A TinyML-Based Edge-AI Module for Microbial Hotspot Detection and Environmental Sensing in Autonomous Field Robotics

DOI

10.2991/978-94-6239-693-7_48How to use a DOI?

Keywords

TinyML; Edge AI; Microbial Hotspot Detection; Environmental Sensing; Nano-Scale Machine Learning; Embedded Intelligence

Abstract

Microbial hotspot sensing and environmental surveillance in remote or hostile locations need intelligent systems that can conduct real-time analysis with strict computational limitations. Traditional cloud-based approaches are often slower, require more bandwidth and reliability, and their performance in stand-alone or connectivity-limited environments is constrained by these deficiencies. In this paper, we present a new framework for microchip-based microbial hotspot detection and environmental monitoring using Edge-AI TinyML. The system is built by coupling lightweight machine learning models along with feature fusion and cross-modal interaction to achieve real-time inference at the edge. The application of efficient deployment of models on resource-limited hardware is achieved through approaches like quantization, pruning, and adaptive sampling. A number of experiments have also been performed, which indicate significantly low inference latency and robustness, demonstrating that high classification accuracy is achieved (approximately 92%) at best. Therefore, the resulting measurements suggest that the proposed method is appropriate for long-term autonomous environmental monitoring in extreme environments.

Copyright

© 2026 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Harini Shrileka
AU  - Aadhi Maheshwaran Sri Hari
PY  - 2026
DA  - 2026/06/16
TI  - A TinyML-Based Edge-AI Module for Microbial Hotspot Detection and Environmental Sensing in Autonomous Field Robotics
BT  - Proceedings of the International Conference on Intelligent Systems for a Sustainable Future (ISSF 2026)
PB  - Atlantis Press
SP  - 492
EP  - 499
SN  - 2589-4919
UR  - https://doi.org/10.2991/978-94-6239-693-7_48
DO  - 10.2991/978-94-6239-693-7_48
ID  - Shrileka2026
ER  -