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)

Evaluation of a Video Generation Method Linking Dance and Scenes

Owing to the impact of COVID-19, the venues for dancers to perform have shifted from the stage to the media. In this study, we focus on the creation of dance videos that allow audiences to feel a sense of excitement without disturbing their awareness of the dance subject and propose a video generation method that links the dance and the scene by utilizing a sound detection method and an object detection algorithm. The generated video was evaluated using the Semantic Differential method, and it was confirmed that the proposed method could transform the original video into an uplifting video without any sense of discomfort. © 2023 SPIE.

An integrative framework for building organizational resilience through environmental scanning: a view of organizational information processing theory: MRN

PurposeThis study aims to investigate the impact of environmental scanning on organizational resilience through the mediation of organizational learning and innovation based on organizational information processing theory (OIPT) within Egyptian small and medium enterprises (SMEs) during the COVID-19 pandemic.Design/methodology/approachThis study adopted a cross-sectional design to collect the data used to carry out mediation analysis. A self-administered questionnaire was used to collect data from a sample consisting of 249 Egyptian SMEs. The smart partial least square structural equation modeling (PLS-SEM) technique was adopted to test the hypotheses.FindingsEnvironmental scanning does not have a direct effect on organizational resilience. However, organizational learning and innovation fully mediate the relationship between environmental scanning and organizational resilience.Research limitations/implicationsThe sample size was small, covering only Egyptian manufacturing SMEs. The results may differ in the service sector and other countries. The study was cross-sectional which is limited to tracing the long-term effects of environmental scanning, organizational learning and innovation on organizational resilience. Accordingly, a longitudinal study may be undertaken.Practical implicationsManagers in Egyptian SMEs should use signals from environmental scanning activities as input for learning and transforming business processes through innovation to develop organizational resilience.Originality/valueThis study is the first to investigate the role of environmental scanning in building organizational resilience through organizational learning and innovation based on the perspective of OIPT within Egyptian SMEs during the COVID-19 crisis.

GPU libraries speed performance analysis for RCWA simulation matrix operations

Rigorous Coupled Wave Analysis (RCWA) method is highly efficient for the simulation of diffraction efficiency and field distribution patterns in periodic structures and textured optoelectronic devices. GPU has been increasingly used in complex scientific problems such as climate simulation and the latest Covid-19 spread model. In this paper, we break down the RCWA simulation problem to key computational steps (eigensystem solution, matrix inversion/multiplication) and investigate speed performance provided by optimized linear algebra GPU libraries in comparison to multithreaded Intel MKL CPU library running on IRIDIS 5 supercomputer (1 NVIDIA v100 GPU and 40 Intel Xeon Gold 6138 cores CPU). Our work shows that GPU outperforms CPU significantly for all required steps. Eigensystem solution becomes 60% faster, Matrix inversion improves with size achieving 8x faster for large matrixes. Most significantly, matrix multiplication becomes 40x faster for small and 5x faster for large matrix sizes. © 2023 SPIE.

Exploring Social Media for Early Detection of Depression in COVID-19 Patients

The COVID-19 pandemic has caused substantial damage to global health. Even though three years have passed, the world continues to struggle with the virus. Concerns are growing about the impact of COVID-19 on the mental health of infected individuals, who are more likely to experience depression, which can have long-lasting consequences for both the affected individuals and the world. Detection and intervention at an early stage can reduce the risk of depression in COVID-19 patients. In this paper, we investigated the relationship between COVID-19 infection and depression through social media analysis. Firstly, we managed a dataset of COVID-19 patients that contains information about their social media activity both before and after infection. Secondly, We conducted an extensive analysis of this dataset to investigate the characteristic of COVID-19 patients with a higher risk of depression. Thirdly, we proposed a deep neural network for early prediction of depression risk. This model considers daily mood swings as a psychiatric signal and incorporates textual and emotional characteristics via knowledge distillation. Experimental results demonstrate that our proposed framework outperforms baselines in detecting depression risk, with an AUROC of 0.9317 and an AUPRC of 0.8116. Our model has the potential to enable public health organizations to initiate prompt intervention with high-risk patients. © 2023 ACM.

