ARYABHAT-1: India’s First Fully Analog AI Processor
Designed & Built in India — A Fully Analog, Energy-Efficient, Performance-Scalable AI Processor
Key Features:
- 8-Core Fully Analog Architecture
- Technology & Energy Scalable Design
- Custom Compiler for AI/ML Algorithms
- Python-based Automated Testing Framework
Built from transistor to system level, ARYABHAT-1 allows users to configure energy and performance modes — making it ideal for edge AI tasks requiring ultra-low power.
Bird Hotspots: Low-Power Acoustic Classification for Ecological Monitoring
Identifying Bird Habitats using TinyML & Neuromorphic Audio Processing
This project from the NeuRonICS Lab, IISc, presents a novel low-power acoustic classification system to automatically identify bird hotspots — enabling real-time ecological insights using resource-constrained, battery-powered devices.
Key Features:
- TinyML-powered low-power acoustic classification
- Neuromorphic audio front-end using in-filter computation
- Template-based SVM model requiring less data and robust to noise
- Easy deployment on low-power microcontrollers
Hardware Highlights:
- TI CC1352 Launchpad (ARM Cortex M4F)
- MEMS microphone for audio capture
- Real-time audio buffering and classification
- On-device bird detection logs
This system enables scalable, automated monitoring of bird species without human intervention — crucial for biodiversity conservation and habitat mapping.
mmWave Radar for Activity Recognition and Localization
Real-time Multi-person Tracking for Healthcare and Surveillance
This project from the NeuRonICS Lab at IISc leverages mmWave radar to track and classify human activities in real-time, with a focus on healthcare, psychiatric ward, and custodial monitoring applications — all while preserving privacy.
Key Features:
- Radar-based Localization & Activity Recognition
- Simultaneous Multi-person Tracking
- Three-layer CNN for Real-time Classification
- Python-based GUI for Visualization & Logging
Technology Highlights:
- Uses IWR6843 mmWave radar (60–64 GHz)
- Robust in low light, dark, or foggy environments
- Preserves privacy by avoiding image capture — uses point cloud data
- Tracks range, velocity, acceleration & zone-based localization
- Supports classification: walking, sitting, resting, jumping, etc.
Unlike cameras, this contactless solution ensures privacy and works reliably in challenging environments. It’s a powerful tool for non-intrusive monitoring of patients or inmates, offering compact, low-power, and real-time insights.
Explore More Demonstrations
Watch more videos and project showcases from the NeuRonICS Lab on our YouTube channel.
Visit Our YouTube Channel →