Claim Extraction and Dynamic Stance Detection in COVID-19 Tweets

The information ecosystem today is noisy, and rife with messages that contain a mix of objective claims and subjective remarks or reactions. Any automated system that intends to capture the social, cultural, or political zeitgeist, must be able to analyze the claims as well as the remarks. Due to the deluge of such messages on social media, and their tremendous power to shape our perceptions, there has never been a greater need to automate these analyses, which play a pivotal role in fact-checking, opinion mining, understanding opinion trends, and other such downstream tasks of social consequence. In this noisy ecosystem, not all claims are worth checking for veracity. Such a check-worthy claim, moreover, must be accurately distilled from subjective remarks surrounding it. Finally, and especially for understanding opinion trends, it is important to understand the stance of the remarks or reactions towards that specific claim. To this end, we introduce a COVID-19 Twitter dataset, and present a three-stage process to (i) determine whether a given Tweet is indeed check-worthy, and if so, (ii) which portion of the Tweet ought to be checked for veracity, and finally, (iii) determine the author's stance towards the claim in that Tweet, thus introducing the novel task of topic-agnostic stance detection. © 2023 ACM.

Efficient COVID-19 Identification Using Deep Learning for IoT

Internet of Things (IoT) has made it possible to diagnose and treat patients remotely, as well as to expedite the transportation of essential drugs and medical equipment to locations that are geographically separated. This has occurred at a time when society has become more socially distant. During the Ebola and COVID-19 outbreaks, the Internet of Things (IoT) technology was put to use in remote patient monitoring and the management of the vaccine cold chain. Concurrently, this study reflects on the variables that are required for IoT to scale. Since December 2019, the COVID-19 outbreak on a worldwide scale has developed into a significant problem. In order for medical treatment to be successful, it is essential to make a prompt and accurate diagnosis of persons who may be infected with the COVID-19 virus. In order to put a halt to the spread of COVID-19, it is important to construct an automated system that is based on deep transfer learning and is capable of detecting the virus based on chest X-rays. The authors of this study present an internet-of-things (IoT) system that makes use of ensemble deep transfer learning to diagnose COVID-19 patients at an earlier stage. It is feasible to keep an eye on potentially hazardous COVID-19 incidents as they occur so long as suitable procedures are adhered to. Inceptions A variety of different deep learning models are included into the framework that has been proposed for the Internet of Things. According to the findings of the study, the method that was suggested assisted radiologists in accurately and quickly identifying patients who could have COVID-19. The proposed effort focuses on developing an effective identification system based on the COVID-19 standard for use in an IoT setting. © 2022 IEEE.

Humans, robots and artificial intelligences reconfiguring urban life in a crisis

Autonomous urban robots were introduced in Milton Keynes (MK), UK, in 2018 to automate on-demand grocery delivery. Two years later the COVID-19 pandemic rendered routine activities such as delivering groceries or visiting the supermarket unexpectedly unsafe for humans. The ensuing disruption provided opportunities to investigate the potentialities of robotic and autonomous systems to provide cities with resources for coping with unexpected situations such as pandemics, heatwaves and blizzards and ultimately to transform and reinforce urban flows, leading to new ways of living in the city that arise as a result of emerging human-robot constellations. The crisis accelerated the ongoing transformation in human-robot relationships and made its tensions and potentials visible. The case of MK suggests that the cognitive capabilities of urban AIs are not to be found exclusively in computer bits and human neurons but arise from encounters and contexts, with institutions, policies, practices and even the materiality of the city itself being crucial to the emergence of urban AI. Copyright © 2023 Valdez and Cook.

