A Review of Deep Learning and Machine Learning Approaches in COVID-19 Detection

COVID-19 resulted from SARS-CoV-2 and has disastrous effects on human. It has obliged researchers worldwide to exploit approaches for an accurate and reliable diagnostic tools for it early detection. However, the pandemic nature of this disease has made the traditional diagnostic methods ineffective. Artificial Intelligence (AI) researchers have come up with a number of promising algorithms to attain most effective and rapid classification system that can alternate the tedious and time consuming traditional diagnostic techniques. These algorithms used either Computed Tomography (CT) images, X-ray images or both for COVID-19 classification. The most recent exploited Deep Learning (DL) and Machine Learning (ML) approaches along with feature extraction techniques mostly on CT images are reviewed in this paper. The overall accuracy of these techniques ranged from 86.1% to 99.7% which indicate that they are applicable in COVID-19 detection. This paper will assist researchers in future development of these techniques for COVID-19 diagnosis. © 2022 IEEE.

Utilization of Transfer Learning Model in Detecting COVID-19 Cases From Chest X-Ray Images

Diagnosis of COVID-19 pneumonia using patients' chest x-ray images is new but yet important task in the field of medicine. Researchers from different parts of the globe have developed many deep learning models to classify COVID-19. The performance of feature extraction and classifier plays a vital role in the recognizing the different patterns in the image. The pivotal process is the extraction of optimum features from the chest x-ray images. The main goal of this study is to design an efficient hybrid algorithm that integrates the robustness of MobileNet (using transfer learning approach) to extract features and support vector machine (SVM) to classify COVID-19. Experiments were conducted to test the proposed algorithm, and it was found to have a high classification accuracy of 95%.

Interactive and Innovative Technologies for Smart Education

New concepts and ideas have emerged in the process of obtaining and disseminating cognitive, ethical, and public knowledge. In the current state of education, learners, tutors, and the knowledge being transferred are all present, and smart education has made the process of acquiring knowledge more flexible. This concept is accomplished through the use of smart devices and technologies that are interconnected to access digital resources. Smart education refers to a new way of learning that has gotten a lot of attention, notably during the 2020 Covid-19 Pandemic. This article examines the technologies that have aided smart education in achieving its educational goals. With smart technological solutions, modern technologies are enhancing the teaching-learning process in today’s education. It is with great hope that the use of modern technologies in smart education will improve educational quality while also making teaching and learning more convenient. © 2022, ComSIS Consortium. All rights reserved.

Deep Learning Models for COVID-19 Detection

Healthcare is one of the crucial aspects of the Internet of things. Connected machine learning-based systems provide faster healthcare services. Doctors and radiologists can also use these systems for collaboration to provide better help to patients. The recently emerged Coronavirus (COVID-19) is known to have strong infectious ability. Reverse transcription-polymerase chain reaction (RT-PCR) is recognised as being one of the primary diagnostic tools. However, RT-PCR tests might not be accurate. In contrast, doctors can employ artificial intelligence techniques on X-ray and CT scans for analysis. Artificial intelligent methods need a large number of images;however, this might not be possible during a pandemic. In this paper, a novel data-efficient deep network is proposed for the identification of COVID-19 on CT images. This method increases the small number of available CT scans by generating synthetic versions of CT scans using the generative adversarial network (GAN). Then, we estimate the parameters of convolutional and fully connected layers of the deep networks using synthetic and augmented data. The method shows that the GAN-based deep learning model provides higher performance than classic deep learning models for COVID-19 detection. The performance evaluation is performed on COVID19-CT and Mosmed datasets. The best performing models are ResNet-18 and MobileNetV2 on COVID19-CT and Mosmed, respectively. The area under curve values of ResNet-18 and MobileNetV2 are 0.89% and 0.84%, respectively. © 2022 by the authors. Licensee MDPI, Basel, Switzerland.

Wi-Fi Attendance System in the IoT Era

Traditionally, attendance is marked manually by students writing down their name on a paper. This whole process wastes some of lecture time and might even get lost. Maintaining the attendance of the students in an institution is a hefty task. This project aims at designing a smart attendance system that automatically monitors and manages attendance of the students in an institution efficiently. The system is developed with an Arduino ESP8266 Wi-Fi microcontroller deployed in the class room. Further, Wi-Fi communication modules was used to make convenient communication between the student’s devices e.g. phone or laptop and the ESP8266 Wi-Fi microcontroller. Database was created where the attendance submitted will be logged and saved. Internet is utilized to transfer the information collected by the micro controller to the database and from the database to the front-end web page GUI graphical user interface. The students and admin will make one-time registration and subsequently establishing a Wi-Fi connection between the student’s device and the microcontroller in the class to mark an attendance. This system will arrange the attendance in a list with a real time timestamp and save it to database, and also be accessible to the lecturer/Admin over internet any time with uses of web browser e.g. Google chrome through the front end graphic user interface (GUI). This system is useful to reduce manual method of attendance by teachers and to alleviate the spread of COVID-19. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.

