COVID-19 Data Prediction and Visualization in Mainland China

Contemporarily, COVID-19 shows a sign of recurrence in Mainland China. To better understand the situation, this paper investigates the growth pattern of COVID-19 based on the research of past data through regression models. The proposed work collects the data on COVID-19 in Mainland China from January 21st, 2020, to April 30th, 2020, including confirmed, recovered, and death cases. Based on polynomial regression and support vector machine regressor, it predicts the further trend of COVID-19. The paper uses root mean squared error to evaluate the performance of both models and concludes that there is no best model due to the high frequency of daily changes. According to the analysis, support vector machine regressors fit the growth of COVID-19 confirmed case better than polynomial regression does. The best solution is to utilize different types of models to generate a range of prediction result. These results shed light on guiding further exploration of the growth of COVID-19. © 2023 SPIE.

DEEP LEARNING BASED AN EFFICIENT HYBRID PREDICTION MODEL FOR COVID-19 CROSS-COUNTRY SPREAD AMONG E7 AND G7 COUNTRIES

The COVID-19 pandemic has caused the death of many people around the world and has also caused economic problems for all countries in the world. In the literature, there are many studies to analyze and predict the spread of COVID-19 in cities and countries. However, there is no study to predict and analyze the cross-country spread in the world. In this study, a deep learning based hybrid model was developed to predict and analysis of COVID-19 cross-country spread and a case study was carried out for Emerging Seven (E7) and Group of Seven (G7) countries. It is aimed to reduce the workload of healthcare professionals and to make health plans by predicting the daily number of COVID-19 cases and deaths. Developed model was tested extensively using Mean Squared Error (MSE), Root Mean Squared Error (RMSE), Mean Absolute Error (MAE) and R Squared (R2). The experimental results showed that the developed model was more successful to predict and analysis of COVID-19 cross-country spread in E7 and G7 countries than Linear Regression (LR), Random Forest (RF), Support Vector Machine (SVM), Multilayer Perceptron (MLP), Convolutional Neural Network (CNN), Recurrent Neural Network (RNN) and Long Short-Term Memory (LSTM). The developed model has R2 value close to 0.9 in predicting the number of daily cases and deaths in the majority of E7 and G7 countries. © 2023 by the authors.

Intelligent Methods and Models for Assessing Level of Student Adaptation to Online Learning

The problem of introducing online learning is becoming more and more popular in our society. Due to COVID-19 and the war in Ukraine, there is an urgent need for the transition of educational institutions to online learning, so this paper will help people not make mistakes in the process and afterward. The paper's primary purpose is to investigate the effectiveness of machine learning tools that can solve the problem of assessing student adaptation to online learning. These tools include intelligent methods and models, such as classification techniques and neural networks. This work uses data from an online survey of students at different levels: school, college, and university. The survey consists of questions such as gender, age, level of education, whether the student is in the city, class duration, quality of Internet connection, government/non-government educational institution, availability of virtual learning environment, whether the student is familiar with IT, financial conditions, type of Internet connection, a device used for studying, etc. To obtain the results on the effectiveness of online education were used the following machine learning algorithms and models: Random Forest (RF), Extra Trees (ET), Extreme, Light, and Simple Gradient Boosting (GB), Decision Trees (DT), K-neighbors (K-mean), Logistic Regression (LR), Support Vector Machine (SVM), Naїve Bayes (NB) classifier and others. An intelligent neural network model (NNM) was built to address the main issue. © 2023 Copyright for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0). CEUR Workshop Proceedings (CEUR-WS.org)

Tweets Emotions Analysis of Community Activities Restriction as COVID-19 Policy in Indonesia Using Support Vector Machine

With the rising number of COVID-19 cases in Indonesia, the government has implemented the Imposition of Restrictions on Emergency Community Activities (Pemberlakuan Pembatasan Kegiatan Masyarakat - PPKM) as Indonesia's COVID-19 policy. Several controversies and protests have colored the implementation of this emergency policy. Some netizens on Twitter voice their opinions about the policy in their tweets. Emotions in tweets can be recognized through text-based emotion detection or emotion analysis. However, text-based emotion detection is a challenging task. One of the main issues in classifying text with a machine learning-based approach deals with the feature dimensions. As a result, appropriate methods for accurately identifying emotion based on the text are required. The research studies an emotions analysis task on Indonesians' PPKM-related tweets to understand their emotional state while implementing the PPKM. The machine learning classification algorithms used are Support Vector Machine (SVM) and random forest. The total number of tweets is 4,401. The results show that SVM with linear kernel function combined with the TF-IDF and Chi-Square methods outperforms other classifiers with an accuracy of 0.7528. The accuracy value is higher than those obtained by previous studies. Moreover, the results of the emotion classification on PPKM tweets reveal that most Indonesians are unhappy with the implementation of the PPKM policy. © 2023 Bina Nusantara University. All rights reserved.