Automated system to detect social distancing among humans during covid pandemic situation

Maintaining the purported Social Separating is one of the essential and greatest ways to stop the new popular episode. Legislators are enacting restrictions on the standard of private distance between people in order to concur with this restriction. In light of this real-life occurrence, it is crucial to evaluate how consistent with realistic imperatives in our lives this is, in order to ascertain the causes of any prospective cracks in such distance obstacles and determine whether this portends an anticipated risk. In order to do this, we offer the Visual Social Removing (VSD) problem, which is defined as the automatic evaluation of the difference between the depiction of connected person aggregations and the private separation from an image.When this requirement is violated, it is vital for VSD to conduct painless research to determine whether people agree to the social distance restriction and to provide assessments of the degree of wellbeing of particular places. We first draw attention to the fact that measuring VSD involves more than simply math;it also suggests a deeper comprehension of the social behavior in the setting. The goal is to genuinely identify potentially dangerous circumstances while avoiding false alerts (such as a family with children or other family members, an elderly person with their guardians), all while adhering to current security protocols. Then, at that point, we discuss how VSD links to earlier research in social sign handling and demonstrate how to investigate fresh PC vision techniques that might be able to address this issue. Future issues about the viability of VSD systems, ethical repercussions, and potential application scenarios are the result. © 2023 IEEE.

Automated Fact-Checking of Articles Related to Neurodevelopmental Disorders

False claims or Fake News related to the health care or medicine field on Social Media have garnered increasing amounts of interest, especially in the aftermath of the COVID-19 pandemic. False claims about the pan-demic which spread on social media have contributed to vaccine hesitancy and lack of trust in the advise of medical professionals. If not detected and disproved early, such claims can complicate future pandemic responses. We focus on false claims in the field of Neurodevelopmental Disorders (NDDs), which is an umbrella term for a group of disorders that includes Autism, ADHD, Cerebral Palsy, etc. In this paper we present our approach to automated systems for fact-checking medical articles related to NDDs. We also present an annotated dataset of 116 web pages which we use to test our model and present our results. © 2022 IEEE.

COVID-19 Detection from Lung Ultrasound Images using a Fuzzy Ensemble-based Transfer Learning Technique

Due to the rapid spread of COVID-19 as a global pandemic, it has become increasingly critical to have fast, cheap, and reliable tools to assist physicians in diagnosing COVID19. Several automated systems using deep learning techniques have demonstrated promising results by analyzing Computed Tomography (CT-scan) or X-ray data to complement conventional diagnostic tools. In this paper, we aim to emphasize the role of point-of-care ultrasound imaging using deep learning as a tool to detect COVID-19 more prominently. Ultrasound imaging is non-invasive and widely available in medical facilities all over the world. This paper presents an ensemble technique based on Sugeno Fuzzy Integrals with convolutional neural networks (CNNs) as the base model. It classifies lung ultrasound (LUS) images of patients into COVID-19 and Non-COVID-19 categories. The lack of COVID-19 data makes it challenging to train a traditional CNN from scratch, so we have adapted a transfer learning approach instead of training the base classifiers VGG16, ResNet-50, and GoogLeNet. We apply the gained knowledge in the target domain of small lung ultrasound frames, considering the ImageNet dataset as the source domain. We have also adapted image pre-processing techniques to remove noises so that the model can only focus on specific features. Our proposed framework is evaluated on a publicly available dataset, achieving 96.7% accuracy. The proposed architecture outperforms the state-of-the-art method on the same dataset and proves to be a reliable COVID-19 detector. © 2022 IEEE.

Automated System and Machine Learning Application in Economic Activity Monitoring and Nowcasting

The amount of data is growing at an extraordinary rate each year. Nowadays, data is used in various fields. One of these areas is economics, which is significantly linked to data analysis. Policymakers, financial institutions, investors, businesses, and households make economic decisions in real-time. These decisions need to be taken even faster in various economic shocks, such as the financial crisis, COVID-19, or war. For this reason, it is important to have data in as frequent a range as possible, as only such data will reliably assess the economic situation. Therefore, automated systems are required to collect, transform, analyse, visualise, perform other operations, and interpret the results. This paper presents the concept of economic activity, classical and alternative indicators describing the economic activity, and describes the automated economic activity monitoring system. Due to the different economic structures and the different availability of data in different countries, these systems are not universal and can only be adapted to specific countries. The developed automated system uses working intelligence methods to predict the future values of indicators, perform clustering, classification of observations, or other tasks. The application’s developed user interface allows users to use different data sources, analyses, visualisations, or results of machine learning methods without any programming knowledge. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.

