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.

Performance Evaluation of State-of-The-Art 2D Face Recognition Algorithms on Real and Synthetic Masked Face Datasets

Face recognition systems based on Convolutional neural networks have recorded unprecedented performance for multiple benchmark face datasets. Due to the Covid-19 outbreak, people are now compelled to wear face masks to reduce the virus's transmissibility. Recent research shows that when given the masked face recognition scenario, which imposes up to 70% occlusion of the face area, the performance of the FR algorithms degrades by a significant margin. This paper presents an experimental evaluation of a subset of the MFD-Kaggle and Masked-LFW (MLFW) datasets to explore the effects of face mask occlusion against implementing seven state-of-the-art FR models. Experiments on MFD-Kaggle show that the accuracy of the best-performing model, VGGFace degraded by almost 40%, from 82.1% (unmasked) to 40.4% (masked). On a larger-scale dataset MLFW, the impact of mask-wearing on FR models was also up to 50%. We trained and evaluated a proposed Mask Face Recognition (MFR) model whose performance is much better than the SOTA algorithms. The SOTA algorithms studied are unusable in the presence of face masks, and MFR performance is slightly degraded without face masks. This show that more robust FR models are required for real masked face applications while having a large-scale masked face dataset. © 2023, Penerbit Akademia Baru. All rights reserved.

A Shuffling Building Block and Augmentation Parameter Tuning Techniques to Handle Small Medical Dataset

The recent COVID-19 outbreak showed us the importance of faster disease diagnosis using medical image processing as it is considered the most reliable and accurate diagnostic tool. In a CNN architecture, performance improves with the increasing number of trainable parameters at the cost of processing time. We have proposed an innovative approach of combining efficient novel architectures like Inception, ResNet, and ResNet-Xt and created a new CNN architecture that benefits Extreme Cardinal dimensions. We have also created four variations of the same base architecture by varying the position of each building block and used X-Ray, Microscopic, MRI, and pathMNIST datasets to train our architecture. For learning curve optimization, we have applied learning rate changing techniques, tuned image augmentation parameters, and chose the best random states value. For a specific dataset, we reduced the validation loss from 0.22 to 0.18 by interchanging the architecture's building block position. Our results indicate that image augmentation parameters can help to decrease the validation loss. We have also shown rearrangement of the building blocks reduces the number of parameters, in our case, from 5,689,008 to 3,876,528. © 2023 IEEE.

Classification of Chest X-Ray Images for COVID-19 Positive Patients Using Transfer Learning

The Coronavirus pandemic COVID-19 which has been declared as a pandemic by the World Health Organization has infected more than 212,165,567 and fatality figure of 4,436,957 as of 22nd August 2021. This infection develops into pneumonia which causes breathing problem;this can be detected using chest x-rays or CT scan. This work aims to produce an automated way of detecting the presence of COVID-19 infection using chest X-rays as a part of transfer learning strategy to extract numerical features out of an image using pre trained models as feature extractors. Then construct a secondary data set out of these features, and use these features which are simple numerical vectors represented in tabular form as an input to simple machine learning classifiers that work well with numerical data in tabular form such as SVM, KNN, Logistic regression and Naive Bayes. This work also aims to extract features using texture-based techniques such as GLCM and use the GLCM to obtain 2nd order statistical features and construct another secondary data set based on texture-based feature extraction techniques on images. These features are again fed into simple machine learning classifiers mentioned above. A comparison is done, between deep learning feature extraction strategies and texture-based feature extraction strategies and the results are compared and analyzed. Considering the deep learning strategies Mobile Net with SVM perform the best with 0.98 test accuracy, followed by logistic regression, KNN and Naive Bayes algorithm. With respect to GLCM feature extraction strategy, KNN with test accuracy with 0.96 performed the best, followed by logistic regression, SVM and naive Bayes. Overall performance wise deep learning strategies proved to be effective but in terms of calculation time and number of features, texture-based strategy of GLCM proved effective. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