COVID-19 Detection by Using Handcrafted Features Extracted From Chest CT-Scan Images

Coronavirus illness, which was initially diagnosed in 2019 but has propagated rapidly across the globe, has led to increased fatalities. According to professional physicians who examined chest CT scans, COVID-19 behaves differently than various viral cases of pneumonia. Even though the illness only recently emerged, a number of research investigations have been performed wherein the progression of the disease impacts mostly on the lungs are identified using thoracic CT scans. In this work, automated identification of COVID-19 is used by using machine learning classifier trained on more than 1000+ lung CT Scan images. As a result, immediate diagnosis of COVID-19, which is very much necessary in the opinion of healthcare specialists, is feasible. To improve detection accuracy, the feature extraction method are applied on regions of interests. Feature extraction approaches, including Discrete Wavelet Transform (DWT), Grey Level Cooccurrence Matrix (GLCM), Grey Level Run Length Matrix (GLRLM), and Grey-Level Size Zone Matrix (GLSZM) algorithms are used. Then the classification by using Support Vector Machines (SVM) is used. The classification accuracy is assessed by using precision, specificity, accuracy, sensitivity and F-score measures. Among all feature extraction methods, the GLCM approach has given the optimum classification accuracy of 95.6%. . © 2023 IEEE.

Study on Dynamic Change of Land Usage in Hongta District Based on Sentinel-2

This work utilizes Sentinel-2A L1C remote sensing photographs from the years 2018, 2020, and 2022 to identify the different land use categories in the study area using the support vector machine (SVM) technique. The accuracy of categorization is greater than 90%. This research explores four factors of the dynamic change in land use in Hongta District from 2018 to 2022: the proportion of various types of land;the extent of something like the changing land usage;land use transfer;and the dynamic degree of the change in land use. According to the study's results, the proportion of cultivated and grassland land grew, while the quantity of barren and construction land fell by 1.90 percent, 0.03 percent, and 0.69 percent, respectively. The water system land portion of total area increased by 2.58 percent and 0.13 percent, respectively. After comparing the two research periods, the entire dynamic degree of the second stage is determined to be 3.5 percent lower than that of the first stage, and the pace of land use change is quite sluggish, which may be associated with the worldwide COVID-19 outbreak in 2020. The outcomes of the research may give the natural resources department the knowledge it needs to manage land resources properly. © 2023 SPIE.

Artificial Intelligence-Based Smart Tele-Assisting Technology for First-Year Engineering Students

Engineering programs emphasize students career advancement by ensuring that engineering students gain technical and professional capabilities during their four-year study. In a traditional engineering laboratory, students "learn by doing", and laboratory equipment facilitates their discipline-specific knowledge acquisition. Unfortunately, there were significant educational uncertainties, such as COVID-19, which halted laboratory activities for an extended period, causing challenges for students to perform and obtain practical experiments on campus. To overcome these challenges, this research proposes and develops an Artificial Intelligence-based smart tele-assisting technology application to digitalize first-year engineering students practical experience by incorporating Augmented Reality (AR) and Machine Learning (ML) algorithms using the HoloLens 2. This application improves virtual procedural demonstrations and assists first-year engineering students in conducting practical activities remotely. This research also applies various machine learning algorithms to identify and classify different images of electronic components and detect the positions of each component on the breadboard (using the HoloLens 2). Based on a comparative analysis of machine learning algorithms, a hybrid CNN-SVM (Convolutional Neural Network - Support Vector Machine) model is developed and is observed that a hybrid model provides the highest average prediction accuracy compared to other machine learning algorithms. With the help of AR (HoloLens 2) and the hybrid CNN-SVM model, this research allows students to reduce component placement errors on a breadboard and increases students competencies, decision-making abilities, and technical skills to conduct simple laboratory practices remotely. © 2023 IEEE.

