A Systematic Review of State-of-the-Art TinyML Applications in Healthcare, Education, and Transportation

Abstract

Tiny Machine Learning (TinyML) has emerged as a transformative paradigm enabling machine learning inference directly on ultra-low-power microcontrollers and edge devices. As AI expands beyond cloud computing to resource-constrained environments, TinyML offers promising solutions for latency-sensitive, bandwidth-efficient, and privacy-preserving applications. This paper presents a Systematic review of state-of-the-art TinyML applications across three critical domains: healthcare, education, and transportation. By analyzing 136 peer-reviewed publications from 2020 to 2025, we identify key trends, representative use cases, and the enabling technologies that support domain-specific deployments. Our review evaluates software frameworks, hardware platforms, model optimization techniques (e.g., quantization, pruning, and neural architecture search), and real-world deployment challenges such as energy consumption, memory limitations, and explainability. We further synthesize the metrics used to assess TinyML systems and highlight open research questions. Unlike previous surveys, our domain-centric approach offers a deeper contextual analysis of how TinyML is being adapted to solve real-world problems across diverse sectors. We conclude by outlining future directions and practical insights to guide researchers and practitioners in designing scalable, resilient, and ethically grounded TinyML systems.