Abstract

Due to the spread of COVID-19 that hit Malaysia, all academic activities at educational institutions including universities had to be carried out via online learning. However, the effectiveness of online learning is remains unanswered. Besides, online learning may have a significant impact if continued in the upcoming academic sessions. Therefore, the core of this study is to predict the academic performance of undergraduate students at one of the public universities in Malaysia by using Recurrent Forecasting-Singular Spectrum Analysis (RF-SSA) and Vector Forecasting-Singular Spectrum Analysis (VF-SSA). The key concept of the predictive model is to improve the efficiency of different types of forecast model in SSA by using two parameters which are window length (L) and number of leading components (r). The forecasting approaches in SSA model was based on the Grading Point Assessments (GPA) for undergraduate students from Faculty Science and Mathematics, UPSI via online classes during COVID-19 outbreak. The experiment revealed that parameter L= 11 (T/20) has the best prediction result for RF-SSA model with RMSE value of 0.19 as compared to VF-SSA of 0.30. This signifies the competency of RF-SSA in predicting the students’ academic performances based on GPA for the upcoming semester. Nonetheless, an RF-SSA algorithm should be developed for higher effectivity of obtaining more data sets including more respondents from various universities in Malaysia.

Keyword

Prediction, Academic performance, COVID-19, Online learning, Singular spectrum analysis, Recurrent forecasting.

Cite this article

Fuad MF, Shaharudin SM, Ismail S, Samsudin NA, Zulfikri MF

Refference

[1][1]https://www.who.int/emergencies/diseases/novel-coronavirus-2019/advice-for-public. Accessed 9 November 2020.

[2][2]https://www.who.int/emergencies/diseases/novel-coronavirus-2019. Accessed 9 November 2020.

[3][3]https://www.malaymail.com/news/malaysia/2020/05/27/higher-education-ministry-all-university-lectures-to-be-online-only-until-e/1869975. Accessed 9 November 2020.

[4][4]http://www.ukm.my/wadahict/pembelajaran-atas-talian-epsa-coursera-edxfuturelearn/. Accessed 9 November 2020.

[5][5]Bao W. COVID‐19 and online teaching in higher education: a case study of Peking University. Human Behavior and Emerging Technologies. 2020; 2(2):113-5.

[6][6]Iyer P, Aziz K, Ojcius DM. Impact of COVID‐19 on dental education in the United States. Journal of Dental Education. 2020; 84(6):718-22.

[7][7]Alvin MD, George E, Deng F, Warhadpande S, Lee SI. The impact of COVID-19 on radiology trainees. 2020; 296(2):246–8.

[8][8]Mian A, Khan S. Medical education during pandemics: a UK perspective. BMC Medicine. 2020; 18:1-2.

[9][9]Rose S. Medical student education in the time of COVID-19. JAMA. 2020; 323(21):2131-2.

[10][10]Kanneganti A, Sia CH, Ashokka B, Ooi SB. Continuing medical education during a pandemic: an academic institution’s experience. Postgraduate Medical Journal. 2020; 96(1137):384-6.

[11][11]Sandhu P, De Wolf M. The impact of COVID-19 on the undergraduate medical curriculum. Medical Education Online. 2020; 25(1):1-2.

[12][12]https://seleritysas.com/blog/2019/ 12/12/types-of-predictive-analytics-models-and- how-they work/#:~:text=There%20are%20several%20types%20of,algorithms%20and%20neural%20network%20algorithms. Accessed 9 November 2020.

[13][13]Burman I, Som S. Predicting students academic performance using support vector machine. In amity international conference on artificial intelligence 2019 (pp. 756-9). IEEE.

[14][14]Lau ET, Sun L, Yang Q. Modelling, prediction and classification of student academic performance using artificial neural networks. SN Applied Sciences. 2019.

[15][15]Hamoud A, Hashim AS, Awadh WA. Predicting student performance in higher education institutions using decision tree analysis. International Journal of Interactive Multimedia and Artificial Intelligence. 2018; 5(2):26-31.