Particle Swarm Optimization for Adaptive Social-distance of Neighborhood in the IoT and COVID-19 Era

While it is well understood that the emerging Social Internet of Things (SIoT) offers a description of a new world of billions of humans which are intelligently communicate and interact with each other. SIoT presents new challenges for suggesting useful objects with certain services for people. This is due to the limitation of social networks between human and objects, such as the evaluation of the various patterns inherent in human walk in cities. In this study we focus services on the problem of recommendation on SIoT which is very important for many applications such as urban computing, smart cities, and health care. The optimized results of swarm of certain infected people COViD-19 introduced in this paper aims at finding a given region of interest. Guided by a fitness function, the particle swarm optimization (PSO) algorithm has proved its efficiency to explore the search space and find the optimal solution. However, in real world scenarios in which the peoples are simulated as particles, there are practical constraints that should be taken into considerations. The most two significant constraints are (1) given the social-distance, the measurement of input variable fluctuations and their possibility of occurring via probability distribution function over the whole particles. (2) given the limited the communication range of particle/people/users, therefore, the spread of the diseases are simulated and evaluated using neighborhood particle swarm optimization (NPSO). © 2021 IEEE.

Investigating the Spread of Coronavirus Disease via Edge-AI and Air Pollution Correlation

Coronavirus Disease 19 (COVID-19) is a highly infectious viral disease affecting millions of people worldwide in 2020. Several studies have shown that COVID-19 results in a severe acute respiratory syndrome and may lead to death. In past research, a greater number of respiratory diseases has been caused by exposure to air pollution for long periods of time. This article investigates the spread of COVID-19 as a result of air pollution by applying linear regression in machine learning method based edge computing. The analysis in this investigation have been based on the death rates caused by COVID-19 as well as the region of death rates based on hazardous air pollution using data retrieved from the Copernicus Sentinel-5P satellite. The results obtained in the investigation prove that the mortality rate due to the spread of COVID-19 is 77% higher in areas with polluted air. This investigation also proves that COVID-19 severely affected 68% of the individuals who had been exposed to polluted air.

COVID-19 Detection on CT Scans Using Local Binary Pattern and Deep Learning

X-ray and CT scans show lungs, and images can be used to differentiate positive and negative cases. Analyzing these scans using an artificial intelligent method might provide fast and accurate COVID-19 detection. In this paper, a local binary pattern based deep learning method is proposed for the detection of COVID-19 infection on CT Scans. The proposed technique generates local binary pattern (LBP) representations of the CT scans, and then these representations are modeled using fine-tuned models. The fine-tuned models are AlexNet, VGG, ResNet-18, ResNet-50, MobileNetV2, and DensNet-121. We show that the proposed local binary pattern based deep learning model provides higher performance than classic deep learning models for COVID-19 detection. The classification performance of the method provides 90 % AUC value for COVID-19 detection. © 2021, ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering.

5G Network Slicing Technology and Its Impact on COVID-19: A Comprehensive Survey

At the end of 2019, no one could have imagined how the world will dramatically change. A new outbreak has emerged causing millions of people to go into lockdown for their own safety. World Health Organization (WHO) has later announced this outbreak of Coronavirus Disease 2019 (COVID-19) as pandemic. This has caused huge stress to medical staff. The need for digital connectivity between communities and nations had arisen. Digital revolutionary services like telehealth, telemedicine, eVisit, etc. play a vital role in reducing the risk and fighting the spread of the pandemic. The industry and academia accept 5G as the potential network capable of serving vertical applications of next generation with specific service needs. In order to achieve this dream, the physical network must be separated into several separate functional blocks of various sizes and systems devoted to specific kind of services depending on their needs (a full slice for large eHealth apps, healthcare servers, IoT apps, smart cities and so on). Network slicing (NS) was described as the foundation of fast-growing 5G. Although, as its standardization advances and consolidation, few literatures which address main concepts, research challenges and service enablers, in a detailed way are available. In this paper these aspects should be provided and discussed. This study covers industry trends and requirements for 5G including both business drivers and performance requirements. Network slicing Key enabling technologies, architectures and implementations, standardization and future challenges will be discussed and briefly viewed. © 2021, ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering.

