Human activity recognition (HAR) has become increasingly popular, in part thanks to the increased use of wearable devices, including the most widely used device, the smartphone. Smartphones contain many sensors to collect large amounts of information and can be considered as a subset of the Internet of Things (IoT), enabling broad data generation.

This big data has in parallel enabled the testing of new scientific and technological advances in machine learning tools and especially deep learning. The objective of HAR is to detect and recognize the dynamic movements of the human body and the activities of individuals from sensor observations. Many of these sensors are within the IoT paradigm, an emerging technology that has improved the human living environment, as well as being a key source of big data generation.

The aim of this Special Issue is to explore, in depth, the latest machine learning models and techniques, including deep learning, as applied to IoT and HAR. All proposals in this direction are welcome and have a twofold advantage, improving the technical aspects of machine learning and deep learning as well as their application to the areas of IoT and HAR. Review articles which describe the current state of the art of machine learning and deep learning applied to the area of IoT and HAR are especially welcome.

Potential topics include but are not limited to the following:

• General IoT and HAR applications of machine learning and deep learning and data augmentation
• Applications based on cloud computing and blockchain architecture in the area of IoT and HAR
• IoT and HAR data generation-oriented applications
• Dashboard generation to visualize IoT and HAR trends
• Digital twins oriented to the areas of IoT and HAR
• Challenges in data quality, including sensor noise, and computational challenges for performing activity recognition in real time
• IoT and HAR-enabled digital twin
• Data-driven scenarios based on digital twin leveraging artificial intelligence (AI)
• Blockchain and security for digital twins
• Innovative deep learning architectures and algorithms for time series data and IoT