Automatic Detection of Lung Ultrasound Artifacts using a Deep Neural Networks approach

The COVID-19 pandemic has challenged many of the healthcare systems around the world. Many patients who have been hospitalized due to this disease develop lung damage. In low and middle-income countries, people living in rural and remote areas have very limited access to adequate health care. Ultrasound is a safe, portable and accessible alternative;however, it has limitations such as being operator-dependent and requiring a trained professional. The use of lung ultrasound volume sweep imaging is a potential solution for this lack of physicians. In order to support this protocol, image processing together with machine learning is a potential methodology for an automatic lung damage screening system. In this paper we present an automatic detection of lung ultrasound artifacts using a Deep Neural Network, identifying clinical relevant artifacts such as pleural and A-lines contained in the ultrasound examination taken as part of the clinical screening in patients with suspected lung damage. The model achieved encouraging preliminary results such as sensitivity of 94%, specificity of 81%, and accuracy of 89% to identify the presence of A-lines. Finally, the present study could result in an alternative solution for an operator-independent lung damage screening in rural areas, leading to the integration of AI-based technology as a complementary tool for healthcare professionals. © 2023 SPIE.

Video-Based Online Interactive System Using CNN Segmentation Method

In recent years, the COVID-19 has made it difficult for people to interact with each other face-to-face, but various kinds of social interactions are still needed. Therefore, we have developed an online interactive system based on the image processing method, that allows people in different places to merge the human region of two images onto the same image in real-time. The system can be used in a variety of situations to extend its interactive applications. The system is mainly based on the task of Human Segmentation in the CNN (convolution Neural Network) method. Then the images from different locations are transmitted to the computing server through the Internet. In our design, the system ensures that the CNN method can run in real-time, allowing both side users can see the integrated image to reach 30 FPS when the network is running smoothly. © 2023 IEEE.

Covid-19 Vaccination Stance Detection Using Natural Language Processing and Machine-Learning Algorithms

The coronavirus outbreak has resulted in unprecedented measures, forcing authorities to make decisions related to establishing lockdowns in areas most affected by the pandemic. Social Media have supported people during this difficult time. On November 9, 2020, when the first vaccine with an efficacy rate over 90% was announced, social media reacted and people around the world began to express their feelings about this vaccination. This paper aims to analyze the dynamics of opinion on COVID-19 vaccination, in which the civil society is highly manifested in the vaccination process. We compared classical machine learning algorithms to select the best performing classifier. 4,392 tweets were collected and analyzed. The proposed approach can help governments create and evaluate appropriate communication tools to provide clear and relevant information to the general public, increasing public confidence in vaccination campaigns. © 2022 Copyright for this paper by its authors.

Fake News Detection Using Transformer and Ensemble Learning Models

On social media, misinformation can spread quickly, posing serious problems. Understanding the content and sensitive nature of fake news and misinformation is critical to prevent the damage caused by them. To this end, the characteristics of information must first be discerned. In this paper, we propose a transformer-based hybrid ensemble model to detect misinformation on the Internet. First, false and true news on Covid-19 were analyzed, and various text classification tasks were performed to understand their content. The results were utilized in the proposed hybrid ensemble learning model. Our analysis revealed promising results, establishing the capability of the proposed system to detect misinformation on social media. The final model exhibited an excellent F1 score (0.98) and accuracy (0.97). The AUC (Area Under The Curve) score was also high at 0.98, and the ROC (Receiver Operating Characteristics) curve revealed that the true-positive rate of the data was close to one in this model. Thus, the proposed hybrid model was demonstrated to be successful in recognizing false information online. © 2022 IEEE.

