Context Aware Automatic Subjective and Objective Question Generation using Fast Text to Text Transfer Learning

Online learning has gained a tremendous popularity in the last decade due to the facility to learn anytime, anything, anywhere from the ocean of web resources available. Especially the lockdown all over the world due to the Covid-19 pandemic has brought an enormous attention towards the online learning for value addition and skills development not only for the school/college students, but also to the working professionals. This massive growth in online learning has made the task of assessment very tedious and demands training, experience and resources. Automatic Question generation (AQG) techniques have been introduced to resolve this problem by deriving a question bank from the text documents. However, the performance of conventional AQG techniques is subject to the availability of large labelled training dataset. The requirement of deep linguistic knowledge for the generation of heuristic and hand-crafted rules to transform declarative sentence into interrogative sentence makes the problem further complicated. This paper presents a transfer learning-based text to text transformation model to generate the subjective and objective questions automatically from the text document. The proposed AQG model utilizes the Text-to-Text-Transfer-Transformer (T5) which reframes natural language processing tasks into a unified text-to-text-format and augments it with word sense disambiguation (WSD), ConceptNet and domain adaptation framework to improve the meaningfulness of the questions. Fast T5 library with beam-search decoding algorithm has been used here to reduce the model size and increase the speed of the model through quantization of the whole model by Open Neural Network Exchange (ONNX) framework. The keywords extraction in the proposed framework is performed using the Multipartite graphs to enhance the context awareness. The qualitative and quantitative performance of the proposed AQG model is evaluated through a comprehensive experimental analysis over the publicly available Squad dataset. © 2023, International Journal of Advanced Computer Science and Applications. All Rights Reserved.

Industry 5.0 and digital innovations: Antecedents to sustainable business model

The concept of Industry 5.0 is not just one more revolution but calls for a tectonic shift in digitization and operationalizing technology with connected value chain across sectors. It is human centric that promotes talents, diversity and empowerment coupled with resilience leading to agile and adaptable technologies with prime focus on sustainability. The COVID-19 pandemic has given impetus to digital transformation and accelerated the focus on other challenges of present time and with extended importance on people, planet and societal concepts. This study shall attempt to examine the nature of association between revolution of Industry 5.0 with perspectives to digital innovation and its implications toward bringing sustainable business model. The main objective of this chapter shall be to uncover interrelated questions in terms of sustainability perspectives of industries in framing business models. This study shall serve as a primer to significance of digital transformation with relevance to businesses that can lead to efficient use of scarce resources and optimal feasible solutions to the business models, given the institutional and organizational frameworks. Further, an attempt shall also be made to underpin the key facets of effects of Industry 5.0 on the knowledge economy. It shall delve into how digital innovations can yield benefits to industry in terms of competitiveness and sustainability with focus on Society 5.0 that attempts to balance economic development with the resolution of societal and environmental problems. It is not restricted to the manufacturing sector but addresses larger social challenges based on the integration of physical and virtual spaces. © 2023 by Parag Shukla and Surabhi Singh. All rights reserved.

Pandemic Outbreak Time: Evaluation of Public Tweet Opinion by Machine Learning

In this work, a Twitter data-set was utilized to do sentiment analysis of people's thoughts on the corona-virus (COVID-19) period, which is a major concern throughout the world these days, impacting a number of nations. To better understand people's feelings about the epidemic, machine learning approaches (mla) and sentiment methodology such as Bert Model (BMO), Naive_Bayes_Bernoulli (nBB), Multi Nominal Naive_Bayes (mnNB), Support_ Vector_Machine (svM), Logistic_Regression (IR), Gradient_Boosting_ Classifier (gbR), Decision Tree Classifiers (dtC), K N eighbors(knN) and Random Forest Classifier (rfC) have been presented in this work. Also, we have classified that which Classifiers provides highest accuracy. Additionally, in this paper, we also analysis from the data set, the most that has been tweeted (hashtag), positive, negative as well as neutral with data visualization in the Covid-19 epidemic time. © 2022 IEEE.

