Novel social distancing detector using local binary pattern in comparison with principal component analysis to improve accuracy

The objective is to detect Novel Social Distancing using Local Binary Pattern (LBP) in comparison with Principal Component Analysis (PCA). Social Distance deduction is performed using Local Binary Pattern(N=20) and Principal Component Analysis(N=20) algorithms. Google AI open Images dataset is used for image detection. Dataset contains more than 10,000 images. Accuracy of Principal Component Analysis is 89.8% and Local Binary Pattern is 93.9%. There exists a statistical significant difference between LBP and PCA with (p<0.05). Local Binary Pattern appears to perform significantly better than Principal Component Analysis for Social Distancing Detection. © 2023 Author(s).

Flexible work arrangements and gender differences in research during the COVID-19 period in Zimbabwean higher learning institutions

This study sought to investigate the impact of COVID-19-induced flexible work arrangements (FWAs) on gender differences in research outputs during COVID-19. A mixed research methodology was used, focusing on higher learning institutions in Zimbabwe. Purposive sampling was applied to select 250 researchers from the 21 registered universities in Zimbabwe. The study's findings revealed that institutions of higher learning in Zimbabwe did not provide the necessary affordances to enable both male and female academics to work from home effectively. The study also established that FWAs were preferred and appreciated by both male and female academics. However, whilst both male and female academics performed their teaching responsibilities without incident, unlike males, females struggled to find time for research, thus affecting professional growth and development negatively for female academics. Cultural traditions were found to subordinate females to domestic and caregiving responsibilities unrelated to their professions. The findings raise questions on the feasibility of the much-recommended FWAs for future work on female academics' research careers. Thus, without the necessary systems and processes to support female researchers, FWAs can only widen the gender gap in research outputs. This study contributes to the Zimbabwean higher learning institutions' perspective on how FWAs' policies and practices could be re-configured to assist female researchers in enhancing their research outputs as well as their career growth.

MIMIC model of teachers and students attitudes towards online learning during Covid-19: A gender perspective

Academic institutions around the globe have shifted to online learning because of the unpredictable spread of COVID-19. The present study aimed to compare teachers' and students' attitudes towards online learning during the pandemic and to examine the effects of gender differences on their attitudes. In study 1, we adapted the Test of eLearning Related Attitudes for Pakistani students in three steps: expert review, piloting, and validation. The individual and collective expert review was performed to adapt the teacher version into the student version using the Technique for Research of Information by the Animation of a Group of Experts (TRIAGE). We tested three sets of measurement invariance models for participants' status and gender in study 2. Data were collected from 289 university teachers (men = 158, women = 131) and 444 undergraduate students (boys = 156, girls = 287). The results demonstrated that both groups had highly positive yet different attitudes towards online learning. Teachers were more satisfied than students. Model fit was poor, and the overall factor structure, factor loadings, and intercepts varied across groups. Intergroup gender invariance illustrated heterogeneity in attitudes towards online learning favoring men teachers and boy students. Study strengths and implications for the promotion of a positive experience of online learning are discussed.

A radiomics-based model for the outcome prediction in COVID-19 positive patients through deep learning with both longitudinal chest x-ray and chest computed tomography images

The coronavirus disease 2019 (COVID-19) pandemic had a major impact on global health and was associated with millions of deaths worldwide. During the pandemic, imaging characteristics of chest X-ray (CXR) and chest computed tomography (CT) played an important role in the screening, diagnosis and monitoring the disease progression. Various studies suggested that quantitative image analysis methods including artificial intelligence and radiomics can greatly boost the value of imaging in the management of COVID-19. However, few studies have explored the use of longitudinal multi-modal medical images with varying visit intervals for outcome prediction in COVID-19 patients. This study aims to explore the potential of longitudinal multimodal radiomics in predicting the outcome of COVID-19 patients by integrating both CXR and CT images with variable visit intervals through deep learning. 2274 patients who underwent CXR and/or CT scans during disease progression were selected for this study. Of these, 946 patients were treated at the University of Pennsylvania Health System (UPHS) and the remaining 1328 patients were acquired at Stony Brook University (SBU) and curated by the Medical Imaging and Data Resource Center (MIDRC). 532 radiomic features were extracted with the Cancer Imaging Phenomics Toolkit (CaPTk) from the lung regions in CXR and CT images at all visits. We employed two commonly used deep learning algorithms to analyze the longitudinal multimodal features, and evaluated the prediction results based on the area under the receiver operating characteristic curve (AUC). Our models achieved testing AUC scores of 0.816 and 0.836, respectively, for the prediction of mortality. © 2023 SPIE.