Real Time Safe Social Distance and Face Mask Detection using YOLO Algorithm and Deep Learning

The pandemic hit the world, and governments all around the world adopted drastic but necessary steps to stop it from spreading may be COVID or other versions. It's difficult to ensure that individuals follow these important social distance principles in large institutions. An automated system is necessary to enable easy tracking of such offenders. As a result, this system was designed to identify specific infractions in real-time. The proposed system's initial use is to recognize faces of people to decide whether they are wearing an approved mask or not. The other use is to evaluate whether the social distance is maintained between two people in the most efficient manner that is very accurate, and easy way possible, requiring the least amount of effort from supervisory authorities. © 2022 IEEE.

A Secured GUI based Flexible Automated System for Face Recognition and Suspicious Behaviour Prediction

Protection of each organization or campus is vital in recent times, as the crime rate in modern days is growing every day. Unauthorized entry of people will affect the secrecy of the data along with adverse economic effects. As the world is transforming towards a complicated technological style, computerized systems have been designed and implemented in many sectors. The rise in the crime rate necessitated the development of automated systems that can replace manual involvement which is tedious and time-consuming. However, these systems should be accurate unless of which the complete objective will go in vain. Much work has been carried out that makes use of biometric strategies and fingerprint-based for getting admission to structures. But these approaches have the constraints of getting mimicked or affecting the decision accuracy of decision making. In this pandemic situation, contactless design development is getting important. As the people are becoming negligible in following Covid precautions affecting the surrounding community, face mask detection systems are introduced that can yield a better solution. The current work proposes a novel system that serves the multiple functionalities of automated security with face recognition for attendance monitoring and secured entry as well as mask detection under Covid pandemic prevailing situations. The novelty of the current work is that it can also be used for identifying emotions and for automated attendance monitoring. © 2022 IEEE.

iCompass at CheckThat! 2022: Combining Deep Language Models for Fake News Detection

Users of social media tend to explore different platforms to obtain news and find information about different events and activities. Furthermore they read, share, publish news with no prior knowledge of the certainty of being real or fake. This necessitates the development of an automated system for fake news detection. In this paper we report a system and its output as part of CLEF2022 - CheckThat! Lab Fighting the COVID-19 Infodemic and Fake News Detection. Task 3 was carried out using two BERT base uncased and data preprocessing with stop-words removal, lemmatization. We achieve an F1 score of 0.339 on news classification on English dataset. © 2022 Copyright for this paper by its authors.

Mask Recognition with Computer Vision in the Age of a Pandemic

In the current age of coronavirus, monitoring and enforcing correct mask-wearing regulation in public spaces is of paramount importance. Specifically, there is a need to monitor whether people wear masks and whether they wear them correctly. However, there is a lack of automated systems to recognize correct mask-wearing compliance. In this paper, we propose a computer-vision-based solution to the problem of mask-wearing monitoring. In particular, we propose a convolutional neural network to recognize images of people wearing masks correctly, people wearing masks incorrectly, and people not wearing masks at all. Our proposed model is shown to predict correct mask-wearing practices with over 98% accuracy. The model can be easily deployed as an automated system to screen people entering indoor spaces, and can replace current manual, time-consuming, temperaturescreening practices. Such applications can serve as an important tool to help reduce transmission rates during the current pandemic. © 2020, by the authors. All rights reserved.

Machine Learning based Real-Time Face Mask Detection System

In the pandemic situation, people are quickly affected in our day-to-day life. Wearing the mask is being normal nowadays for controlling the spread of COVID-19. The government and public sectors will ask the public/customers to wear masks to control the spread of COVID-19. Mask detection has become an essential task to help society's well-being to protect our life. This paper provides a simplified approach to detect face masks using basic ML packages in PYTHON like tensor Flow, Keras, OpenCV. This paper helps to analyze an image to detect the face correctly and then identifies whether there is a mask on the face or not. It is a surveillance task to perform the security to create awareness among the people. This method attains the accuracy of scanning face up to 96.88% and 92.39% respectively. This detection is based on two datasets, one is about without wearing a mask and with wearing a mask. This mechanism helps to detect the mask on people's faces in real-time scenarios. © 2022 IEEE.