Text Emotion Analysis Using Deep Learning For COVID- 19 Dataset

Managing mental health and psychological well-being is just as critical as managing physical health throughout COVID-19. The difficulty of detecting, classifying, and quantifying emotions in text in any form are addressed in this study. We consider English text collected from social media sites such as Twitter and various Kaggle datasets that can provide information useful in a variety of ways, particularly opinion mining. However, analysing and categorising text based on emotions is a difficult task and might be thought of as a more advanced kind of Sentiment Analysis. This work provides a system for categorising text into three types of emotions: positive, negative, and neutral. This analysis can be utilized by authorities to better understand people's mental health and to make appropriate policy decisions to combat the coronavirus, which is hurting the world's social well-being and economy. © 2022 IEEE.

A Critical Review of the Impact of COVID-19 on Plastic and Food Waste

This research aims to show the positive and negative indirect effects of COVID-19 on municipal solid waste management systems, especially for plastic waste and food waste. The COVID-19 pandemic has affected the entire waste management sector. As the pandemic spread and lockdowns were enforced in many countries, government and municipal waste operators had to quickly adapt their waste management programs and procedures to the situation. In the pandemic condition, waste generation has switched from industry and commercial to domestic areas. Reduced recycling activities have made municipal waste collection and disposal more difficult. This paper focuses on all the challenges and it's possible resolutions for managing food and plastic waste during the pandemic of COVID-19. © 2022 Technoscience Publications. All rights reserved.

Twitter Opinion Mining on COVID-19 Vaccinations by Machine Learning Presence

The COVID-19 pandemic has effectively shut down the whole planet. Most countries have now suspended lockdowns or semi-lockdowns, although lockdowns still exist in many countries. The coronavirus epidemic has disrupted people's daily lives. People from all across the globe have flocked to social media to voice their thoughts and feelings on the phenomenon that has gone viral. In a very short period of time, the social networking site Twitter saw an extraordinary rise in tweets pertaining to the novel coronavirus. With the discovery of several vaccines for the virus, the new year of 2021 brought with it new hope. A global vaccine campaign is under way, and we anticipate that the world will quickly recover from this pandemic and return to normalcy. This paper is devoted to the vaccination drive's tweets. This is used to predict the attitude of tweets on vaccinations. We have taken note of how sentiment changes over time, with respect to vaccination, through the general people who tweeted. For analysis, VADER and LSTM, Z-score, have been used. Additionally, with vaccine data visualization, the most common positive and negative, all hashtags, and the source of the data have been analyzed. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

Healthcare Disaster Prediction with IoT, Data Analytics, and Machine Learning

Disaster may be natural or man-made, for example, terrorist attack, earthquakes, landslides, cyclones and storms/wave surges, floods or disease epidemics, and insect/animal plagues like COVID-19. Due to disaster, normal patterns of life get disturbed affecting the physical and psychological health. It is challenging to predict the likelihood of occurrence of disaster but people should have the aim to handle this acute and long term. Any type of disaster affecting the health stresses for healthcare. Due to this pandemic situation, the health of the person is affected. In the current scenario, so much has been impacted due to COVID-19. People are affected because they didn’t get proper help, timely and admissible solutions for the same. When no one is prepared for this type of situation like disasters, people face issues like availability of hospitals and medicine, loss of their family, etc. To handle this problem, the Internet of things (IoT) is playing an important role in healthcare. There are so many android apps and IoT devices for health monitoring. To minimize the impact of this disaster or to predict it early, technical and medical innovations are necessary. One such example is Aarogya Setu app that is making use of GPS and Bluetooth to track coronavirus-infected people. IoT devices generate a huge amount of data that needs to be analyzed. This chapter will discuss different IoT devices, data analytics, and machine learning (ML) algorithms that are used to predict disasters, thus, affecting the health. © 2023 by Apple Academic Press, Inc.

