A comparison between CNN and combined CNN-LSTM for chest X-ray based COVID-19 detection

COVID-19 detection through radiological examination is favoured since it is fast and produces more accurate results than the laboratory approach. However, when it has infected many people and put a strain on the healthcare system, the need for fast, automatic COVID-19 detection in patients has become critical. This study proposes to detect COVID-19 from chest X-ray (CXR) images with a machine learning approach. The main contributions of this paper are to compare two powerful deep learning models, i.e., convolutional neural networks (CNN) and the combination of CNN and Long Short-Term Memory (LSTM). In the combination model, CNN is recommended for feature extraction, and COVID-19 is classified using the features of LSTM. The dataset used in this study amounted to 4,095 CXR images, consisting of 1,400 images of normal conditions, 1,350 images of COVID-19, and 1,345 images of pneumonia. Both CNN and CNN-LSTM were executed in a similar experimental setup and evaluated using a confusion matrix. The experiment results provide evidence that the CNN-LTSM is better than the CNN deep learning model, with an overall accuracy of about 98.78%. Furthermore, it has a precision and recall of 99% and 98%, respectively. These findings will be valuable in the fast and accurate detection of COVID-19. © 2023 by the authors;licensee Growing Science, Canada.

Time series prediction of novel coronavirus COVID-19 data in west Java using Gaussian processes and least median squared linear regression

In 2019, the COVID-19 epidemic swept throughout the globe. The virus was first identified in Wuhan, China. By the time several months had gone by, this virus had spread to numerous locations throughout the world. Consequently, this virus has become a worldwide pandemic. Multiple efforts have been made to limit the transmission of this virus. A possible course of action is to lock down the territory. Unfortunately, this strategy wrecked the economy, worsening the terrible situation. The world health organization (WHO) would breathe a sigh of relief if there were to be no new cases. However, the government should explore employing data from the future in addition to the data it already has. Prediction of time series may be utilized for this purpose. This study indicated that the Gaussian processes method outperformed the least median squared linear regression method (LMSLR). Applying a Pearson VII-based global kernel produces MAE and RMSE values of 23.12 and 53.43, respectively.(c) 2023 by the authors;licensee Growing Science, Canada.

Time series prediction of novel coronavirus COVID-19 data in west Java using Gaussian processes and least median squared linear regression

In 2019, the COVID-19 epidemic swept throughout the globe. The virus was first identified in Wuhan, China. By the time several months had gone by, this virus had spread to numerous locations throughout the world. Consequently, this virus has become a worldwide pandemic. Multiple efforts have been made to limit the transmission of this virus. A possible course of action is to lock down the territory. Unfortunately, this strategy wrecked the economy, worsening the terrible situation. The world health organization (WHO) would breathe a sigh of relief if there were to be no new cases. However, the government should explore employing data from the future in addition to the data it already has. Prediction of time series may be utilized for this purpose. This study indicated that the Gaussian processes method outperformed the least median squared linear regression method (LMSLR). Applying a Pearson VII-based global kernel produces MAE and RMSE values of 23.12 and 53.43, respectively. © 2023 by the authors;licensee Growing Science, Canada.

Analysis of Government Policy Sentiment Regarding Vacation during the COVID-19 Pandemic Using the Bidirectional Encoder Representation from Transformers (BERT)

To address the COVID-19 situation in Indonesia, the Indonesian government has adopted a number of policies. One of them is a vacation-related policy. Government measures with regard to this vacation policy have produced a wide range of viewpoints in society, which have been extensively shared on social media, including YouTube. However, there has not been any computerized system developed to date that can assess people's social media reactions. Therefore, this paper provides a sentiment analysis application to this government policy by employing a bidirectional encoder representation from transformers (BERT) approach. The study method began with data collecting, data labeling, data preprocessing, BERT model training, and model evaluation. This study created a new dataset for this topic. The data were collected from the comments section of YouTube, and were categorized into three categories: positive, neutral, and negative. This research yielded an F-score of 84.33%. Another contribution from this study regards the methodology for processing sentiment analysis in Indonesian. In addition, the model was created as an application using the Python programming language and the Flask framework. The government can learn the extent to which the public accepts the policies that have been implemented by utilizing this research. © 2023 by the authors.

