article · Neural Computing and Applications
Human activity recognition using inertial motion data is expanding rapidly across diverse sectors, including healthcare, sports, manufacturing, and commerce. This growth is largely enabled by the widespread presence of inertial sensors in everyday mobile and wearable devices such as smartphones and smartwatches. Effective recognition relies on analysing temporal observation series from these sensors to identify human actions, characteristics, and intentions. Key considerations for building viable systems include the utilisation of public benchmark datasets and the selection of appropriate feature extraction and learning methods, spanning classical handcrafted approaches to modern automatic representation learning. Furthermore, addressing real-world deployment challenges requires transfer learning techniques, embedded implementations directly on wearable hardware, and robust defences against adversarial attacks to protect user privacy and system security. Together, these elements reflect the essential data science pipeline required for modern, intelligent activity tracking systems.
Smart devices increasingly rely on built-in motion sensors to understand what people are doing in real time. Knowing how to process this sensor data reliably allows industries to develop responsive healthcare tools, fitness monitors, and workplace safety systems, while also ensuring that the sensitive personal data gathered by wearables remains protected against adversarial threats and privacy breaches.
The underlying technologies apply directly to wearable and mobile applications in healthcare monitoring, sports analytics, and smart manufacturing. Commercial developers looking to deploy products on edge hardware can draw upon embedded implementation methods and transfer learning to adapt models efficiently. Because the work reviews existing benchmark datasets, embedded methods, and security concerns rather than validating a specific product, the findings support early-stage development to applied deployment across consumer and industrial electronics.
AI-generated from the published abstract. Always read the original work before citing.
Abstract Human activity recognition (HAR) using inertial motion data has gained a lot of momentum in recent years both in research and industrial applications. From the abstract perspective, this has been driven by the rapid dynamics for building intelligent, smart environments, and ubiquitous systems that cover all aspects of human life including healthcare, sports, manufacturing, commerce, etc., which necessitate and subsume activity recognition aiming at recognizing the actions, characteristics, and goals of one or more agent(s) from a temporal series of observations streamed from one or more sensors. From a more concrete and seemingly orthogonal perspective, such momentum has been driven by the ubiquity of inertial motion sensors on-board mobile and wearable devices including smartphones, smartwatches, etc. In this paper we give an introductory and a comprehensive survey to the subject from a given perspective. We focus on a subset of topics, that we think are major, that will have significant and influential impacts on the future research and industrial-scale deployment of HAR systems. These include: (1) a comprehensive and detailed description of the inertial motion benchmark datasets that are publicly available and/or accessible, (2) feature selection and extraction techniques and the corresponding learning methods used to build workable HAR systems; we survey classical handcrafted datasets as well as data-oriented automatic representation learning approach to the subject, (3) transfer learning as a way to overcome many hurdles in actual deployments of HAR systems on a large scale, (4) embedded implementations of HAR systems on mobile and/or wearable devices, and finally (5) we touch on adversarial attacks, a topic that is essentially related to the security and privacy of HAR systems. As the field is very huge and diverse, this article is by no means comprehensive; it is though meant to provide a logically and conceptually rather complete picture to advanced practitioners, as well as to present a readable guided introduction to newcomers. Our logical and conceptual perspectives mimic the typical data science pipeline for state-of-the-art AI-based systems.
This page summarises published work. The authoritative version sits with the publisher.
DOI: 10.1007/s00521-023-08863-9
Is something wrong with this record? Report it or request removal.
Discussion
Have you built on this work, tried to replicate it, or seen it applied in practice? Share what you know. Verified researchers and MARATTO™ domain experts can open a discussion, and any member can reply. Contributions are reviewed before they appear.
No discussion yet. Open the first thread.
New to MARATTO™? Create a free account.
