Machine Learning Models Tailored to Resource-Constrained Environments, with a Focus on Data Preprocessing Techniques
Noor Afza, M Suresh · 2025
In the era of pervasive computing, machine learning (ML) is increasingly deployed on resource-constrained devices, such as smartphones, IoT devices, and edge nodes. This research explores ML models designed for environments with limited computing power, memory, and energy capacity. It also delves into data preprocessing techniques that enhance the efficiency and accuracy of ML applications within these environments. The paper aims to identify efficient ML algorithms and preprocessing techniques to ensure robust model performance without compromising the device’s resource limitations.