Machine learning-based diffusion model for prediction of coronavirus-19 outbreak.

The coronavirus pandemic has been globally impacting the health and prosperity of people. A persistent increase in the number of positive cases has boost the stress among governments across the globe. There is a need of approach which gives more accurate predictions of outbreak. This paper presents a novel approach called diffusion prediction model for prediction of number of coronavirus cases in four countries: India, France, China and Nepal. Diffusion prediction model works on the diffusion process of the human contact. Model considers two forms of spread: when the spread takes time after infecting one person and when the spread is immediate after infecting one person. It makes the proposed model different over other state-of-the art models. It is giving more accurate results than other state-of-the art models. The proposed diffusion prediction model forecasts the number of new cases expected to occur in next 4 weeks. The model has predicted the number of confirmed cases, recovered cases, deaths and active cases. The model can facilitate government to be well prepared for any abrupt rise in this pandemic. The performance is evaluated in terms of accuracy and error rate and compared with the prediction results of support vector machine, logistic regression model and convolution neural network. The results prove the efficiency of the proposed model.

Diagnosis of Pulmonary Edema and Covid-19 from CT slices using Squirrel Search Algorithm, Support Vector Machine and Back Propagation Neural Network

A Computer Aided Diagnosis (CAD) framework to diagnose Pulmonary Edema (PE) and covid-19 from the chest Computed Tomography (CT) slices were developed and implemented in this work. The lung tissues have been segmented using Otsu's thresholding method. The Regions of Interest (ROI) considered in this work were edema lesions and covid-19 lesions. For each ROI, the edema lesions and covid-19 lesions were elucidated by an expert radiologist, followed by texture and shape extraction. The extracted features were stored as feature vectors. The feature vectors were split into train and test set in the ratio of 80 : 20. A wrapper based feature selection approach using Squirrel Search Algorithm (SSA) with the Support Vector Machine (SVM) classifier's accuracy as the fitness function was used to select the optimal features. The selected features were trained using the Back Propagation Neural Network (BPNN) classifier. This framework was tested on a real-time PE and covid-19 dataset. The BPNN classifier's accuracy with SSA yielded 88.02%, whereas, without SSA it yielded 83.80%. Statistical analysis, namely Wilcoxon's test, Kendall's Rank Correlation Coefficient test and Mann Whitney U test were performed, which indicates that the proposed method has a significant impact on the accuracy, sensitivity and specificity of the novel dataset considered. Comparative experimentations of the proposed system with existing benchmark ML classifiers, namely Cat Boost, Ada Boost, XGBoost, RBF SVM, Poly SVM, Sigmoid SVM and Linear SVM classifiers demonstrate that the proposed system outperforms the benchmark classifiers' results. [ FROM AUTHOR] Copyright of Journal of Intelligent & Fuzzy Systems is the property of IOS Press and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full . (Copyright applies to all s.)

Evaluation of AI Techniques for Detecting Deceptive Reviews in Cyberspace: A Study of Pre- and Post-COVID-19 Trends

With cyberspace's continuous evolution, online reviews play a crucial role in determining business success in various sectors, ranging from restaurants and hotels to e-commerce applications. Typically, a favorable review for a specific product draws in more consumers and results in a significant boost in sales. Unfortunately, a few businesses are using deceptive methods to improve their online reputation by using fake reviews of competitors. As a result, detecting fake reviews has become a difficult and ever-changing research field. Verbal characteristics extracted from review text, as well as nonverbal features such as the reviewer's engagement metrics, the IP address of the device, and so on, play an important role in detecting fake reviews. This article examines and compares various machine learning techniques for detecting deceptive reviews on various online platforms such as e-commerce websites such as Amazon and online review websites such as Yelp, among others. © 2023 IEEE.