Mapping the Suitability of Existing and Probable Isolation Facilities

This study aimed to map the accessibility of the existing isolation facilities in Cabagan, Isabela, and propose probable locations suitable for establishing isolation facilities using the Geographic Information System (GIS). Digital datasets of the current isolation facilities were used in the study, along with factors such as land uses, hazards, landfills, and road networks that should be taken into consideration when choosing potential locations for isolation facilities. These factors follow the guidelines set by the Department of Health (DOH). The processing and generation of layers related to the criteria were done using GIS techniques, specifically overlay analysis tools. In order to project an appropriate map of potential isolation facilities in Cabagan, Isabela, the layers were combined and overlaid. The existing isolation facilities are accessible to Milagros Albano District Hospital (MADH) since all of them are adjacent to national or barangay roads. More than half, or 65.38%, of the isolation facilities, belong to areas with low to moderate susceptibility to flooding, and 26.92% are in areas with high susceptibility to flooding. Furthermore, all isolation facilities are open to the public, with 53.85% of existing isolation facilities in residential areas, 7.69% in commercial areas, and 38.46% in agricultural areas. The suitability map of proposed isolation facilities was successfully generated, showing that 100% of the proposed isolation facilities are accessible from any road network in the municipality with low and moderate susceptibility to flooding and low susceptibility to landslides. © 2022 IEEE.

Concept Drift Aware Analysis of Learning Engagement During COVID-19 Pandemic Using Adaptive Windowing

Change is the only thing in the real world which has been known to last forever. It takes various forms and progressions, ranging from gradual in some cases and abrupt in the others to even constantly incremental in yet other cases like ageing. Machine learning (ML) algorithms, in its simplest definitions, use the statistical analysis of static past data records to make predictions about the future and have reached a fair amount of accuracy on diverse data sets across different application domains. There exists an inherent contradictory friction between real life analysis and machine learning models based on above definitions, and it gets compounded while capturing the ever-changing data from streaming sources. Concept drift is a principle used for description of unpredictable variations in streaming data sourced from the real world through a given time period. The drift phenomenon occurring even in a single feature, if left unaddressed leads to silent decay and can play havoc with the accuracy of a previously accurate ML model. With increasing prevalence and scale of real-world deployments of ML analytics, models cannot remain invariant to instability of data distributions and must adapt to concept drift. We analyse the occurrence and effect of concept drift in the COVID-19 online education data sourced from LearnPlatform edtech Company in this paper. The data set has almost 20 million entries related to engagement index and can be fairly assumed to be big data for processing purposes. A comparative case analysis for the accuracy of concept drift aware modelling using adaptive windowing (ADWIN) vis-a-vis the basic ML counterpart to predict the student engagement based on digital connectivity and education technology has been carried out for the study. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

Chaotic Binary Ant Lion Optimizer Approach for Feature Selection on Medical Datasets with COVID-19 Case Study

Binary version of the ant lion optimizer (ALO) are suggested and utilized in wrapper-mode to pick the best feature subset for classification. ALO is a recently developed bio-inspired optimization approach that mimics ant lion hunting behavior. Furthermore, ALO balances exploration and exploitation utilizing a unique operator to explore the space of solutions adaptively for the best solution. The difficulties of a plethora of noisy, irrelevant, and misleading features, as well as the capacity to deal with incorrect and inconsistent data in real-world subjects, provide rationale for feature selection to become one of the most important requirements. A difficult machine learning problem is to choose a subset of important characteristics from a vast number of features that characterize a dataset. Choosing the most informative markers and conducting a high-accuracy classification across the data may be a difficult process, especially if the data is complex. The feature selection task is usually expressed as a bio-objective optimization challenge, with the goal of enhancing the performance of the prediction model (data training fitting quality) while decreasing the number of features used. Various evaluation criteria are employed to determine the success of the suggested approach. The findings show that the suggested chaotic binary algorithm can explore the feature space for optimum feature set efficiently. © 2022 IEEE.

Perceptual Encryption-based Privacy-Preserving Deep Learning for Medical Image Analysis

The widespread adoption of deep learning (DL) solutions in the healthcare organizations is obstructed by their compute intensive nature and dependability on massive datasets. In this regard, cloud-services such as cloud storage and computational resources are emerging as an effective solution. However, when the image data are outsourced to avail such services, there is a privacy concern that the data should be kept protected not only during transmission but during computations as well. To meet these requirements, this study proposed a privacy-preserving DL (PPDL) scheme that enable computations without the need of decryption. The encryption is based on perceptual encryption (PE) that only hides the perceivable information in an image while preserves other characteristics that are necessary for DL computations. Precisely, we have implemented a binary classifier based on EfficientNetV2 for the COVID-19 screening in the chest X-ray (CXR) images. For the PE algorithm, the suitability of two pixel-based and two block-based PE methods was analyzed. The analysis have shown that when global contents are left unmodified (pixel-based PE), then the DL-based model achieved the classification accuracy same as that of the plain images. On the other hand, for block-based PE algorithms, there is up to 3% drop in the model's accuracy and sensitivity scores. © 2023 IEEE.