Challenges of Global Healthcare Disasters

Human health is rising under the fear of an emerging international health crisis where public health can be easily compromised. In this chapter, various factors that directly or indirectly target public health infrastructure and lead to global crisis like extreme climate changes, refugee health crisis, terrorism and technologyrelated incidents, are discussed. On analysis of the factors that may lead to such disasters, various challenges faced during the disasters are listed specifically pertaining to the healthcare system. The greater risk of disaster can be seen there, where there is a lack of basic amenities, limited access to healthcare, and lack of resources required to cope up from disease. In such situations, it becomes an utmost priority to contain infectious disease and prepare for epidemics, protecting adolescents, elevating health in the climate debate, and delivering healthcare in areas of conflict and crisis. Some of the challenges that are acknowledged by the WHO experts from around the world are issues like healthcare equality, access to medicine, preparedness for epidemics, preventing use of dangerous products, developing new technology and most important clean water, sanitation and hygiene. © 2023 by Apple Academic Press, Inc.

Monitoring COVID-19 Patients Using Cardio-Pulmonary Stethoscope RF Technology: Computer Simulation Study Using CT Scans of Patients

In 2020, the COVID-19 pandemic claimed 3 million lives worldwide in span of a year;the death toll is still on rise as of writing of this article. Hospitals around the globe overwhelmed with COVID-19 patients faced medical resource shortages preventing them from providing services to even severe cases, leaving patients to selfcare. The identified COVID-19 patients had to observe the symptoms escalation or take imaging tests such as CT scans to determine the disease progression. While these imaging methods provide detailed accounts of damage inflicted to lungs by COVID-19, they have their own limitations and risks. In this article, we use computer simulations to examine the possibility of using the Cardio-Pulmonary Stethoscope (CPS) to continually monitor the COVID-19 afflicted lungs. Using a CT scan of a real COVID-19 patient, an infection was introduced in the lungs of an anatomically correct digital human model to be studied using simulation method. The preliminary results of simulations showed that the least detectable size of infection was an ellipsoid of 0.9 cubic cm, and the CPS was most sensitive while detecting infection in the lungs without preexisting conditions like edema. Based on the results and resolution, signal sensitivity of the CPS to COVID-19 infection is established and it can be argued that CPS could be an alternative method for continuous monitoring of COVID-19 disease.

Retrospective Analysis of Arterial Carbon Dioxide Level and Arterial pH Level at the Time of Initiation of Respiratory ECMO and Outcome

Introduction Respiratory extracorporeal membrane oxygenation (ECMO) is well established and its popularity has increased during coronavirus disease 2019 (COVID-19) time. The efficacy of ECMO has been proved in refractory respiratory failure with varied etiology. More than 85,000 respiratory ECMO cases (neonatal, pediatric, adult) registered as per Extracorporeal Life support Organization (ELSO) statistics April 2022 report, with survived to discharge or transfer ranging from 58 to 73%. Early initiation of ECMO is usually associated with shorter ECMO run and better outcome. Many patient factors have been associated with mortality while on ECMO. Pre-ECMO patient pH and arterial partial pressure of carbon dioxide (paCO2) have been associated with poor outcome. We designed a retrospective study from a single tertiary care center and analyzed our data of all respiratory ECMO (neonatal, pediatric, and adult) to understand the effect of pre ECMO, paCO2, and arterial pH to ECMO outcome. Methods It is a retrospective analysis of data collected of patients with acute respiratory failure managed on ECMO from January 2010 to December 2021. Pre-ECMO (1-6 hours before initiation), paCO2, and arterial pH level were noted and analyzed with primary and secondary outcome. Primary outcome goal was survivor and discharged home versus nonsurvivor, while secondary goal was the number of ECMO days and incidence of neurological complications. The statistical analysis was done for primary outcome and incidences of neurological complications and p-value obtained by using chi-squared method. Meta-analysis was done by classifying the respiratory ECMO cases in three major category-COVID-19, H1N1 non-COVID-19, and H1N1 respiratory failure. Results The total 256 patients of respiratory failure were treated with ECMO during specified period by Riddhi Vinayak Multispecialty Hospital ECMO team. Data analysis of 251 patients (5 patients were transferred for lung transplant, hence been not included in study) done. Patients were divided on the basis of pH level less than 7.2 and more than 7.2 and analyzed for primary and secondary outcome. Similarly, patients were divided on the basis of paCO2 level of less than 45 and more than 45. Patient with pre-ECMO pH level more than 7.2 has statistically better survived extracorporeal life support (ECLS) (p-value: 0.008) and survival to discharge home (p-value: 0.038) chances. Pre-ECMO paCO2 level of less than 45 also showed better survival chance of survived ECLS (46.67 vs. 36.02) and survived to discharge home (42.22 vs. 31.06) but not statistically significant (p-value: 0.15 and 0.18, respectively). There was no significant difference in average number of ECMO days in patient survived to discharge home with paCO2 less than 45 and more than 45 (15.7 vs. 11.1 days), and also in pH more than 7.2 and pH less than 7.2 (15.8 vs. 11.6). The incidence of neurological complications was also found lower in patient with pH more than 7.2 (7.5 vs. 17.3%, p-value: 0.034) and in paCO2 level of less than 45 (4.4 vs. 12.65, p-value: 0.15). Conclusion Pre-ECMO arterial pH of more than 7.2 (statistically significant) and paCO2 of less than 45 (statistically not significant) have definitely better survival chances and have lesser incidences of neurological complications. There was no significance difference in the number of ECMO days in either group. Authors recommends early initiation of ECMO for mortality and morbidity benefits.

