Early-Stage Detection of Covid-19 Patient using ML Model: A Case Study

The Covid-19 pandemic has drastically changed the daily living style of human beings by astonishing the cultural, educational, regional, business, social, and marketing activities within a limited boundary. It also has impacted the healthcare system globally and provided a lot of burden on the healthcare system. The circumstances that arose due to such a pandemic require a vital solution to deal with it. In such a situation, most innovative technologies have grown up to find alternative solutions to track the situation that arises due to Covid-19. Among all innovative technologies, IoT can be counted as the best approach to deal with such a type of pandemic due to its associated features of transmitting data from any remote location without human intervention. Such type of technology has the capability of providing connectivity among various medical devices either in hospitals or other deliberate places to deal with such type of pandemic. First of all, this paper introduces the concept of IoT to deal with the circumstances of the Covid-19 pandemic. Along with that, a framework of a real-time Covid-19 patient monitoring system has been proposed in this paper that can be utilized in the future. The proposed framework helps in monitoring the symptoms of Covid-19 infected patients. On the basis of that model, a case study is done on Covid-19 symptom data by using different ML algorithms. The findings indicate that all algorithms achieved an accuracy of more than 80% and RFT achieved the highest accuracy of 92%. Based on these findings, we believe that these algorithms will produce efficient and precise outcomes when applied to real-time symptom data. © Ismail Saritas. All rights reserved.

Fuzzy Modelling of Clinical and Epidemiological Factors for COVID-19

During this pandemic outbreak of COVID-19, the whole world is getting severely affected in respect of population health and economy. This novel virus has brought the whole world including the most developed countries to a standstill in a very short span like never before. The prime reason for this unexpected outburst of COVID-19 is lack of effective medicine and lack of proper understanding of the influencing factors. Here, the authors aim to find the effect of epidemiological factors that influence its spread using a fuzzy approach. For the same, a total of nine factors have been considered which are classified into risk and preventive factors. This fuzzy model supports to understand and evaluate the impact of these factors on the spread of COVID-19. Also, the model establishes a basis for understanding the effect of risk factors on preventive factors and vice versa. It is worth mentioning that this is the first attempt to analyze the effect of clinical and epidemiological factors with respect to COVID-19 using a fuzzy approach.

Feedback Analysis of Online Teaching Using SVM

Study examined how we can upgrade the quality of online teaching (Feng and Bienkowski in Enhancing teaching and learning through educational data mining and learning analytics. Department of Education, Office of Educational Technology [Feng M, Bienkowski M (2012) Enhancing teaching and learning through educational data mining and learning analytics. Department of Education, Office of Educational Technology]) in the upcoming years. Data were collected through the Google form which were filled up by the students. Feedback is the most important attribute of assessment as it provides students with a statement of their learning and advises how to improve. Result was helping to enhance the quality of online teaching in educational system and also provide the constituent which helps in improving the online teaching. We will use sentiment analysis (Kumar and Nezhurina in Sentiment analysis on tweets for trains using machine learning. Research Gate, p 10 [Kumar S, Nezhurina MI (2020) Sentiment analysis on tweets for trains using machine learning. Research Gate, p 10]) also. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

Feedback Analysis of Online Teaching Using SVM

Study examined how we can upgrade the quality of online teaching (Feng and Bienkowski in Enhancing teaching and learning through educational data mining and learning analytics. Department of Education, Office of Educational Technology [Feng M, Bienkowski M (2012) Enhancing teaching and learning through educational data mining and learning analytics. Department of Education, Office of Educational Technology]) in the upcoming years. Data were collected through the Google form which were filled up by the students. Feedback is the most important attribute of assessment as it provides students with a statement of their learning and advises how to improve. Result was helping to enhance the quality of online teaching in educational system and also provide the constituent which helps in improving the online teaching. We will use sentiment analysis (Kumar and Nezhurina in Sentiment analysis on tweets for trains using machine learning. Research Gate, p 10 [Kumar S, Nezhurina MI (2020) Sentiment analysis on tweets for trains using machine learning. Research Gate, p 10]) also. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

Antiphospholipid antibodies in patients with acute ischaemic stroke during the COVID-19 pandemic