Smart Attendance System using Dlib Pre-Trained Neural Network

Recognizing and remembering various people is the most frequent task, which the human brain performs. With regard to this, the process of attendance becomes one of the hectic tasks, which requires subsequent modernization. The spread of COVID- 19 is also drastically increasing and are pushed to the situation of wearing mask the entire time. This brings in a situation of misidentifying the individuals and are also prone to impersonation in many official gatherings such as exams, meetings, etc. This cannot be decreased by unmasking their face in this pandemic situation just for the purpose of verification as it may lead to increase in COVID risk. Here, this research study implements a contactless face recognition system with a simple and smart database, which can take in any form of data as per the convenience. This system solves the above problem by making the face recognition smart using Histogram of Oriented Gradients (HOG) and Support Vector Machine (SVM) classifier. The main task of the system is to recognize the user's face (live) and automatically mark the time of recognition directly in the Google sheet along with the alphabets of P(Present), A(absent) or L(late) according to the given time range. This system makes effective use of google sheet for easy share ability, accessibility, and error free management. This can be used for number of purposes such as exam centers, schools, colleges, companies, hospitals and various other places in order to verify the people (contact less). © 2023 IEEE.

A Real-Time Crowd Detection and Monitoring System using Machine Learning

The COVID-19 pandemic has unquestionably warned all of us that, the outbreak of an infection can lead to a pandemic-like situation all over the world. In order to prevent outbreaks and provide better healthcare, appropriate crowd detection and monitoring systems must be deployed in public areas. By effectively implementing social distancing measures, the number of new infections can be greatly decreased. This idea served as the inspiration for the creation of a real-time Crowd Detection and Monitoring System (CDMS) for social distancing. This paper proposes a fully autonomous system for Real-Time Crowd Detection and Monitoring to help the educational institutions to monitor the students inside the premises more effectively. This system is developed using an OpenCV based Histogram of Oriented Gradients (HOG) and Support Vector Machine (SVM) detector to detect and count the number of people gathered at an instance. The system raises an alarm to alert the people and adhere to the rules if the gathering is more than the threshold/permitted number of people in the cluster. © 2023 IEEE.

Automatic detection of novel corona virus (SARS-CoV-2) infection in computed tomography scan based on local adaptive thresholding and kernel-support vectors

The recent studies have indicated the requisite of computed tomography scan analysis by radiologists extensively to find out the suspected patients of SARS-CoV-2 (COVID-19). The existing deep learning methods distribute one or more of the subsequent bottlenecks. Therefore, a straight forward method for detecting COVID-19 infection using real-world computed tomography scans is presented. The detection process consists of image processing techniques such as segmentation of lung parenchyma and extraction of effective texture features. The kernel-based support vector machine is employed over feature vectors for classification. The performance parameters of the proposed method are calculated and compared with the existing methodology on the same dataset. The classification results are found outperforming and the method is less probabilistic which can be further exploited for developing more realistic detection system.

A Model based on Deep Learning for COVID-19 X-rays Classification

Throughout the COVID-19 pandemic in 2019 and until now, patients overrun hospitals and health care emergency units to check up on their health status. The health care systems were burdened by the increased number of patients and there was a need to speed up the diagnoses process of detecting this disease by using computer algorithms. In this paper, an integrated model based on deep and machine learning for covid-19 x-rays classification will be presented. The integration is built-up open two phases. The first phase is features extraction using deep transfer models such as Alexnet, Resnet18, VGG16, and VGG19. The second phase is the classification using machine learning algorithms such as Support Vector Machine (SVM), Decision Trees, and Ensemble algorithm. The dataset selected consists of three classes (COVID-19, Viral pneumonia, and Normal) class and the dataset is available online under the name COVID-19 Radiography database. More than 30 experiments are conducted to select the optimal integration between machine and deep learning models. The integration of VGG19 and SVM achieved the highest accuracy possible with 98.61%. The performance indicators such as Recall, Precision, and F1 Score support this finding. The proposed model consumes less time and resources in the training process if it is compared to deep transfer models. Comparative results are con-ducted at the end of the research, and the proposed model overcomes related works which used the same dataset in terms of testing accuracy. © 2023, Modern Education and Computer Science Press.

