Thesis subject

Sensor Solutions for Wellbeing Applications (MSc)

This project investigates the current use of sensor solutions for wellbeing applications, to support individuals living alone with self-limiting conditions.

Short description

Wellbeing devices installed in homes are used to support a person in their independence, safety and health management. Typically, solutions are divided into two categories, physical aids and remote surveillance. Both approaches assist in performing daily tasks, keeping track of medical conditions and automatically alerting healthcare staff when required. However, the success of such solutions requires the deployment of sensors around the home and/or on the person. These include motion sensors, cameras, fall detectors and communication hubs. Diverse wearable technologies include personal emergency response systems, wearable body networks for ECG, pulse oximeter, blood pressure and acceleration monitoring.
Yet there are many limitations with existing solutions. One such challenge is that technological developments and the growing Internet of Things (IoT) have increased the amount of digital information being produced. As a result, dealing with extremely large datasets is now commonplace and of specific interest to the research community for the development of intelligent, unobtrusive, cost-effective, assisted independent living platform for people living along with long-term health conditions. Big data processing requirements are now needed to collate the information into a meaningful output.
This project, therefore, involves an investigation into how sensor/IoT technologies are currently used for wellbeing applications in homes, and the conceptual design of a framework that is able to integrate varied IoT solutions into a meaningful output for the support of individuals living alone.


Objectives

  1. Investigate the current sensor/IoT technologies employed for wellbeing applications.
  2. Propose/design a framework/platform for sensor integration for the development of wellbeing applications.

    Tasks

    The work in this master thesis entails:

    • To collect full-text articles/PDFs/SLRs in the sensor, IoT and wellbeing/health domain.
    • To assess the solutions available to extract data from the scientific literature in a scalable and efficient manner.
    • To design or develop a conceptual framework for the integration of varied sensor types for assistive home living for individuals with self-limiting conditions.


    Literature

    • Hurst, W., Curbelo Montañez, C. A., Shone, N., & Al-Jumeily, D., An Ensemble Detection Model Using Multinomial Classification of Stochastic Gas Smart Meter Data to Improve Wellbeing Monitoring in Smart Cities, IEEE Access Special Issue on Urban Computing & Well-being in Smart Cities: Services, Applications, Policymaking Considerations, Vol. 8, pp. 7877-7898, 2020.
    • Curbelo Montañez, C. A., & Hurst, W., A Machine Learning Approach for Unemployment Detection using the Smart Metering Infrastructure, IEEE Access, 2020


    Requirements

    • Courses: No prior specific courses are required (but some knowledge of Big Data (INF-34306), Data Science Concepts (INF-34306), Machine Learning (FTE-35306) or Artificial Intelligence (INF-50306) would be ideal).
    • Required skills/knowledge: This project requires no previous specific learning track or prior skills training.

      Key words: Wellbeing, Sensors, IoT, Big Data

      Contact person(s)

      Dr. Will Hurst (will.hurst@wur.nl)
      Prof. Bedir Tekinerdogan (bedir.tekinerdogan@wur.nl)