Rough Set: Utilizing Machine Learning for the Covid-19 Vaccine

Rough Set is a machine learning algorithm that analyses and determines important attributes based on an uncertain data set. The purpose of this study is to classify public interest in the Covid-19 vaccine. Vaccination is one of the solutions from the government that is considered the most appropriate to reduce the number of Covid-19 cases. Data collection was taken through a questionnaire distributed to the village community in Air Manik Village, Padang-West Sumatra, randomly as many as 100 respondents. The assessment attributes in this study are Vaccine Understanding (1), Environment (2), Community Education (3), Vaccine Confidence (4), and Cost (5), while the target attribute is the result that contains the community's interest or not to participate in vaccination. The analysis process is assisted using the Rosetta application. This study resulted in 3 reductions with 58 rules based on 100 respondents. This study concludes that the Rough Set algorithm can be used to classify public interest in the Covid-19 vaccine. Based on this research, it is hoped that it can provide information and input for local governments to be more aggressive in urging and encouraging the public to be vaccinated. © Published under licence by IOP Publishing Ltd.

Tweet Emotion Dynamics: Emotion Word Usage in Tweets from US and Canada

Over the last decade, Twitter has emerged as one of the most influential forums for social, political, and health discourse. In this paper, we introduce a massive dataset of more than 45 million geo-located tweets posted between 2015 and 2021 from US and Canada (TUSC), especially curated for natural language analysis. We also introduce Tweet Emotion Dynamics (TED) - metrics to capture patterns of emotions associated with tweets over time. We use TED and TUSC to explore the use of emotion-associated words across US and Canada;across 2019 (pre-pandemic), 2020 (the year the pandemic hit), and 2021 (the second year of the pandemic);and across individual tweeters. We show that Canadian tweets tend to have higher valence, lower arousal, and higher dominance than the US tweets. Further, we show that the COVID-19 pandemic had a marked impact on the emotional signature of tweets posted in 2020, when compared to the adjoining years. Finally, we determine metrics of TED for 170,000 tweeters to benchmark characteristics of TED metrics at an aggregate level. TUSC and the metrics for TED will enable a wide variety of research on studying how we use language to express ourselves, persuade, communicate, and influence, with particularly promising applications in public health, affective science, social science, and psychology. © European Language Resources Association (ELRA), licensed under CC-BY-NC-4.0.

On the Analysis of a Real Dataset of COVID-19 Patients in Alava

COVID-19 has been spread to many countries all over the world in a relatively short period, largely overwhelmed hospitals have been a direct consequence of the explosive increase of coronavirus cases. In this dire situation, the demand for the development of clinical decision support systems based on predictive algorithms has increased, since these predictive technologies may help to alleviate unmanageable stress on healthcare systems. We contribute to this effort by a comprehensive study over a real dataset of covid-19 patients from a local hospital. The collected dataset is representative of the local policies on data gathering implemented during the pandemic, showing high imabalance and large number of missing values. In this paper, we report a descriptive analysis of the data that points out the large disparity of data in terms of severity and age. Furthermore, we report the results of the principal component analysis (PCA) and Logistic Regression (LR) techniques to find out which variables are the most relevant and their respective weight. The results show that there are two very relevant variables for the detection of the most severe cases, yielding promissing results. One of our paper conclussions is a strong recommendation to the local authorities to improve the data gathering protocols. © 2022, Springer Nature Switzerland AG.