APPLYING HUNGER GAME SEARCH (HGS) FOR SELECTING SIGNIFICANT BLOOD INDICATORS FOR EARLY PREDICTION OF ICU COVID-19 SEVERITY

This paper introduces an early prognostic model for attempting to predict the severity of patients for ICU admission and detect the most significant features that affect the prediction process using clinical blood data. The proposed model predicts ICU admission for high-severity patients during the first two hours of hospital admission, which would help assist clinicians in decision-making and enable the efficient use of hospital resources. The Hunger Game search (HGS) meta-heuristic algorithm and a support vector machine (SVM) have been integrated to build the proposed prediction model. Furthermore, these have been used for selecting the most informative features from blood test data. Experiments have shown that using HGS for selecting features with the SVM classifier achieved excellent results as compared with four other meta-heuristic algorithms. The model that used the features that were selected by the HGS algorithm accomplished the topmost results (98.6 and 96.5%) for the best and mean accuracy, respectively, as compared to using all of the features that were selected by other popular optimization algorithms © 2023 Author(s). This is an open access publication, which can be used, distributed and reproduced in any medium according to the Creative Commons CC-BY 4.0 License

A novel proposed CNN-SVM architecture for ECG scalograms classification.

Nowadays, the number of sudden deaths due to heart disease is increasing with the coronavirus pandemic. Therefore, automatic classification of electrocardiogram (ECG) signals is crucial for diagnosis and treatment. Thanks to deep learning algorithms, classification can be performed without manual feature extraction. In this study, we propose a novel convolutional neural networks (CNN) architecture to detect ECG types. In addition, the proposed CNN can automatically extract features from images. Here, we classify a real ECG dataset using our proposed CNN which includes 34 layers. While this dataset is one-dimensional signals, these are transformed into images (scalograms) using continuous wavelet transform (CWT). In addition, the proposed CNN is compared to known architectures: AlexNet and SqueezeNet for classifying ECG images, and we find it more effective than others. This study, which not only performed CWT but also implemented short-time Fourier transform, examines the success in recognizing ECG types for the proposed CNN. Besides, different split methods: training and testing, and cross-validation are applied in this study. Eventually, CWT and cross-validation are the best pre-processing and split methods for the proposed CNN, respectively. Although the results are quite good, we benefit from support vector machines (SVM) to obtain the best algorithm and for detecting ECG types. Essentially, the main aim of the study increases classification results. In this way, the proposed CNN is utilized as deep feature extractor and combined with SVM. As a conclusion of this study, we achieve the highest accuracy of 99.21% from the proposed CNN-SVM when using CWT. Therefore, we can express that this framework can be used as an aid to clinicians for ECG-type identification.

Diagnosis of Pulmonary Edema and covid-19 from CT slices using squirrel search algorithm, support vector machine and back propagation neural network

A Computer Aided Diagnosis (CAD) framework to diagnose Pulmonary Edema (PE) and covid-19 from the chest Computed Tomography (CT) slices have been developed and implemented in this work. The lung tissues have been segmented using Otsu's thresholding method. The Regions of Interest (ROI) considered in this work were edema lesions and covid-19 lesions. For each ROI, the edema lesions and covid-19 lesions were elucidated by an expert radiologist, followed by texture and shape extraction. The extracted features were stored as feature vectors. The feature vectors were split into train and test set in the ratio of 80 : 20. A wrapper based feature selection approach using Squirrel Search Algorithm (SSA) with the Support Vector Machine (SVM) classifier's accuracy as the fitness function was used to select the optimal features. The selected features were trained using the Back Propagation Neural Network (BPNN) classifier. This framework was tested on a real-time PE and covid-19 dataset. The BPNN classifier's accuracy with SSA yielded 88.02%, whereas, without SSA it yielded 83.80%. Statistical analysis, namely Wilcoxon's test, Kendall's Rank Correlation Coefficient test and Mann Whitney U test were performed, which indicates that the proposed method has a significant impact on the accuracy, sensitivity and specificity of the novel dataset considered. Comparative experimentations of the proposed system with existing benchmark ML classifiers, namely Cat Boost, Ada Boost, XGBoost, RBF SVM, Poly SVM, Sigmoid SVM and Linear SVM classifiers demonstrate that the proposed system outperforms the benchmark classifiers' results. [ FROM AUTHOR]