Intracranial manifestations of rhinocerebral mucormycosis: a pictorial essay

Rhinocerebral mucormycosis has emerged as a common coinfection in coronavirus disease 2019 (COVID-19) patients during the convalescence period. Frequent spread of disease from sinonasal mucosa to bone, neck spaces, orbit, and brain occurs along the perivascular/perineural routes or through direct invasion. Brain involvement represents severe manifestation and is often associated with poor functional outcomes and high mortality rates. Magnetic resonance imaging (MRI) is the modality of choice for the intracranial assessment of disease severity in mucormycosis. Early and accurate identification of intracranial extension is imperative to improve survival rates. With this pictorial essay, we aim to familiarize the readers with the cross-sectional imaging features of intracranial complications of mucormycosis. The radiological details in this essay should serve as a broad checklist for radiologists and clinicians while dealing with this fulminant infection.

Monitoring COVID-19 Patients Using Cardio-Pulmonary Stethoscope RF Technology

The COVID-19 disease recognized as pandemic in 2020 created worldwide shortage of medical resources causing hospitals to admit only the severe cases and leaving the rest to selfcare. The identified covid19 patient with non-life-threatening stage had to monitor the disease progression based on the escalation of symptoms or do imaging tests like CT scans, x-ray. The imaging method while reliable comes with its own limitation and risks of exposure. In this paper, we checked the efficacy of utilizing Cardio-Pulmonary Stethoscope (CPS) to monitor the COVID-19 patient and assess the disease progressive status. The simulations were ran on anatomically realistic human model with infection at various location, size and spread reflecting real COVID-19 infected lungs. The least detectable size of injury was found to be the ellipsoid of 0.9 cubic cm, and the most consistent result was observed in the healthy lung with water content of 20%. The results presented in this paper suggest that CPS could be used as the alternative to CT scans for continuous monitoring. © 2021 IEEE.

