WHC 2025 Abstracts

Area 1 - Wearable HealthCare
Full Papers Short Papers

Area 1 - Wearable HealthCare

Full Papers
Paper Nr: 7
Title:

Powered Wearable Technologies for Dementia Care: Evaluating Activity Recognition Models and Dataset Challenges
Authors:

Mariana Carvalho, Inês C. Rocha, Marcelo Arantes, Ricardo Linhares, José Soares, António Moreira, João L. Vilaça, Demétrio Matos, Pedro Morais and Vítor Carvalho
Abstract: Dementia is a progressive neurological condition affecting millions worldwide, posing significant challenges for patients and caregivers. Wearable technologies integrated with artificial intelligence (AI) provide promising solutions for continuous activity monitoring, supporting dementia care. This study evaluates the performance of various AI models, including tree-based methods and deep learning approaches, in recognizing activities relevant to dementia care. While the first excelled in handling class imbalances and recognizing common activities, deep learning models demonstrated superior capabilities in capturing complex temporal and spatial patterns. Additionally, a comprehensive analysis of 30 datasets revealed significant gaps, including limited representation of elderly participants, insufficient activity coverage, short recording durations, and a lack of real-world environmental data. To address these gaps, future work should focus on developing datasets tailored to dementia care, incorporating long-duration recordings, diverse activities, and realistic contexts. This study highlights the potential of AI-powered wearable systems to transform dementia management, enabling accurate activity recognition, early anomaly detection, and improved quality of life for patients and caregivers.
Download
Paper Nr: 8
Title:

Development of a Proof-of-Concept Portable Electrostimulation Device for Lower Limbs Blood Flow Enhancement
Authors:

Ricardo Pinto, Ana Almeida, Inês Rocha, Diogo Carvalho, Alexander Oks, Miguel Carvalho, João L. Vilaça and Vítor Carvalho
Abstract: This paper presents the design and implementation of a proof of concept of a wearable electrostimulation device aimed at improving blood flow in the lower limbs. The portable system, integrated into wearable compression socks, delivers electrical pulses for muscular stimulation in specific areas of the leg, using conductive yarns in their structure, promoting better blood flow. This device addresses the growing sedentary lifestyle and the resulting health issues like poor circulation, which can lead to severe complications. It features Bluetooth Low Energy (BLE) communication for real-time session control via a mobile application. The preliminary results demonstrate effective electrical stimulation, validated through testing, ensuring the feasibility of the system.
Download
Paper Nr: 10
Title:

Gesture Recognition Through the Implementation of a Bimodal Acquisition System Using EMG and FMG Signals
Authors:

Nuno Pires and Milton P. Macedo
Abstract: This study is part of a broader project, the Open Source Bionic Hand, which aims to develop and control, in real time, a low-cost 3D-printed bionic hand prototype using signals from the muscles of the forearm. In this work, it is intended to implement a bimodal signal acquisition system, which uses EMG signals and Force Myography (FMG), in order to optimize the recognition of gesture intention and, consequently, the control of the bionic hand. The implementation of this bimodal EMG/FMG system will be described. It uses two different signals from BITalino EMG modules and Flexiforce™ sensors from Tekscan™. The dataset was built from thirty-six features extracted from each acquisition using two of each EMG and FMG sensors in extensor and flexor muscle groups simultaneously. The extraction of features is also depicted as well as the subsequent use of these features to train and compare Machine Learning models in gesture recognition, through MATLAB's Classification Learner tool. Preliminary results obtained from a dataset of three healthy volunteers, show the effectiveness of this bimodal EMG/FMG system in the improvement of the efficacy on gesture recognition as it is shown for example for the Quadratic SVM classifier that raises from 75,00% with EMG signals to 87,96% using both signals.
Download
Short Papers
Paper Nr: 5
Title:

Detection of Arm Swing Limitations in Simulated Parkinson’s Disease Gait Conditions: A Pilot Study
Authors:

Carlos Polvorinos-Fernández, Luis Sigcha, María Centeno-Cerrato, Elena Muñoz-Bellido, César Asensio, Juan Manuel López, Guillermo de Arcas and Ignacio Pavón
Abstract: Human gait is a biomechanical process vital to health, with abnormalities often linked to neurological disorders like Parkinson's disease (PD). In PD patients, arm swing during walking becomes asymmetric and reduced in amplitude, providing a potential biomarker for early diagnosis and monitoring disease progression. This pilot study focuses on detecting variations in arm swing amplitude and asymmetry using data collected from smartwatches worn by 24 participants under different gait conditions. Participants walked while carrying progressively heavier loads (0 kg, 2 kg, and 4 kg) to simulate restricted arm swing. Machine learning models were developed to classify these conditions using accelerometer and gyroscope data. Results showed that the K-Nearest Neighbours algorithm performed best, achieving up to 94.3% accuracy. Although the models effectively distinguished between load and no-load conditions, it was difficult to differentiate between different load levels. These findings highlight the potential of wearable devices for PD gait analysis, though further refinement and testing with PD patients are needed for clinical application.
Download
Paper Nr: 6
Title:

From Controlled to Free-Living Contexts: Expanding the Monitoring of Motor Symptoms in Parkinson’s Disease with Wearable mHealth Technologies
Authors:

María Centeno-Cerrato, Carlos Polvorinos-Fernández, Luis Sigcha, Guillermo de Arcas, César Asensio, Juan Manuel López and Ignacio Pavón
Abstract: This study examines the application of wearable mobile health (mHealth) technologies, specifically smartwatches equipped with inertial sensors, for the monitoring of Parkinson’s disease (PD). The aim is to investigate how the integration of the Monipar tool, designed to monitor supervised exercises, with the BioCliTe system, which continuously collects data during free-living activities, can improve the assessment of motor fluctuations and disease progression. The study proposes a set of free-living activities which can serve as characteristic indicators for assessing motor symptoms. By combining structured exercises with everyday tasks, this approach provides a more comprehensive evaluation of PD, capturing motor symptoms in both controlled and real-world environments. The research seeks to advance disease monitoring and patient care through more accurate tracking and the development of personalized treatment strategies.
Download
Paper Nr: 9
Title:

Exploring the EarMetrics Concept: The Bony Ear Canal as a Non-Pigmented Site for Photoplethysmography
Authors:

David Western, John Eveness, Beshoy Agayby, Xicai Alex Yue, Timothy Cox, Alistair Foster and Nick Gompertz
Abstract: Photoplethysmography (PPG) is a well-established form of physiological sensing, but persistent challenges include skin-tone-dependent variations in performance and trade-offs between performance and acceptance factors in site selection. We propose that the inner, bony portion of the ear canal may offer several advantages over established sites, including reduced sensitivity to skin tone. We support this position through a combination of anatomical analysis, colorimetry, and the first examples of PPG data collected from the bony ear canal, including pulse oximetry calculations during voluntary breathholds. Colorimetry revealed no statistically significant differences in lightness, chroma, or hue of the bony canal between subjects with lighter versus darker external skin tones. The commonly used ratio-of-ratios (R) method for pulse oximetry was sensitive to de-oxygenation from breathholds, showing statistically significant correlation with breathhold duration. Our results show that the bony ear canal is not pigmented, and that PPG signals can be obtained from this site, even in the presence of idiosyncracies such as earwax and myringosclerosis.
Download