Early-Stage Detection of Covid-19 Patient using ML Model: A Case Study

The Covid-19 pandemic has drastically changed the daily living style of human beings by astonishing the cultural, educational, regional, business, social, and marketing activities within a limited boundary. It also has impacted the healthcare system globally and provided a lot of burden on the healthcare system. The circumstances that arose due to such a pandemic require a vital solution to deal with it. In such a situation, most innovative technologies have grown up to find alternative solutions to track the situation that arises due to Covid-19. Among all innovative technologies, IoT can be counted as the best approach to deal with such a type of pandemic due to its associated features of transmitting data from any remote location without human intervention. Such type of technology has the capability of providing connectivity among various medical devices either in hospitals or other deliberate places to deal with such type of pandemic. First of all, this paper introduces the concept of IoT to deal with the circumstances of the Covid-19 pandemic. Along with that, a framework of a real-time Covid-19 patient monitoring system has been proposed in this paper that can be utilized in the future. The proposed framework helps in monitoring the symptoms of Covid-19 infected patients. On the basis of that model, a case study is done on Covid-19 symptom data by using different ML algorithms. The findings indicate that all algorithms achieved an accuracy of more than 80% and RFT achieved the highest accuracy of 92%. Based on these findings, we believe that these algorithms will produce efficient and precise outcomes when applied to real-time symptom data. © Ismail Saritas. All rights reserved.

Predicting Intensive Care Unit Admission Using Machine and Deep Learning: COVID-19 Case Study

The COVID-19 pandemic has affected the entire world by causing widespread panic and disrupting normal life. Since the outbreak began in December 2019, the virus has killed thousands of people and infected millions more. Hospitals are struggling to keep up with large patient flows. In some situations, hospitals are lacking enough beds and ventilators to accommodate all of their patients or are running low on supplies such as masks and gloves. Predicting intensive care unit (ICU) admission of patients with COVID-19 could help clinicians better allocate scarce ICU resources. In this study, many machine and deep learning algorithms are tested over predicting ICU admission of patients with COVID-19. Most of the algorithms we studied are extremely accurate toward this goal. With the convolutional neural network (CNN), we reach the highest results on our metrics (90.09% accuracy and 93.08% ROC-AUC), which demonstrates the usability of these learning models to identify patients who are likely to require ICU admission and assist hospitals in optimizing their resource management and allocation during the COVID-19 pandemic or others. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

Deep Learning for Detection and Prediction of Covid-19 Virus on CT-Scan Image Dataset

As we all know, COVID-19 appears to be having a terrible impact on world health and well-being. Furthermore, at its peak, the COVID-19 cases worldwide reached a huge number i.e., in millions. The objective of the present work is to develop a model that detects COVID-19 utilizing CT-Scan Image Dataset and DL Techniques. As the number of verified cases rises, it becomes more critical to monitor and precisely categorize healthy and infected people. RT-PCR testing is the most used approach for the detection of Covid-19. However, several investigations have found that it has a low sensitivity in the early stages. Computer tomography (CT) is also used to detect image-morphological patterns of COVID-19-related chest lesions. The RT-PCR technique for diagnosing COVID has some drawbacks. For starters, test kits are insufficiently available, necessitating greater testing time and the sensitivity of testing varies. Therefore, employing CT scan pictures to screen COVID-19 is essential. The results showed that CT scan pictures might efficiently identify COVID-19, saving more lives. A Convolutional Neural Network (CNN) is a sort of Artificial Neural Network that is commonly used for image/object detection with class. An Input layer, Hidden layers, and an Output layer are common components of a neural network (NN). CNN is inspired by the brain's architecture. Artificial neurons or nodes in CNNs, like neurons in the brain, take inputs, process them, and deliver the result as output. Illness severity can be detected and calculated for future scopes and research. Another challenge encountered when dealing with severity infection detection and extending the existing work by using frameworks in order to increase accuracy. The proposed ECNN technique outperformed than CNN in terms of accuracy (95.35), execution time, and performance. This study could be extended or improved in the future by directing severity identification on the CT-Scan image dataset. © 2023 IEEE.

Accurate Machine Learning Algorithm for Monkey Pox Based on Covid-19

The Covid-19 virus is still marching all over the world. Many people are getting infected and a few are fatal to death. This research paper expressed that supervised learning has revealed supreme results than unsupervised learning in machine learning. Within supervised learning, random forest regression outplays all other algorithms like logistic regression (LR), support vector machine (SVM), decision tree (DT), etc. Now monkeypox is escalating in other countries at present. This virus is allied to human orthopox viruses. It can expand from one to one through contact person having rash or body fluids etc. The symptoms of monkeypox are much similar to covid19 virus-like fever, cold, fatigue, and body pains. Herewith we concluded that random forest regression shows possible foremost (97.15%) accuracy. © 2023 IEEE.