Assessing the impact on freight transport and treating uncertainty in freight transport modelling in the Covid pandemic: the case of Greece

This paper contains an investigation of the COVID-19 impacts on freight flows and the handling of uncertainty in freight forecasting models, based on data from Greece. It collects and analyses, over a 7-year period before and during the pandemic, data for freight transport operations and some related factors in order to macroscopically examine any statistically significant changes in their values over time. This period wasjudged necessary in order to establish the pattern of fluctuations in the relevant data during the non-pandemic years and thus make the visual comparison with the previous period and the years during the pandemic, more clear. First, the paper tests the impact of the pandemic as expressed by the number of daily COVID-19 cases on freight flow variables in order to find the dynamic behavior of these variables and trace their reactions over time. This analysis is made by using the Vector Autoregressive Model (VAR). By implementing VAR modelling, we analyzed the dynamic relationship between freight transport volumes and other factors such as GDP, the industrial production index, exporting transactions and the number of coronavirus cases. The main result of the model analysis and the employment of impulse response functions revealed that the unexpected shock of COVID has a negative reaction to the economy and the freight transport volumes and a rather shortterm limited duration disruption effect on the growth of exports as well as on the industrial production index, of approximately eight months. Secondly, the paper discusses how, unpredicted events like the pandemic, influence the uncertainty inherent in freight transport modelling and formulates a novel freight modelling framework procedure based on scenario building, regular monitoring and data updates on a permanent basis. [ FROM AUTHOR] Copyright of Advances in Transportation Studies is the property of Advances in Transportation Studies 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.)

Bitcoin and money supply relationship: An analysis of selected country economies

Bitcoin has become quite known after the 2008 economic crisis and the COVID-19 health crisis. For some, these cryptocurrencies constitute rebellion against the existing system as governments encourage uncontrolled expansions in the money supply;for some others, it is a quick source of income. Undeniably, the volume of the crypto money market has grown considerably in recent years, regardless of the reasoning of the people who invest and trade in this field. At this point, one of the most important questions to be investigated is "what variables have caused the tremendous growth in the crypto money quantities in recent years?" This study tests the assumption that changes in cryptocurrencies are affected by changes in national currencies. Thus, the Bitcoin price is the dependent variable, and M1 monetary supply changes in the USA, European Union and Japanese economies are considered independent variables. The variables in this study were tested using the time-varying Granger causality method. The results obtained from this study confirm the philosophy of Bitcoin's emergence and the possibility that it can be a hedge against the inflationary effects of money, especially after the COVID-19 pandemic.

Classification of COVID-19 Tweets

Classification is a vital work to human beings in day today life as it breaks down complex subjects. In the same way, text classification is very important to understand and realize the subject of the text. © 2021 Copyright for this paper by its authors.

TwIdw—A Novel Method for Feature Extraction from Unstructured Texts

Featured ApplicationThe research has a potential application in the field of fake news detection. By using the feature extraction technique, TwIdw, proposed in this paper, more relevant and informative features can be extracted from the text data, which can lead to an enhancement in the accuracy of the classification models employed in these tasks.This research proposes a novel technique for fake news classification using natural language processing (NLP) methods. The proposed technique, TwIdw (Term weight–inverse document weight), is used for feature extraction and is based on TfIdf, with the term frequencies replaced by the depth of the words in documents. The effectiveness of the TwIdw technique is compared to another feature extraction method—basic TfIdf. Classification models were created using the random forest and feedforward neural networks, and within those, three different datasets were used. The feedforward neural network method with the KaiDMML dataset showed an increase in accuracy of up to 3.9%. The random forest method with TwIdw was not as successful as the neural network method and only showed an increase in accuracy with the KaiDMML dataset (1%). The feedforward neural network, on the other hand, showed an increase in accuracy with the TwIdw technique for all datasets. Precision and recall measures also confirmed good results, particularly for the neural network method. The TwIdw technique has the potential to be used in various NLP applications, including fake news classification and other NLP classification problems.