Visual Analysis of Social Robots in Twitter on China Agenda Setting

With the development and progress of intelligent algorithms, more and more social robots are used to interfere with the information transmission and direction of international public opinion. This paper takes the agenda of COVID-19 in Twitter as the breakthrough point, and through the methods of web crawler, Twitter robot detection, data processing and analysis, aims at the agenda setting of social robots for China issues, that is, to carry out data visualization analysis for the stigmatized China image. Through case analysis, concrete and operable countermeasures for building the international communication system of China image were provided. © 2022 IEEE.

Integrating deep learning algorithms for the lung segmentation and body-part-specific anatomical classification with Medical Imaging and Data Resource Center (MIDRC)

Medical Imaging and Data Resource Center (MIDRC) has been built to support AI-based research in response to the COVID-19 pandemic. One of the main goals of MIDRC is to make data collected in the repository ready for AI analysis. Due to data heterogeneity, there is a need to standardize data and make data-mining easier. Our study aims to stratify imaging data according to underlying anatomy using open-source image processing tools. The experiments were performed using Google Colaboratory on computed tomography (CT) imaging data available from the MIDRC. We adopted the existing open-source tools to process CT series (N=389) to define the image sub-volumes according to body part classification, and additionally identified series slices containing specific anatomic landmarks. Cases with automatically identified chest regions (N=369) were then processed to automatically segment the lungs. In order to assess the accuracy of segmentation, we performed outlier analysis using 3D shape radiomics features extracted from the left and right lungs. Standardized DICOM objects were created to store the resulting segmentations, regions, landmarks and radiomics features. We demonstrated that the MIDRC chest CT collections can be enriched using open-source analysis tools and that data available in MIDRC can be further used to evaluate the robustness of publicly available tools. © 2023 SPIE.

HarDNet and Dual-Code Attention Mechanism based model for medical images segmentation

During the formation of medical images, they are easily disturbed by factors such as acquisition devices and tissue backgrounds, causing problems such as blurred image backgrounds and difficulty in differentiation. In this paper, we combine the HarDNet module and the multi-coding attention mechanism module to optimize the two stages of encoding and decoding to improve the model segmentation performance. In the encoding stage, the HarDNet module extracts medical image feature information to improve the segmentation network operation speed. In the decoding stage, the multi-coding attention module is used to extract both the position feature information and channel feature information of the image to improve the model segmentation effect. Finally, to improve the segmentation accuracy of small targets, the use of Cross Entropy and Dice combination function is proposed as the loss function of this algorithm. The algorithm has experimented on three different types of medical datasets, Kvasir-SEG, ISIC2018, and COVID-19CT. The values of JS were 0.7189, 0.7702, 0.9895, ACC were 0.8964, 0.9491, 0.9965, SENS were 0.7634, 0.8204, 0.9976, PRE were 0.9214, 0.9504, 0.9931. The experimental results showed that the model proposed in this paper achieved excellent segmentation results in all the above evaluation indexes, which can effectively assist doctors to diagnose related diseases quickly and improve the speed of diagnosis and patients’quality of life. Author

Stacking Classifier-based Automated Insurance Fraud Detection System

During the Covid-19 pandemic, the insurance industry's digital shift quickened, resulting in a surge in insurance fraud. To combat insurance fraud, a system that securely manages and monitors insurance processes must be built by combining a machine learning classification framework with a web application. Examining and identifying fraudulent features is a frequent method of detecting fraud, but it takes a long time and can result in false results. One of these issues is addressed by the proposed solution. By digitalizing the paper-based workflow in insurance firms, this paper intends to improve the efficiency of the existing approach. This method also aimed to improve the present approach's data management by integrating a web application with a machine learning stacking classifier framework experimented on a linear regression-based iterative imputed data for detecting fraud claims and making the entire claim processing and documentation process more robust and agile. © 2022 IEEE.

