Medical Image Contrast Enhancement using Tuned Fuzzy Logic Intensification for COVID-19 Detection Applications

Recently, COVID-19 is spreading rapidly and fast detection of COVID-19 can save millions of lives. Further, the COVID-19 can be detected easily from computed tomography (CT) images using artificial intelligence methods. However, the performance of these application and methods are reduced due to noises presented in the CT images, which degrading the performance of overall systems. Therefore, this article is focused on implementation of an innovative method for quickly processing CT images of low quality, which enhances the contrast using fuzzy logic. This method makes use of tuned fuzzy intensification operators and is intended to speed up the processing time. Extensive experiments were carried out to test the processing capacity of the method that was proposed, and the results obtained demonstrated that it was capable of filtering a variety of images that had become degraded. © 2022 IEEE.

IoT-based COVID-19 Realtime Monitoring and Alerting System in Brunei

A novel coronavirus, severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2, also known as COVID-19) is a major problem for many countries in the world. Brunei is also affected by this COVID-19 pandemic in many ways. To alleviate the burden on the health ministry, we developed a low-cost, reliable Internet of Things (IoT) based real-time health monitoring system to diagnose early COVID-19 symptoms for patients at home. This diagnosis includes the three important physiological parameters such as body temperature, heart rate and oxygen saturation level (SpO2) in the blood. This system comes with an OLED LCD to display the three parameters. Apart from that, these parameters are also displayed on a mobile dashboard using the Cayenne IoT platform for easy access. This system was evaluated against many people, and the results were compared against the industry-standard pulse oximeters which are remarkably close and dependable. © 2022 IEEE.

Machine Learning based Identification of Covid-19 Future Forecasting

The propagation of Covid-19 disease spread across the world has put humanity in serious risk. The largest global economies are alarmed by the widespread infections or contagiousness. As Covid-19 is regarded as a viable concern in the eyes of humanity, the emerging Machine Learning [ML] models have the potential to estimate the number of prospective patients impacted by Covid-19. In particular, the value identification models, namely Exponential Smoothing (ES) and Support Vector Machine (SVM) are used by considering the significant factors of Covid-19. Every model is governed by three types of assumptions: the number of contaminated cases, fatalities, and recoveries. In some cases, the existing model fails to infer the patients' real outcomes. To mitigate this challenge, the proposed technique introduces the Exponential Smoothing (ES) model to extrapolate and predict the number of Covid-19 cases based on the effectiveness of preventive measures such as convivial segregation or confinement based on the disease severity. © 2022 IEEE.

Simultaneous microwave-assisted reduction and B/N co-doping of graphene oxide for selective recognition of VOCs

Herein, the influence of heteroatom domains on the volatile organic compound (VOC) detection properties of B/N co-doped graphene oxide nanostructures was investigated by using different boron (B) and nitrogen (N) sources, in the form of ammonia borane (AB) and tetramethylammonium borohydride (TMABH). XPS studies revealed the dependence of bonding configurations on the choice of the doping material, with AB co-doping leading to predominant hBN domains with a B : N ratio of 0.5, whilst TMABH co-doping resulted in predominantly BC3 and N-C bonds. Furthermore, Raman analysis showed that AB promoted rGO lattice restoration and the formation of larger crystallites. Upon VOC screening, the BN-rGO(AB) sample responded to both methanol and ethanol vapours, while the BN-rGO(TMABH) sample responded only to methanol vapour. Most importantly, B/N co-doping promoted better stability of up to similar to 3 weeks with improved selectivity to methanol and/or ethanol in a mixture of VOC vapours. The study showed the significance of B and N configurations on the charge carrier transport properties of B/N co-doped graphene nanostructures for application in room temperature VOC sensing devices.

F1-taught orthopaedic teaching for students (FOTS)

Introduction: F1 doctors, despite being expected to teach, have had reduced opportunity to do so during COVID-19. Medical students have also become increasingly concerned for upcoming exams due to time away from placements. A national orthopaedic teaching programme was designed to provide F1 doctors with opportunities to develop their teaching skills and synergistically improve students' confidence in performing clinical orthopaedic examinations. Method: A University Trauma & Orthopaedics society coordinated the teaching programme consisting of 6-weekly online sessions on each joint examination (shoulder, hip, knee, hand, ankle and lumbar spine). Each session was delivered by two F1 tutors. Pre- and post-session MCQs were provided to students to assess improvement in knowledge. Anonymous feedback forms were also disseminated. Results: From the 341 students that attended, 87.1% provided feedback. 86.2% felt that they had de-skilled due to time off, with a mean 15 weeks off from placement. Based on a 5-point Likert scale, students displayed a mean improvement in confidence (1.9±1.1, p<0.001) and MCQ scores (1.4±1.3, p<0.001) before and after the sessions. 91.6% of students agreed that the use of online teaching increased attendance. Of the 10 tutors, all reported improvement in confidence to teach and teaching skills. Conclusions: We demonstrate that online delivery of clinical orthopaedic examinations is effective and present our findings to encourage similar teaching programmes to be adopted at other locations and specialities.