Automated Prognosis of Alzheimer's Disease using Machine Learning Classifiers on Spontaneous Speech features

Early prediction of Alzheimer's disease and related Dementia has been a great challenge. Recently, preliminary research has shown that neurological symptoms in Covid-19 patients may accelerate the onset of Alzheimer's disease. With such a further rise in Alzheimer's and related Dementia cases, having an early prediction system becomes vital. Speech can provide a non-invasive diagnostic marker for such neurodegenerative diseases. This work mainly focuses on studying significant temporal speech features extracted directly from the recordings of the Dementia bank dataset and applying Machine Learning algorithms to classify the Alzheimer's disease related Dementia Group and the healthy control group. The result shows that Support Vector Machine outperformed other machine learning algorithms with an accuracy of 87%. Compared to prior research, which used manual transcriptions provided with the dataset, this study used audio recordings from the Dementia bank dataset and an advanced Automatic Speech Recognizer to extract speech features from the audio recordings. Furthermore, this method can be applied to the spoken responses of subjects during a neuropsychological assessment. © 2023, Ismail Saritas. All rights reserved.

Analysis and Prediction of Student Performance Based on Moodle Log Data using Machine Learning Techniques

During the COVID-19 Pandemic, many universities in Thailand were mostly locked down and classrooms were also transformed into a fully online format. It was challenging for teachers to manage online learning and especially to track student behavior since the teacher could not observe and notify students. To alleviate this problem, one solution that has become increasingly important is the prediction of student performance based on their log data. This study, therefore, aims to analyze student behavior data by applying Predictive Analytics through Moodle Log for approximately 54,803 events. Six Machine Learning Classifiers (Neural Network, Random Forest, Decision Tree, Logistic Regression, Linear Regression, and Support Vector Machine) were applied to predict student performance. Further, we attained a comparison of the effectiveness of early prediction for four stages at 25%, 50%, 75%, and 100% of the course. The prediction models could guide future studies, motivate self-preparation and reduce dropout rates. In the experiment, the model with 5-fold cross-validation was evaluated. Results indicated that the Decision Tree performed best at 81.10% upon course completion. Meanwhile, the SVM had the best result at 86.90% at the first stage, at 25% of the course, and Linear Regression performed with the best efficiency at the middle stages at 70.80%, and 80.20% respectively. The results could be applied to other courses and on a larger e-learning systems log that has similar student activity conditions and this could contribute to more accurate student performance prediction © 2023, International Journal of Emerging Technologies in Learning.All Rights Reserved.

Comparison Analysis of Prediction the Number of Covid-19 Cases Using Support Vector Regression and Long Short-Time Memory

Covid-19 emerged as a pandemic outbreak that spread almost worldwide at the end of December 2019. While this research was carried out, the Covid-19 pandemic was still ongoing. Many countries have made various attempts to overcome Covid-19. In Indonesia, the government and stakeholders, including researchers, have made many activities to reduce the number of positive patients. One of many activities that the government made is the vaccination program. The vaccination program is believed to be the most effective in reducing the number of positive cases of Covid-19. But nobody knows when the Covid-19 pandemic will end. Stakeholder has to know how the trend of Covid-19 cases in Indonesia to make a better decision for facing Covid-19 cases. This study aims to predict the number of positive Covid-19 cases in Indonesia by conducting a comparative analysis performance of Support Vector Regression (SVR) method and Long Short-Term Memory (LSTM) method in machine learning to the prediction of the number of Covid-19 cases. This study was conducted using the dataset Covid-19 in Indonesia from Control Team from 13 January 2021 until 08 November 2021 and with 300 records. The evaluation has been conducted to know the performance of the model prediction number of Covid-19 with Support Vector Regression method and Long Short-Term Memory method based on values of R-Square (R2), the value of Mean Absolute Error (MAE) and Mean Square Error (MSE). The research found that the method Support Vector Regression has better performance than Long Short-Term Memory method for making a prediction of the number Covid-19 using Machine Learning model based on the value of accuracy and error rate based with the value of R-Squared, MAE, and MSE are consecutively 0.902, 0.163, and 0.072. © 2022 IEEE.