E-Learning Readiness Assessment Using Machine Learning Methods

Assessing e-learning readiness is crucial for educational institutions to identify areas in their e-learning systems needing improvement and to develop strategies to enhance students' readiness. This paper presents an effective approach for assessing e-learning readiness by combining the ADKAR model and machine learning-based feature importance identification methods. The motivation behind using machine learning approaches lies in their ability to capture nonlinearity in data and flexibility as data-driven models. This study surveyed faculty members and students in the Economics faculty at Tlemcen University, Algeria, to gather data based on the ADKAR model's five dimensions: awareness, desire, knowledge, ability, and reinforcement. Correlation analysis revealed a significant relationship between all dimensions. Specifically, the pairwise correlation coefficients between readiness and awareness, desire, knowledge, ability, and reinforcement are 0.5233, 0.5983, 0.6374, 0.6645, and 0.3693, respectively. Two machine learning algorithms, random forest (RF) and decision tree (DT), were used to identify the most important ADKAR factors influencing e-learning readiness. In the results, ability and knowledge were consistently identified as the most significant factors, with scores of ability (0.565, 0.514) and knowledge (0.170, 0.251) using RF and DT algorithms, respectively. Additionally, SHapley Additive exPlanations (SHAP) values were used to explore further the impact of each variable on the final prediction, highlighting ability as the most influential factor. These findings suggest that universities should focus on enhancing students' abilities and providing them with the necessary knowledge to increase their readiness for e-learning. This study provides valuable insights into the factors influencing university students' e-learning readiness.

Research on the classification of CT images of COVID-19 by pre-training model based on self-attention mechanism

Nowadays, with the outbreak of COVID-19, the prevention and treatment of COVID-19 has gradually become the focus of social disease prevention, and most patients are also more concerned about the symptoms. COVID-19 has symptoms similar to the common cold, and it cannot be diagnosed based on the symptoms shown by the patient, so it is necessary to observe medical images of the lungs to finally determine whether they are COVID-19 positive. As the number of patients with symptoms similar to pneumonia increases, more and more medical images of the lungs need to be generated. At the same time, the number of physicians at this stage is far from meeting the needs of patients, resulting in patients unable to detect and understand their own conditions in time. In this regard, we have performed image augmentation, data cleaning, and designed a deep learning classification network based on the data set of COVID-19 lung medical images. accurate classification judgment. The network can achieve 95.76% classification accuracy for this task through a new fine-tuning method and hyperparameter tuning we designed, which has higher accuracy and less training time than the classic convolutional neural network model. © 2023 SPIE.

A Dynamic-Static Dual Input Deep Neural Network Algorithm for Diagnosing COVID-19 by Cough

The COVID-19 (corona virus disease 2019) has caused serious impacts worldwide. Many scholars have done a lot of research on the prevention and control of the epidemic. The diagnosis of COVID-19 by cough is non-contact, low-cost, and easy-access, however, such research is still relatively scarce in China. Mel frequency cepstral coefficients (MFCC) feature can only represent the static sound feature, while the first-order differential MFCC feature can also reflect the dynamic feature of sound. In order to better prevent and treat COVID-19, the paper proposes a dynamic-static dual input deep neural network algorithm for diagnosing COVID-19 by cough. Based on Coswara dataset, cough audio is clipped, MFCC and first-order differential MFCC features are extracted, and a dynamic and static feature dual-input neural network model is trained. The model adopts a statistic pooling layer so that different length of MFCC features can be input. The experiment results show the proposed algorithm can significantly improve the recognition accuracy, recall rate, specificity, and F1-score compared with the existing models. © 2023 Chinese Institute of Electronics. All rights reserved.

