Forecasting the Amount of Book Usage by Time Series Techniques

Main Article Content

ฉริยะ อัครวรรณ จารี ทองคำ


This research aims to compare an efficiency of time series techniques in predicting usage of library members' books. Data of book usage were collected from 2014 to 2017. Dewey Decimal of Classification was used to construct effective models consist of : (1) Artificial Neural Network (ANN) (2) Multi-Layer Perceptron Regression (MLPR) (3) Artificial Neural Network Regression (ANNR) (4) Support Vector Machine for Regression (SVMR) (5) Logistic Regression Analysis (LR) and (6) Reduced Error Pruning Tree (REPT). The models were compared with Sliding Windows method measured by values of Mean Absolute Error (MAE) and Root Mean Square Error (RMSE). The results showed that the prospective of library members book usage with the Support Vector Machine for Regression was the highest efficient. The MAE value was 9.42 and the RMSE was 11.46, respectively. 


Article Details

How to Cite
อัครวรรณฉ., & ทองคำจ. (2018). Forecasting the Amount of Book Usage by Time Series Techniques. Journal of Industrial Technology Ubon Ratchathani Rajabhat University, 8(2), 183-194. Retrieved from
Research Article


[1] Pena, M. A., Brenning, A., & Liao, R. Classifying fruit-tree crops by Landsat-8 time series. In Daniel Luhrt. 2017 First IEEE International Symposium of Geoscience and Remote Sensing (GRSSCHILE); 2017 June, 15-16; Engineering Faculty of the Universidad Austral de Chile. Valdivia, Chile. p. 1-5.
[2] Office of Academic Resources and Information Technology. The history of Office of Academic Resources and Information Technology [Internet]. 2015 [cited 2018 May 14] available from: (in Thai)
[3] Hancokkruad A. Road Accident Risk Prediction Model at Sakonnakhon Province using Data Mining Techniques [Master Thesis]. Mahasarakham: Mahasarakham University; 2013. (in Thai)
[4] Wandee Ch. A Study of the effected Factors for Choosing Career of Bachelor Graduates Using Data Mining Techniques [Master Thesis]. Mahasarakham: Mahasarakham University; 2017. (in Thai)
[5] Janecha M. Development of the Average of Water Stream Flow Prediction Models for Nakhonratsima Province [Master Thesis]. Mahasarakham: Mahasarakham University; 2017. (in Thai)
[6] Kourentzes, N., Barrow, D., & Crone, S. Neural network ensemble operators for time series forecasting. Expert Systems With Applications. 2014; 41(9): 4235-4244.
[7] Bahadir, E. Using Neural Network and Logistic Regression Analysis to Predict Prospective Mathematics Teachers’ Academic Success upon Entering Graduate Education. Educational Sciences: Theory & Practice. 2016; 16(3): 943-964.
[8] Zhang, G. P., & Qi, M. Neural network forecasting for seasonal and trend time series. European Journal of Operational Research. 2005; 160(2): 501-514.
[9] Lenz, B., & Barak, B. Data Mining and Support Vector Regression Machine Learning in Semiconductor Manufacturing to Improve Virtual Metrology. In Shidler College of Business. 2013 46th Hawaii International Conference on System Sciences; 2013 January, 7-10; Piscataway, New Jersey. Wailea, Maui, HI: United States; 2013. p. 3447-3456.
[10] Bozpolat, E. Investigation of the Self-Regulated Learning Strategies of Students from the Faculty of Education Using Ordinal Logistic Regression Analysis. Educational Sciences: Theory & Practice. 2016; 16(1): 301-318.
[11] Abdel-Aty, M., Uddin, N., Pande, A., Abdalla, F., & Hsia, L. Predicting Freeway Crashes from Loop Detector Data by Matched Case-Control Logistic Regression. Transportation Research Record: Journal of the Transportation Research Board. 1897; 1: 88-95
[12] Wongprachanukul N. A Proper method for decision tree pruning in scientific data mining [Master Thesis]. Nakhon Ratchasima; Suranaree University of Technology; 2005. (in Thai)
[13] Lundkvist, E. Decision Tree Classification and Forecasting of Pricing Time Series Data. KTH: sPublikationsdatabas DIVA [Internet]. 2014 [cited 2017 July 19] available from :