COVID-19 Patient Care: A Content-Based Collaborative Filtering Using Intelligent Recommendation System

COVID-19 is a more transferable illness caused by a new novel coronavirus. It is highly emerging with efficient biosensors such as sensitive and selective that afford the diagnostic tools to infer the disease early. It can maintain a personalized healthcare system to evaluate the growth of disease under proper patient care. To discover as a personalized technology, the healthcare system prefers collaborative filtering. It can effectively deal with cold-start and sparse-data to conduct useful extensions. Due to the continuous expansion of scaling data in a medical scenario, content-based, collaborative filtering, and similarity metrics are preferred. It relies on the most similar social users or threats when the information is large. Many neighbors gain importance to obtain a set of users with whom a target user is likely to match. Forming communities reveal vulnerable users and also reduce the challenges of collaborative filtering like data-sparsity and cold-start problems. Thus, this framework proposes content-based collaborative filtering using intelligent recommendation systems (CCF-IRS) based on high correlation and shortest neighbor in the social community. The result is shown that the proposed CCF-IRS achieves better accuracy than the existing algorithms. © 2021, ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering.

Automated Segmentation of COVID-19 Lesion from Lung CT Images Using U-Net Architecture

Pneumonia caused by the novel Coronavirus Disease (COVID-19) is emerged as a global threat and considerably affected a large population globally irrespective of their age, race, and gender. Due to its rapidity and the infection rate, the World Health Organization (WHO) declared this disease as a pandemic. The proposed research work aims to develop an automated COVID-19 lesion segmentation system using the Convolutional Neural Network (CNN) architecture called the U-Net. The traditional U-Net scheme is employed to examine the COVID-19 infection present in the lung CT images. This scheme is implemented on the benchmark COVID-19 images existing in the literature (300 images) and the segmentation performance of the U-Net is confirmed by computing the essential performance measures using a relative assessment among the extracted lesion and the Ground-Truth (GT). The overall result attained with the proposed study confirms that, the U-Net scheme helps to get the better values for the performance values, such as Jaccard (>86%), Dice (>92%) and segmentation accuracy (>95%). © 2021, ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering.

IoT and AI for COVID-19 in Scalable Smart Cities

COVID-19 which is also known as the novel coronavirus started from China. Motivated by continuous advancement and employments of the Artificial Intelligence (AI) and IoT in various regions, in this study we focus on their underlining deployment in responding to the virus. In this survey, we sum up the current region of AI applications in clinical associations while battling COVID-19. We moreover survey the component, challenges, and issues identified with these technologies. A review was made in requesting AI and IoT by then recognizing their applications in engaging the COVID-19. In like manner, emphasis has been made on a region that utilizes cloud computing in combating diverse similar diseases and the COVID-19 itself. The investigated procedures set forth drives clinical information examination with an exactness of up to 95%. We further end up with a point by point discussion about how AI utilization can be in an ideal situation in battling diverse diseases. This paper gives masters and specialists new bits of information in which AI and IoT can be utilized in improving the COVID-19 situation, and drive further assessments in ending the flare-up of the infection. © 2021, ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering.

Application of IoT, AI, and 5G in the Fight Against the COVID-19 Pandemic

Coronavirus disease 2019 (COVID-19) outbreak has affected people worldwide and radically changed routine functions to mankind. We have to use our gifted intelligence as a species on this earth to encounter this novel coronavirus. Using technology, proper governance, healthcare, and coordinated public behavior can help to mitigate the risk. The technological support in dealing with this situation is irreplaceable. In this paper, we are discussing the use of IoT, AI, and 5G technologies to manage the outbreak. We touch a number of areas where IoT, AI, and 5G play an essential role in mitigating the COVID-19’s effect. This survey paper also focuses on different ways in which IoT, AI, and 5G technologies can be used to improve people’s health while assuring the accuracy in drug and medicine delivery process. We have overviewed several examples of the technologies that are being used and will be used for more advanced and safer healthcare in the future. © 2021, The Author(s), under exclusive license to Springer Nature Switzerland AG.

