Recent trends in wearable signal analysis (WSA) tend to be on the continuous, non-invasive monitoring of key physiological parameters without significantly affecting daily behaviour or interfering with an individual's mental health status. In parallel, wearable sensor applications are accelerating as hardware technology advances, specifically in cognitive health care where wearable signal analysis is a key focus.
The acquisition and analysis of healthcare data from noisy and intricate sources is a great challenge. Feature extraction from such data is especially hard, due to the variability of the inputs and their potential to garner uncertain results even with rigorous processes. To surmount this difficulty, deep learning techniques are used in conjunction with (wearable sensor algorithms to conduct a thorough data analysis with limited computing and memory resources for accurate real-time outputs. However, these wearable sensors still need to be improved in capturing efficient strategies related to human body information.
Furthermore, the lack of effective methods to analyse data streaming from wearable sensors is preventing their broader applications such as in monitoring systems. The data collected usually have high dimensionality and multiple commotion sources, as well as a vast number of variable devices.
Nonetheless, with latest wearable sensors rapidly gaining popularity, in particular commercial activity trackers, and the requirements of clinical research becoming more stringent, the interest in applying deep learning methods to wearable data continues to grow. Deep learning can be used to address the challenges that come with the rise of wearable sensors being used for patient monitoring, and bring state-of-the-art performance both in professional and consumer applications.
In this Special Issue, we seek original, high-quality submissions in the domain of Deep Learning for Wearable Signal Analysis in Cognitive Healthcare. We welcome research that addresses the scalability and sustainability of relevant innovations for real-world applications, as well research investigating emerging sensing technologies at the proof-of-concept stage.
Submitted papers must not be under consideration elsewhere. We invite papers that consider, but are not limited to, the following topics:
- Deep learning for identification of leukocytes as an e-healthcare service
- Integrating wearable gadget for cardiac diagnostics through remote monitoring using deep learning
- Automated agent-based web of healthcare things framework for recognizing brain reaction from electroencephalography information using a bag-of-neural system
- A wearable medical sensor based on an actual emotional stress detection technique using deep learning
- Adjustable temperature and humidity detector with lattice design for voice recognition driven by deep learning
- The role of modelling aerobic activity calorie expenditure in elderly adults using a multilayer perceptron design using deep learning
- The role of emotional virtual assistants for real-time surveillance and co-facilitation of physician treatment using deep learning
- Automated detection of insomnia using adaptive filtering characteristics collected from electromyogram data using deep learning
- Intelligent machines enabled customizable support tools to improve the education of students with neuropsychiatric disorders
- Brain cancer identification with remote patient monitoring magnetic resonance devices using cognitive intelligence and clusters techniques using deep learning
- Dynamic temporal distortion technique for improved neurological disability identification using healthcare signal analysis using deep learning
- A predictive model for correlating music atmosphere and human feeling based on physiological data using deep learning
- Submission deadline: 30 September 2023
- First notification: 30 November 2023
- Revised version deadline: 31 January 2024
- Final notification: 31 March 2024
- Publication date: June 2024
- Gwanggil Jeon (Managing Guest Editor), Incheon National University, Korea. email@example.com
- Shiping Wen, University of Technology Sydney, Australia. shiping.Wen@uts.edu.au
- Abdellah Chehri, Royal Military College of Canada, Canada. firstname.lastname@example.org
- Ernesto Damiani, Università degli Studi di Milano Statale, Italy. email@example.com