An Automated System for Facial Mask Detection and Social Distancing during COVID-19 Pandemic

Since December 2019, the world has started getting affected by a widely spreading virus which we all call the coronavirus. This virus is spread all across the globe, causing many severe health problems and deaths too. COVID-19 is spread when a healthy person comes in contact with the droplets generated when an infected person coughs or sneezes. So, the WHO has suggested some precautionary measures against the spread of this disease. These measures include wearing a mask in public, maintaining social distancing, avoiding mass gatherings. To help reduce the virus’ spread, in this paper, we are proposing a system that detects unmasked people, identifies them, checks if social distancing is followed or not, and also provides a feature of contact tracing. The proposed system consists of mainly two modules: face mask detection and social distancing. There are two more modules which include face recognition and contact tracing. We used two datasets for training our models. First one to detect masks on faces. For this purpose, we collected the image dataset from GitHub and Kaggle. And, the second dataset was for face recognition in which we took our own images for training purposes. It is hoped that our model contributes toward reducing the spread of this disease. Along with COVID-19, this model can also help reduce the spread of similar communicable disease scenarios. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

Automated Diagnosis of Pneumonia through Capsule Network in conjunction with ResNet50v2 model

The world has witnessed one of the most devastating phases in the history of mankind after being hit with the COVID-19 pandemic which still continues to spread rapidly all across the globe. The disease is believed to majorly cause respiratory disorders in humans. Detecting COVID-19 patients through X-Ray images is the only way to slow down the expansion of the pandemic, detecting pneumonia has equally become a demanding task as both exhibit similar properties of affecting the human lungs. Pneumonia is said to be an illness caused by a bacteria in the alveoli of lungs that may accompany to the death of an individual if its treatment is ignored. Hence, developing an automated system to detect the disease can be beneficial to the human race. With continuous progressions in the expertise of deep learning and machine learning;its fundamentals are observed to continuously contribute towards analysis of medical images and classification of patients exhibiting the disease. In this work, we appraise the concepts of ResNet50v2 model and capsule network to predict the affected and unaffected patients using chest X-Ray images. The authors propose a novel classification framework consisting of a convolutional layer, primary capsule layer and digit capsule layer, wherein the radiographic images are categorized through dynamic routing followed by disease prediction through ResNet50v2 model. The proposed work is implemented on images with a resolution of $224 \times 224$ and a batch size of 10. Further, parametric functions are applied to verify the model being trained. © 2022 IEEE.

A Convolutional Neural Network Model for Detecting COVID-19 from CT Scans

Using deep learning approaches, this work presents a fully automated system for diagnosing COVID-19 from volumetric chest computed tomography (CT) scans. Transfer learning technique has been used to detect and classify CT scan data into three categories: COVID-19, CAP (Community-acquired pneumonia), and normal cases. The proposed model was built on top of the pre-trained AlexNet model's architecture and was capable of performing multi-classification tasks with a promising accuracy of 98.03%. The results demonstrate that the proposed model outperforms other current models and may thus be utilized as a potential tool for COVID-19 patient diagnosis. © 2021 IEEE.

