Classic Augmentation based Classifier Generative Adversarial Network (CACGAN) for COVID-19 Diagnosis

Computer-aided diagnosis of COVID-19 from lung medical images has received increasing attention in previous clinical practice and research. However, developing such automatic model is usually challenging due to the requirement of a large amount of data and sufficient computer power. With only 317 training images, this paper presents a Classic Augmentation based Classifier Generative Adversarial Network (CACGAN) for data synthetising. In order to take into account, the feature extraction ability and lightness of the model for lung CT images, the CACGAN network is mainly constructed by convolution blocks. During the training process, each iteration will update the discriminator's network parameters twice and the generator's network parameters once. For the evaluation of CACGAN. This paper organized multiple comparison between each pair from CACGAN synthetic data, classic augmented data, and original data. In this paper, 7 classifiers are built, ranging from simple to complex, and are trained for the three sets of data respectively. To control the variable, the three sets of data use the exact same classifier structure and the exact same validation dataset. The result shows the CACGAN successfully learned how to synthesize new lung CT images with specific labels. © 2023 SPIE.

Life Cycle Assessment of Nanofibrous Air Filtering Materials and Respirators

The current spread of COVID-19 pandemics resulted in a surge of a need of respiratory protection devices, including medical facemasks and facepiece respirators. Large amounts of products based on nonwoven filtration material from non-renewable petroleum based plastics (polyethylene) has raised global concerns about excessive environmental impacts of these products. Unfortunately, the replacement of polypropylene nonwoven microfibre based single use masks by the multiple use products did not appear as an effective strategy due to a lower filtration performance, although potentially lower environmental impacts. Nanofibre based filtration devices introduce themselves as potentially more environmentally friendly ones due to a lower overall usage of raw polymer compared to microfibrous ones. We present the LCA modelling of environmental impacts of respiratory protective devices with nanofibrous filter materials and compare those against traditional micro fibrous materials (FFP1 and FFP2 respirator) and medical facemask. Generally, due to a lower mass of nanofibre, these products emerge as a better environmental option, providing similar protection level. © 2022 17th International Conference on Indoor Air Quality and Climate, INDOOR AIR 2022. All rights reserved.

Misinformation Detection Using Unsupervised Approach on CoAID Dataset

COVID-19 has had an impact on everyone's life. People have slowly moved online for information access regarding COVID-19. This resulted in a large amount of misinformation spread among the people. This has a widespread impact on business, economy, education, and various other factors of society. Recent research techniques have developed models to detect COVID-19 misinformation using a mainly supervised learning approach that demands a labeled dataset. Several datasets have been generated since the COVID-19 pandemic using social media and web platforms. However, considering the large amount of information generated online with unstructured, incomplete, and noisy data, it is difficult to obtain labeled data for supervised learning. Therefore, in this research authors have proposed an unsupervised learning technique using k-means with a domain-specific sentimental bagof-words on the CoAID dataset. CoAID dataset has been created during the initial stages of the COVID-19 pandemic and is popular and widely used. Initially, the authors have done an extensive analysis of the literature based on the CoAID dataset to explore the various techniques developed on this dataset. Further, a k-means clustering algorithm is employed with six different distance measures viz. Euclidean, Squared Euclidean, Chi-square, Canberra, Chebychav, and Manhattan. The Elbow method is used to identify the optimal number of clusters. To evaluate the performance of the proposed model authors have used various metrics like purity, precision, silhouette score, word clouds, and sentiment analysis. The model showed a purity score of 0.96 and a precision of 1 for k=2. © 2022 IEEE.