Modified Multi-Kernel Support Vector Machine for Mask Detection

Indonesia is one of the countries most affected by the Coronavirus pandemic with millions confirm cases. Hence, the government has increased strict procedures for using face masks in public areas. For this reason, the detection of people wearing face masks in public areas is needed. Face mask detection is a part of the classification problem. Thus Support Vector Machine (SVM) can be implemented. SVM is still known as one of the most powerful and efficient classification algorithms. The research aims to build an automatic face mask detector using SVM. However, it needs to modify it first because it only can classify linear data. The modification is made by adding kernel functions, and a Multi-kernel approach is chosen. The proposed method is applied by combining various kernels into one kernel equation. The dataset used in the research is a face mask image obtained from Github. The data are public datasets consisting of faces with and without masks. The results present that the proposed method provides good performance. It is proven by the average value. The values are 83.67% for sensitivity, 82.40% for specificity, 82.00% for precision, 82.93% for accuracy, and 82.77% for F1-score. These values are better than other experiments using single kernel SVM with the same process and dataset. © 2022 CommIT Journal. All rights reserved.

ANALYZING THE IMPACT OF SLEEP TRAIT IN THE DETECTION AND PREDICTION OF STRESS THROUGH MACHINE LEARNING

People are thriving towards perfection, performance, and profit in the society which inturn is leading to disturbances among them both mentally and physically. One issue faced by most of the people irrespective of the age groups is "Stress". With the onset of Covid-19 pandemic, Stress has become a disastrous disorder faced by most of the people today. Most of the people are unaware that they are suffering from such a disorder. Stress lays in the hands of at-most all people either knowingly or unknowingly. There are numerous methods to detect stress manually. People don't come forward to take up treatments for stress. This disorder peeps out of humans through various symptoms like irritation, loss of appetite, agitation, depression, anxiety, reduced performance, sleep disturbance, etc. Among the afore mentioned symptoms, sleep disturbance is the major and most influential parameter in detecting and predicting stress. The SaYo Pillow is the "Smart-Yoga Pillow" which assists in concerning the relationship pertaining to sleep and stress. Although there are other methods to track sleep like Fitbit trackers to track sleeping patterns, SaYo Pillow stands out as it detects the psychological behaviors that occurs during sleep. This tracking of psychological behavior is lacking in case of other devices like Fitbit used for sleep pattern detection. The data obtained from this pillow can be used to study how stress can affect sleep. Machine Learning methods are applied to the data to detect if the person is stressed or not. Thereby adding to it, prediction is also done to understand will the person be stressed in near future. Machine Learning algorithms such as Support Vector Machine (SVM), Random Forest Classifier and Gradient Boosting Classifier was used to detect and predict stress among the individuals. The performance of these algorithms was compared to identify the best performing algorithms. After identifying the best performing algorithm, the same was applied to the data to detect and predict the occurrence of stress. In addition to that, an application was developed which suggests some activities to the candidate to overcome stress. © 2022 University of Stockholm. All rights reserved.

Data mining techniques for patients healthcare analysis during COVID-19 Pandemic conditions

Nowadays various health-related surveys use data mining and machine learning techniques for the analysis and prediction of health-related records. Current day, people are suffering from COVID-19 health issues, which cause serious health issues around the world. To predict health-related issues, classification techniques are used. Within the classification techniques, one can process a large amount of data. Previous research uses various classification techniques for data mining applications that are k-nearest neighbour, Naives Bayes, ANN, and SVM, which takes much time to execute the result. The proposed research work uses an Ordered support vector machine (O-SVM) learning algorithm with the advance in kernel-based technique. In health-related research, the health records are collected from different sources and the algorithm will identify the research-related records in the training process. The training data sets are mentioning the normal and abnormal conditions of the patients. By using the proposed classification technique, the medical images are classified by various regions to identify the defect. This paper is mainly used for COVID-19 detection and prediction using image processing and data mining techniques. The image processing techniques are used to identify the defect presented in the image. This proposed model is done by MATLAB in the adaptation of 2018a. The proposed research work provides the best result as compared to the most recent related literature. © 2022, Scibulcom Ltd.. All rights reserved.