Hybrid Model Teaching in the Postepidemic Period: From Nucleic Acid to Antigen for the Fluorescence Analysis of SARS-CoV-2

Owing to the global spread of the coronavirus disease 2019 (COVID-19), education has shifted to distance online learning, whereas some face-to-face courses have been resumed with the improvement of the outbreak prevention and management situation, including a laboratory course for senior undergraduate students in chemical biology. Here, we present an innovative chemical biology experiment covering COVID-19 topics, which was created for third-year undergraduates. The basic principles of two nucleic-acid- and antigen-based diagnostic techniques for SARS-CoV-2 are demonstrated in detail. These experiments are designed to provide students with comprehensive knowledge of COVID-19 and related diagnoses in daily life. Crucially, the biosafety of this experimental manipulation was ensured by using artificial nucleic acids and recombinant protein. Furthermore, an interactive hybrid online-facing teaching model was designed to cover the key mechanism regarding PCR and serological tests of COVID-19. Finally, a satisfactory evaluation was obtained through a questionnaire, and simultaneously, reasonable improvements to the course design were suggested. The proposed curriculum provides all the necessary information for other instructors to create new courses supported by research. © 2023 American Chemical Society and Division of Chemical Education, Inc.

Politics Go "Viral": A Computational Text Analysis of the Public Attribution and Attitude Regarding the COVID-19 Crisis and Governmental Responses on Twitter

The U.S. confronts an unprecedented public health crisis, the COVID-19 pandemic, in the presidential election year in 2020. In such a compound situation, a real-time dynamic examination of how the general public ascribe the crisis responsibilities taking account to their political ideologies is helpful for developing effective strategies to manage the crisis and diminish hostility toward particular groups caused by polarization. Social media, such as Twitter, provide platforms for the public's COVID-related discourse to form, accumulate, and visibly present. Meanwhile, those features also make social media a window to monitor the public responses in real-time. This research conducted a computational text analysis of 2,918,376 tweets sent by 829,686 different U.S. users regarding COVID-19 from January 24 to May 25, 2020. Results indicate that the public's crisis attribution and attitude toward governmental crisis responses are driven by their political identities. One crisis factor identified by this study (i.e., threat level) also affects the public's attribution and attitude polarization. Additionally, we note that pandemic fatigue was identified in our findings as early as in March 2020. This study has theoretical, practical, and methodological implications informing further health communication in a heated political environment. [ FROM AUTHOR] Copyright of Social Science Computer Review is the property of Sage Publications Inc. and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full . (Copyright applies to all s.)

The influence of interdisciplinary literacy on learning effects among college students: the mediating effects of online physical education on learning behavior

IntroductionThe development of high-quality physical education curriculums is required in the information age. Interdisciplinary literacy and student learning behavior are two significant factors that affect the quality of teaching and learning. This study explores the relationship between interdisciplinary literacy (IDL) and learning effects (LE) among Chinese college students during the COVID-19 pandemic, as well as the mediating effects of online physical education learning behaviors (OPELB). This research aims to provide a reference for the development of high-quality online physical education. MethodsThe study involved 691 college students from 10 general universities in Shaanxi Province as research subjects. Descriptive statistics, Pearson correlation analysis, multiple regression analysis and Bootstrap testing were used to evaluate the mediating effects. ResultsThere was a significant positive relationship between the three variables of IDL, OPELB, and LE (p < 0.001). Multiple regression analysis found that IDL significantly and positively predicted LE and OPELB (p < 0.001), and OPELB predicted LE (p < 0.001). IDL among college students had a total effect of 0.816 on LE, with OPELB accounting for 22.67% of the mediated effect. DiscussionThis study demonstrates that OPELB has a partial mediating effect on IL and LE, and stable IDL and OPELB improve LE. Therefore, teachers should pay attention to improving students' IDL while encouraging them to develop better OPELB to achieve satisfactory learning outcomes.