Educational Innovation Faced with COVID-19: Deep Learning for Online Exam Cheating Detection

Because the COVID-19 epidemic has limited human activities, it has touched almost every sector. Education is one of the most affected areas. To prevent physical touch between students, schools and campuses must adapt their complete learning system to an online environment. The difficulty with this technique arises when the teachers or lecturers administer exams. It is difficult to oversee pupils one by one online. This research proposes the development of a computer program to aid in this effort. By applying deep learning models, this program can detect a person's activities during an online exam based on a web camera. The reliability of this system is 84.52% based on the parameter F1-score. This study built an Indonesian-language web-based application. Teachers and lecturers in Indonesia can use this tool to evaluate whether students are cheating on online exams. Unquestionably, this application is a tool that may be utilized to develop distance learning educational technology in Indonesia.

Physical activities patterns among Indonesian pregnant women: a cross-sectional study

Many evidence revealed that physical activity (PA) has positive effects on pregnancy outcomes. Healthy pregnant women are suggested to have a combination of PA in light to moderate-intensity activities for 150 minutes per week. The purpose of this study was to analyze the type, the intensity of PA of pregnant women, and the average energy expenditure per week. A cross-sectional study involving 110 pregnant women who came from four community health centers in Bandung city, Indonesia was carried out from April to June 2021. The pregnancy physical activity questionnaire (PPAQ) was used to collect data. Descriptive data were presented using median and percentile. Mann-Whitney and Kruskal Wallis test were used to statistical test. The results of the study where the median energy expenditure per week was 250.50 METs. Most of the PA was light-intensity activities and household/child caring activities. There were still 10% pregnant women who did not exercise. Employed pregnant women had energy expenditure per week higher compared to unemployed pregnant women. Sports/exercise activities were seldom been carried out. This study demonstrated that during pandemic COVID-19, pregnant women are still doing PA. During pandemic COVID-19, health care providers should motivate healthy pregnant women to exercise by creating innovations using social media or online platforms so that pregnant women can exercise at home safely. © 2023, Intelektual Pustaka Media Utama. All rights reserved.

Lung and Infection CT-Scan-Based Segmentation with 3D UNet Architecture and Its Modification.

COVID-19 is the disease that has spread over the world since December 2019. This disease has a negative impact on individuals, governments, and even the global economy, which has caused the WHO to declare COVID-19 as a PHEIC (Public Health Emergency of International Concern). Until now, there has been no medicine that can completely cure COVID-19. Therefore, to prevent the spread and reduce the negative impact of COVID-19, an accurate and fast test is needed. The use of chest radiography imaging technology, such as CXR and CT-scan, plays a significant role in the diagnosis of COVID-19. In this study, CT-scan segmentation will be carried out using the 3D version of the most recommended segmentation algorithm for bio-medical images, namely 3D UNet, and three other architectures from the 3D UNet modifications, namely 3D ResUNet, 3D VGGUNet, and 3D DenseUNet. These four architectures will be used in two cases of segmentation: binary-class segmentation, where each architecture will segment the lung area from a CT scan; and multi-class segmentation, where each architecture will segment the lung and infection area from a CT scan. Before entering the model, the dataset is preprocessed first by applying a minmax scaler to scale the pixel value to a range of zero to one, and the CLAHE method is also applied to eliminate intensity in homogeneity and noise from the data. Of the four models tested in this study, surprisingly, the original 3D UNet produced the most satisfactory results compared to the other three architectures, although it requires more iterations to obtain the maximum results. For the binary-class segmentation case, 3D UNet produced IoU scores, Dice scores, and accuracy of 94.32%, 97.05%, and 99.37%, respectively. For the case of multi-class segmentation, 3D UNet produced IoU scores, Dice scores, and accuracy of 81.58%, 88.61%, and 98.78%, respectively. The use of 3D segmentation architecture will be very helpful for medical personnel because, apart from helping the process of diagnosing someone with COVID-19, they can also find out the severity of the disease through 3D infection projections.

Single Mother in The Digital Economy: Stimulating Entrepreneurship & Covid-19 Challenges

Empowering women is a prerequisite for a healthy nation and robust economic performance. This vision poses huge challenges to developing female entrepreneurs, especially single-mother entrepreneurs. Single mothers are the breadwinners for their family and are often responsible for accommodating the needs of family members. The paper aims to identify the tendency of single mothers to become successful entrepreneurs. Using a quantitative design, surveys were conducted with 521 female entrepreneurs with online businesses. Expensive technology and the lack of relevant knowledge and skills in using digital tools are among the leading constraints single-mothers face in growing their business. Findings showed that single mother entrepreneurs who use internet applications in their business tend to have a high level of skill and high motivation in digital entrepreneurship world. For inclusive growth, it is critical to increasing women’s participation in business and the global marketplace by developing their capacity to fully participate in the digital economy. The effects of COVID-19 which hit for two years gave a lot of lessons and experience to women entrepreneurs to continue trying to face the current economic challenges with full tenacity and patience. The government has provided training to increase knowledge and skills to improve the economy of single mothers as provided by the Women's Department and Department of Social Welfare. © 2018 Malaysian Consumer and Family.

