Logistic Regression Model for Measuring Perception on Open and Distance Learning (ODL) during COVID-19 Pandemic based on Impeding Factors among Students

Authorities have suggested emergency remote instruction to guarantee that students are not left idle during the pandemic due to the sudden closing of educational facilities. Then for the time being, traditional methods (face-to-face) have been replaced by Open and Distance Learning (ODL). Face-to-face learning was preferred by the majority of students over online learning since students were not able transit to online learning and lacked inspiration. Hence, this study focuses on perception towards ODL during COVID-19 among statistics' students at FSKM UiTM Shah Alam based on some impeding factors such as social issue, lecturer issue, accessibility issue, academic issue, generic skills and learner intentions. The aim of this study is to investigate the perception of statistics' students on ODL based on impeding factors and to identify the significant impeding factors effect on statistics students' perception on ODL. There are 160 observations that are used in this study. The methods that are being used in this study are descriptive analysis and logistic regression. Overall, from the result obtained, students' perception on ODL are approximately to agree for social issue, academic issue and learner intentions variables. Meanwhile, the significance impeding factors in this study are social issue and learner intentions. This study may help higher education institution to improve and make a better strategy to improve the existing teaching method that have been applied by all lecturers. © 2022 IEEE.

COVID-19 Patient Recovery Prediction Using Efficient Logistic Regression Model

This research develops a COVID-19 patient recovery prediction model using machine learning. A publicly available data of infected patients is taken and pre-processed to prepare 450 patients' data for building a prediction model with 20.27% recovered cases and 79.73% not recovered/dead cases. An efficient logistic regression (ELR) model is built using the stacking of random forest (RF) and logistic regression (LR) classifiers. Further, the proposed model is compared with state-of-art models such as logistic regression (LR), support vector machine (SVM), decision tree (C5.0), and random forest (RF). All the models are evaluated with different metrics and statistical tests. The results show that the proposed ELR model is good in predicting not recovered/dead cases and handling imbalanced data. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

Using Deep Learning Algorithm for Prediction and Detection of Covid-19

As the Covid-19 puts the great impact on the world health and economic situations, which directly leads toward the crisis. Prediction helps us to take precaution accordingly. Currently, more than 293 million of positive cases have been detected and more than 5.4 million deaths have been recorded. To prevail the spread of virus many countries open sourced datasets of Covid-19 positive cases for scientists to predict the curve. Therefore, countries can take the measures accordingly. It helps to obtain a rough idea about the pandemic end date, which is very difficult to predict because of its uncertainty. This article takes the dataset of many countries and predicts the curve of positive cases of the top 10 countries. We used this data to integrate it with logistic regression model to have a future view of pandemic. The article consists of two parts. First part includes the prediction by using logistic regression. This function used Python programming, Panda's machine learning library, whereCovid-19 dataset has been taken from the open-source dataset available on the internet. Second part includes the detection of Covid-19 using Deep Learning Convolution neural network method. CNN method is used by training the model with the dataset of X-ray Images. CNN can detect the virus at early stages because of its powerful deep learning multiple layers ‘algorithm. There are several stages of detection such as processing image datasets and applying image-processing techniques to have a clear understanding of features in X-ray images. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

Comparison of Machine Learning Prediction of Covid-19 Spread in Indonesia

COVID-19 is an infectious disease caused by the corona virus which is a respiratory pathogen. This work focuses on predicting the COVID-19 pandemic in Indonesia and seeing how each different model performs in making predictions. Prediction is done using the Support Vector Machine model with each kernel rbf, poly, and sigmoid, Linear Regression, and Logistic Regression. The category split into Indonesia Time Zone which are WIB, WITA, and WIT. The results of the number of predicted cases obtained from the Support Vector Machine kernel poly model on day 305 for the WIB time zone is 606344, WITA is 167757, and WIT is 38979. The Linear Regression model on day 305 for the WIB time zone is 321388, WITA is 86840, and WIT is 20406. Logistic Regression model on day 305 for the time zone of WIB is 361356, WITA is 84918, and WIT is 20826. From analyzing the number of predicted cases with the number of factual cases, the Support Vector Machine model with the poly kernel has the number of prediction cases that are closest to factual. © 2022 IEEE.

Using Machine Learning classification methods to detect COVID-19 Status in Selangor District

Recently, Covid 19 pandemic has been recognized as a public health emergency of international concern. According to global COVID-19 infection data, the total number of cases is over 147 million, with over 3 million fatalities. Common model that use to predict binary outcome is Logistic regression model. However, the majority of the models have not been implemented widely by using ML approaches. Thus, the interest of this study has been coined to the Covid 19 cases prediction model that influence the extend of risk to urge Covid 19 infection. Therefore, this study addressed how to use four ML algorithms offered by Rapid Miner software tools to identify the optimum classification model. The results show that Decision Tree has been very promising to produce a high percentage of accuracy rate of 75.47% compared to other models. Further research on the data structure is necessary to be conducted in order to address problems like bias and an unbalanced dataset. In addition, new factors like vaccination status should be incorporated into the model to determine whether the respondent is at risk of contracting COVID 19 or not. © 2022 IEEE.

Spatial and temporal patterns and factors influencing the spread of the COVID-19 pandemic in China

It is essential to unravel the spatial and temporal patterns of the spread of the epidemic in China during the backdrop of the global coronavirus disease 2019 (COVID-19) outbreak in 2020, as the underlying drivers are crucial for scientific formulation of epidemy-preventing strategies. A discriminant model for the spatio-temporal pattern of epidemic spread was developed for 317 prefecture-level cities using accumulated data on confirmed cases. The model was introduced for the real-time evolution of the outbreak starting from the rapid spread of COVID-19 on January 24, 2020, until the control on March 18, 2020. The model was used to analyze the basic characteristics of the spatio-temporal patterns of the epidemic spread by combining parameters such as peak position, full width at half maximum, kurtosis, and skewness. A multivariate logistic regression model was developed to unravel the key drivers of the spatio-temporal patterns based on traffic accessibility, urban connectivity, and population flow. The results of the study are as follows. (1) The straight-line distance of 588 km from Wuhan was used as the effective boundary to identify the four spatial patterns of epidemic spread, and 13 types of spatio-temporal patterns were obtained by combining the time-course categories of the same spatial pattern. (2) The spread of the epidemic was relatively severe in the leapfrogging model. Besides the short-distance leapfrogging model, significant differences emerged in the spatial patterns of the time course of epidemic spread. The peaks of the new confirmed cases in various spatio-temporal patterns were mostly observed on February 3, 2020. The average full widths at the half maximum of all ordinary cities were approximately 14 days, thus, resonating with the incubation period of the COVID-19 virus. (3) The degree of the population correlation with Wuhan city has mainly influenced the spreading and the short-distance leapfrogging spatial patterns. The existence of direct flight from Wuhan city exhibited a positive effect on the long-distance leapfrogging spatial pattern. The number of population outflows has significantly affected the leapfrogging spatial pattern. The integrated spatial pattern was influenced by both primary and secondary epidemic outbreak sites. Thus, cities should pay great attention to traffic control during the epidemic as analysis has shown that the spatio-temporal patterns of epidemic spread in the respective cities can curb the spread of the epidemic from key links. © 2022, Science Press. All right reserved.