COVID-19 Associated Brain Fog and Neurocognitive Assessment

BACKGROUND/AIMS: In this study, we aimed to make detailed neurocognitive assessments of patients who presented with brain fog after coronavirus disease-2019 (COVID-19) infection and to investigate their complaints after one-year of follow-up. MATERIALS AND METHODS: Patients who had COVID-19, which was not severe enough to require intensive care, and who subsequently applied to neurology due to cognitive complaints were included in this study. A neurocognitive test battery was applied to those patients who agreed to detailed examination (n=16). This battery consisted of the following tests: mini-mental test, enhanced cued recall test, phonemic fluency, categorical fluency, digit span, counting the months backwards, clock-drawing, arithmetic operations, trail-making, cube copying, intersecting pentagons, and the interpretation of proverbs and similes. At one year, the patients were called by phone and questioned as to whether their cognitive complaints had persisted. Those patients with ongoing complaints were invited to the hospital and re-evaluated via cognitive tests. The results are presented in comparison with age-matched healthy controls (n=15). RESULTS: Almost all of the patients' scores were within the "normal" range. The Spontaneous recall of the patients was statistically significantly lower than the controls (p=0.03). Although there were decreases in executive functions and central processing speed (trail making-A, trail making-B and reciting the months backwards tests) in the patient group, these differences were not statistically significant (p=0.07;p=0.14 and p=0.22, respectively) compared to the controls. We observed that the cognitive complaints of the patients had disappeared by the one-year follow-up. CONCLUSION: In our patients with brain fog, most of whom had mild COVID-19, we observed that among all cognitive functions, memory domain was most affected compared to the controls. At the one-year follow-up, COVID-related brain fog had disappeared.

Characterizing food systems to better understand their vulnerabilities: a case study in Québec and São Paulo

Characterizing food systems, i.e., describing their organizational features, can help to generate a better understanding of the structural vulnerabilities that constrain transitions towards sustainable food security. However, their characterization across different economic contexts remains challenging. In this paper, by linking key concepts from research on food regimes, food system vulnerabilities and responsible innovation, we aim to characterize food systems in a developing and a developed economy to identify their shared vulnerabilities. We applied a case study design to characterize food production, processing and distribution in the province of Québec (Canada) and in the state of São Paulo (Brazil). In both cases, the processing and distribution stages have higher economic predominance when compared to the agricultural production stage. Furthermore, we observed concentration in a few activities in both food systems, with a shared focus on export-oriented supply chains. Vulnerabilities in both food systems include: (1) increased interdependence because some supply chains are export-oriented or depend on foreign labor and are, therefore, exposed to external risks;(2) concentration in a few activities, which threatens present and future local food diversity and (3) unequal power relations, making small and medium players vulnerable to decisions made by big players. The characterization developed in this study shows that the two food systems are mainly pursuing economic goals, following the institutional logics of the neoliberal food regime, which are not necessarily aligned with food security goals. It also exposes the presence of characteristics of ‘responsibility' that may eventually help overcome food systems' vulnerabilities and support transitions toward sustainability.

The reference and experience of food hygiene security in a major field activity

To summarize thepractice and experience of targeted food hygiene security measures in a major field activity of the army in order to provide references for diverse tasks. Considering the characteristics of heavy activity, field operations and the influence of COVID-19, a series of support measures related to food hygiene surveillance were strengthened. The first measure was review of recipes, health management and training of employees, procurement and storage of raw materials, warehouse management, processing and manufacturing management, disinfection of tableware, as well as food sample retention. Secondly, the control points that probably cause spread of COVID-19 in the phase of food service industry were analyzed, then relevant supervision and guidance were carried out from the aspects of employees and diners, foods of cold chain logistics, environment and emergency response plan. Finally, in order to assure the safety of food processing and crowd-gathered diet in the field, the following measures were guided to adopted including selecting the site of cooking and dining properly, cleaning the environment, making dishes using pure water and semi-manufactured foodstuff, keeping food sanitation in the course of transport and dinning, as well as supervising the robot machines for cooking automatically. The main experiences were listed as follows: promoting food safety awareness of the principal and the employees of the canteen, enhancing legal enforcement capacity and technical capacity of health supervisors, focusing on new risks related to food safety as well as reinforcing the management of health supervisors and employees in the field.

