Healthcare in Motion: Innovations in Mobility-integrated Health Systems

Permanent URI for this collection

https://hdl.handle.net/10125/109921

Browse

Recent Submissions

Now showing 1 - 4 of 4
  • Thumbnail Image
    Item
    Mobilizing Health Monitoring: The Development and Integration of a Health-eScooter System
    (2025-01-07) Warnecke, Joana; Bollmann, Julian; Ryll, Lukas; Singh, Himanshu; Deserno, Thomas
    In preventive medicine, continuous health monitoring through technology is essential. This paper presents an innovative approach using an eScooter equipped with sensors for electrocardiography and photoplethysmography to monitor vital signs during commutes. Integrating rental identity management with biomedical analytics, we ensure secure and private health data collection from shared eScooters. Our study involved 20 participants and demonstrated the feasibility of acquiring health data using a convolutional neural network (CNN) combined with a long short-term memory (LSTM) model-based algorithm and a user interface. The results show that around 65 percent of the driving time is utilizable for medical analysis. Additionally, we develop a user-friendly interface for the iOS app. The Health-eScooter exemplifies how everyday transport can serve as an effective tool for health monitoring, offering convenience and mobility, thereby paving the way for mobile and everyday health technology.
  • Thumbnail Image
    Item
    Driver Behaviour Detection Using Multimodal Physiological Signals and Regularized Deep Kernel Learning
    (2025-01-07) Kaveti, Pavan; Ganapathy, Nagarajan
    Integrating contextual cues from the driver, cabin, and surrounding environment is crucial for enhancing semi-automated vehicle safety. Current systems often rely on video streams to capture driver behaviours and environmental conditions, yet face challenges in low-light settings and privacy intrusion. In this study, we investigated multimodal physiological signals and Kernelized Convolutional Neural Networks (K-CNN) for assessing driver behaviour. For this, electrocardiography (ECG) and respiration (RSP) data were collected from 15 healthy volunteers wearing smart shirts in two driving scenarios. Signals were sampled at 256Hz and 128Hz, respectively. From this data we have extracted time-domain, frequency-domain and non-linear features using Neurokit2 toolkit. These features are fed to the K-CNN framework where task specific representation is extracted using Radial Basis Function, Linear, Polynomial Degree 2 and Polynomial Degree 3 kernels and these representation fed to 1D CNN to extract temporal features and these features are fused to detect driver behaviour using sigmoid. The proposed approach is able to classify driver behaviour states using multimodal data, achieving an average accuracy of 70.54% and an average F-score of 62.22% for linear kernel. Textile-based physiological data proved more reliable in classifying car driver behaviour states using K-CNN than with conventional machine learning techniques.
  • Thumbnail Image
    Item
    A Comparative Analysis on Using Low Earth Orbit and Geosynchronous Orbit Satellite Communication Systems to Support Telemedical Networks in Austere Environments
    (2025-01-07) Buhl, Victor; Kennedy, Sean; Barber, Don; Tummala, Murali; Mceachen, James; Rogers, Darren; Mceachen, John
    In remote locations, satellite communication is the only practical option for telemedical backhaul. Enabling telemedical applications over low earth orbit (LEO) and geosynchronous orbit (GEO) satellite communications links requires a detailed analysis of how the characteristics of these links impact telemedical applications. This article investigates the characteristics of Starlink LEO and Viasat GEO satellite communications to assess which is better suited to support telemedicine in remote locations. Through experimentation, the performance of medical application traffic over LEO, GEO, and terrestrial internet service provider links is compared to show how different link characteristics impact network traffic. Terrestrial internet service provider links provide a baseline for comparison since most applications perform optimally on high-speed terrestrial communication links. The analysis uses objective data to show that the non-interactive and near real-time application tested performs better on a GEO link, while the interactive near-real time and interactive telemetry with messaging applications tested perform better on LEO links. While GEO links add latency impacts to interactive communication that cannot be mitigated, this work reveals that the protocol stack for telemedical applications can be selected or designed to optimize performance over LEO satellite communication links.
  • Thumbnail Image
    Item