Ensemble Deep Convolution Neural Network for Sars-Cov-V2 Detection

-The continuing Covid-19 pandemic, caused by the SARS-CoV2 virus, has attracted the eye of researchers and many studies have focussed on controlling it. Covid-19 has affected the daily life, employment, and health of human beings along with socio-economic disruption. Deep Learning (DL) has shown great potential in various medical applications in the past decade and continues to assist in effective medical image analysis. Therefore, it is effectively being utilized to explore its potential in controlling the pandemic. Chest X-Ray (CXR) images were used in studies pertaining to DL for medical image analysis. With the burgeoning of Covid-19 cases by day, it becomes imperative to effectively screen patients whose CXR images show a tendency of Covid-19 infection. Several innovative Convolutional Neural Network (CNN) models have been proposed so far for classifying medical CXR images. Moreover, some studies used a transfer learning (TL) approach on state-of-art CNN models for the classification task. In this paper, we do a comparative study of these CNN models and TL approaches on state-of-art CNN models and have proposed an ensemble Deep Convolution Neural Network model (DCNN). General Terms: Neural Network, Deep Learning (DL), Covid-19, Chest X-Ray (CXR), Medical Image Analysis. © 2022 by Subrat Sarangi, Uddeshya Khanna and Rohit Kumar.

Risk Analysis and Prediction of Covid-19 Infection Using Machine Learning Techniques

Coronavirus (COVID-19), the lethal contagious virus which has caused a pandemic, has metastasized all over the world starting from China. The figures observed of the number of casualties, is in millions and billions. This new malicious virus has caused panic amongst pubic, implanted fear and number of doubts in people's minds. There is lack of information as scientists are working on eradicating this deadly virus, less information has instilled doubts and people are panicking being helpless about how to cope up with the virus. Ways to protect oneself from getting infected, how could and where could one seek medical help when needed, these kinds of queries should be sorted out and the public needs to be educated about the virus. This will help calm down the public. This would also aid in keeping tranquil environment and even help in health and government sector workers to carry on with their duties without any obstacles. © 2022 WCSE. All Rights Reserved.

A Modern Replica for COVID-19 Pestilential Disease Identification

Detection of COVID-19 disease and its unmasking, demands a certain level of proficiency. The Work exhibited in the paper proposes a novel Deep Learning based approach to recognize COVID-19 contagious infection using CT scans and X- Rays of lungs in Humans. So that labour and risk intensive task for radiotherapists of taking samples from the patients can be minimized and risk of community spread can be avoided. Our model takes into the CT scan chest images of the patient having a certainty of infection and returns the most significant disease category related to that patient. In our study, we demonstrated a Deep Learning framework model that follows the methodology of up-skilled feature extraction techniques along with Logistic Regression [LR] and other usable classifiers. This is used on images to detect and report the presence of infection that is being prevailed in an organ with a considerably pinpoint accuracy of 97.8%. Also after trying the model on spatial information real- time dataset of our Family members, who were infected by the disease, this model was able to detect 8 out of 10 images correctly. © 2022 IEEE.