Bio-Inspired Framework for Security in IoT Devices

One of the many things COVID-19 has taught humanity is that the Internet is not just a commodity but a vital service integral to the modern world. As we become ever more connected, there is a growing need to secure data and communication streams. If data is valued, then it should be protected. Unfortunately, some of the least secure devices in modern electronic systems are the Internet of Things (IoT) devices—partly due to their low processing power and always—on functionality. Polymorphism is the notion of changing one’s form. In biological organisms, polymorphic (mutating or changing) viruses trick the natural security mechanisms by changing their unique signatures (e.g. DNA or proteins). In computing, antivirus software systems are adapted to detect and remove constantly changing software viruses. However, polymorphism at the firmware level and over the wireless medium is neither well understood nor explored for IoT devices. This paper proposes a novel and bio-inspired framework for securing distributed IoT devices often assumed to be working at the intersection of engineering, computing, and cybersecurity domains. The proposed framework attempts to exploit the notion of polymorphism in resource-constrained (e.g. memory, power, bandwidth) IoT devices. The framework’s core aim is to detect, reject, and block foreign agents individually or collaboratively and in real-time within a client and server model by changing the access credentials and encryption keys as soon as an unauthorised client is detected. The framework proposed for the bio-inspired framework for security in IoT devices is designed to remain operationally compartmentalised, functionally integrated, and objectively unified. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

IoT-Based Horticulture Monitoring System

With climate change and global warming in mind, vertical farms, hydroponics and urban greenhouses can now be found in many cities worldwide as we transform the ways we produce food. Additionally, recent implications of the COVID-19 pandemic prove that as a society we can harness the benefit of remote monitoring and automation for controlled-environment agriculture and horticulture. The subject matter of this paper is implementation of a solar-powered, Internet of Things (IoT)-based Real-time Autonomous Horticulture Monitoring System (RAHMS). The RAHMS integrates a mobile application for viewing the greenhouse crop data and camera feed of plants, and interacts with cloud databases such as Firebase and MATLAB ThingSpeak for the scalability. In particular, a simple and distinctive design of a solar-powered, low energy consuming, and inexpensive greenhouse monitoring system is presented. The paper outlines RAHMS design methodology and showcases a proof-of-concept prototype with its core hardware and software components. The proposed system has a potential to further advance the practical aspects of the remote solutions for the cultivation and monitoring of horticulture and controlled-environment agriculture. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

Effects of Covid-19 on Patients with Cardiovascular Diseases: A Systematic Review

Aim of Object: During the COVID-19 pandemic, the entire world is experiencing a mortality situation;most people are battling against the corona virus, but some individuals have already suffered from cardiovascular problems. For improved patient care, adequate information and comprehension of the relationship between cardiovascular disorders and COVID-19 is required. The dominant clinical manifestations of the corona virus infection are on the respiratory system. In this instance, the acute cardiac injury is the most often reported cardiac abnormality, in which the degree of cardiac output is increased, troponin levels rise, and mostly it is found in about 8% to 12% of patients. The involvement of viral cardiomyocytes and systemic inflammation is the most prevalent mechanism for cardiac damage. The corona virus attaches itself and enters through angiotensin converting enzyme-II. Discussion and Conclusion: Recent articles on COVID-19 have revealed nothing regarding these individuals' cardiac vascular manifestations. This is a critical component of all that has a big influence on COVID-19 patients' cardiovascular systems. To fully comprehend the method and effects, more study is required.

Data visualization using machine learning for efficient tracking of pandemic - COVID-19

From the first case in December 2019 to more than 2.92 million cases in just 3 months, COVID-19 became a pandemic. COVID-19 is spreading all around the world, and due to this pandemic situation, humans’ life is at risk. On one side, healthcare and sanitization workers are stretching themselves to deal with this situation at the frontline, and on the other, data scientists and machine learning (ML) experts are researching to provide data in an understandable form to the world. This chapter provides the details of different ways of processing and visualizing the huge amount data generated on this pandemic. This includes the clusters on the basis of symptoms in different age groups, effects of COVID-19 on different countries, etc. © The Institution of Engineering and Technology 2021.