Implementing a Data Integration Infrastructure for Healthcare Data – A Case Study

Conducting epidemiologic research usually requires a large amount of data to establish the natural history of a disease and achieve meaningful study design, and interpretations of findings. This is, however, a huge task because the healthcare domain is composed of a complex corpus and concepts that result in difficult ways to use and store data. Additionally, data accessibility should be considered because sensitive data from patients should be carefully protected and shared with responsibility. With the COVID-19 pandemic, the need for sharing data and having an integrated view of the data was reaffirmed to identify the best approaches and signals to improve not only treatments and diagnoses but also social answers to the epidemiological scenario. This paper addresses a data integration scenario for dealing with COVID-19 and cardiovascular diseases, covering the main challenges related to integrating data in a common data repository storing data from several hospitals. Conceptual architecture is presented to deal with such approaches and integrate data from a Portuguese hospital into the common repository used to explore data in a standardized way. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

Tune Down the Misinformation, Please: Generating Corrective Messages for COVID-19 Misinformation

The ongoing COVID-19 pandemic drastically changed our lives in multiple aspects, one of which is the reliance on social media during quarantine, both for social interaction and information-seeking purposes. However, the wide dissemination of misinformation on social media has impacted public health negatively. Previous studies on COVID-19 misinformation mainly focused on exploration of impacts and explanation of motivations, with few exceptions. In this study, we propose an analytical pipeline that generates corrective messages toward COVID-19 misinformation in a semiautomatic fashion, and then evaluate it against a large amount of data. Both the automated and manual evaluation results suggest the efficiency of the proposed pipeline, which can be used in combination with human intelligence by individuals and public health organizations in fighting COVID-19 misinformation. © 2022 IEEE Computer Society. All rights reserved.

Risk Perception and Misinformation in Brazilian Twitter during COVID-19 Infodemic

During the COVID-19 pandemic, different groups had different perceptions of how dangerous the coronavirus was. This difference in behavior was intensified by the large amount of misinformation shared across social media. This work presents an analysis aimed at understanding the extent to which people perceived risk at different levels, and at uncovering the relationship between these differences and the spread of misinformation. In particular, we focus on Brazil, because it is well-known that its Ministry of Health has sponsored campaigns that raised suspicious regarding the effectiveness of the vaccines. To achieve this goal, we gathered tweets written in Portuguese related to the COVID-19 and analyzed their psycholinguistic traits. Among those traits, we found 'Anxiety' to be a good proxy for risk perception. We validate this choice by showing that, at moments of high (resp. low) infection rates in the world, the Anxiety score was higher (resp. lower). We grouped users into 'low' and 'high' risk perception based on the users' anxiety score, and analyzed the relation of each group with the spread of misinformation. Our results show that Twitter users with a lower perceived risk were more inclined to share fake news and harmful information, while the group with a higher level of anxiety tends to share more scientifically-backed information. This is an important step towards helping minimize the spread of false and harmful health information around the internet. © 2022 IEEE.

A COVID-19 detection method based on self-supervised learning and transfer learning

Since the global outbreak of COVID-19, the epidemic has had a great impact on people's lives and the world economy. Diagnosis of COVID-19 using deep learning has become increasingly important due to the inefficiency of traditional RT-PCR test. However, training deep neural networks requires a large amount of manually labeled data, and collecting a large number of COVID-19 CT images is difficult. To address this issue, we explore the effect of Pretext-Invariant Representation Learning (PIRL) using unlabeled datasets to pre-train the network on classification results. In addition, we also explore the prediction effect of PIRL combined with transfer learning (TF). According to the experimental results, applying the TF-PIRL prediction model constructed in this paper to COVID-19 diagnosis, the accuracy and AUC are 0.7734 and 0.8556 respectively, which outperform the network training from scratch, transfer learning-based network training and PIRL-based network training. © 2022 IEEE.

