Radar-based human activity recognition with adaptive thresholding towards resource constrained platforms.

Radar systems are increasingly being employed in healthcare applications for human activity recognition due to their advantages in terms of privacy, contactless sensing, and insensitivity to lighting conditions. The proposed classification algorithms are however often complex, focusing on a single domain of radar, and requiring significant computational resources that prevent their deployment in embedded platforms which often have limited memory and computational resources. To address this issue, we present an adaptive magnitude thresholding approach for highlighting the region of interest in the multi-domain micro-Doppler signatures. The region of interest is beneficial to extract salient features, meanwhile it ensures the simplicity of calculations with less computational cost. The results for the proposed approach show an accuracy of up to 93.1% for six activities, outperforming state-of-the-art deep learning methods on the same dataset with an over tenfold reduction in both training time and memory footprint, and a twofold reduction in inference time compared to a series of deep learning implementations. These results can help bridge the gap toward embedded platform deployment.

Graph neural network-based cell switching for energy optimization in ultra-dense heterogeneous networks.

The development of ultra-dense heterogeneous networks (HetNets) will cause a significant rise in energy consumption with large-scale base station (BS) deployments, requiring cellular networks to be more energy efficient to reduce operational expense and promote sustainability. Cell switching is an effective method to achieve the energy efficiency goals, but traditional heuristic cell switching algorithms are computationally demanding with limited generalization abilities for ultra-dense HetNet applications, motivating the usage of machine learning techniques for adaptive cell switching. Graph neural networks (GNNs) are powerful deep learning models with strong generalization abilities but receive little attention for cell switching. This paper proposes a GNN-based cell switching solution (GBCSS) that has a smaller computational complexity than existing heuristic algorithms. The presented performance evaluation uses the Milan telecommunication dataset based on real-world call detail records, comparing GBCSS with a traditional exhaustive search (ES) algorithm, a state-of-the-art learning-based algorithm, and the baseline without cell switching. Results indicate that GBCSS achieves a 10.41% energy efficiency gain when compared with the baseline and achieves 75.76% of the optimal performance obtained with ES algorithm. The results also demonstrate GBCSS' significant scalability and generalization abilities to differing load conditions and the number of BSs, suggesting this approach is well-suited to ultra-dense HetNet deployment.

A Secure Occupational Therapy Framework for Monitoring Cancer Patients' Quality of Life.

Once diagnosed with cancer, a patient goes through a series of diagnosis and tests, which are referred to as "after cancer treatment". Due to the nature of the treatment and side effects, maintaining quality of life (QoL) in the home environment is a challenging task. Sometimes, a cancer patient's situation changes abruptly as the functionality of certain organs deteriorates, which affects their QoL. One way of knowing the physiological functional status of a cancer patient is to design an occupational therapy. In this paper, we propose a blockchain and off-chain-based framework, which will allow multiple medical and ambient intelligent Internet of Things sensors to capture the QoL information from one's home environment and securely share it with their community of interest. Using our proposed framework, both transactional records and multimedia big data can be shared with an oncologist or palliative care unit for real-time decision support. We have also developed blockchain-based data analytics, which will allow a clinician to visualize the immutable history of the patient's data available from an in-home secure monitoring system for a better understanding of a patient's current or historical states. Finally, we will present our current implementation status, which provides significant encouragement for further development.