Covid Prediction and Covid Detection via X-Ray Images

The situation of the novel coronavirus is deteriorating day by day. There are more than 373 million cases recorded across the globe to date. The first incident of the disease was reported in China's Wuhan province in the month of December 2019. The virus is called COVID-19 which is an abbreviation for Corona Virus Disease 2019 or 2019-nCoV. The covid virus belongs to the same virus family as SARS, which stands for the severe acute respiratory syndrome. To date, approx. 5.5 million people have died due to the virus. The worst affected countries are the USA, India, Brazil, France, and Turkey. Most countries face the Second Wave of the coronavirus, which is more dangerous than the previous wave. India is currently passing through a rough phase, registering more than 50,000 positive cases daily for the past few weeks. Around 1000 people are dying every day as per the official data issued by government bodies. With a population of 1.4 billion people, it is challenging to break the chains of the spread of the disease. The country is facing serious medical shortages which include Oxygen support, medicines, ICUs, and Ventilators. A sudden surge of the cases created a panic situation across the country. It is nearly impossible to calculate the actual cases and the number of deaths. The conventional Rapid Antigen tests and RT-PCR tests (i.e., real-time polymerase chain reaction) are not completely efficient and quick. The Rapid Antigen tests have just 50 -60% accuracy, and the RT-PCR test takes 24 to 48 hours to declare whether a person is Covid positive or negative. Time plays an important role during covid. The early the infection can be detected, the early that person can start his/her medications, consult a doctor, and isolate himself/herself to prevent further spreading of the virus. So, in this study, X-Ray scans are used to ascertain whether a person is covid positive or not in few seconds. A Machine Learning model is also included in the study to forecast the number of instances in the next few days. © 2022 IEEE.

An Ensemble Method for Covid-19 Positive Cases Detection using Machine Learning Algorithms

In recent days, people from all over the world is facing a severe issue related to their survival of life. Due to Covid-19, many people lost their loved ones. It was a major threat not only to human beings but also to all the living creatures. Many Organizations are trying to find out the solution and at the same time, the corona affected people's rate is also increasing tremendously. Thousands and thousands of people lost their lives. The reason behind the increased death rate is that, many people were not aware of whether they are infected with the Covid virus or not. So, to solve the issue and to take remedies before it is too late, a method is proposed which helps people to identify whether they were affected with the Covid virus or not. The data in the dataset contains 152 Covid-19 positive cases and 1143 negative or healthy cases in India. In order to identify the positive and healthy cases efficiently, preprocessing is done on the collected data and features are extracted using MFCC before classification. Using several classifiers, the level of accuracy has been predicted. The classifier which gives highest level of accuracy is considered as the best classifier and using the classifier, Covid-19 positive cases are identified. Oversampling is performed on the extracted features in order to provide good accuracy. Several metrics like precision, recall, confusion matrix, Mathew's Correlation coefficient, F1-score and accuracy has been calculated to produce efficient results. Finally, K-NN classifies the Covid affected patients with 92% of accuracy, also scored good results in all the metrics calculated. © 2022 IEEE.

SARS-CoV-2 Future Forecasting Using Multi-Linear Regression Model

The 2019 pandemic in Wuhan, China caused a devastating global outbreak of the Coronavirus Disease (SARSCoV-2). Machine learning offers a number of prediction models for future events that are based on training and testing, including conventional machine learning and Deep Learning. This study shows that machine-learning models can anticipate the number of future SARS-CoV-2 patients that are currently seen as a possible risk to the human race. Supervised machine learning models like linear regression, vector support and regression tree are used for prediction. Data on the total cases and recovery cases are based on two types of predictions: new infections and recovery situations. The machine-learning regression model is used to generate the outcome. In this paper, we present prediction of future forecasting of Covid cases based on current situation by applying dataset of before and after pre-trial vaccine. © 2022, Ismail Saritas. All rights reserved.

The impact of public health emergencies on hotel demand - Estimation from a new foresight perspective on the COVID-19.

This paper proposes a new foresight approach to estimate the impact of public health emergencies on hotel demand. The forecasting-based influence evaluation consists of four modules: decomposing hotel demand before an emergency, matching each decomposed component to a forecasting model, combining the predictions as the expected demand after the emergency, and estimating the impact by comparing actual demand against that predicted. The method is applied to analyze the impact of COVID-19 on Macao's hotel industry. The empirical results show that: 1) the new approach accurately estimates COVID-19's impact on hotel demand; 2) the seasonal and industry development components contribute significantly to the estimate of expected demand; 3) COVID-19's impact is heterogeneous across hotel services.