Autonomous UAV with obstacle management using AIoT: a case study on healthcare application

With the simultaneously connected 26.66 billion devices worldwide, the Internet of Things (IoT) is becoming a vast field of research and helping hand to every individual. However, when IoT and Artificial Intelligence (AI) and machine learning (ML) consolidate, it results in smart applications and future revolutions that are known as Artificial Intelligent of Things (AIoT). Similarly, the unmanned aerial vehicle (UAV) domain is also developing daily, helping many unrest people in the healthcare industry. One step towards developing the healthcare industry is the use of UAV devices like drones embedded with AIoT to work autonomously in the healthcare industry. This can help the healthcare industry in many ways. This chapter proposes an algorithm to recast these UAV drones to autonomous UAV drones and use them as intelligent or smart for various healthcare purposes like COVID-19. The proposed autonomous UAV drone uses Raspberry Pi 3, a Hubney, and a bearing formula to automatically determine the direction of the UAV movement, making it work without any controller. Also, the comparative study presented in this chapter highlighted the benefits of this proposed algorithm with others present in the literature.

A Decision Support System Based on Machine Learning to Counteract Covid-Like Pandemic Events

In this paper, the authors aim to design a decision support system (DSS) based on machine learning (ML) to assist institutions in implementing targeted countermeasures to combat and prevent emergencies such as the COVID -19 pandemic. The DSS relies on an ensemble of several ML models that combine heterogeneous data to predict risk levels at the micro and macro levels. Some preliminary analyses have already been conducted showing the correlation between nitrogen dioxide (NO2), mobility-related parameters, and COVID -19 data. However, given the complexity of the virus spread mechanism, which is related to many different factors, these preliminary studies confirmed the need to perform more in-depth analyses on the one hand and to use ML algorithms on the other hand to capture the hidden relationships between the huge amounts of data that need to be processed.

Successful Role of Data Science In Managing Covid-19 Battle

The corona pandemic's wild and unchecked spread over more than a few months around the world is a worldwide problem. To solve this worldwide issue, information technology innovation is employed along with medicine, biotechnology, and medical equipment. The fight against COVID-19 is greatly aided by Machine-Learning (ML), Artificial-Intelligence (AI), and data science (DS). By utilising such technologies, there is a good chance that the pandemic may be stopped, and that life can return to normal, as it did before the pandemic. In this essay, many technologies are analysed in relation to various situations, including social exclusion and prevention, confinement and isolation, corona virus testing and detection, management of the hospital, patient care, and therapy. This study provides transparent planning, technological techniques, digital procedures, together with the most recent smart technology in a number of disciplines, to battle the severity of the coronavirus. © 2023 IEEE.

Machine learning methods and approaches for predicting Covid19

The extensive existence about COVID-19 diseases has led to global initiatives to regulate and manage the virus with the goal of eradicating it. Machine Learning (ML) is one key for analyzing and combating COVID-19 in line with research. This is a hotly debated topic right now. Even though numerous studies are in line with medical literature, there is a requirement to follow maintain with fast-increasing quantity of papers on ML applications connected to COVID-19. Day-to-day information on the COVID-19 virus's transmission is critical for assessing the virus's global behavior. As a result, in the state of COVID-19, this paper examines forecasting methods for COVID-19 affected instances utilizing existing machine learning methods. Most of the ML algorithms used in the early detection and diagnosis of contagion are guided learning methods. The prognosis features reported by ML models are in line with medical literature findings. Many of the relevant studies are still in their early phases. One of the limitations of machine learning approaches is the use of unbalanced datasets exposed to bias in selection. © 2023 Author(s).

Multilayer Perceptron Neural Network Approach to Classifying Learning Modalities Under the New Normal

Because of community quarantines and lockdowns during COVID–19 times, the Philippine’s Department of Education (DepEd) implemented blended learning (BL) both online and offline distance learning modalities (LM) among basic educational institutions in the hope of continuing learners’learning experiences amidst the pandemic. Learners’LM are classified through the use of an Algorithm for Learning Delivery Modality as recommended by DepEd. Based on initial investigation, mismatches in learners’LM were, however, observed, resulting in learners’massive shifting from one LM to another in the middle of the school year. In this study, we introduced an approach to classifying learner’s LM using machine learning (ML) techniques. We compared the effectiveness of five ML classifiers, namely the random forest (RF), multilayer perceptron neural network (MLP NN), K-nearest neighbor (KNN), support vector machine (SVM), and Naïve Bayes (NB). Learner’s enrolment and survey form (LESF) data from the repository of a local private high school in the Philippines is used in model formulation. We also compared three existing feature selection (FS) algorithms (recursive feature elimination (RFE), Boruta algorithm (BA), and ReliefF)–integrated into the five ML classifiers as data feature reduction techniques. Results show that the combination of MLP NN and BA yielded a considerably high performance among the rest of the formulated models. Sensitivity analysis revealed that asynchronous LM is most sensitive to “existing health condition”feature, modified asynchronously, is highly characterized by low educational attainment and unstable employment status of parents or guardians, while synchronous learners have high socio–economic status as compared to other LM. IEEE

