No abstract

Regular retinal examinations can contribute to the management of both hypertensive and diabetic retinopathy. One of the most successful means of evaluating these retinopathies is by means of a fundus camera generating a fundus photograph. Patients in rural clinics unfortunately often lack the financial means to undergo regular examinations. This study produced a handheld ophthalmoscope that combines with a digital camera to capture retinal images. The images are transferred to a mobile phone and then sent to a central website for evaluation. The evaluation report is automatically returned to the mobile phone via SMS. The quality of the images was rated as acceptable for clinical use by medical specialists at the Department of Ophthalmology of the Health Sciences Faculty of Stellenbosch University, South Africa.

Tuberculosis is a common and potentially deadly infectious disease, usually affecting the respiratory system and causing the sound properties of symptomatic infected lungs to differ from non-infected lungs. Auscultation is often ruled out as a reliable diagnostic technique for TB due to the random distribution of the infection and the varying severity of damage to the lungs. However, advancements in signal processing techniques for respiratory sounds can improve the potential of auscultation far beyond the capabilities of the conventional mechanical stethoscope. Though computer-based signal analysis of respiratory sounds has produced a significant body of research, there have not been any recent investigations into the computer-aided analysis of lung sounds associated with pulmonary Tuberculosis (TB), despite the severity of the disease in many countries. In this paper, respiratory sounds were recorded from 14 locations around the posterior and anterior chest walls of healthy volunteers and patients infected with pulmonary TB. The most significant signal features in both the time and frequency domains associated with the presence of TB, were identified by using the statistical overlap factor (SOF). These features were then employed to train a neural network to automatically classify the auscultation recordings into their respective healthy or TB-origin categories. The neural network yielded a diagnostic accuracy of 73%, but it is believed that automated filtering of the noise in the clinics, more training samples and perhaps other signal processing methods can improve the results of future studies. This work demonstrates the potential of computer-aided auscultation as an aid for the diagnosis and treatment of TB.

Pleural effusion is one of the most widespread respiratory diseases in the world. Current diagnostic techniques include a combination of medical history and x-ray or CT scan imaging of the chest. However, these techniques are expensive and impractical in resource limited settings. We propose a new method based on sound transmission into the respiratory system through the chest wall. To evaluate this technique, a sine sweep signal with a frequency range between 100 Hz and 1000 Hz was transmitted into a phantom model of the human lungs capable of simulating healthy and effused conditions. The frequency response of the model under both conditions was computed and compared to evaluate the diagnostic performance of the new method. The results indicate that there is a significant difference between the frequency response of healthy and effused lungs, which suggests that the new technique may be suitable for the clinical diagnosis of pleural effusion.

In this project an electronic manufacturing process, namely ribbon cable assembly, was adapted for execution by intellectually disabled individuals. To make the work accessible to them, human error was controlled by a Poka-yoke approach. The design of the work process used industry standard tooling. Mistake-proofing design identified possible errors, and introduced mechanisms and tests that enabled the worker to avoid them. Test results were analysed using learning theory. It is concluded that intellectually disabled individuals can be enabled to perform the task within normal variation compared with a minimum task time, by using the Poka-yoke approach. Selection, however, is desirable. OPSOMMING'n Elektroniese vervaardigingsproses, naamlik platkabelsamestelling, word aangepas vir uitvoering deur intellektueel gestremde persone. Vir toeganklikheid deur hierdie groep, word menslike foute beheer deur die Poka-yoke-benadering. Die ontwerp van die werkproses maak gebruik van standaard nywerheidgereedskap. Die ontwerp fokus daarop om die moontlikheid van foute te identifiseer en kenmerke, meganismes, en toetsapparaat te inkorporeer om die voorkoms daarvan onmoontlik te maak. Toetsresultate word ontleed met leerteorie. Die slotsom is dat intellektueel gestremde persone bemagtig kan word, met die Poka-yoke-benadering, om hierdie taak uit te voer binne normale variasie vergeleke met die minimum taaktyd. Keuring is wel wenslik.