ABSTRACT
The efforts to inoculate majority of the population have been slower than expected and this is especially true for lower income countries. This problem has caused a lot of worries and further accentuates the importance of timely and effective mass testing considering the emergence of newer variants. The RT-PCR is still the gold standard diagnostic test for COVID-19 detection, but its limitations has led researchers and scientists to explore supplementary screening methods. One effective tool to consider is Chest X-Ray (CXR) imaging and combining it with deep learning has piqued attention from the artificial intelligence (AI) community. To further contribute to this research area, this work focuses on creating, evaluating, and comparing lightweight and mobile-phone-suitable COVID-detecting models. These transfer learning models together with their corresponding dynamic-range quantized versions are first tested according to their classification performance. Afterwards, the models are pushed in a low-tier phone to measure their resource consumption and inference timings. Results show that the utilization of EfficientNetB0 and MobileNetV3 (Small & Large) architectures for transfer learning without any quantization can produce at least 91 % overall average accuracy for 3-class classification scheme. For systems requiring more efficient models, using the quantized versions of the transfer learning models particularly with EfficientNetB0 and MobileNetV3Large as foundation can render at most 0.79 % accuracy loss but still show more than 95% f1-scores for the COVID-19 class. © 2022 IEEE.
ABSTRACT
Digital Contact tracing with smartphone apps may help control the spread of serious pathogens, such as COVID-19. Such apps typically use peer-to-peer Bluetooth data transfer to record a contact. However, they suffer from low adoption rates, high false alarm contact indications, battery drain, and user privacy concerns. This paper proposes BECT or BEacon-based Contact Tracing, a contact tracing framework using static Bluetooth beacon devices installed in public or private places that periodically broadcast packets to nearby users that are stored as coins. Users that are positively diagnosed submit their coin IDs to a third-party service (e.g., local health authority) which can mark these coins as infected and disseminate them to other users. A match between a user's stored coins and an infected coin implies that the user has come in direct or indirect contact with an infected person. The BECT framework does not expose users' private data and conserves the device battery. We use MATLAB simulations to compare the performance of the BECT framework to phone-phone apps in a restaurant scenario and show that BECT has superior contact tracing performance. We also provide general deployment guidelines. © 2022 IEEE.
ABSTRACT
Android phones are one of the most common accessories used all over the world. Although once a luxury, it has now become a basic need for all generations. It is a multipurpose tool that can be used for all sorts of necessities and entertainment. Through our android app corona care, a mobile phone can be a helping hand for health care. This app can help prevent the deadly virus known as COVID-19 through plasma donation, consultation with doctors, setting up appointments, predicting corona risk assessment from symptoms using the Gaussian Naive Bayes method of predicting the risk percentage, providing emergency health services and updating users about the safety instructions about Covid-19. Our application consists of most features needed in a mHealth application that can provide necessary medical assistance to each and every household. © 2021 IEEE.
ABSTRACT
Covid-19 has forced millions of office workers to telework without proper training or job redesign. This paper investigates how telework frequency has affected the use of communication media, and subsequently knowledge sharing. A large sample of full-time Japanese employees with no prior telework experience is examined using mediation analysis. Results suggest that telework resulted in a lower use of face-to-face meetings and phone calls, and in a higher use of chat and virtual meetings, and had no effect on email use. Moreover, phone call, chat, and virtual meeting frequencies were found to mediate the relationship between telework frequency and knowledge sharing. These findings highlight the importance of both existing and newer communication media in offsetting the loss of face-to-face meeting opportunities, and show that companies have found ways to achieve effective knowledge sharing during mandatory telework. Firms should therefore invest in tools and training to speed up the adoption of instant messaging and virtual meeting solutions. © 2022, Springer Nature Switzerland AG.
ABSTRACT
Since COVID 19, there have been significant advancements in the field of teaching and learning. Academic institutions are going digital to provide their students more resources. Due to technology, students now have more alternatives to study and improve skills at their own pace. In terms of assessments, there has been a shift toward online tests. The absence of a physical invigilator is perhaps the most significant impediment in online mode. Henceforth, online proctoring services are becoming more popular, and AI-powered proctoring solutions are becoming demanding. In this project, we describe a strategy for avoiding the physical presence of a proctor during the test by developing a multi-modal system. We captured video using a webcam along active window capture. The face of the test taker is identified and analyzed to forecast his emotions. To identify his head pose, his feature points are identified. Furthermore, aspects including a phone, a book, or the presence of another person are detected. This combination of models creates an intelligent rule-based inference system which is capable of determining if any malpractice took place during the examination. © 2022 IEEE.
ABSTRACT
First Order Differential Equations is a topic that is prevalent in mathematics and is foundational to several engineering disciplines. Electrical engineering is a field where understanding first order systems is crucial. It is a cornerstone of topics such as transient electrical systems including RC and RL circuits. Despite this, many students struggle with conceptual understanding of this subject. The equations and mathematics can be overwhelming and frustrating, in part because it is often hard to visualize the concept. Today's students have plenty of distractions at their fingertips. In the midst of the COVID-19 pandemic, which has resulted in more online-learning, students will oftentimes browse the internet or pull out their phones if they begin feeling bored or frustrated with a topic. Simply put, today's students learn differently. They learn more intuitively and have shorter attention spans, and lessons should compensate for this with presentation methods that are clear, visual, and intuitive. The primary focus of this work is to help teachers explain, and learners to understand, the fundamental concepts of First Order Differential Equations through the use of intuitive and example-based approaches as they relate primarily to electrical engineering. This paper seeks to simplify the introduction to the topic of First Order Differential Equations into something that is clear and easy to comprehend. To accomplish this, the paper starts with a visual background of first order systems and an explanation of exponential growth vs. exponential decay. It then moves into (1) electrical examples, including the charging rate of cell phones and the idea of transient response in electrical systems such as RC and RL circuits, (2) electromechanical examples, including DC motors and heat transfer rates of different types of stoves, (3) various topics from other STEM disciplines, such as vehicle accelerations (dynamics), diffusion (physics), and currency depletion (economics). The paper concludes with a related brain teaser. The goal of this approach is to provide students with examples that translate textbook explanations to real life and help in understanding the material. We believe that when using these intuitive examples students tend to better understand first order systems, especially as they relate to the field of electrical engineering. This paper should be considered a work in progress. The presented information is meant to be supplemental in nature and not to replace existing textbooks or other teaching and learning methodologies. The contents of this work have been shared with students in a remote (Zoom-based) classroom setting and assessed following the lecture using an anonymous questionnaire. The initial results, based on 40 responses, indicate that this teaching method is effective in helping students comprehend the basic idea behind the concept of First Order Differential Equations. This intuitive and engaging approach to teaching and learning has been tested in the past for many topics including Statics (explaining center of gravity), Calculus (explaining integration and explaining derivation by chain, product, and quotient rules), Thermodynamics (explaining entropy), Statistics (explaining normal distribution), Differential Equations, Control Systems, Digital Signal Processing, Newton's Laws of Motion, and Computer Algorithms. In all of these cases, students highly praised the approach and found it to be very effective for learning. © American Society for Engineering Education, 2021