Abstract
Education competitiveness is a key feature of national competitiveness. It is crucial for nations to develop and enhance student and teacher potential to increase national competitiveness. The decreasing population of children has caused a series of social problems in many developed countries, directly affecting education and com.petitiveness in an international environment. In Taiwan, a low birthrate has had a large impact on schools at every level because of a substantial decrease in enrollment and a surplus of teachers. Therefore, close attention must be paid to these trends. In this study, combining a whale optimization algorithm (WOA) and support vector regression (WOASVR) was proposed to determine trends of student and teacher numbers in Taiwan for higher accuracy in time-series forecasting analysis. To select the most suitable support vector kernel parameters, WOA was applied. Data collected from the Ministry of Education datasets of student and teacher numbers between 1991 and 2018 were used to examine the proposed method. Analysis revealed that the numbers of students and teachers decreased annually except in private primary schools. A comparison of the forecasting results obtained from WOASVR and other common models indicated that WOASVR provided the lowest mean absolute percentage error (MAPE) and root mean square error (RMSE) for all analyzed datasets. Forecasting performed using the WOASVR method can provide accurate data for use in developing education policies and responses.
Highlights
The near-global decline in fertility has led to considerable socioeconomic changes. e low fertility rate observed in many countries is likely the result of economic, social, cultural, and institutional transformations [1]
From 1999 to 2018, data were collected in a Ministry of Education database, and demographics were categorized for public and private schools [59]. e training data used to train the algorithms consisted of the annual data for 1999–2012. e forecast accuracy was evaluated using the testing data, which consisted of the annual student enrollment and teacher statistics data for 2013–2018
Two popular machine learning algorithms, namely, particle swarm optimization (PSO) and whale optimization algorithm (WOA), are proposed to optimize Support vector regression (SVR) hyperparameters. e population size in PSO was set as 50, the acceleration factors c1 and c2 were set as 2.0, and the maximum number of iterations was set as 100. e aforementioned hyperparameters were selected in accordance with the study of Bratton and Kennedy [61]. e population size in WOA was set as 20, and the maximum number of iterations was set at 100. e training results obtained from GRIDSVR, PSOSVR, and WOA and SVR (WOASVR) methods with the selected hyperparameters for student and teacher forecasting are presented in Tables 1 and 2, respectively
Summary
The near-global decline in fertility has led to considerable socioeconomic changes. e low fertility rate observed in many countries is likely the result of economic, social, cultural, and institutional transformations [1]. The near-global decline in fertility has led to considerable socioeconomic changes. E low fertility rate observed in many countries is likely the result of economic, social, cultural, and institutional transformations [1]. Some theories linking broad social changes to fertility decline may be relevant to all countries. Common trends for fertility patterns are present in many regions. Other theories discuss the situation unique to a particular country. The fertility transition has taken place globally, the rate of fertility decline, levels that have been hit, and current fertility rates differ by country. E decline in fertility rates in certain societies is likely to result from an interplay of global phenomena, regional policies, and local forces. Weakening economic and global competitiveness and decreasing birthrates will challenge the competitiveness of a nation by leaving it with a labor shortage
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