Improving cloud/edge sustainability through artificial intelligence: A systematic review

In recent years, the increase in the use of services in cloud, fog, edge, and IoT ecosystems has been very notable. On the one hand, environmental sustainability is affected by this type of ecosystem since it can produce a large amount of energy consumption which translates into CO2 emissions into the atmosphere. On the other hand, due to the COVID-19 pandemic, the use of these ecosystems has increased considerably. Thus, it is necessary to apply policies and techniques to maximize sustainability within these ecosystems. Some of these policies and techniques are those based on artificial intelligence. However, the current processing of these policies and techniques can also consume a lot of resources. From this perspective, this article aims to clarify whether the sustainability of cloud/fog/edge/IoT ecosystems is improved by the application of artificial intelligence. To do this, a systematic literature review is developed in this paper. In addition, a set of classifications of the analyzed works is proposed based on the different aspects related to these ecosystems, their sustainability, and the applicability of artificial intelligence to improve them. © 2023 The Author(s)

Understanding Desire to Touch Using Large-scale Twitter Data

I and research colleagues investigated people's desire to touch by collecting and analyzing a large amount of text data that contain phrases such as "want to touch” on Twitter. We revealed the relationship between the body part that people want to touch and the touch gesture. We also revealed the effects of the COVID-19 pandemic on the desire to touch. Specifically, we observed "skin hunger,” i.e., the strong desire for physical communication, and variation of touch avoidance toward objects such as doorknobs. Our results will be beneficial for understanding human behavior as well as for the further development of haptic technology. © 2023 Nippon Telegraph and Telephone Corp.. All rights reserved.

COVID-19 Vaccines Analysis to Predict Its Impact Across the World

In recent years, due to the widespread of COVID-19 pandemic, a large amount of data set is available about the various types of vaccines used by different countries for the protection of their citizens. So it is very important and useful if one is able to perform effective analysis of the same to make the awareness and the effectiveness of each vaccine known to mankind. It is found that COVID-19 vaccines increase the immune system, prepare the body to fight against the virus, and reduce the probability of contracting COVID-19.this can be done with the help of regression techniques such as The MAE, MSE, RMSE values to predict and evaluate the observations with more efficiency. The RMSE technique measures the standard deviation of results and provides more accuracy. This analysis helps to find out how COVID-19 vaccines are provided in various countries and the countries where 80% of the population is vaccinated. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.

A Systematic Literature Survey of Emotion Detection of Students in E-learning

Affective computing is a part of artificial intelligence, which is becoming more important and widely used in education to process and analyze large amounts of data. Consequently, the education system has shifted to an E-learning format because of the COVID-19 epidemic. Then, e-learning is becoming more common in higher education, primarily through Massive Open Online Courses (MOOCs). This study reviewed many prior studies on bolstering educational institutions using AI methods, including deep learning, machine learning, and affective computing. According to the findings, these methods had a very high percentage of success. These studies also helped academic institutions, as well as teachers, understand the emotional state of students in an e-learning environment. © 2022 IEEE.

Selected dechlorination of triclosan by high-performance g-C3N4/Bi2MoO6 composites: Mechanisms and pathways

Environmental-friendly and efficient strategies for triclosan (TCS) removal have received more attention. Influenced by COVID-19, a large amount of TCS contaminants were accumulated in medical and domestic wastewater discharges. In this study, a unique g-C3N4/Bi2MoO6 heterostructure was fabricated and optimized by a novel and simple method for superb photocatalytic dechlorination of TCS into 2-phenoxyphenol (2-PP) under visible light irradiation. The as-prepared samples were characterized and analyzed by XRD, BET, SEM, XPS, etc. The rationally designed g-C3N4/Bi2MoO6 (4:6) catalyst exhibited notably photocatalytic activity in that more than 95.5% of TCS was transformed at 180 min, which was 3.6 times higher than that of pure g-C3N4 powder. This catalyst promotes efficient photocatalytic electron-hole separation for efficient dechlorination by photocatalytic reduction. The samples exhibited high recyclable ability and the dechlorination pathway was clear. The results of Density Functional Theory calculations displayed the TCS dechlorination selectivity has different mechanisms and hydrogen substitution may be more favorable than hydrogen ion in the TCS dechlorination hydrogen transfer process. This work will provide an experimental and theoretical basis for designing high-performance photocatalysts to construct the systems of efficient and safe visible photocatalytic reduction of aromatic chlorinated pollutants, such as TCS in dechlorinated waters. © 2022 Elsevier Ltd

Optimization of gasification process parameters for COVID-19 medical masks using response surface methodology