Concepts and techniques in deep learning applications in the field of IoT systems and security

Deep learning (DL), a subdivision of machine learning (ML), i.e., an integral part of artificial intelligence used in various applications in today's life. At present, machine learning approach is almost completely dependent on DL techniques, which produce accurate results with the help of human centric nature of learning. It has gone off in the community awareness, mostly as extrapolative and analyt-ical products that saturate our planet in most useful, organized, and time- and cost-competent method of ML approach. There are some algorithms, like genera¬tive adversarial networks, multilayer perceptions, convolution neural networks, or self-organizing maps, that have entirely changed the thinking toward information processing means. Currently, DL is using in numerous domains like knowledge, commerce, science, administration sectors;it can be employed on novel corona virus prediction, detection, and analysis of clinical and method logical character¬istics too is also a matter of discussion here. Our work is absolutely displays on the notion of crucial sophisticated design, method, inspirational characteristics and constraint of DL. This writing section describes a detailed analysis of chronolog¬ical and modern trailblazing approaches to the distribution of conjecture, myth, and text;social network analysis;and innovative advances in natural language pro¬cessing, extensive research around spin, and in-depth learning activities. The main target of this work is to describe the newly developed DL techniques for Internet of Things (IoT) architecture and its security. IoT security threats associated with the underlying or newly introduced threat are talked about and diverse possible IoT system attacks and probable threats connected to all facets are thrashed out. The possibilities, advantages, and limitations of both systems are illustrated systematically by analyzing the DL strategy aimed at IoT security. We provide perspectives and related issues regarding IoT security from ML/DL. Discussed approaches and problems of potential expectations can serve as research guide-lines for the future endeavor. © 2023 Scrivener Publishing LLC. All rights reserved.

IoT & ML-Based Healthcare Monitoring System-Review

Intelligent medical management is one of several modern city and society management fields where the Internet of Things (IoT) is essential. Smart cities' current engagement between technology and the health care system is strengthened by the intelligent IoT's limitless networking capabilities for big data analysis in medicine. Allows for more practical methods for efficiently monitoring patients' health and providing medical services remotely online assessment of patients' health status by doctors, nurses, and other healthcare professionals. The of the current study aims to provide a full examination of the function of IoT in medical management systems, analyse the available concerns, and address many of the open questions. It also aims to provide an up-to-date and comprehensive review of this field. Enabling technology and hints at a variety of uses There have been suggested research plans. The following are some examples of IoT applications from previous studies: wearable technology, monitoring technology, rehabilitation technology, telehealth, behaviour modification, smart city, and smart home. This comprehensive review identifies the crucial elements that make it possible to comprehend the healthcare possibilities and obstacles providers to put IoT applications into action. Lastly, anticipated COVID-19 effects on IoT uptake this review assessed in the field of healthcare. © 2022 IEEE.

Hybrid Data mining Based Breast Prediction of COVID-19

Coronavirus, Corona Virus Disease-2019, brought about by an original Severe Acute Respiratory Syndrome Corona Virus 2 (SARS-CoV-2). A compelling screening of this infection can empower speedy and proficient finding of COVID-19 can diminish the weight on the medical care framework. A nitty gritty examination gave dataset can assemble unique and different kinds of AI calculations, which their exhibition could be processed and further assessed. This paper proposed a mixture information mining method that coordinated Random Forest with SVM (Support Vector Machines). The accompanying case proposed model is to beat the wide range of various Machine Learning models like SVM, Decision Tree, KNN and Logistic Regression. © 2023 American Institute of Physics Inc.. All rights reserved.