A Survey on Machine Learning Techniques for Multimodal Biomedical Signal Processing

In recent years, there has been a significant growth in the development of machine learning algorithms towards better experience in patient care. In this paper, a contemporary survey on the deep learning and machine learning techniques used in multimodal signal processing for biomedical applications is presented. Specifically, an overview of the preprocessing approaches and the algorithms proposed for five major biomedical applications are presented, namely detection of cardiovascular diseases, retinal disease detection, stress detection, cancer detection and COVID-19 detection. In each case, processing on each multimodal data type, such as an image or a text is discussed in detail. A list of various publicly available datasets for each of these applications is also presented. © 2023 IEEE.

Project transition to the digital Middle Ages via COVID-19 pattern

The analysis of current trends in the implementation of effective socio-economic solutions and their development under the influence of COVID-19 is made. The prospects of using innovative and telecommunication technologies, robotics, big data processing methods and knowledge management methods in the formation and management of global economic clusters were noted. The clustering of delivery robots under pandemic conditions by methods of machine learning was carried out. The peculiarities of COVID-19 assessment as the main formative factor influencing socio-economic decision-making on a global scale are disclosed. The necessity and possible consequences of adopting and implementing new decisions designed to minimize the negative effects of COVID-19 on Russian and global economies are discussed. It is noted that the design and development of innovations in the system of management and transfer of knowledge is an indispensable condition for the successful development of future socio-economic relations. On the basis of the obtained results conclusions are made about the background of the applied solutions, about the vector of their direction and makes it clear what should be paid special attention to when assessing the current situation in society and determine which solutions are most effective and how the social order should be transformed to successfully withstand the new challenges. © 2023 SPIE.

Analyzing COVID-Related Social Discourse on Twitter using Emotion, Sentiment, Political Bias, Stance, Veracity and Conspiracy Theories

Online misinformation has become a major concern in recent years, and it has been further emphasized during the COVID-19 pandemic. Social media platforms, such as Twitter, can be serious vectors of misinformation online. In order to better understand the spread of these fake-news, lies, deceptions, and rumours, we analyze the correlations between the following textual features in tweets: emotion, sentiment, political bias, stance, veracity and conspiracy theories. We train several transformer-based classifiers from multiple datasets to detect these textual features and identify potential correlations using conditional distributions of the labels. Our results show that the online discourse regarding some topics, such as COVID-19 regulations or conspiracy theories, is highly controversial and reflects the actual U.S. political landscape. © 2023 ACM.

Thermal Image Processing System for the measurement of body temperature using a Drone

In December 2019, several cases of pneumonia caused by SARS-CoV-2 were identified in the city of Wuhan (China), which was declared by the WHO as a pandemic in March 2020 because it caused enormous problems to public health due to its rapid transmission of contagion. Being an uncontrolled case, precautions were taken all over the world to moderate the coronavirus that undoubtedly was very deadly for any person, presenting several symptoms, among them we have fever as a common symptom. A biosecurity measure that is frequently used is the taking of temperature with an infrared thermometer, which is not well seen by some specialists due to the error they present, therefore, it would not represent a safe measurement. In view of this problem, in this article a thermal image processing system was made for the measurement of body temperature by means of a drone to obtain the value of body temperature accurately, being able to be implemented anywhere, where it is intended to make such measurement, helping to combat the spread of the virus that currently continues to affect many people. Through the development of the system, the tests were conducted with various people, obtaining a more accurate measurement of body temperature with an efficiency of 98.46% at 1.45 m between the drone and the person, in such a way that if it presents a body temperature higher than 38° C it could be infected with COVID-19. © 2023 IEEE.