Forecasting student admissions using back propagation multilayer neural network model Anyawee Chaiwachiragompol1,*, Sakchan Luangmaneerote1, Jeeranun Tasuntia1, Boonlueo Nabumroong1
Article Sidebar
Main Article Content
Abstract
In this study, the feed forward multilayer neural network model for predicting student admissions was examined and developed. Crucial influencing factors of under-the increase and decrease of the number of students in the Faculty of Agriculture and Technology Rajamangala University of Technology Isan Surin Campus. This research used the historical data of students and were analyzed the characteristics of each student for training the model. An algorithm for supervised learning and the WEKA program were used in the research. There were two stages to the research: an analyzing the appropriate factors affecting students' attendance in step one, and then bringing the information from the first step factors into the model to create learning for the model in step two. In this study, selecting of proper model in the learning of the data is established by structuring the appropriate structure and offering the best validity. This research is divided data in two parts: the first part of this study data 70% was conducted by building learning for the model, the second part consisted of data 30% was analyzed by testing for the model. Moreover, the feed forward multilayer neural network's structural parameters were 8-19-2 and its learning cycles were 500. The result found that the testing on 387 participants showed a mean absolute error (MAE), the root mean square error (RMSE), and the accuracy value was 0.2179, 0.3696, 82.74%, respectively.
Downloads
Article Details
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
ลิขสิทธิ์ต้นฉบับที่ได้รับการตีพิมพ์ในวารสารนวัตกรรมวิทยาศาสตร์เพื่อการพัฒนาอย่างยั่งยืนถือเป็นกรรมสิทธิ์ของคณะวิทยาศาสตร์และเทคโนโลยี มหาวิทยาลัยสวนดุสิต ห้ามผู้ใดนำข้อความทั้งหมดหรือบางส่วนไปพิมพ์ซ้ำ เว้นแต่จะได้รับอนุญาตอย่างเป็นลายลักษณ์อักษรจากคณะวิทยาศาสตร์และเทคโนโลยี มหาวิทยาลัยสวนดุสิต นอกจากนี้ เนื้อหาที่ปรากฎในบทความเป็นความรับผิดชอบของผู้เขียน ทั้งนี้ไม่รวมความผิดพลาดอันเกิดจากเทคนิคการพิมพ์
References
Chaiwachiragompol, A. and Suwannata, N. (2016). The features extraction of infants cries by using discrete wavelet transform techniques, international electrical engineering congress. Procedia Computer Science, 86, 285–288. https://doi.org/10.1016/j.procs.2016.05.073.
Intawee, T. (2021). Factors in affecting decision making in selecting educational institutions for higher education. Journal of Educational Innovation and Research. 5(1), 1–14. [In Thai].
Jabjone, S. (2015). Data mining. Nakhon Ratchasima: Faculty of Science and Technology, Nakhon Ratchasima Rajabhat University. [In Thai].
Kaewwijit, T. (2016). The improvement of support vector regression to forecast time series. (Master’s Thesis). Nakhon Ratchasima: Suranaree University of Technology. [In Thai].
Kanjanasamranwong, P., Urawong, K., Mad A Dam, R., and Mad A Dam, S. (2017). The opportunities forecast model in choosing to attend the Prince of Songkhla University of grade 12 students, Songkhla Province. Journal of Education Naresuan University. 19(2), 12–24. [In Thai].
Kijsirikul, B. (2003). Artificial Intelligence. Bangkok: Faculty of Engineering, Chulalongkorn University. [In Thai].
Lorpunmanee, S., Chimphlee, S., Chimphlee, W., Nedtharnn, W. and Piromnok, N. (2019). The forecasting patterns of juvenile recidivism. Journal of Science Innovation for Sustainable Development. 1(1), 80–95. [In Thai].
Ngamlamom, W. (2022). The human resource management of public sector in the disruption era. University of the Thai Chamber of Commerce Journal Humanities and Social Sciences. 42(1), 176–197. [In Thai].
Pacharawongsakda, E. (2014). An Introduction to data mining techniques. Bangkok: Data cube. [In Thai].
PimPa, P. (2018). Current Thai studies. Academic Journal of Mahamakut Buddhist University Roi Et Campus. 7(1), 242–249. [In Thai].
Rahman, H. (2009). Data mining applications for empowering knowledge societies. New York: Information Science Reference. P.12.
Roiger, R. J. and Geatz, M. W. (2003). Data mining: A tutorial-based primer. Boston: Addison Wesley. P.4.
Supabut, P., Hengpraprohm, K., Hengpraprohm, S., and Thammasiri, D. (2015). The comparison of prediction efficiency between linear regression and back-propagation neural network method. joint conference on ACTIS & NCOBA 2015. [In Thai].
Taesombat, S. (1996). Quantitative forecasting techniques. Bangkok: physics-center. [In Thai].
Treepuech, W. (2019). The analysis of injured and dead people data from accident in Songkran Festival by using data mining techniques. VRU Research and Development Journal, Science and Technology. 14(1), 11–20. [In Thai].
Visutthirat, T. (2018). Using data mining in an analysis and model building of the relationship between social quality and happiness of population in chanthaburi province. (Doctoral dissertation). Bangkok: National Institute of Development Administration (NIDA). [In Thai].
Wanon, S. and Muangsan, R. (2020). A study and development of forecasting model for the suitability characteristics on the applying major selection by using data mining techniques. Journal of Management Sciences. 7(1), 135–152. [In Thai].
Winston, P. H. (1992). Artificial Intelligence. Addison-Wesley Publishing Company. (3rd ed.). Massachusetts. US. 443–469.
Witten, I. H. and Frank, E. (2005). Data mining: Practical machine learning tools and technique (2nd ed.). San Francisco: Morgan Kaufmann Publishers. US. P.5.