A Review of Developments and Metrology in Machine Learning and Deep Learning for Wearable IoT Devices

This research explores the integration of Artificial Intelligence (AI) in wearable devices, including smartwatches, fitness trackers, smart clothing, and smart eyewear. Machine Learning (ML) and Deep Learning (DL) play a crucial role in enhancing these devices, leveraging sophisticated algorithms within the Internet of Things (IoT) ecosystem. AI-powered wearables incorporate metrology and advanced computational techniques, with Convolutional Neural Network (CNN) and Recurrent Neural Network (RNN) driving applications in activity recognition, health monitoring, and personalized recommendations. The work presents case studies, highlighting AI applications in smart devices, such as stress detection via Heart Rate Variability, personalized exercise guidance, muscular activity monitoring, and real-time image recognition. Additionally, this review presents metrological approaches for evaluating AI performance in wearable systems, including data quality parameters such as accuracy, precision, and sampling rate. It also examines how algorithm selection influences model performance metrics and computational efficiency, which are critical for real-time and resource-constrained applications. Real-world implementations will illustrate the practical deployment of AI in commercial wearable products. Moreover, the research will address privacy and data security challenges associated with AI-driven wearable technology, ensuring the safeguarding of user information.