Infectious Disease Modeling with Socio-Viral Behavioral Aspects-Lessons Learned from the Spread of SARS-CoV-2 in a University.

When it comes to understanding the spread of COVID-19, recent studies have shown that pathogens can be transmitted in two ways: direct contact and airborne pathogens. While the former is strongly related to the distancing behavior of people in society, the latter are associated with the length of the period in which the airborne pathogens remain active. Considering those facts, we constructed a compartmental model with a time-dependent transmission rate that incorporates the two sources of infection. This paper provides an analytical and numerical study of the model that validates trivial insights related to disease spread in a responsive society. As a case study, we applied the model to the COVID-19 spread data from a university environment, namely, the Institut Teknologi Bandung, Indonesia, during its early reopening stage, with a constant number of students. The results show a significant fit between the rendered model and the recorded cases of infections. The extrapolated trajectories indicate the resurgence of cases as students' interaction distance approaches its natural level. The assessment of several strategies is undertaken in this study in order to assist with the school reopening process.

Online Food Delivery App Distribution and Determinants of Jakarta's Gen Z Spending Habits

Purpose: Considering the COVID-19 pandemic and the increasing number of online food delivery applications (OFDA), this study aims to assess the distribution of the presence of Indonesian OFDA and to measure the factors that influence the spending habits of OFDA users. Research design, data and methodology: Two hundred and nine OFDA users from Jakarta's Generation Z were surveyed via a questionnaire. The data were analyzed using Structural Equation Modeling and SMART PLS 3.0. Results: OFDAs were introduced into Indonesia in the recent past with varying degrees of popularity determined by the number of downloads. Users' intention to use was not determined by the speed of the introduction of an OFDA. This study also reveals that previous experience of the service, the orientation of time and price savings had a significant effect on spending habits. A moderating role of the saving variable on time and price was not demonstrated. Conclusions: The results of the study suggest that, in COVID-19 pandemic conditions, the spending habits of Generation Z are not based on impulse, thrift, or extravagance. The pandemic shaped specific motivations in spending habits, namely prioritizing need. This study has limitations, including the small sample size and the use of internal variables. © 2022. The Author(s). All Rights Reserved.

Sentiment Analysis on Telemedicine App Reviews using XGBoost Classifier

In recent years, companies have widely used sentiment analysis with machine learning classification algorithms to help business decision-making. Sentiment analysis helps evaluate customer opinions on a product in goods or services. Companies need this opinion or sentiment to improve the performance, quality of their products, and customer satisfaction. Machine learning algorithms widely used for sentiment analysis are Naive Bayes Classifier, Maximum Entropy, Decision Tree, and Support Vector Machine. In this study, we propose an approach of sentiment analysis using a very popular method, Extreme Gradient Boosting or XGBoost. XGBoost combines weak learners into an ensemble classifier to build a strong learner. This study will focus on the reviews data of the most popular telemedicine application in Indonesia, Halodoc. This study aims to examine the people's sentiment towards telemedicine applications in Indonesia, especially during the COVID-19 pandemic. We also showed a fishbone diagram to analyze the most factors the users complained about. The data we have are imbalanced;however, XGBoost can perform well with 96.24% accuracy without performing techniques for imbalanced data. © 2021 IEEE.