Due to the COVID-19 pandemic, large amounts of medical wastes have been produced and their disposal has resulted in environmental and human health problems. This medical waste may include face masks, gloves, face shields, goggles, coverall suits, and other related wastes, such as hand sanitizer and disinfectant containers. To address this issue, the effect was investigated of gasification process parameters (type of COVID-19 medical mask based on the polypropylene ratio, pressure, steam ratio, and temperature) on hydrogen syngas and cold gas efficiency. The gasification model was developed using process modeling based on the Aspen Plus software. Response surface methodology with a 3k statistical factorial design was used to optimize the process aiming for the highest hydrogen yield and cold gas efficiency. Analysis of variance showed that both the steam ratio and temperature were significant parameters regarding the hydrogen yield and cold gas efficiency. Proposed models were constructed with very high accuracy based on their coefficient of determination (R2) values being greater than 0.97. The optimum conditions were: 65 % polypropylene in the mixture, a pressure of 1 bar, a steam ratio of 0.38, and a temperature of 900 °C, producing a maximum hydrogen yield of 40.61 % and cold gas efficiency of 81.43 %. These results supported the efficacy of the primary design for steam gasification using a mixture of plastic wastes as feedstock. The hydrogen could be utilized in chemical applications, whereas the efficiency could be used as a basis for further development of the process. © 2022 THE AUTHORS

Health Informatics on Big COVID-19 Pandemic Data via N-Shot Learning

Nowadays, very large amounts of data are generating at a fast rate from a wide variety of rich data sources. Valuable information and knowledge embedded in these big data can be discovered by data science, data mining and machine learning techniques. Biomedical records are examples of the big data. With the technological advancements, more healthcare practice has gradually been supported by electronic processes and communication. This enables health informatics, in which computer science meets the healthcare sector to address healthcare and medical problems. As a concrete example, there have been more than 635 millions cumulative cases of coronavirus disease 2019 (COVID-19) worldwide over the past 3 years since COVID-19 has declared as a pandemic. Hence, effective strategies, solutions, tools and methods - such as artificial intelligence (AI) and/or big data approaches - to tackle the COVID-19 pandemic and possible future pandemics are in demand. In this paper, we present models to analyze big COVID-19 pandemic data and make predictions via N-shot learning. Specifically, our binary model predicts whether patients are COVID-19 or not. If so, the model predicts whether they require hospitalization or not, whereas our multi-class model predicts severity and thus the corresponding levels of hospitalization required by the patients. Our models uses N-shot learning with autoencoders. Evaluation results on real-life pandemic data demonstrate the practicality of our models towards effective allocation of resources (e.g., hospital facilities, staff). These showcase the benefits of AI and/or big data approaches in tackling the pandemic. © 2022 IEEE.

Generating Synthetic Images & Data to Improve Object Detection in CCTV Footage from Public Transport

Passenger behaviour on public transport has become a source of great interest in the wake of the COVID-19 pandemic. Operators are interested in employing new methods to monitor vehicle utilisation and passenger behaviour. One way to do this is through the use of Machine Learning, using the CCTV footage that is already being captured from the vehicles. However, one of the limitations of Machine Learning is that it requires large amounts of annotated training data, which is not always available. In this poster, we present a technique that uses 3D models to generate synthetic training images/data and discuss the effect that training with the synthetic data had on the Machine Learning models when applied to real-world CCTV footage. © 2022 IEEE.

Democratising large scale instrument-based science through e-Infrastructure

Modern scientific instruments are becoming essential for discoveries because they provide unprecedented insight into physical or biological events - often in real time. However, these instruments may generate large amounts of data, and increasingly they require sophisticated e-infrastructure for analysis, storage and archive. The increasing complexity and scale of the data, processing steps and systems has made it difficult for domain scientists to perform their research, narrowing the user base to a select few. In this paper, we present a framework that democratises large-scale instrument-based science, increasing the number of researchers who can engage. We discuss a prototype at the University of Queensland. The system is illustrated through two case studies, one involving light microscopy imaging of the innate immune system, and the other electron microscopy imaging of the SARS-CoV-2 viral proteins. © 2022 IEEE.

