From the perspective of students' needs: Improve the information construction under the smart campus in the Chinese Universities

With the development of science and technology and the impact of the COVID-19 in recent two years, the concept of the smart campus has gradually played an increasingly important role in universities of China, especially for students. Smart campus is defined as physical space and information space are organically connected, so that anyone, anytime and anywhere can easily obtain resources and services. To better enable students to benefit from the construction of the smart campus in the post-epidemic era, this paper investigates Chinese students and analyzes the data after the average classification by using the statistical method of the linear regression model. Finally, it discusses the relationship between the students' needs and the score of smart campus construction to put forward suggestions for the construction of the smart campus in universities in China © 2022 ACM.

A new ridge estimator for linear regression model with some challenging behavior of error term

Ridge regression is a variant of linear regression that aims to circumvent the issue of collinearity among predictors. The ridge parameter (Formula presented.) has an important role in the bias-variance tradeoff. In this article, we introduce a new approach to select the ridge parameter to deal with the multicollinearity problem with different behavior of the error term. The proposed ridge estimator is a function of the number of predictors and the standard error of the regression model. An extensive simulation study is conducted to assess the performance of the estimators for the linear regression model with different error terms, which include normally distributed, non-normal and heteroscedastic or autocorrelated errors. Based upon the criterion of mean square error (MSE), it is found that the new proposed estimator outperforms OLS, commonly used and closely related estimators. Further, the application of the proposed estimator is provided on the COVID-19 data of India. © 2023 Taylor & Francis Group, LLC.

Deep Reinforcement Learning for Portfolio Management

This paper discussed how to build deep reinforcement learning (DRL) agents to determine the allocation of money for assets in a portfolio so that the maximum return can be gained. The policy gradient method from reinforcement learning and convolutional neural network/recurrent neural network/convolutional neural network concatenated with the recurrent neural network from deep learning are combined together to build the agents. With the proposed models, three types of portfolios are tested: stocks portfolio which has a positive influence due to the Covid-19, stocks portfolio which has a negative influence due to the Covid-19, and portfolio of stocks combined with cryptocurrency which are randomly selected. The performance of our DRL agents was compared with that of equal-weighted agent and all the money fully invested on one stock agents. All of our DRL agents showed the best performance on the randomly selected portfolio, which has an overall stable up-ticking trend. In addition, the performance of linear regression model was also tested with the random selected portfolio, and it shows a poor result compared to other agents. © 2022, EasyChair. All rights reserved.

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.

COVID-19 Pandemic Prediction using Machine Learning Methods

In this paper, we aim to predict the cases of covid-19 pandemic according to linear regression model and random forest model. We decide to try to predict the virus using the daily high and low temperatures because it is one of the biggest factors that can affect the spread and death of the virus.we decide to use days_num, vaccine_days, and ma_temp_high as features.Cases and deaths as labels. We find that that the virus surely has some relationship with temperature. If the theory turns out to be true, in the future, adjusting control efforts based on temperature could greatly improve efficiency and save money. Reduce ineffective expenditures and improve the quality of prevention and control. © 2022 SPIE.

Impact of COVID-19 Pandemic on Energy Demand in Estonia

The COVID-19 pandemic triggered a question of how to measure and evaluate adequacy of the applied restrictions. Available studies propose various methods mainly grouped to statistical and machine learning techniques. The current paper joins this line of research by introducing a simple-yet-accurate linear regression model which eliminates effects of weekly cycle, available daylight, temperature, and wind from the electricity consumption data. The model is validated using real data and enables the qualitative analysis of economical impact. © 2022 IEEE.

Covid-19's Impact On The Airline Industry In The US Stock Market Based on the Regression Model

In this paper, our group evaluates the effect of Covid-19 on the stock prices of the top 10 American airline companies and the NYSE Arca Airline Index using event study methodology. We accomplish this by comparing the Actual Returns and Expected Returns of an airline stock. We derive our Expected Return through a linear regression model between the airline stock returns and the market returns. We then subtract the Expected Return from the Actual Return to find the Abnormal Return. After that, we construct a confidence interval to test the significance of the Abnormal Return. If the Abnormal Return exceeds the confidence interval, we claim that Covid-19 had a significant effect on the stock price of our chosen Airlines. Our group's results showed that Covid-19 had a significant impact on the airline industry. We also looked at the impact of government-issued relief and mass vaccination, and we saw that airline stock prices recovered slowly but steadily. © 2021 IEEE.

Analysis and Implementation of a Novel AI-Based Hybrid Model for Detecting, Predicting and Identification of COVID-19 Spread

The beginning of Coronavirus spread in humans started during December of 2019 in Wuhan, China leading to its extension throughout the world by March 2020. INDIA is the third-largest infected country in the world and the infection is increasing exponentially day by day. There needs to be a full-stack algorithm to Detect, Predict and identify the spread of COVID-19, which will play a vital role in minimizing the fatalities. Already multiple algorithms like Support Vector Regression (SVR) Polynomial Regression (PR) Deep Learning regression models are used widely for predicting the COVID-19 spread. These algorithms are based on Neural Networks and work efficiently. They also do have limitations related to the time taken for identification, detection, and prediction at the early stage of the spread, as they lack the necessary feature. The paper proposes a total idiot proof model dependent on AI to do early identification of the COVID-19 spread. The proposed half breed model depends on novel neglected calculations utilized in Covid-19 examination. The exploratory outcome on the plague information of a few normal regions and urban communities in India shows that 25% of the people with Covid-19 have a higher disease rate inside the single day after they were tainted. The proposed AI-based cross breed model can fundamentally decrease the mistakes of the forecast results and predicts the pattern of the pestilence. © 2021 IEEE.