The Syncretic Effect of Dual-Source Data on Affective Computing in Online Learning Contexts: A Perspective from Convolutional Neural Network with Attention Mechanism

Affective computing (AC) has been regarded as a relevant approach to identifying online learners' mental states and predicting their learning performance. Previous research mainly used one single-source data set, typically learners' facial expression, to compute learners' affection. However, a single facial expression may represent different affections in various head poses. This study proposed a dual-source data approach to solve the problem. Facial expression and head pose are two typical data sources that can be captured from online learning videos. The current study collected a dual-source data set of facial expressions and head poses from an online learning class in a middle school. A deep learning neural network using AlexNet with an attention mechanism was developed to verify the syncretic effect on affective computing of the proposed dual-source fusion strategy. The results show that the dual-source fusion approach significantly outperforms the single-source approach based on the AC recognition accuracy between the two approaches (dual-source approach using Attention-AlexNet model 80.96%;single-source approach, facial expression 76.65% and head pose 64.34%). This study contributes to the theoretical construction of the dual-source data fusion approach, and the empirical validation of the effect of the Attention-AlexNet neural network approach on affective computing in online learning contexts.

Mixup-Inf-Net: A data augmentation algorithm for segmentation of new coronary pneumonia infections

In 2020, the global spread of Coronavirus Disease 2019 exposed entire world to a severe health crisis. This has limited fast and accurate screening of suspected cases due to equipment shortages and and harsh testing environments. The current diagnosis of suspected cases has benefited greatly from the use of radiographic brain imaging, also including X-ray and scintigraphy, as a crucial addition to screening tests for new coronary pneumonia disease. However, it is impractical to gather enormous volumes of data quickly, which makes it difficult for depth models to be trained. To solve these problems, we obtained a new dataset by data augmentation Mixup method for the used chest CT slices. It uses lung infection segmentation (Inf-Net [1]) in a deep network and adds a learning framework with semi-supervised to form a Mixup-Inf-Net semi-supervised learning framework model to identify COVID-19 infection area from chest CT slices. The system depends primarily on unlabeled data and merely a minimal amount of annotated data is required;therefore, the unlabeled data generated by Mixup provides good assistance. Our framework can be used to improve improve learning and performance. The SemiSeg dataset and the actual 3D CT images that we produced are used in a variety of tests, and the analysis shows that Mixup-Inf-Net semi-supervised outperforms most SOTA segmentation models learning framework model in this study, which also enhances segmentation performance. © 2023 SPIE.

MOOCs Usage in Russian Higher Educational Institutions: Why Is Not There Any Increasing Demand for MOOCs During Emergency Distance Learning

The abrupt transition to distance learning during the outbreak of the COVID-19 pandemic triggered an urgent need for online resources at higher education institutes (HIEs). Creating analogues of traditional full-time courses demanded for competencies and time resources. In this case ready-made massive open online courses (MOOCs) were supposed to be the most obvious and fastest solution for HIEs. However, analytics demonstrated that educational institutions did not consider MOOC a promising option. This contradiction served as an incentive to conduct this research, which includes the analysis of both non-reactive (MOOCs platform analytics) and reactive (online survey and interviews with instructors) data. Based on our research, we can conclude that the reasons for not integrating MOOCs at Russian HIEs during the COVID-19 pandemic are the following: the peculiarities of MOOCs format, low motivation of instructors, administrative risks, and the uncertainty of HIEs' and national policies on MOOCs integration. This article will be useful for those who determine educational policy in Russia, university administrators, methodologists responsible for the development of digital educational technologies in HIEs, as well as researchers of higher education. © 2023 Moscow Polytechnic University. All rights reserved.