Background: COVID-19 is associated with arterial thromboembolism, including acute ischaemic stroke (AIS). An association with antiphospholipid antibodies (aPL) has been noted;however, the prevalence of aPL and their clinical relevance in COVID 19-associated AIS are undefined. Aim(s): The aim was to assess the prevalence, subtypes and persistence of aPL in COVID-19- associated AIS. Method(s): We retrospectively reviewed AIS patients consecutively admitted to the Hyperacute Stroke Unit, University College London Hospitals, during local COVID-19 admission waves (18-Mar- 2020 to 31-May- 2020 and 01-Dec- 2020 to 24-Feb- 2021). Electronic patient records were reviewed for relevant study data, including COVID-19 and aPL status (in accordance with international consensus criteria). Result(s): 380 patients with AIS were identified (median age 74 years, range 24-99);35/380 (9.2%) had active/recent COVID-19 infection (median age 79 years, range 37-93). 132/380 patients were further analysed (those <=65 years), including 11/132 with COVID-19- associated- AIS. Overall, 105/132 (79.5% [including 31/32 (97.9%) patients < 50]), were screened for aPL, of which 26/105 (24.8% [including 7/31 (22.6%) patients < 50]) were aPL positive. In patients with AIS that were screened, aPL prevalence was significantly higher in those associated with COVID-19 than those not associated with COVID-19: 10/11 (90.9%) vs. 16/94 (17.0%), p< 0.05 (Fisher's exact test). Within the COVID-19 AIS group, 8/10 aPL positive patients had an isolated lupus anticoagulant (LA);1/10 was double aPL positive. Five of 10 patients with COVID-19- associated AIS underwent repeat aPL assessment: aPL were persistently positive beyond 12 weeks in 1/5, and transient in 4/5. In the non-COVID- 19 AIS group, 7/16 underwent repeat aPL testing, with 4/7 (57.1%) demonstrating persistence. aPL subtypes are shown in Table 1. Conclusion(s): Among AIS patients, aPL, mainly LA, are more frequent in those with COVID-19 infection. Patients with AIS (with or without COVID-19) found to have aPL should be retested for aPL persistence, potentially leading to a diagnosis of antiphospholipid syndrome.

Assessment of the psychological impact of COVID-19 pandemic on undergraduate medical students in India

BACKGROUND: Medical students who are prone to psychological stress due to their overburdened curriculum, are at an increased risk of getting adversely affected by the pandemic. The present study was planned to assess the anxiety level among undergraduate medical students across the country using generalized anxiety disorder scale (GAD-7). MATERIALS AND METHODS: In this online survey, anonymous data was collected through Google forms from undergraduate students from all the phases of MBBS course across the country from August 15, 2020, to October 15, 2020. Section I collected various demographic information, section II included GAD-7 questionnaire for assessing anxiety and section III had open- ended questions about their impending fear, uncertainties, and apprehensions. The data was expressed in percentage and association among the variables was determined using Chi-square test. Thematic analysis of the open-ended responses was done. RESULTS: Among the sample of 1208 students, 81% were from urban areas. During the pandemic, 77% were residing with their parents and 71% parents having stable jobs. Eighty percent students had no relative diagnosed with COVID-19, whereas 52% students had family members with comorbidity. The GAP score showed mild, moderate, and severe anxiety in 27, 24, and 16% students, respectively. Anxiety was significantly associated with rural setting and with COVID-19 positive or comorbid family member (P < 0.05). Open ended responses revealed that majority of the students were finding it difficult to cope with the academic stress at home but still did not want to join back. CONCLUSION: With such a high incidence of anxiety among medical students, it is pertinent to safeguard the mental health and implement efficient approaches to upkeep the scholastic, physical, emotional, and professional well-being of medical students during such vulnerable times. © Shahad A. Hafez et al., 2022;Published by Mary Ann Liebert, Inc. 2022.

