Publications by authors named "Bhekumuzi Mathunjwa"
Background: Monitoring the lifestyles of older adults helps promote independent living and ensure their well-being. The common technologies for home monitoring include wearables, ambient sensors, and smart household meters. While wearables can be intrusive, ambient sensors require extra installation, and smart meters are becoming integral to smart city infrastructure.
View Article and Find Full Text PDFArticle Synopsis
- The study explores a motion-sensing mattress developed to prevent patient falls in care settings by detecting bed-exit intentions through pressure patterns from 30 sensing areas.
- It analyzes how sleep-related data from the mattress can provide comprehensive care information, improve caregiver support, and enhance monitoring of residents' wellbeing.
- Field trials conducted in a dementia nursing home in Taiwan demonstrated that the smart mattress care system (SMCS) effectively alerted caregivers to residents’ sleep patterns and abnormalities, ultimately aiding in better communication and care quality.
Article Synopsis
- The paper introduces a portable device-friendly algorithm for classifying arrhythmias using ECG recurrence plots and CNN classifiers, leveraging public databases for data input.
- It employs a two-stage classification process with ResNet-18 for detecting ventricular fibrillation and noise, and ResNet-50 for identifying other arrhythmias like atrial fibrillation and premature contractions.
- The proposed method demonstrates high accuracy rates (97.21% and 98.36%), improved memory efficiency for portable use, but faces challenges with data imbalance in the first stage due to grouping multiple arrhythmia types under a single label.
This study evaluates cardiovascular and cerebral hemodynamics systems by only using non-invasive electrocardiography (ECG) signals. The Massachusetts General Hospital/Marquette Foundation (MGH/MF) and Cerebral Hemodynamic Autoregulatory Information System Database (CHARIS DB) from the PhysioNet database are used for cardiovascular and cerebral hemodynamics, respectively. For cardiovascular hemodynamics, the ECG is used for generating the arterial blood pressure (ABP), central venous pressure (CVP), and pulmonary arterial pressure (PAP).
View Article and Find Full Text PDFHypertension affects a huge number of people around the world. It also has a great contribution to cardiovascular- and renal-related diseases. This study investigates the ability of a deep convolutional autoencoder (DCAE) to generate continuous arterial blood pressure (ABP) by only utilizing photoplethysmography (PPG).
View Article and Find Full Text PDF