Explainable artificial intelligence approach towards classifying educational android app reviews using deep learning

Mobile application developers rely largely on user reviews for identifying issues in mobile applications and meeting the users' expectations. User reviews are unstructured, unorganized and very informal. Identifying and classifying issues by extracting required information from reviews is difficult due to a large number of reviews. To automate the process of classifying reviews many researchers have adopted machine learning approaches. Keeping in view, the rising demand for educational applications, especially during COVID-19, this research aims to automate Android application education reviews' classification and sentiment analysis using natural language processing and machine learning techniques. A baseline corpus comprising 13,000 records has been built by collecting reviews of more than 20 educational applications. The reviews were then manually labelled with respect to sentiment and issue types mentioned in each review. User reviews are classified into eight categories and various machine learning algorithms are applied to classify users' sentiments and issues of applications. The results demonstrate that our proposed framework achieved an accuracy of 97% for sentiment identification and an accuracy of 94% in classifying the most significant issues. Moreover, the interpretability of the model is verified by using the explainable artificial intelligence technique of local interpretable model-agnostic explanations. (PsycInfo Database Record (c) 2023 APA, all rights reserved)

A Comprehensive Review of Sound-Based Modalities for Automatic COVID-19 Detection using Deep Learning-Based Techniques

The World Health Organization has labeled the novel coronavirus illness (COVID-19) a pandemic since March 2020. It's a new viral infection with a respiratory tropism that could lead to atypical pneumonia. Thus, according to experts, early detection of the positive cases with people infected by the COVID-19 virus is highly needed. In this manner, patients will be segregated from other individuals, and the infection will not spread. As a result, developing early detection and diagnosis procedures to enable a speedy treatment process and stop the transmission of the virus has become a focus of research. Alternative early-screening approaches have become necessary due to the time-consuming nature of the current testing methodology such as Reverse transcription polymerase chain reaction (RT-PCR) test. The methods for detecting COVID-19 using deep learning (DL) algorithms using sound modality, which have become an active research area in recent years, have been thoroughly reviewed in this work. Although the majority of the newly proposed methods are based on medical images (i.e. X-ray and CT scans), we show in this comprehensive survey that the sound modality can be a good alternative to these methods, providing faster and easiest way to create a database with a high performance. We also present the most popular sound databases proposed for COVID-19 detection. © 2022 IEEE.

Performance Analysis of Learner Behavior Through Online Learning Using Learning Management System

This paper discusses the performance analysis of learner behavior through online learning using Learning Management System (LMS). The analysis is performed based on the survey of lecturers and students activities. The parameters of survey consist of the problems discussion which arise in the online learning, the level of student absorption of lecture material, the level of student attendance, and the feedback on lecturer performance carried out by students. Problems that arise in the online learning include lecturers are not being able to control as much as 37%, network disturbances are as much as 22%, students having difficulty understanding lecture material are as much as 19% which are indicated by students with D score of 10%, C score of 60%, and B score of 30%. Meanwhile 17% of students use LMS and the remaining 5% have no problems with the online learning. On the other hand, students have difficulty obtaining connection for online learning of 45%, do not have a quota of 28%, and lazy of 17%. Lecturer performance feedback carried out by students based on competency parameters of pedagogic, personality, professionalism, and social shows very good score. © 2023 IEEE.

Examination of Variables Affecting the Perceptions of Academic Performance of Higher Education Students during the Distance Education Process

COVID-19 has had serious consequences in all areas of social life, including education. In this period, distance education appeared as an inevitable solution. Even today, when the pandemic process is over and re-normalization has begun, online teaching environments have become such an indispensable part of education systems that it has been decided that a certain proportion of the courses will be conducted online in universities. For this reason, determining student experiences in online courses is important in planning the future of distance education. Since academic performance is the output of the teaching process, students' academic performance is one of the topics of interest in higher education research. There may be different factors affecting the academic performance of students in the distance education process, which imposes more responsibility on students and requires self-control. This study aimed to examine the relationship of academic performance in the distance education with home infrastructure, student interaction, computer skills, academic satisfaction. This research is based on a large-scale study, "The impact of the COVID-19 pandemic on the lives of higher education students", examining the pandemic's impact on higher education student perceptions in 2020. It has been observed that home infrastructure has a significant impact on the student's academic performance. The infrastructure increases the interaction of the student. When home infrastructure is taken as a control variable, students' computer skills are the highest predictor of their perception of academic performance, followed by their online interactions and, finally, perceived satisfaction. Today, pandemic conditions are still ongoing. In addition, even as the pandemic ends, online education has become an indispensable part of our education system. Therefore, the findings of the research would be beneficial for the ongoing planning process.

