MUMBAI, India, Aug. 12 -- Intellectual Property India has published a patent application (202641093717 A) filed by Sri Eshwar College Of Engineering on August 03, 2026, for An Edge-Iot Framework For Remote Neuromuscular Monitoring: Designing A High-Snr Analog Front- End With Mqtt Telemetry.
Inventors include Ms. J. Yashwandra; Mr. S. Aravind; Mrs. K. Gowthami; and Dr. R. Babitha Lincy.
The application for the patent was published on August 07, 2026, under issue no. 32/2026.
Abstract: Musculoskeletal strain and neuromuscular fatigue constitute major occupational safety, sports medicine, and physical rehabilitation industry concerns worldwide. Conventional methods of electromyography monitoring suffer from extremely high levels of network congestions, data packet losses and fast battery drain due to computationally expensive software-based filtering loops on raw data streamed in continuous mode from the cloud. In order to solve latency and power consumption problems mentioned above, the current invention is a cyber-physical hardware system which is IoT-enabled and capable of mapping muscle fatigue locally and performing closed-loop interventions in real-time. System architecture is based on ultra-efficient analog front end (AFE) pipeline comprising an instrument amplifier (AD620) with high common mode rejection ratio, an active bandpass filter, and a custom hardware active Twin-T notch filter for powerline hum and motion artifact removal. The proposed solution allows reaching very efficient Signal to Noise Ratio (SNR) performance in the analog domain and avoiding any use of digital clock cycles in doing so. An analog waveform outputted by the AFE is digitized locally by an embedded Wi-Fi enabled microcontroller core (ESP32), running an integrated windowed Fast Fourier Transform (FFT) to compute MNF power spectrum density decrease. Through executing these resource-intensive spectral extraction operations locally on the edge node, the bulky raw data arrays of biopotential data are transformed into lightweight metrics for diagnosis. In this case, the system works as an IoT publisher and publishes real-time data payloads using the MQTT protocol over a local wireless network to the remote web-based clinical dashboard with current muscle status, fatigue confidence percentages, and power metrics. At the same time, once the local edge engine detects that the frequency index exceeds a certain pre-codes safety limit, a localized physical intervention is performed. A timely digital logic pulse is executed by the microcontroller to a positive displacement peristaltic actuator, controlled using galvanically isolated optical air-gap relay networking. Isolation protects the sensitive edge-AI computing logic and radio-frequency transceivers from any inductive back-electromotive force (back-EMF) voltage spikes. The final result is a reliable and power-efficient telemetry network node, which ensures biological data privacy, eliminates cloud latency constraints, and provides full electronic stability.
Disclaimer: Curated by HT Syndication.
