[Online]Deployment of TinyML on THEJAS32 based IoT Platform

Deployment of TinyML on THEJAS32 based IoT Platform
ID:37 Submission ID:82 View Protection:ATTENDEE Updated Time:2025-12-29 14:41:52 Hits:455 Online

Start Time:2025-12-29 15:45 (Asia/Amman)

Duration:15min

Session:[S2] Track 2: IoT and applications » [S2-1] Track 2: IoT and applications

Presentation File

Tips: The file permissions under this presentation are only for participants. You have not logged in yet and cannot view it temporarily.

Abstract

THEJAS32 SoC is based on the VEGA ET1031 processor, a 32-bit single core, in-order, 3-stage pipeline processor developed by C-DAC under the MDP. This work presents the maiden attempt to deploy Tiny Machine Learning (TinyML) on a hardware platform built around the THEJAS32 SoC. A TinyML model was trained and optimized using the TensorFlow framework using Google Colab and deployed to the hardware using the VEGA Software Development Kit (SDK). The model was compressed by as much as 97% compared to the one developed using TensorFlow. This validates the viability of the TinyML-IoT-THEJAS32 platform for TinyML applications.


 
Keywords
TinyML,RISC-V,Edge AI,THEJAS32,VEGA SDK
Speaker
Aleena Vinod
Project Engineer Centre for Development of Advanced Computing

Shibu R M
Scientist G Centre for Development of Advanced Computing

Prem Krishnan N
Scientist E Centre for Development of Advanced Computing

Subina Gafoor A
Project Engineer Centre for Development of Advanced Computing

Bhagyasree V S
OS Engineer Centre for Development of Advanced Computing

Submission Author
Aleena Vinod Centre for Development of Advanced Computing
Prem Krishnan N Centre for Development of Advanced Computing
Shibu R M Centre for Development of Advanced Computing
Subina Gafoor A Centre for Development of Advanced Computing
Bhagyasree V S Centre for Development of Advanced Computing
Comment submit
Verification code Change another
All comments

CONTACT US

Email: asiancomnet@usssociety.org

Website & IT Support: hi@aconf.org 

Registration Submit Paper