COVID-19 Outbreak from the Experience of Wave 1 and start of Wave 2: Comparison and Analysis

COVID-19 has proved to be one of the greatest outbreaks the world has ever seen. COVID-19 is a respiratory disease, whose fatality varies from person to person depending on factors like age group, weakened immune system, and many more. To date, it is believed that the world is fighting the second wave of Novel Coronavirus disease. The first case was observed in Wuhan, China, on December 31st, 2019, and in India, the first case was reported on January 30th, 2020. In this paper, we will be analyzing the data of daily active cases, comparing the 1st and the 2nd wave of the coronavirus in India. The data is collected from December 2019 to May 2020 (1st Wave) and from June 2020 to April 2021 (2nd Wave). We will be using the Machine Learning, Linear Regression model for comparison, and through a series of graphs, we will study how differently each wave hit India. There are 2 datasets for 2 phases, and we have compared them in this paper. © 2021 IEEE.

Machine learning model of covid-19 forecasting in Ukraine based on the linear regression

Coronavirus or COVID-19 is a widespread pandemic that has affected almost all countries around the globe. The quantity of infected cases and deceased patients has been increasing at a fast pace globally. This virus not only is in charge of infecting billions of people but also affecting the economy of almost the whole world drastically. Thus, detailed studies are required to illustrating the following trend of the COVID-19 to develop proper short-term prediction models for forecasting the number of future cases. Generally, forecasting techniques are be inculcated in order to assist in designing better strategies and as well as making productive decisions. The forecasting techniques assess the situations of the past thereby enabling predictions about the situation in the future would be possible. Moreover, these predictions hopefully lead to preparation against potentially possible consequences and threats. It’s crucial to point out that Forecasting techniques play a vital role in drawing accurate predictions. In this research, we categorize forecasting techniques into different types, including stochastic theory mathematical models and data science/machine learning techniques. In this perspective, it is feasible to generate and develop strategic planning in the public health system to prohibit more deceased cases and managing infected cases. Here, some forecast models based on machine learning are introduced and comprising the Linear Regression model which is assessed for time series prediction of confirmed, deaths, and recovered cases in Ukraine and the globe. It turned out that the Linear Regression model is feasible to implement and reliable in illustrating the trend of COVID-19. © 2021 IEEE.

Linear Regression and Holt's Winter Algorithm in Forecasting Daily Coronavirus Disease 2019 Cases in Malaysia: Preliminary Study

Coronavirus disease 2019 is a fatal viral disease presently sweeping the globe. COVID-19 is a novel coronavirus that produces an infectious illness. Thus, COVID-19 detection in the general population may be helpful. The involvement of machine learning in combating COVID-19 had rapidly increased because of its efficiency to scale up, faster processing capacity, and more dependable than humans in some healthcare activities. This paper will focus on two models which are Linear Regression (LR) model and Holt's Winter model. The COVID-19 dataset was taken from the Ministry of Health for Malaysia's website. Daily confirmed cases were recorded from 24th of January 2020 to 31st July 2021 and stored in Microsoft Excel. Waikato Environment for Knowledge Analysis (WEKA) software was utilized to perform the prediction of daily cases in the next 14-days and the quality of forecasting models is evaluated by two performance metrics, Mean Absolute Deviation (MAD) and Mean Absolute Percentage Error (MAPE). The best model is selected by the lowest value of performance metrics. The comparison shows that the forecasting result of Holt's Winter is more accurate than the LR model. The developed prediction model can help public health officials make better decisions and manage resources to decrease COVID-19 pandemic morbidity and mortality. Therefore, preparation and control procedures can be established. © 2021 IEEE.

Entrepreneurial alertness in different generations

Under COVID 19 environment it is important to analyse if there are differences between generations (X, Y, Z) within the context of entrepreneurial alertness (EA), and its influence in the creation of a new business. This study used a quantitative methodology trough a survey by questionnaire based on a sample of 978 people organized by age groups. We used, an exploratory factor analysis with principal components and varimax rotation, a one-way analysis of variance (ANOVA) by Tamhane Test and a linear regression model. An exploratory factor analysis is presented, to assess the dimensions of the entrepreneurial alertness from which two factors were obtained: the competence of processing information and establish connections to assure a profitable business (F1) and the capability of searching information and acknowledging opportunities (F2). Then, were applied one-way ANOVA and a linear regression model to compare different generations in relation with EA, and its relation to create a new business. The results demonstrate that generation Z has less propensity than generation Y in respect to F2. Besides F1 has the same importance for all generations. We found either, that the X generation has lower propension to start a new business. Testing the effects of different dimensions of EA, through a linear regression, with the propensity to develop a new business, we confirm that only F1 is significative while F2 is partial rejected. This research contributes to the field by demonstrating how different generations assign distinct relevance to entrepreneurial alertness dimensions and its importance to promote a new activity. © 2021, Academic Conferences and Publishing International Limited. All rights reserved.