Internet of Things (IoT) devices often operate with limited resources while interacting with users and their environment, generating a wealth of data. Machine learning models interpret such sensor data, enabling accurate predictions and informed decisions. However, the sheer volume of data from billions of devices can overwhelm networks, making traditional cloud data processing inefficient for IoT applications. This paper presents a comprehensive survey of recent advances in models, architectures, hardware, and design requirements for deploying machine learning on low-resource devices at the edge and in cloud networks. Prominent IoT devices tailored to integrate edge intelligence include Raspberry Pi, NVIDIA’s Jetson, Arduino Nano 33 BLE Sense, STM32 Microcontrollers, SparkFun Edge, Google Coral Dev Board, and Beaglebone AI. These devices are boosted with custom AI frameworks, such as TensorFlow Lite, OpenEI, Core ML, Caffe2, and MXNet, to empower ML and DL tasks (e.g., object detection and gesture recognition). Both traditional machine learning (e.g., random forest, logistic regression) and deep learning methods (e.g., ResNet-50, YOLOv4, LSTM) are deployed on devices, distributed edge, and distributed cloud computing. Moreover, we analyzed 1000 recent publications on “ML in IoT” from IEEE Xplore using support vector machine, random forest, and decision tree classifiers to identify emerging topics and application domains. Hot topics included big data, cloud, edge, multimedia, security, privacy, QoS, and activity recognition, while critical domains included industry, healthcare, agriculture, transportation, smart homes and cities, and assisted living. The major challenges hindering the implementation of edge machine learning include encrypting sensitive user data for security and privacy on edge devices, efficiently managing resources of edge nodes through distributed learning architectures, and balancing the energy limitations of edge devices and the energy demands of machine learning.

Wearable technologies have developed relatively quickly in the modern years. This development has impacted the management of personal health and wellness to a considerable extent. The purpose of this study is to understand to what extent the interest of individuals in health and fitness, coupled with their general orientation towards technology, affects the acceptance of wearable technologies and related applications in the Saudi Arabian environment. Utilizing the UTAUT model, the research examines six hypotheses, revealing that health information- seeking behavior (β = 0.316, p < 0.001) and personal innovativeness in IT (β = 0.273, p < 0.001) are strong predictors of behavioral intention (BI) to adopt wearables. Performance expectancy (β = 0.186, p = 0.030) also significantly influences BI, while facilitating conditions (β = 0.267, p < 0.001) and BI (β = 0.528, p < 0.001) are crucial for actual use behavior (UB). These findings provide valuable insights for healthcare practitioners promoting wearable fitness devices, as they underscore the importance of enhancing public understanding of exercise benefits and active living. These would have significant implications for healthcare practitioners when promoting wearable fitness gadgets to the general population. In that respect, healthcare professionals could play significant roles in enhancing the general population’s understanding of physical exercise benefits and an active life by disseminating information and knowledge gained from these equipment and gadgets. Wearable technology companies can subsequently learn from and integrate such valuable inputs. At the same time, designers and marketing strategists design plans to satisfy the unique needs and tastes of the Saudi market. The results may further explain how personal health concerns and technical trends interact in embracing new, creative, health-focused solutions.