi Shweta Vishnu; Prasad Nitin Varade; and Mr. Pradeep Kumar Mahapatro, Indore, Madhya Pradesh, on Nov. 12, 2025, for 'vlsi-based abnormal heartbeat detection via knowledge-infused dynamic spiking graph neural network optimized with wader hunt algorithm.'

Inventor(s) include Dr. Aditya Mandloi; Mr. Kush Soni; Dr. Vinita Tomar; Smt. Gosavi Shweta Vishnu; Prasad Nitin Varade; and Mr. Pradeep Kumar Mahapatro.

The application for the patent was published on Dec. 12, under issue no. 50/2025.

According to the abstract released by the Intellectual Property India: "VLSI-Based Abnormal Heartbeat Detection via Knowledge-Infused Dynamic Spiking Graph Neural Network Optimized with Wader Hunt Algorithm 2. Abstract VLSI based abnormal heartbeat detection via a knowledge infused dynamic spiking graph neural network optimized with the Wader Hunt algorithm presents a novel and energy efficient solution for real time cardiac monitoring. The proposed framework integrates low power Very Large Scale Integration architecture with biologically inspired spiking neural dynamics enabling temporal pattern recognition essential for accurate heartbeat classification. A knowledge infused learning mechanism enhances interpretability by embedding domain specific clinical insights into the dynamic graph structure ensuring robust detection even under noisy physiological conditions. The adaptive graph topology models complex cardiac signal dependencies while the spiking neurons capture fine grained temporal variations in ECG waveforms. The Wader Hunt optimization algorithm improves parameter convergence by guiding efficient weight adaptation reducing computational overhead and enhancing inference stability. The hardware friendly architecture enables seamless deployment on edge devices supporting continuous remote health monitoring for wearable and implantable systems. Experimental results demonstrate high detection accuracy low latency and reduced energy consumption compared to conventional deep learning approaches. The system achieves reliable real time identification of arrhythmias facilitating early diagnosis and clinical intervention. The combination of VLSI implementation spiking graph network modeling knowledge infusion and meta heuristic optimization provides a comprehensive solution for scalable biosignal processing. The design supports online learning enabling the system to adapt to patient specific heartbeat patterns over time. Extensive validation on benchmark ECG datasets confirms the robustness of the proposed method across varying signal intensities heart rates and artifact levels. The synergy between hardware efficiency and intelligent learning mechanisms demonstrates the viability of the approach for large scale continuous health monitoring applications. The optimized architecture ensures that computational complexity remains manageable without compromising diagnostic precision. The proposed system exhibits strong generalization capabilities making it suitable for diverse clinical environments. The fusion of biological inspiration algorithmic intelligence and hardware optimization ushers in a new direction for next generation cardiac monitoring technologies. This work contributes to bridging the gap between advanced neural computing models and practical VLSI implementations for real world biomedical applications. The results highlight the effectiveness of incorporating domain knowledge into spiking neural architectures for improved clinical reliability. The Wader Hunt algorithm further enhances adaptability and search efficiency fostering stable long term performance. Overall the proposed VLSI based abnormal heartbeat detection system demonstrates a powerful and energy efficient platform capable of delivering accurate interpretable and real time cardiac diagnostics supporting early intervention and personalized healthcare. Keywords VLSI architecture, spiking graph neural network, abnormal heartbeat detection, knowledge infusion, Wader Hunt optimization, real time cardiac monitoring."

Disclaimer: Curated by HT Syndication.