Sensitizing breast cancers to immune checkpoint inhibitors through CD27 agonism and vaccination against tumor-associated antigen

Project objective: Despite the recent revolution in immune checkpoint inhibitors (ICIs), only modest improvement in overall survival and likely caused by not enough potent cellular immunity among BC patients. Our lab has been focus on inducing cellular immunity against HER2+ BC through vaccination against the tumor-associated antigen HER2. Approximately 20 years ago, we performed an experimental pilot study by administrating HER2 peptide and recombinant protein pulsed dendritic cells (DC vaccine) to six patients with refractory HER2+ advanced or metastatic (stage II (>= 6 +LN), III, or stage IV) BC. We followed the patients on 2019 found that all of the six patients were still alive, 18 years after vaccination. Their blood sample were analyzed with cytometry by time-offlight (CyTOF) and found there is a significantly increased presence of CD27 expressing memory T cells in response to HER2 peptide stimulation. Recent report on the SARS-CoV2 mRNA vaccine also suggested that CD27 expressing memory T cells plays a critical role in long-lasting cellular immunity against SARS-CoV2 infection. Therefore, we hypothesized that CD27 plays a critical role in cellular immunity against BC, and the stimulation of CD27 expressing T cells with mAb targeting CD27 significantly increase the cellular immunity triggered by vaccination against tumor-associated antigen. Result(s): We recapitulate the rise of CD27+ antigen specific T cells among the vaccinated patients using a transgenic mouse model expressing human CD27. When combined the adenoviral-vector based HER2 (Ad-HER2) vaccination with a single dose of human aCD27 antibody (Varlilumab), we found there is a robust increase in the HER2 specific T cells compared to vaccination alone, especially CD27+CD44+ memory CD4 T cells, even after 120 days post vaccination. Using an ICIinsensitive syngeneic HER2+ BC models, we found 50% of mice in the combination group of aCD27 antibody plus Ad-HER2 showed total tumor regression by the end of study. When combined with anti-PD1 antibody, the combination of AdHER2 and Varlilumab leads to total tumor regression in 90% of tumor bearing mice with syngeneic HER2+ BC, indicating that the vaccination against tumor associated antigen HER2 plus anti-CD27 antibody sensitized ICI-insensitive HER2+ BC toward ICI. Conclusion(s): Our data demonstrates that the administration of anti-CD27 antibody significantly increase the long term presence of CD27+ antigen specific memory T cells after vaccination against tumor associated antigen HER2. As consequence, combination of anti-CD27 with HER2 sensitized the immune unresponsive breast cancer toward anti-PD1 antibody. Our study suggests that the vaccination against tumor-associated antigen with mAb targeting CD27 leads to the robust cellular immunity, which is required for successful ICIs against breast cancer.

Towards Detection of Cyberbullying in Hinglish Code Mixed Data

Covid-19 eruption and lockdown situation have increased the usages of online platforms which have impacted the users. Cyberbullying is one of the negative outcomes of using social media platforms which leads to mental and physical distress. This study proposes a machine learning-based approach for the detection of cyberbullying in Hinglish text. We use the Hinglish Code-Mixed Corpus, which consists of over 6,000 tweets, for our experiments. We use various machine learning algorithms, including Logistic regression (LR), Multinomial Naive Bayes (MNB), Support vector machine (SVM), Random Forest (RF), to train our models. We evaluate the performance of the models using standard evaluation metrics such as precision, recall, and F1-score. Our experiments show that the LR with Term Frequency-Inverse Document Frequency (TFIDF) outperforms the other models, achieving 92% accuracy. Our study demonstrates that machine learning models can be effective for cyberbullying detection in Hinglish text, and the proposed approach can help identify and prevent cyberbullying on social media platforms. © 2023 Bharati Vidyapeeth, New Delhi.

The Granger Causality of Bahrain Stocks, Bitcoin, and Other Commodity Asset Returns: Evidence of Short-Term Return Spillover before and during the COVID-19 Pandemic

This study examines the tendency of short-term return spillover across Bahrain stocks, bitcoin, and other commodity assets factoring in the dynamic effect of the COVID-19 pandemic. The study employed vector autoregression (VAR) model using the daily returns of Bahrain All Shares Index, bitcoin, crude oil, and gold futures from January 2018 to March 2022. The results showed a persistent unidirectional short-term spillover of return from the Bahrain stock market to the futures gold market for both the period before and during the pandemic. Moreover, the results also showed that the significant positive shock in the bitcoin returns as granger-caused by the returns of the Bahrain stock market is only during the period before the pandemic. Finally, a significant negative contemporaneous short-term effect on the crude oil market returns can be statistically explained by the shocks in the Bahrain stock market only during the COVID-19 period. © 2023 IGI Global. All rights reserved.