Stacked BiLSTM with ResNet50 for Medical Image Classification

The healthcare sector plays a significant role in the industry, where a client looks for the highest amount of care and services, no matter the cost. However, this sector has not satisfied society's presumption, even if this industry consumes a considerable percentage of the national budget. In the past, medical experts have been looking for smart medical solutions. This work focuses on accurate and early detection of illness from various medical images. Early detection not only aids in the development of better medications but can also save a life in the long run. Deep learning provides an excellent solution for early medical imaging in healthcare. This paper proposed a Stacked-based BiLSTM with Resnet50 Model using an AdaSwarm optimizer to classify and analyze the medical illnesses from the different medical image datasets. For this study, four medical datasets were used as benchmarks: Covid19, Pneumonia, Ma, and Lung Cancer. Accuracy, AUC, ROC, and F1 Score performance metrics are used to evaluate the prosed model from other models. The proposed model gives a mean ACCURACY, AUC, ROC, and F1 Score on these four datasets are 98%, 99%, 97%, and 98%, respectively. © 2022 IEEE.

Household Electricity Consumer Classification Using Novel Clustering Approach, Review, and Case Study

There is an increasing demand for electricity on a global level. Thus, the utility companies are looking for the effective implementation of demand response management (DRM). For this, utility companies should know the energy demand and optimal household consumer classification (OHCC) of the end users. In this regard, data mining (DM) techniques can give better insights and support. This work proposes a DM-technique-based novel methodology for OHCC in the Indian context. This work uses the household electricity consumption (HEC) of 225 houses from three districts of Maharashtra, India. The data sets used are namely questionnaire survey (QS), monthly energy consumption (MEC), and tariff orders. This work addresses the challenges for OHCC in energy meter data sets of the conventional grid and smart grid (SG). This work uses expert classification and clustering-based classification methods for OHCC. The expert classification method provides four new classes for OHCC. The clustering method is employed to develop eight different classification models. The two-stage clustering model, using K-means (KM) and the self-organizing map (SOM), is the best fit among the eight models. The result shows that the two-stage clustering of the SOM with the KM model provides 88% of overlap-free samples and 0.532 of the silhouette score (SS) mean compared to the expert classification method. This study can be beneficial to the electricity distribution companies for OHCC and can offer better services to consumers.

CNN-based Prediction of COVID-19 using Chest CT Images

The coronavirus disease (COVID-19) pandemic that is caused by the SARS-CoV2 has spread all over the world. It is an infectious disease that can spread from person to person. The severity of the disease can be categorized into five categories namely asymptomatic, mild, moderate, severe, and critical. From the reported cases thus, it has been seen that 80% of the cases that test positive with COVID-19 infection have less than moderate complications, whereas 20% of the positive cases develop severe and critical complications. The virus infects the lungs of an individual, therefore, it has been observed that the X-ray and computed tomography (CT) scan images of the infected people can be used by the machine learning-based application programs to predict the presence of the infection. Therefore, in the proposed work, a Convolutional Neural Network model based upon the DenseNet architecture is being used to predict the presence of COVID-19 infection using the CT scan images of the chest. The proposed work has been carried out using the dataset of the CT images from the COVID CT Dataset. It has 349 images marked as COVID-19 positive and 397 images have been marked as COVID-19 negative. The proposed system can categorize the test set images with an accuracy of 91.4%. The proposed method is capable of detecting the presence of COVID-19 infection with good accuracy using the chest CT scan images of the humans.

COVID-19 and psychology: Questionnaire data from two SCORE projects

In the early months of the COVID pandemic, numerous studies were done on the psychological implications of the pandemic. This paper details two independent replications of studies that were posted in PsyArXiv in March and April of 2020. These data reported in this manuscript were collected during the summer of 2020 and look at two separate phenomena associated with the COVID crisis (looking at conspiracy beliefs and COVID;looking at empathy and contagion control behaviours). The data reported in this manuscript are stored on the Open Science Framework and could allow for an evaluation of evolving nature of the psychological response to the COVID epidemic. (PsycInfo Database Record (c) 2022 APA, all rights reserved)

Towards more accurate and efficient human iris recognition model using deep learning technology

[...]in this study a new structure of deep CNN is presented as a high-level of security identification system which detects iris patterns automatically. The classification accuracy of the deep learning techniques can be improved by image preprocessing and augmenting the existing data better than collecting new raw data [25]. [...]the variety of available data can be greatly improved the performance for the training models. In this study, the raw dataset includes 460 iris images. [...]it was important to augment images for increasing the size of dataset usin image data augmenter tool in Matlab deep learning toolbox [26] for generating sets of augmented images and creating modified versions of images in the dataset such as images cropping, shifting, scaling, shearing, and flipping, as demostrated in Table 1. [...]CLAHE technique works on small areas called named tiles in the image by improving the contrast of each tile in the image, so that the output area histogram roughly matches a specified histogram.

