Research Outputs

Permanent URI for this communityhttps://hdl.handle.net/10539/37787

Browse

Subject: search.filters.subject.Remote sensing

Search Results

Now showing 1 - 2 of 2
  • Thumbnail Image
    Item
    Explainable early prediction of gestational diabetes biomarkers by combining medical background and wearable devices: a pilot study with a cohort group in South Africa
    (Institute of Electrical and Electronics Engineers, 2024) Norris, Shane; Kolozali, Sefki; White, Sara L.; Fasli, Maria; van Heerden, Alastair
    This study aims to explore the potential of Internet of Things (IoT) devices and explainable Artificial Intelligence (AI) techniques in predicting biomarker values associated with GDM when measured 13–16 weeks prior to diagnosis. We developed a system that forecasts biomarkers such as LDL, HDL, triglycerides, cholesterol, HbA1c, and results from the Oral Glucose Tolerance Test (OGTT) including fasting glucose, 1-hour, and 2-hour postload glucose values. These biomarker values are predicted based on sensory measurements collected around week 12 of pregnancy, including continuous glucose levels, short physical movement recordings, and medical background information. To the best of our knowledge, this is the first study to forecast GDM-associated biomarker values 13 to 16 weeks prior to the GDM screening test, using continuous glucose monitoring devices, a wristband for activity detection, and medical background data. We applied machine learning models, specifically Decision Tree and Random Forest Regressors, along with Coupled-Matrix Tensor Factorisation (CMTF) and Elastic Net techniques, examining all possible combinations of these methods across different data modalities. The results demonstrated good performance for most biomarkers. On average, the models achieved Mean Squared Error (MSE) between 0.29 and 0.42 and Mean Absolute Error (MAE) between 0.23 and 0.45 for biomarkers like HDL, LDL, cholesterol, and HbA1c. For the OGTT glucose values, the average MSE ranged from 0.95 to 2.44, and the average MAE ranged from 0.72 to 0.91. Additionally, the utilisation of CMTF with Alternating Least Squares technique yielded slightly better results (0.16 MSE and 0.07 MAE on average) compared to the well-known Elastic Net feature selection technique. While our study was conducted with a limited cohort in South Africa, our findings offer promising indications regarding the potential for predicting biomarker values in pregnant women through the integration of wearable devices and medical background data in the analysis. Nevertheless, further validation on a larger, more diverse cohort is imperative to substantiate these encouraging results.
  • Thumbnail Image
    Item
    Geological Remote Sensing
    (Acdemic Press, United Kingdom, 2021) Booysen, René; Nex, Paul A.M.; Gloaguen, Richard; Lorenz, Sandra; Zimmermann, Robert; Alderton, David; Elias, Scott A.
    The field of remote sensing has recently witnessed major innovations that have been translated to Earth science applications. Before they can be used, remote sensing data must be corrected for effects originating from the sensors, the platforms on which they are deployed, atmospheric characteristics, and geometrical constraints. When the data are calibrated and geolocated, they can be used either as physical quantities, such as reflectance and temperatures, or as images. The recent development of new sensors has permitted the remote measurement of a large area of the Earth's surface, with direct geological applications. Additionally, advances in machine vision, machine learning and artificial intelligence, combined with an unprecedented increase in computer processing power, have led to innovative remote sensing data processing techniques that simplify the handling of large amounts of complex data. As a consequence, it is now possible to characterize the geological settings of large areas with precision and even their changes through time. Remote sensing data are now directly integrated into modelling algorithms that describe surface and subsurface processes at different scales. Geological remote sensing currently encompasses multi temporal, multi-source and multi scale approaches. The retrieval of big data in disseminated archives, as well as (near) real time processing are the challenges that remain to be solved. These new applications in geology ensure cost efficient, safe, and rapid surveys and monitoring that not only benefit the research community but society at large.