Electronic News Sentiment Analysis Application to New Normal Policy during the Covid-19 Pandemic Using Fasttext and Machine Learning

The new phase in handling COVID-19 in Indonesia, called New Normal, gives various public perspectives regarding this policy. This study aims to analyze public sentiment towards the New Normal policy through an electronic news comment column. This study uses text data in the form of comments were collected from electronic news media sites, namely www.detik.com and www.kompas.com, and taken from the comments column on Instagram social media, namely the @detikcom account. Also, use FastText method to extract features by converting data into vector values and using three classification methods, Naive Bayes (NB), Support Vector Machine (SVM), and Multilayer Perceptron (MLP). This study conducted a hyperparameter test to obtain the most optimal model. Testing the hyperparameters from FastText produces an optimal model with dimensions of 250, window size 8, epoch 1.000, and a learning rate of 0,0025. Hyperparameter testing was also carried out on the SVM and MLP classifiers. Hyperparameter testing of the SVM and MLP classifiers produces the most optimal model with the SVM method using the RBF kernel, C of 1.000, gamma of 10. In contrast, the MLP method uses the relu activation function, hidden size layer (250,250), adam optimizer, alpha 0,0001, and adaptive learning rate. The classification model was evaluated using K-fold cross-validation to produce an average f1score. The result is for the NB method 72,25% f1score, for the SVM method 92,21% f1score, and for the MLP method 90,75% f1score. © 2021 IEEE.

Analysis of Prediction Data for the Third Wave of COVID-19 in Bogor Regency

The COVID-19 pandemic is far from over. The government has carried out several policies to suppress the development of COVID-19 is no exception in Bogor Regency. However, the public still has to be vigilant especially now we will face a year-end holiday that can certainly be a trigger for the third wave of COVID-19. Therefore, researchers aim to make predictions of the increase in positive cases, especially in the Bogor Regency area to help the government in making policies related to COVID-19. The algorithms used are Gaussian Process, Linear Regression, and Random Forest. Each Algorithm is used to predict the total number of COVID-19 cases for the next 21 days. Researchers approached the Time Series Forecasting model using datasets taken from the COVID-19 Information Center Coordinationn Center website. The results obtained in this study, the method that has the highest probability of accurate and appropriate data contained in the Gaussian Process method. Prediction data on the Linear Regression method has accurate results with actual data that occur with Root Mean Square Error 1202.6262. © 2021 IEEE.

COVID-19 Social Safety Nets Sentiment Analysis on Twitter Using Gated Recurrent Unit (GRU) Method

One of the Indonesian government's programs in dealing with Covid19 problems is the Social Safety Net program which is given to the community, especially Covid19 assistance which is given every month to the community. Based on the assistance provided by the government, many people expressed their opinions through Twitter social media. This study aims to analyze the sentiment on Twitter tweets regarding the Social Safety Net Program from March to December 2020. The data collected is 4061 tweets data. The data is classified into two classes, namely positive and negative. The classification algorithm used is Gated Recurrent Unit (GRU). Hyperparameter testing is carried out in order to produce an optimal model. In the optimal GRU hyperparameter, when there are 10 GRU units, the activation function is sigmoid, the optimizer used is Adam, the batch size is 128, with 10 epochs of iteration and 0.2 dropout size. The GRU model produces an f1score of 92.09%, a precision of 90.34%, and a recall of 93.90%. © 2021 IEEE.

Face Recognition Using Fisherface and Support Vector Machine Method

COVID-19 is declared as a pandemic by WHO and until now COVID-19 pandemic remains a problem in 2021. Many efforts have been made to reduce the spreading virus, one way to reduce its spread is by wearing a mask but most people often ignore it. Monitoring large groups of people becomes difficult by the government or the authorities. Face recognition, a biometric technology, is based on the identification of a face features of a person. This paper describes a face recognition using Fisherface and Support Vector Machine method to classify face mask dataset. Face recognition using Fisherface method is based on Principal Component Analysis (PCA) and Fisher's Linear Discriminant (FLD) method or also known as Linear Discriminant Analysis (LDA). The algorithm used in the process for feature extraction is Fisherface algorithm while classification using Support Vector Machine method. The results show that for face recognition on face mask dataset using cross validation with 10 fold, the average percentage accuracy is 99.76%. © 2021 IEEE.

COVID-19 Detection in Chest X-Rays Using Inception Resnet-v2

Screening for COVID-19 is a vital part of the triage process. The current COVID-19 gold standard, the RT-PCR test, is regarded to be costly and time consuming. Artificial intelligence can be utilized to identify COVID-19 in radiographic pictures to overcome the limitations of existing testing methods. This study describes how the Inception-ResNet-v2 architecture was used to categorize pictures into three categories using transfer learning (Normal, Viral Pneumonia, and COVID-19,). Despite only running for 29 epochs, the resultant model had an accuracy of 0.966. This demonstrates the utility of AI in the diagnosis of illnesses. © 2021 IEEE.