LionKeeper: Automatically Discovering Timely Cybercrime Dynamics in the Age of COVID-19

As more activities are moving to digital platforms in the age of COVID-19 pandemic, cyber security becomes an increasingly critical issue. Thus, understanding how the recent pandemic has changed the Singapore cyber security landscape gains importance in unearthing potential weaknesses present in the infrastructure, which unfortunately is very challenging. In this paper, we propose, LionKeeper, an automated system for discovering the cyber security dynamics timely in Lion City - Singapore through social media data analytics. In particular, considering that the social media platforms like news websites provide immediate reports on local and global cybercrime incidents, in our system, we first crawl all the news articles from mainstream news sources such as CNA and Strait Times. Then, we analyze these news articles to identify those related to cybercrimes, the date and the location of cybercrime incidents, and employ a scoring system to detect the cyber security attack types and their significance. Additionally, based on the extracted information, we perform various analyses to generate meaningful insights for users to understand the cyber attack landscape dynamics before and during the COVID-19 pandemic automatically and intelligently. To the best of our knowledge, this is the first automated solution to understand the Singapore cyber landscape via social media analytics. © 2021 IEEE.

IoT-based COVID-19 Patient Vital Sign Monitoring

The number of COVID-19 cases is growing rapidly, while there is not enough healthcare workers which can help the patients. Even worse, the highly contagious nature of this disease, requires the medical staff to be more restrictive and wear the Personal Protective Equipment (PPE) all the time when handling the patients directly. In this situation, a remote system which can monitor patient progress from a distant is inevitable. The emerge of Internet of Thing (IoT) technology has been implemented in many domain. The availability of smart technology, where almost all devices around us has connectivity to the internet, allow people to automate process from distance. The implementation of IoT has also been shown very helpful in medical domain, especially during the pandemics. The IoT technology can be a suitable solution for monitoring patients with a highly contagious disease. The technology can also be very helpful for people who live far from healthcare facility. This can allow people to report immediately and even connect to the hospital system in real-time. In this paper, we propose the use of three different sensors, namely: heart-rate and pulse oximeter sensor (MAX30102), temperature sensor(DS18b20) and accelerometer sensor, which is integrated in a web-based early warning monitoring system for COVID-19 patients. © 2021 IEEE.

Intelligent Healthcare System for Recuperation and Inoculation of Communicable Diseases

Human life gets interrupted a lot when a communicable disease starts in a society. People are alerted a lot on a different basis and eventually, it leads to difficulty for continuing their normal life. This paper is focused on a communicable disease, the COVID-19, which gave an outbreak for all world counties into a state where their fellow human had to stop their daily job and stay back at home. Common people find it difficult to get treatment when they are identified as positive and also most of them lack the awareness of post covid recovery. The idea of this work is to create a healthcare system that initiates right from the covid test, appropriate treatment according to severity, post-recovery, and vaccination awareness and jabs. These units will have less human interaction and they will be fully automated till in need of pure doctor consultation. The automated system is programmed to identify the infection, its severity and prescribe the treatment accordingly, and follow up recovery needs. On-side, automated vaccination system will allow direct walk-in, identify the customer and do the needful. © 2021 Institute of Physics Publishing. All rights reserved.

WICO Text: A Labeled Dataset of Conspiracy Theory and 5G-Corona Misinformation Tweets

The COVID-19 pandemic has been accompanied by a flood of misinformation on social media, which has been labeled an "infodemic". While a large part of such fake news is ultimately inconsequential, some of it has the potential to real-world harm, but due to the massive amount of social media contents, it is impossible to find this misinformation manually. Thus, conventional fact-checking can typically only counteract misinformation narratives after they have gained significant traction. Only automated systems can provide warnings in advance. However, the automatic detection of misinformation narratives is very challenging since the texts that spread misinformation may be short messages on Twitter. They may also transmit misinformation by implication rather than by stating counterfactual information outright, and satirical messages complicate the issue further. Thus, there is a need for highly sophisticated detection systems. In order to support their development, we created substantial ground truth data by human annotation. In this paper, we present a dataset that deals with a specific piece of misinformation: the idea that the COVID-19 pandemic is causally connected to the 5G wireless network. We selected more than 10,000 tweets that deal with COVID-19 and 5G and labeled them manually, distinguishing between tweets that propagate the specific 5G misinformation, those that spread other conspiracy theories, and tweets that do neither. We provide the human-annotated dataset along with an additional large-scale automatically (by using the human-annotated dataset as the training set) labelled dataset consist of more than 100,000 tweets. © 2021 ACM.