Current updates on diagnostic methods available for COVID-19 infection

The abrupt pandemic set off by the novel coronavirus 2019 (COVID-19) has caused severe chaos among people worldwide. ''SARS-CoV2'', a previously unknown strain of coronaviruses caused a severe respiratory disease called Coronavirus disease (COVID-19) which emerged from Wuhan city of China on 30 December 2019 and declared as Universal health problem by the World Health Organisation in a month. COVID-19 has created panic, and scientists are urged to test the efficiency and safety of drugs used to treat this disease. Various diagnostic kits to test for COVID-19 are available, and repurposing therapeutics for (COVID-19 has shown to be clinically effective). In the analytic stage, real-time reverse transcription-PCR (RT-PCR) assays remain the molecular test of choice for the etiologic diagnosis of SARS-CoV-2 infection while antibody-based techniques are being introduced as supplemental tools. In the post-analytical stage, testing results should be cautiously interpreted using both molecular and serological findings. This review discusses the updates on specimens/samples and recent efficient diagnostics to control the disease. It covers the latest issues and challenges for the laboratory diagnosis of infections caused by severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2).

Crisis behind closed doors domestic workers' struggles during the pandemic and beyond

The impact of the national lockdown due to COVID-19 on domestic workers in New Delhi and Gurugram is examined. Through extensive surveys with members of three labour unions, it was found that not only were domestic workers able to fi nd less work, but were also paid lower wages, while unable to access government schemes or fi nancial or in-kind support from their employers. This points to a dire need for policies that protect domestic workers' interests. © 2021 Economic and Political Weekly. All rights reserved.

A Social Distance Monitoring System to ensure Social Distancing in Public Areas

Social distancing measures are important to reduce Covid spread. In order to break the chain of spread, social distancing is strictly followed as a norm. This paper demonstrates a system which is useful in monitoring public places like ATMs, malls and hospitals for any social distancing violations. With the help of this proposed system, it would be conveniently possible to monitor individuals whether they are maintaining the social distancing in the area under surveillance and also to alert the individuals as and when there is any violations from the predefined limits. The proposed deep learning technology based system can be installed for coverage within a certain limited distance. The algorithm could be implemented on the live images of CCTV cameras to perform the task. The simulated model uses deep learning algorithms with OpenCV library to estimate distance between the people in the frame, and a YOLO model trained on COCO dataset to identify people in the frame. The system has to be configured according to the location it is being installed at. By implementing the algorithm, the number of violations are reported based on the distance and set threshold. Number of violations reported are one and two for two real time images respectively. The red box highlighting the violations are displayed along with distance. Reporting efficiency and correctness were validated for more number of samples. © 2021 IEEE.

Abstract No. 527 High incidence of large-bore temporary hemodialysis catheter thrombosis in patient with COVID-19–related kidney injury

Purpose: To evaluate the incidence of large-bore hemodialysis catheter thrombosis in the setting of COVID-19. Materials and Methods: A retrospective review was performed of all patients who underwent placement of a temporary hemodialysis catheter after developing kidney injury after COVID 19 infection at our institution. Data collected included demographic information, procedure related information, and incidence of replacement due to lumen thrombosis. Groups were compared using students t-test for continuous variables and Fisher’s exact test for nominal variables. Results: 64 patients (43M, mean age 63.2 ± 13.3) underwent placement of temporary hemodialysis catheter placement for kidney injury related to COVID 19 infection. 31 (48.4%) of catheters were placed via an internal jugular vein (IJV) access and 33 (52.6%) of catheters were placed via a common femoral vein (CFV) access. Overall, 15 (23.4%) catheters required replacement due to lumen thrombosis despite heplock. There were no difference in age or sex in patients who required replacement to those who did not (P.0.05) [sic]. Of the replacements, 5/31 (16%) were placed via an IJV access and 10/33 (30.3%) were placed via a CVF access, although this difference was not statistically significant (P = 0.18). The average time to malfunction/replacement was 7.8 ± 4.8 days for catheters placed via an IJ access versus 3.4 ± 3.3 days for catheters placed via a CFV access (P = 0.055), trending toward significance. Conclusions: A high incidence of temporary dialysis catheter lumen thrombosis was present in patients with COVID-19 infection. This may be due to COVID related thrombosis versus decreased level of catheter care. Catheters placed via a femoral vein access had more frequent malfunction and with shorter indwelling time, although not significant, which may be due to small sample size.