Prediction New Cases of COVID-19 in Indonesia Using Vector Autoregression (VAR) and Long-Short Term Memory (LSTM) Methods

The addition of Covid-19 cases is still uncontrolled, especially in Indonesia. Often the addition of Covid-19 cases in Indonesia always experiences a significant upward trend after a slightly loose government policy. This is because the government does not think there will be a spike in cases after cases go down. This is where the importance of predicting new cases of Covid-19 in Indonesia to be a reference for the government in taking policy. With deep learning, the prediction results will be more accurate. The implementation of vector autoregression (VAR) and long-short term memory (LSTM) methods can reach an accretion rate of up to 98%. With this method, the prediction results can be used for the government in anticipating if there is a surge in new cases per day because it has been predicted from the beginning. In fact, this method can predict new cases for up to a year. © 2021 IEEE.

Framing analysis of COVID-19 news on social media Instagram Lombok

Coronavirus or Coronavirus disease-19 (COVID-19) since the beginning of 2020 has become news that fills mass media and social media. Instagram is a social media that is used for COVID-19 news. Instagram accounts @ insidelombok and @instalombok are two accounts that are quite active in providing information about COVID-19 in West Nusa Tenggara. Some media have their own style in writing the news. The purpose of this study is to find out how the two Instagram @insidelombok and @instalombok social media accounts frame (framing) COVID-19 news in West Nusa Tenggara. The framing analysis model used is the Robert N. Entman model. The subjects in this study were Instagram accounts on the island of Lombok namely @insidelombok and @instalombok. The object of this research is the upload of two Instagram accounts @insidelombok @instalombok about COVID-19 news in West Nusa Tenggara. The two accounts are framing the development of the number of positive COVID-19 patients per day by including trusted official sources in each framing of the timeline uploads of the two accounts. The difference in the framing of the news presented by the Instagram account @insidelombok and @instalombok can be seen from the way it is presented in the Instagram account timeline. The Instagram account @insidelombok is consistent with the display’s characteristic features in the form of a photo explanation of news uploads consisting of several slides. While the Instagram @instalombok account tends to upload a photo by giving an explanation in the form of news content on the uploaded caption.

Pengetahuan masyarakat tentang protokol kesehatan dengan tindakan pencegahan penularan COVID-19 di wilayah Kabupaten Sikka

The aim of this study is to find out the relationship between public knowledge about health protocols and prevention measures for COVID-19 transmission in the Sikka Regency area. This type of research is analytic observational with cross sectional design. A questionnaire was given to measure public knowledge about health protocols and an observation sheet to see the behavior of the community to prevent COVID-19 transmission. The sample in the study was 147 people using purposive sampling technique. Data analysis used Chi-Square with a significance level of α = 0.05. Results: of this study obtained public knowledge about the health protocol for the prevention of COVID-19 transmission was in a good category of 53.7% and most people made efforts to prevent COVID-19 transmission by 5M as much as 62.6%. And the results of statistical tests using the Chi Square test obtained p value = 0.029 <α = 0.05. Conclusion: there is a significant relationship between public knowledge about health protocols and measures to prevent COVID-19 transmission in the Sikka Regency area. Therefore, all forms of health education to the public related to COVID-19 must continue to be carried out and carry out tiered evaluations related to the implementation of health protocols and it is hoped that the community will be more obedient to implementing health protocols to prevent COVID-19 transmission through 5M measures. Keywords: COVID-19;Health Protocol;Knowledge

Movement campaign Don’t Slack! Discipline of wearing a mask in Poso Regency

The number of confirmed cases of COVID-19 in Poso Regency tends to be low. Until this article was written there were only 19 cases without a death case of which 18 people have been declared cured and 1 person is still being treated. This condition causes people to be less disciplined in implementing 3M (using masks, maintaining distance, and washing hands). Regarding the use of masks some argue that they do not have masks, and some are not afraid of being infected. Therefore, this activity seeks to campaign for the Don’t Slack! Discipline of Wearing Masks for the community goes through the stages of socialization and campaigning for the benefits of using masks, the right types of masks and how to use them as well as the distribution of masks. This activity was held at 3 central places in Poso City namely the Central Market Kasiguncu Market and the Welcome Kauwa Statue. Campaign activities for Don't Slack! Discipline of Wearing a Mask has succeeded in educating hundreds of citizens and distributing 1000 masks. It is hoped that with this campaign people in Poso Regency will be more orderly in complying with health protocols for the prevention of COVID-19.