SENTIMENT ANALYSIS MODEL FOR TWITTER ON COVID-19 VACCINE

Sentiment analysis is a classification technique that specializes in categorizing a body of texts into various emotions. This categorization had proven to be handy in classifying tweets into positive, negative, or neutral emotions. The focus of this paper is to determine the sentiment analysis of Indians and Americans. Using a lexicon-based analytic architecture and a dataset used for this research work was gotten from an online database Kaggle dataset called "All COVID-19 Vaccines Tweets". The dataset contains 125,906 entries with 16 columns with every country in the world from which tweets with location marked India and USA/United States were extracted. The analysis was done in Python Programming Software with the application of a python module TextBlob. The result shows that the Americans have larger positive sentiments over the Indians with 3.26%.

A DATASET OF LOCATION-BASED TWEETS IN AFRICA ON COVID-19 OUTBREAK

Twitter has proven to be a ready venue for democratizing opinion data even during the COVID-19 pandemic. During the protracted periods of the resultant lockdown, access to the internet allowed citizens of various nations and government agencies to express their opinions online using their Twitter handles. In this data article, a collection of 619,203 tweets posts were provided on COVID-19 in some selected countries in Africa. This data was collected over 180 days, from February 14, 2020, to August 14, 2020. This dataset can attract researchers' attention related to different fields of knowledge such as data science, natural language processing, social science, informatics, tourism, and infodemiology

Observational data from uncrewed systems over Southern Great Plains

Uncrewed Systems (UxS), including uncrewed aerial systems (UAS) and tethered balloon/kite systems (TBS), are significantly expanding observational capabilities in atmospheric science. Rapid adaptation of these platforms and the advancement of miniaturized instruments have resulted in an expanding number of datasets captured under various environmental conditions by the Department of Energy (DOE) Atmospheric Radiation Measurement (ARM) user facility. In 2021, observational data collected using ARM UxS platforms, including seven TigerShark UAS flights and 133 tethered balloon system (TBS) flights, were archived by the ARM Data Center (https://adc.arm.gov/discovery/#/, last access: 11 February 2022) and made publicly available at no cost for all registered users (10.5439/1846798) (Mei and Dexheimer, 2022). These data streams provide new perspectives on spatial variability of atmospheric and surface parameters, helping to address critical science questions in Earth system science research. This paper describes the DOE UAS/TBS datasets, including information on the acquisition, collection, and quality control processes, and highlights the potential scientific contributions using UAS and TBS platforms.

Capsule Network-Based Deep Transfer Learning Model for Face Recognition

Face recognition (FR) is a technique for recognizing individuals through the use of face photographs. The FR technology is widely applicable in a variety of fields, including security, biometrics, authentication, law enforcement, smart cards, and surveillance. Recent advances in deep learning (DL) models, particularly convolutional neural networks (CNNs), have demonstrated promising results in the field of FR. CNN models that have been pretrained can be utilized to extract characteristics for effective FR. In this regard, this research introduces the GWOECN-FR approach, a unique grey wolf optimization with an enhanced capsule network-based deep transfer learning model for real-time face recognition. The proposed GWOECN-FR approach is primarily concerned with reliably and rapidly recognizing faces in input photos. Additionally, the GWOECN-FR approach is preprocessed in two steps, namely, data augmentation and noise reduction by bilateral filtering (BF). Additionally, for feature vector extraction, an expanded capsule network (ECN) model can be used. Additionally, grey wolf optimization (GWO) combined with a stacked autoencoder (SAE) model is used to identify and classify faces in images. The GWO algorithm is used to optimize the SAE model’s weight and bias settings. The GWOECN-FR technique’s performance is validated using a benchmark dataset, and the results are analyzed in a variety of aspects. The GWOECN-FR approach achieved a TST of 0.03 s on the FEI dataset, whereas the AlexNet-SVM, ResNet-SVM, and AlexNet models achieved TSTs of 0.125 s, 0.0051 s, and 0.0062 s, respectively. The experimental results established that the GWOECN-FR technology outperformed more contemporary approaches.