[16][16]Aggarwal D, Sharma D. Application of clustering for student result analysis. International Journal of Recent Technology and Engineering. 2019; 7(6C):50-3.

[17][17]Asif R, Merceron A, Pathan MK. Predicting student academic performance at degree level: a case study. International Journal of Intelligent Systems and Applications. 2014:49-61.

[18][18]Zakaria R, Satari SZ, Damahuri NA, Khairuddin R. Descriptive analysis of students’ CGPA: a case study of Universiti Malaysia Pahang. In IOP conference series: materials science and engineering 2019 (pp. 1-9). IOP Publishing.

[19][19]Shaharudin SM, Ahmad N, Yusof F. Effect of window length with singular spectrum analysis in extracting the trend signal on rainfall data. In AIP conference proceedings 2015 (pp. 321-6). American Institute of Physics.

[20][20]Shaharudin SM, Ahmad N, Zainuddin NH. Modified singular spectrum analysis in identifying rainfall trend over peninsular Malaysia. Indonesian Journal of Electrical Engineering and Computer Science. 2019; 15(1):283-93.

[21][21]Shaharudin SM, Ahmad N, Mohamed NS, Aziz N. Performance analysis and validation of modified singular spectrum analysis based on simulation torrential rainfall data. International Journal on Advanced Science, Engineering and Information Technology. 2020; 10(4): 1450-6.

[22][22]Vile JL, Gillard JW, Harper PR, Knight VA. Predicting ambulance demand using singular spectrum analysis. Journal of the Operational Research Society. 2012; 63(11):1556-65.

[23][23]Alexandrov T, Golyandina N, Spirov A. Singular spectrum analysis of gene expression profiles of early drosophila embryo: exponential-in-distance patterns. Research Letters in Signal Processing. 2008.

[24][24]De Carvalho M, Rua A. Real-time nowcasting the US output gap: singular spectrum analysis at work. International Journal of Forecasting. 2017; 33(1):185-98.

[25][25]Golyandina N, Shlemov A. Variations of singular spectrum analysis for separability improvement: non-orthogonal decompositions of time series. arXiv preprint arXiv:1308.4022. 2013.

[26][26]Golyandina N, Korobeynikov A. Basic singular spectrum analysis and forecasting with R. Computational Statistics & Data Analysis. 2014; 71:934-54.

[27][27]Danilov DL. Principal components in time series forecast. Journal of Computational and Graphical Statistics. 1997; 6(1):112-21.

[28][28]Danilov D. The caterpillar method for time series forecasting. Principal Components of Time Series: The Caterpillar Method. 1997:73-104.

[29][29]Hassani H, Mahmoudvand R. Multivariate singular spectrum analysis: a general view and new vector forecasting approach. International Journal of Energy and Statistics. 2013; 1(01):55-83.

[30][30]Ghodsi M, Hassani H, Rahmani D, Silva ES. Vector and recurrent singular spectrum analysis: which is better at forecasting? Journal of Applied Statistics. 2018; 45(10):1872-99.

[31][31]Golyandina N, Nekrutkin V, Zhigljavsky AA. Analysis of time series structure: SSA and related techniques. CRC press; 2001.

[32][32]Mahmoudvand R, Alehosseini F, Rodrigues PC. Forecasting mortality rate by singular spectrum analysis. REVSTAT–Statistical Journal. 2015; 13(3):193-206.

[33][33]Dong Y, Zhang L, Liu Z, Wang J. Integrated forecasting method for wind energy management: a case study in China. Processes. 2020; 8(1):1-26.

[34][34]Shaharudin SM, Ismail S, Tan ML, Mohamed NS, AininaFilzaSulaiman N. Predictive modelling of covid-19 cases in Malaysia based on recurrent forecasting-singular spectrum analysis approach. International Journal of Advanced Trends in Computer Science and Engineering. 2020; 9(1.4):175-83.