Awareness, Perceived Risk, and Protective Behavior Towards Covid-19 Among Undergraduate Students of Delhi and NCR, India

Preventive measures are the best cure for any disease as they reduce the infection rate. Preventive measures are affected by knowledge, attitudes, and practices towards the disease. Therefore, this study aimed to assess the awareness, perceived risk, and protective behavior toward COVID-19 among undergraduate students of the Delhi and National Capital Region, India. An online questionnaire-based random survey was conducted amongst 605 undergraduate students to assess the demographic characteristics of participants, their level of awareness, perceived risk, and protective behavior regarding COVID-19. The overall awareness, perceived risk, and protective behavior for COVID-19 were found high in undergraduate students (0.000***,0.000***,0.000***). When variable (Gender, area of living, and subject studies) based analysis was performed among participants, a non-statistical significance difference was observed in total awareness among them (p>0.05) towards COVID-19 (p=0.996, 0.121, 0.937). Whereas Female, urban, and science participants were found to perceive the risk for COVID-19 more accurately in comparison to male, rural and non-science participants in total perceive risk analysis (p= 0.016**, 0.035**, 0.036**). However, urban participants showed more Total protective behavior as compared to the rural participants (p=0.048**) and there was no statistical significance difference in protective behavior in terms of Male/Female and Science/ non-science participants (p=0.189, 0.100). These findings will contribute to the continued regional/ global efforts to better understand preventive crisis response to the COVID-19 pandemic. This study emphasizes the need for conducting periodic webinars for educational intervention for all college students which could be useful to create more awareness.

Machine Learning Classification of X-RAY of the Diagnosis of Covid-19

Coronavirus, also known as covid-19, was a newly found disease in 2019. It is a highly transmissible virus that has a noxious effect on people all over the world. The most familiar indication of covid-19 are wheezing, cold and raised body temperature. Doctors and medical field experts need to assess at topmost priority a patient with symptoms relating to COVID-19. The most Critical task is to diagnose it with low resource settings. To help in detection of COVID-19, we propose the extraction of features from Chest X-ray images, a technology available at most hospitals and classifying them using machine learning. We compiled 3-class dataset of X-ray chest images including COVID-19, Viral pneumonia, normal cases. We labeled datasets then using Vertex AI and Vision AI trained the model. It automatically uses 80% of the dataset for training, 10% for corroborating and 10% for testing whereas Vision AI process the images for training. © 2022 IEEE.

The Role of Learning Analytics in Higher Education: A Strategy towards Sustainability

The impact of COVID-19 has been vast and enormous on every sector globally. But a tremendous change in the plan of action has been seen in the healthcare facilities and Education Sector. With the drastic shift from full-time offline modes of teaching to an online or hybrid model of teaching and learning, learning analytics has gained momentum. Learning Analytics can be broadly defined as a field focused on analyzing educational data to understand and improve learning processes. Precision in the education sector and its effectiveness in the learning process have been the areas of major academic investigations in the last decade of scholarly research work. This research study explores the available literature to make an empirical understanding of the development in this field of study. The primary objective is to explore the various constructs that lead to precise learning analytics, leading to the precision in higher education of the country. In alignment with the significant change in the functioning of the higher education institutions due to COVID-19, the study also focuses on the impact of COVID-19 in the development of learning analytics to promote a judicious learning environment for individuals and institutions. The study incorporates qualitative descriptive methodology for the analysis of the research objectives. The findings from this study corroborate the existing literature on learning analytics. It also aims to add a further scope of work in the same field. The study also outlines the significant drawback in promoting sustainable and precise learning in higher education. © 2021 IEEE.

A Blockchain-based Contactless Delivery System for Addressing COVID-19 and Other Pandemics

The coronavirus (COVID-19) pandemic has significantly impacted and changed our daily routines. Worldwide, people have had to adapt by undergoing remote work and self-quarantine. This situation has required transforming strategies for various logistics services for a variety of service providers, such as retail stores and restaurants. The concept of contactless delivery has emerged to help prevent the spread of the coronavirus. However, contactless delivery only reduces the direct interaction between the delivery personnel and the customer. In addition to peer-to-peer contact, items still go through insecure interactions between and among the delivery personnel and other unknown third parties. Even if the items are delivered without physical contact, concerns remain about their routes in the supply chain. In this paper, we present a novel blockchain-based framework to enable the traceability of products in the supply chain. This framework records and tracks delivery traces and the medical status of delivery personnel in a privacy-preserved manner, ultimately contributing to COVID-19 prevention and control. We build a Hyperledger Fabric-based blockchain prototype system as our testbed. Several smart contract functions are implemented and evaluated to show the efficiency of the proposed framework. In conjunction with the implementation and evaluation, we also perform comprehensive security and privacy analyses of this framework. © 2021 IEEE.

