Machine Learning for Human Activity Recognition

Dear Colleagues,

Human activity recognition (HAR) refers to the detection and recognition of human gestures and activities such as walking, falling, and drawing a circlein indoor and outdoor environments. HAR has different applications in security, health care, smart homes, and human–machine interaction. Wearable sensors (e.g., gyroscope and accelerometer), cameras (e.g., still image and video), and radio wireless signals (e.g., WiFi signals) are some methods for collecting data and sensing the environment.

Machine learning and deep learning in particular are promising approaches for HAR. Generally, these approaches have a large number of trainable parameters, require tremendous quantities of labelled training data, need major hyper-parameter tuning, and are resource-hungry in training and inference. These can cause difficulties in training and inference for HAR on edge and resource-limited devices. Pruning, tiny ML models by design, augmentation, and novel representation learning techniques can potentially overcome these challenges.

This Special Issue of /Journal of Imaging/ aims to feature reports of recent advances in machine learning for HAR and its applications. Particularly, innovative methods using graph representation learning, self-supervised, semi-supervised, few-shot, and unsupervised learning and implementation appraoches for real-world applications are welcomed.

Dr. Hojjat Salehinejad
Guest Editor

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Journal of Imaging is an international peer-reviewed open access monthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 1800 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

• human activity recognition
• wearables
• computer vision
• channel state information
• wifi for detection and sensing
• Internet of Things
• integrated sensing
• reconfigurable intelligence surfaces
• deep learning
• graph representation learning
• semi-supervised learning
• unsupervised learning
• few-shot learning