A Network Modeling and Analysis of COVID-19 Hospital Patient Data

There are currently large amounts of public databases on COVID-19 patients. Among them the FAPESP COVID-19 Data Sharing/BR has gathered laboratory tests and hospitalization data from large health centers in the São Paulo metropolitan area. This paper uses part of such a repository to assemble a set of networks of positive COVID-19 patients according to the similarity of their age and laboratory tests results. Next, popular complex network metrics such as clustering coefficient and average path length are extracted from such networks and compared to the expected values observed for classical networks. Similarities of the clustering coefficient values with those of Watts-Strogatz networks were observed, although there are no sustainable characteristics of Small World networks. There are also similarities to scale-free networks, such as high-degree variance and the presence of hubs of nodes. In addition, a partition of the networks based on the modularity measure using the Fast Greedy algorithm is obtained and analyzed. An structure with four clusters and modularity values greater than zero was found, indicating that the network has some community structure. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.

Research on several major diseases based on machine learning models

Due to the continuous growth of disease types and past cases, it is more and more difficult to diagnose diseases only by manpower. Machine learning is a model mechanism that is sensitive to data and relies on a large amount of data to complete training. It is very suitable for medical diagnosis. Many scholars have tried to use ML to develop medical diagnosis systems, but they are basically not used in the real world at this stage. This article reviews the work related to medical detection of three major diseases (heart disease, cancer, and COVID-19), aiming to summarize previous experiences to help future scholars conduct research. Specifically, this paper summarizes the research status of the prediction of these three types of diseases based on machine learning methods, evaluate the accuracy and universality of the corresponding prediction models based on time as a clue, and use a comparative method to find out the progress researchers have made in this area and limitations still exist at this stage. And at the end of the article, the results and some potential work fields of the future in these studies are summarized. © 2022 IEEE.

Big Data-Enabled Solutions for Covid-19

In the time of the pandemic like CORONA, Covid-19, everyone is ftghting against this deadly virus. Besides, governments are looking for a barrier that stops spread of virus until the vaccine is made. In modern era, technology plays an important role. This paper brings the way by using a powerful technology called Big data. Big data know for handling a large amount of data and provide powerful insights into the data. Big data integrated with Artificial Intelligence is a powerful tool to ftght against this pandemic. Many countries like Taiwan, China with the use of Big Data stop this pandemic up to some extent. But the collection of data itself comes up with the big challenge of PRIVACY AND SECURITY. In the recent times, the world has seen the effect of data leaking whether by Facebook or by Google. Many European countries due to this big challenge will not be able to use this technology. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

Minimizing the infected peak utilizing a single lockdown: a technical result regarding equal peaks

Due to the usage of social distancing as a means to control the spread of the novel coronavirus disease COVID-19, there has been a large amount of research into the dynamics of epidemiological models with time-varying transmission rates. Such studies attempt to capture population responses to differing levels of social distancing, and are used for designing policies which both inhibit disease spread but also allow for limited economic activity. One common criterion utilized for the recent pandemic is the peak of the infected population, a measure of the strain placed upon the health care system;protocols which reduce this peak are commonly said to 'flatten the curve."In this work, we consider a very specialized distancing mandate, which consists of one period of fixed length of distancing, and address the question of optimal initiation time. We prove rigorously that this time is characterized by an equal peaks phenomenon: the optimal protocol will experience a rebound in the infected peak after distancing is relaxed, which is equal in size to the peak when distancing is commenced. In the case of a non-perfect lockdown (i.e. disease transmission is not completely suppressed), explicit formulas for the initiation time cannot be computed, but implicit relations are provided which can be pre-computed given the current state of the epidemic. Expected extensions to more general distancing policies are also hypothesized, which suggest designs for the optimal timing of non-overlapping lockdowns. © 2022 American Automatic Control Council.