Artificial Intelligence driven security model for Internet of Medical Things (IoMT)

The Internet of Medical Things (IoMT) has been applied to provide health care facilities for elders and parents. Remote health care is essential for providing scarce resources and facilities to coronavirus patients. Ongoing IoMT communication is susceptible to potential security attacks. In this research, an artificial intelligence-driven security model of the IoMT is also proposed to simulate and analyses the results. Under the proposed plan, only authorized users will be able to access private and sensitive patient information, and unauthorized users will be unable to access a secure healthcare network. The various phases for implementing artificial intelligence (AI) techniques in the IoMT system have been discussed. AI-driven IoMT is implemented using decision trees, logistic regression, support vector machines (SVM), and k-nearest neighbours (KNN) techniques. The KNN learning models are recommended for IoMT applications due to their low consumption time with high accuracy and effective prediction. © 2023 IEEE.

Gene Editing/Gene Therapies: BIOREACTOR RECOMBINANT PRODUCTION OF SARS-COV-2 VIRUS ANTIGENS IN CHO CELL CLONES BY USING NEW UCOE LENTIVIRAL VECTOR SYSTEM

Background & Aim: The new UCOE models we have recently developed, tested on many cell groups (including mouse ES and human iPS cells) and human mAb recombinant production studies as well, shows a powerful resistance to DNA methylation- mediated silencing and provides a higher and stable transfection profile. By the urgent need of vaccine development for COVID-19 during the pandemic, in this study we aimed to produce a potential recombinant vaccine by using the new generation UCOEs models of our own design. Methods, Results & Conclusion(s): Existing new-generation UCOE models and standard plasmid vectors to be used as control group were provided. Then, the sequences related to the PCR method were amplified for sufficient stock generation and cloning experiments. Verification in the plasmid vector was carried out in gel electrophoresis. Transfection of 293T cells was performed with clone plasmids carrying antigen genes and plasmids carrying genetic information of lentivirus units for the production of lentiviral vectors. Afterwards, 293T cells produced lentiviral vectors carrying antigen genes. Harvesting of these vectors was carried out during 48th and 72nd hours. Afterwards, CHO cells were transduced with appropriate quantity of lentiviral vectors. Isolation and purification of targeted proteins from the relevant medium were performed by HPLC and Q-TOF methods. A part of the spike and nucleocapsid gene sequences of COVID-19 were firstly cloned into our UCOE models. These UCOEs plasmids were then transferred into 293T cells along with plasmids carrying the genes that will form the lentivirus vectors (LVs). After harvesting and calculation of LV vector titers, the cloned vectors were then transfected into the CHO cells which the targeted recombinant production of the antigen proteins will be carried out. Antigenic structures were then isolated from the culture medium of CHO cells in following days for confirmation. Using HPLC and qTOF mass spectrometer methods, these structures in the medium were confirmed to be the units of spike and nucleocapsid proteins of the COVID-19 virus. In order to produce large amount of the recombinant antigens, the culture was then carried out with bioreactors in liters. At the final stage, these recombinantly produced antigen proteins were tested on rats to measure their immunogenic responses, and the study recently been completed successfully as a potential recombinant vaccine against COVID-19.Copyright © 2023 International Society for Cell & Gene Therapy

Artificial Intelligence-based Speech Signal for COVID-19 Diagnostics

The speech signal has numerous features that represent the characteristics of a specific language and recognize emotions. It also contains information that can be used to identify the mental, psychological, and physical states of the speaker. Recently, the acoustic analysis of speech signals offers a practical, automated, and scalable method for medical diagnosis and monitoring symptoms of many diseases. In this paper, we explore the deep acoustic features from confirmed positive and negative cases of COVID-19 and compare the performance of the acoustic features and COVID-19 symptoms in terms of their ability to diagnose COVID-19. The proposed methodology consists of the pre-trained Visual Geometry Group (VGG-16) model based on Mel spectrogram images to extract deep audio features. In addition to the K-means algorithm that determines effective features, followed by a Genetic Algorithm-Support Vector Machine (GA-SVM) classifier to classify cases. The experimental findings indicate the proposed methodology's capability to classify COVID-19 and NOT COVID-19 from acoustic features compared to COVID-19 symptoms, achieving an accuracy of 97%. The experimental results show that the proposed method remarkably improves the accuracy of COVID-19 detection over the handcrafted features used in previous studies. © 2022 ACM.