Effect of Distant Education on Children's Academic Achievement in Primary Schools During Corona Pandemic in Dubai Emirate- Field Study

This study aimed to examine the effect of distance education on the level of educational achievement of children during the Corona period in ten primary schools in the Emirate of Dubai. To achieve the objectives of the study the researchers adopted the descriptive analytical approach. The quantitative method of data collection had been applied using the electronic questionnaire tool consisted of four main axes for data collection and had been distributed to the study sample consisted of 190 students' parents and administrators selected by using simple random techniques. The results of the study indicated that the participation of students in the educational process, and in the establishment of appropriate educational programs and applications for the transmission to distance learning have contributed to reducing the negative effects of the process of shifting from traditional education / face-to-face education classroom teaching to virtual classroom (ZOOM).The study recommended the need for strengthening distance education mechanisms, which contribute in developing the student's interests, tendencies, attitudes, concentrating on the study material, and using of safe and secured electronic devices to increase the search for additional information to reach the correct knowledge. Also, the school administration should have good e-learning plan ahead with required financial credits that will help in overcoming the crisis and mange distance learning processes to reach future objectives successfully. © 2022 Owner/Author.

Embracing DDMT Teaching Model and Design Thinking for Organization Development

The multi-generational workforce presents challenges for organizations, as the needs and expectations of employees vary greatly between different age groups. To address this, organizations need to adapt their development and learning principles to better suit the changing workforce. The DDMT Teaching Model of Tsing Hua STEAM School, which integrates design thinking methodology, aims to address this challenge. DDMT stands for Discover, Define, Model & Modeling, and Transfer. The main aim of this study is to identify the organization development practices (OD) and gaps through interdisciplinary models such as DDMT and design thinking. In collaboration with a healthcare nursing home service provider, a proof of concept using the DDMT-DT model was conducted to understand the challenges in employment and retention of support employees between nursing homes under the healthcare organization. The paper highlights the rapid change in human experiences and mindsets in the work culture and the need for a design curriculum that is more relevant to the current and future workforce. The DDMT-DT approach can help organizations address these challenges by providing a framework for HR personnel to design training curricula that are more effective in addressing the issues of hiring and employee retention. By applying the DDMT-DT model, HR personnel can better understand the needs and motivations of the workforce and design training programs that are more relevant to their needs. The proof-of-concept research pilot project conducted with the healthcare nursing home service provider demonstrated the effectiveness of the DDMT-DT model in addressing the issues of hiring and employee retention. The project provides a valuable case study for other organizations looking to implement the DDMT-DT model in their HR practices. Overall, the paper highlights the importance of adapting HR practices to better suit the changing workforce. The DDMT-DT model provides a useful framework for organizations looking to improve their HR practices and better address the needs of their workforce.

Multifactor data analysis to forecast an individual's severity over novel COVID-19 pandemic using extreme gradient boosting and random forest classifier algorithms

AI and machine learning are increasingly often applied in the medical industry. The COVID-19 epidemic will start to spread quickly over the planet around the start of 2020. At hospitals, there were more patients than there were beds. It was challenging for medical personnel to identify the patient who needed treatment right away. A machine learning approach is used to predict COVID-19 pandemic patients at high risk. To provide input data and output results that execute the machine learning model on the backend, a straightforward Python Flask web application is employed. Here, the XGBoost algorithm, a supervised machine learning method, is applied. In order to predict high-risk patients based on their current underlying health issues, the model uses patient characteristics as well as criteria like age, sex, health issues including diabetes, asthma, hypertension, and smoking, among others. The XGBoost model predicts the patient's severity with an accuracy of about 98% after data pre-processing and training. The most important factors to the models are chosen to be age, diabetes, sex, and obesity. Patients and hospital personnel will benefit from this project's assistance in making timely choices and taking appropriate action. This will let medical personnel decide how much time and space to devote to the COVID-19 high-risk patients. providing a treatment that is both efficient and ideal. With this programme and the necessary patient data, hospitals may decide whether a patient need immediate care or not.