Application of AI Techniques for COVID-19 in IoT and Big Data Era: A Survey

The infectious novel coronavirus (COVID-19) is said to have originated from China. The COVID-19 pandemic has spread over a hundred nations and regions on the planet and has fundamentally influenced each part of our day-by-day lives. As of present, the quantities of COVID-19 cases and deaths despite everything increment fundamentally and do not indicate a very much controlled circumstance;over a thousand cases have been accounted for around the world. Artificial intelligence (AI) goal is to adapt to human conceptual cutoff points. It is getting an outlook on human organizations, filled by the developing accessibility of helpful clinical information and the snappy movement of keen systems. Inspired by ongoing progress and uses of the artificial intelligence (AI) and Big Data in different territories, in this survey we target their underlying significance in reacting to the coronavirus flare-up and forestalling the extreme effect of the epidemic. In this survey, we initially summarize the current territory of AI applications in clinical organizations while combating COVID-19. Besides, we feature the use of Big Data while cubing this infection. We additionally review the feature, difficulties, and issues related to discovering solutions. An overview was made in ordering AI and Big Data, at that point distinguishing their applications in battling against COVID-19. Likewise, an accentuation has been made on districts that use cloud computing in battling different comparable infections to COVID-19 and COVID-19 itself. The explored strategies put forth propel clinical data investigation with a precision of up to 90%. We further end up with a point-by-point conversation about how AI usage can be in a favorable position in fighting different comparative infections. This paper gives specialists and researchers new bits of knowledge into the manners in which AI and Big Data can be used in improving the COVID-19 circumstance and drive further examinations in halting the outbreak of the virus. © 2021, The Author(s), under exclusive license to Springer Nature Switzerland AG.

Artificial Intelligence in face of the Novel CoronaVirus

Artificial intelligence (AI) technology has been one savior in fighting the novel coronavirus pandemic. Moreover, it is helping to accelerate the reduction in costs associated with COVID-19 and speeding up efforts to overcome it. AI fields of applications can be classified according to the measures that have been taken against the pandemic: identification, detection, prevention, prediction, and therapeutic. Dataset collection is one of the most critical issues facing researchers who apply AI models, who tend to use augmentation data to make up for the lack of an actual dataset. According to our study, in this survey we find that the majority of COVID-19 solutions focus on how to apply AI techniques, how to collect real data, and how to further develop existing AI methods used in attacking this pandemic. © 2021, The Author(s), under exclusive license to Springer Nature Switzerland AG.

Smart Technologies for COVID-19: The Strategic Approaches in Combating the Virus

As the world navigates through the turbulent waters herald by the coronavirus pandemic, digital technologies and the Internet of Things (IoT) have crucial roles to play in bringing lasting solutions. From dissemination of information about COVID-19, protection from the virus, detection of the infected ones, and to the treatment, digital technology has been the best to help and support. This chapter reviews the use of smart technologies in the fight against COVID-19 and suggests the approaches to be adopted in this battle. It examines various digital technologies that have been applied in the fight so far and recommends adjusted ways for better results. This chapter discusses the benefits of the application of the digital technology in health sectors and highlights the challenges which have been encountered. © 2021, The Author(s), under exclusive license to Springer Nature Switzerland AG.

Technology Landscape for Epidemiological Prediction and Diagnosis of COVID-19

The COVID-19 outbreak initiated from the Chinese city of Wuhan and eventually affected almost every nation around the globe. From China, the disease started spreading to the rest of the world. After China, Italy became the next epicentre of the virus and witnessed a very high death toll. Soon nations like the USA became severely hit by SARS-CoV-2 virus. The World Health Organisation, on 11th March 2020, declared COVID-19 a pandemic. To combat the epidemic, the nations from every corner of the world has instituted various policies like physical distancing, isolation of infected population and researching on the potential vaccine of SARS-CoV-2. To identify the impact of various policies implemented by the affected countries on the pandemic spread, a myriad of AI-based models have been presented to analyse and predict the epidemiological trends of COVID-19. In this work, the authors present a detailed study of different artificial intelligence frameworks applied for predictive analysis of COVID-19 patient record. The forecasting models acquire information from records to detect the pandemic spreading and thus enabling an opportunity to take immediate actions to reduce the spread of the virus. This paper addresses the research issues and corresponding solutions associated with the prediction and detection of infectious diseases like COVID-19. It further focuses on the study of vaccinations to cope with the pandemic. Finally, the research challenges in terms of data availability, reliability, the accuracy of the existing prediction models and other open issues are discussed to outline the future course of this study.