Rate Insight: A Comparative Study on Different Machine Learning and Deep Learning Approaches for Product Review Rating Prediction in Bengali Language

In this contemporary era of digital marketing, ecommerce has emerged as one of the most preferred methods for day-to-day shopping. Ever since the COVID-19 pandemic, online shopping behavior has forever changed to less or no human-to-human interaction. As a result, it is getting more difficult for e-commerce enterprises to observe and evaluate market trends, particularly when done through consumer behavior analysis. To identify behavioral patterns and customer review-rating discrepancies, extensive analysis of product reviews is a substantial research field. Lack of benchmark corpora and language processing techniques, predicting review ratings in Bengali has become increasingly problematic. This paper thoroughly analyzes the approach to product review rating prediction for Bengali text reviews exploiting our own constructed dataset that was collected from an e-commerce website called DarazBD1. We acquired product reviews with labels known as ratings of five sentiment classes, from "1"to "5". It is noteworthy that we established a well-balanced dataset using our automated scraping system and a significant amount of time and effort is spent to maintain quality standards through the human annotation process. Exploration of multiple approaches to machine learning models such as logistic regression, random forest, multinomial naïve Bayes, and support vector machine, the best classification accuracy score of 78.63% is achieved by SVM. Subsequently, using Word2Vec, FastText, and GloVe embeddings with three deep neural network(DNN) architectures: CNN, Bi-LSTM, and a combination of CNN and Bi-LSTM, CNN+Bi-LSTM gave the highest accuracy score of 75.25% among the DNN architectures. © 2022 IEEE.

A Comprehensive Review of Scab Disease Detection on Rosaceae Family Fruits via UAV Imagery

Disease detection in plants is essential for food security and economic stability. Unmanned aerial vehicle (UAV) imagery and artificial intelligence (AI) are valuable tools for it. The purpose of this review is to gather several methods used by our peers recently, hoping to provide some knowledge and assistance for researchers and farmers so that they can employ these technologies more advantageously. The studies reviewed in this paper focused on Scab detection in Rosaceae family fruits. Feature extraction, segmentation, and classification methods for processing the UAV-obtained images and detecting the diseases are discussed briefly. The advantages and limitations of diverse kinds of UAVs and imaging sensors are also explained. The widely applied methods for image analysis are machine learning (ML)-based models, and the extensively used UAV platforms are rotary-wing UAVs. Recent technologies that cope with challenges related to disease detection using UAV imagery are also detailed in this paper. Some challenging issues such as higher costs, limited batteries and flying time, huge and complex data, low resolution, and noisy images, etc., still require future consideration. The prime significance of this paper is to promote automation and user-friendly technologies in Scab detection.

An effective classification of Skin Disease using Deep Learning Techniques

According to WHO, Skin Infection is very common but sometimes very serious and affects a large no population all over the world. Monkeypox, Chickenpox, and Measles are the major infectious disease that causes skin infection all over the world. It has been obverse that the cases of Monkeypox have drastically increased as an effect of Covid 19. This infection has spread easily and exponentially that cause serious health issues in many underdeveloped and developing countries. Some time it has been observed that people are not able to properly classify the type of skin infection well in time, which can be a main reason of serious health issues. So, it became important to propose an effective classification of Skin Disease. In this paper the authors have proposed an effective classification of Skin Disease using Deep Learning Techniques. This approach will help in classification of chicken pox, measles, and monkeypox through skin images. The authors have utilized Monkeypox Skin Images Dataset (MSID) dataset to apply the proposed approach. The Loss, Accuracy, Precision, Recall, AUC, and F1 Score parameters have been used to analyze the performance of proposed approaches. The best algorithms with maximum accuracy and other parameters are Xception, EfficientNetV2L, and EfficientNetV2M, and CNN, VGG16, and VGG19 are the least favored algorithms for this research. © 2023 IEEE.

A WATERMARK-BASED SECURE MODEL FOR DATA SECURITY AGAINST SECURITY ATTACKS FOR MACHINE LEARNING ALGORITHMS

Machine Learning (ML) has been known as one of the most widely used by the decision-based application. Most of the security sensitive applications have been using DL for the improvement and betterment of outcomes while solving real-life applications. Poisoning and evasions attacks are the common examples of security attacks where the attacker deliberately inject malicious injections into the dataset to get the information of model settings and dataset. Hence, in this paper we have proposed a watermark-based secure model for ensuring data security and robustness against poisoning and evasion attacks before training and testing the DL algorithms. Our proposed model has been developed on ML algorithms e.g., eXtreme Gradient Boosting (XGBOOST) and Random Forest to ensure the data security against most common security attacks. We have evaluated proposed watermark based secure model using benchmark mechanism to show that the by introducing secure model, the performance has not been disturbed. We have computed prediction of daily cases on COVID-19 dataset and achieved similar results. Finally, our proposed model can detect significant attack detection rate even for large numbers of attacks (poisoning and evasion attacks). It is believed that our proposed model can also be implemented in other learning environment to mitigate the security issues and improve security applications. © School of Engineering, Taylor's University.