Prediction and Detection of COVID-19 Using Machine Learning

Presently, the discovery of COVID infection 2019 (Coronavirus) is one of the fundamental difficulties on the planet, given the fast spread of the illness. Ongoing insights show that the quantity of individuals determined to have Coronavirus is expanding dramatically, with more than 1.6 million affirmed cases;the sickness is spreading to numerous nations across the world. In this investigation, we dissect the frequency of Coronavirus appropriation across the world. We present a computerized reasoning strategy dependent on a profound convolutional neural organization (CNN) to distinguish COVID-19 patients utilizing genuine world datasets. Our framework inspects chest X-beam pictures to recognize such patients. Our discoveries demonstrate that such an investigation is important in Coronavirus conclusion as X-beams are helpfully accessible rapidly and at low expenses. Experimental discoveries acquired from 1000 X-beam pictures of genuine patients affirmed that our proposed framework is valuable in recognizing Coronavirus and accomplishes a F-measure scope of 95–99%. Our proposed framework can essentially help distinguish the most tainted urban communities, and it has uncovered that waterfront territories are intensely affected by the Coronavirus spread as the quantity of cases is fundamentally higher in those regions than in non-seaside zone. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

Evaluation of Data Mining Techniques and Its Fusion with IoT Enabled Smart Technologies for Effective Prediction of Available Parking Space

After experiencing the hard times of pandemic situations we learned that if we could have a smart system that can help us in automatic parking of the vehicles then it could be a great help to society. This idea motivated us to carry out this current work. Though, nowadays, in almost every application domain, IoT techniques are the buzzword. IoT techniques can also be used to achieve efficacy in predicting free available parking space in advance. But the biggest challenge with IoT techniques is that they generate numerous data, which makes its analysis intangible. It was realized that if IoT techniques can be fused with outperforming data mining techniques, more efficient predictions can be performed. Thus, for this purpose, the main objective of our paper is to firstly, select the most appropriate data mining technique, based on performance evaluation, and then to perform prediction of available parking space in advance by fusing it with IoT techniques. Due to the busy schedule, the drivers need to get information about free parking spaces in advance by using smart phones. With the help of this information, it will be easy for the drivers to park their vehicle in the exact location without wasting their precious time and will maintain social distancing in crowded areas too. Data mining techniques can play an important role in the prediction of available parking space, by extracting only relevant and important information when applied to the given dataset. For this purpose, a comparative analysis of five data mining techniques such as the Support Vector Machine, K-Nearest approach, Decision Tree, Random Forest, and Ensemble learning approaches are applied on PK lot data set by using Python language. For calculation of result anaconda (spyder) is used as a supportive tool. The main outcome of the paper is to find the technique that will give better results for the prediction of the available space and if we fused data mining techniques with IoT technologies results are improvised. Evaluation parameters that are used for finding the best technique are precision, recall, accuracy, and F1-Score. For numerical calculation of the results, the k-fold cross-validation method is used. As the empirical results are calculated using the Pk lot dataset, the decision tree outperformed the best among all the techniques that are selected for analysis.

Analysing time-frequency relationship between COVID-19 and FII trading activities using wavelet coherence analysis

Recently, the emerging markets like India have exhibited huge volatility due to trading activities of FIIs in the pandemic situation due to COVID-19. The fear of a lockdown situation during the pandemic raised concerns among the market participants and the investors that resulted in a steep fall of 27% in NIFTY50 during 10-23 March 2020. The infusion and withdrawal of portfolio investments have added research dimension as to whether the trading behaviour is due to pandemic and subsequent government actions or has resulted from the other markets like the oil crisis. This paper uses wavelet coherence analysis to examine the co-movement of COVID-19 cases and net investments from FIIs during the different phases of the lockdown period. © 2021 Inderscience Enterprises Ltd.

CNN-based person recognition system for masked faces in a post-pandemic world

With everyone now covering their faces with a face mask to avoid contagion of the COVID-19 virus, it becomes an increasingly difficult challenge for the facial recognition systems to identify people wearing masks. Algorithms devised before the pandemic for facial recognition often fail in this context, and consequently a need to understand the working of facial recognition algorithms when presented with occluded faces arises. This project aims to develop a new lightweight Convolutional Neural Network-based algorithm to resolve this issue. The proposed model gives a comparable accuracy with similar models developed in the past. Further, the proposed algorithm is used to create a robust system to ensure adherence of COVID-19 protocols in a real-world environment. © 2021 IEEE.