An Intensive Reviews on AI and its Impact on E-commerce

We now understand the value of practicing social distance thanks to COVID-19. The only way to meet our basic necessities in the year 2020 due to a sudden global lockdown was through e-commerce websites and online purchasing, and since technology has advanced, having a website online is now essential. All of these items, including meals, groceries, and our go-to clothing, are now available online. During the shutdown, it was seen that the firms with no social media presence faced significant losses. On the other hand, those who had already developed a web presence noticed a sharp increase in their overall sales. This research explores how recent developments in AI and ML have increased sales across a range of industries. After making a lot of observations and analyzing the consumer behavior patterns that affect sales, the ML model eventually contributes to the creation of an algorithm that is an effective recommendation system. This study also covers how transactions can be safeguarded and authenticated with the help of blockchain technology and cyber security, which has helped e-commerce businesses thrive by winning over customers' trust. © 2022 IEEE.

Role of artificial intelligence and internet of things based medical diagnostics smart health care system for a post-COVID-19 world

The present chapter is focused on the latest available technique and technology helpful in monitoring a large number of people having after corona disease effect. The most favorable way of monitoring a large number of people together can be possible only through the online wireless monitoring system. Artificial intelligence (AI) and machine learning (ML) technique-based systems can only handle this kind of post COVID scenario, as it is quick, accurate and many a time automatic. Thus present book chapter is focused on the review of the present latest AI/ML-based health monitoring systems. Separate sub-topics on cardiac, nephrology, and diabetics have been taken elaborately. The health monitoring system shall be capable of monitoring diseases such as cardiac, nephrology, and diabetes. Internet of things (IoT) wearable devices (medical sensors) are useful for recording various body parameters of the patient like comprehensive pressure, fever, physics activity, heart rate, etc. A real-time IoT-based system is capable to deliver the data to caregiving medical centers, doctors, or family members for proper treatment. IoT-based patient monitoring has a few drawbacks related to the error in analysis and acceptability among the medical fraternity. Other issues include security and privacy. Devices capture private health-related information and these data are highly vulnerable as being in the public domain through the internet. Thus it may attract unethical people for misuse. © 2023 Elsevier Inc. All rights reserved.

ADPT: An Automated Disease Prognosis Tool Towards Classifying Medical Disease Using Hybrid Architecture of Deep Learning Paradigm

The Covid 19 beta coronavirus, commonly known as the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2), is currently one of the most significant RNA-type viruses in human health. However, more such epidemics occurred beforehand because they were not limited. Much research has recently been carried out on classifying the disease. Still, no automated diagnostic tools have been developed to identify multiple diseases using X-ray, Computed Tomography (CT) scan, or Magnetic Resonance Imaging (MRI) images. In this research, several Tate-of-the-art techniques have been applied to the Chest-Xray, CT scan, and MRI segmented images' datasets and trained them simultaneously. Deep learning models based on VGG16, VGG19, InceptionV3, ResNet50, Capsule Network, DenseNet architecture, Exception and Optimized Convolutional Neural Network (Optimized CNN) were applied to the detecting of Covid-19 contaminated situation, Alzheimer's disease, and Lung infected tissues. Due to efforts taken to reduce model losses and overfitting, the models' performances have improved in terms of accuracy. With the use of image augmentation techniques like flip-up, flip-down, flip-left, flip-right, etc., the size of the training dataset was further increased. In addition, we have proposed a mobile application by integrating a deep learning model to make the diagnosis faster. Eventually, we applied the Image fusion technique to analyze the medical images by extracting meaningful insights from the multimodal imaging modalities. © 2022 IEEE.

X-Ray Image Classification for COVID-19 Using Transfer Learning

SARS-CoV-2, the cause of one of the significant pandemics in history, first appeared in Wuhan, China. It spreads rapidly, with symptoms like fever, cough, tiredness, and loss of taste or smell. We came up with many measures where the most effective was vaccines. Yet it's not enough against the rapidly appearing waves of SARS-CoV-2. A deep learning algorithm has proven efficient in detecting Covid-19 based on pneumonia and respiratory problems. These problems have been identified with the help of CT scans and X-ray images. It'll make it a lot easier to determine who's Infected and would save a lot of time and expenses overall would provide for extensive relief in the Covid-19 pandemic. This paper uses publically available COVID-19 X-Ray and CT Scan images to create a dataset. The Deep Learning based model is used to train and test the dataset. In the experiment, the overall accuracy is 98%, and in the testing process, the overall accuracy is 99%. © 2023 The authors and IOS Press.