Comparison of singular spectrum analysis forecasting algorithms for student’s academic performance during COVID-19 outbreak

Fuad, Muhammad Fakhrullah Mohd; Shaharudin, Shazlyn Milleana; Ismail, Sarimah; Samsudin, Nor Ain Maisarah; Zulfikri, Muhammad

doi:10.19101/ijatee.2020.s1762138

Cited by 5 publications

(3 citation statements)

References 20 publications

(13 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, many students have no access to online teaching due to a lack of means or instruments because of the economic and digital divide. Hence, these virtual and digital strategies as a whole learning process seem to give a huge impact on university students, especially on their academic achievement [4].…”

Section: Introductionmentioning

confidence: 99%

Mapping of Students’ Academic Performance in Online Learning Environment during Pandemic Using Multiple Correspondence Analysis

Rosmadi¹,

Shaharudin²,

Rajoo³

et al. 2023

IJIET

View full text Add to dashboard Cite

The virtual and digital learning process seems to hugely impact academic achievement due to the COVID-19 outbreak, globally. Thus, improving student performance is one of the important focuses of educational management. Mapping students’ actual conditions is a mandatory requirement before designing the performance improvement program. Therefore, this study proposed a statistical investigation to map out students’ performance and the problems they encountered during online learning using Multiple Correspondence Analysis (MCA), revealing the hidden pattern and classifying students based on their demographics (programs, CGPA, and origin) and learning environments. The data samples consist of 234 undergraduate students in the Department of Mathematics, Faculty of Science and Mathematics, Universiti Pendidikan Sultan Idris (UPSI). The study findings formed from two different profiles where each profile has its respective categories. The study found that the students of the Bachelor of Education (Mathematics) with Honour, categorized as smart students, preferred to study face-to-face because of poor internet connection from using mobile data. On the other hand, the students of the Bachelor of Science (Mathematics) with Education, who were categorized as average students, had no difficulty continuing either synchronous or asynchronous online learning in the future because of stable internet access using their home Wi-Fi connection. Moreover, the preference made was also due to family interruption issues.

show abstract

Section: Introductionmentioning

confidence: 99%

Mapping of Students’ Academic Performance in Online Learning Environment during Pandemic Using Multiple Correspondence Analysis

Rosmadi¹,

Shaharudin²,

Rajoo³

et al. 2023

IJIET

View full text Add to dashboard Cite

show abstract

“…Due to these issues, IHLs, including the engineering program, used a cumulative grade point average (CGPA) as a key performance to measure the overall academic standing in the decade. Various studies have been conducted to evaluate the effects of the CGPA on the student's academic performance [9]- [12]. However, many employers still believe that a CGPA of 3.0 or higher demonstrates competence and capacity to perform the job and hence use it to screen candidates for an initial interview [13].…”

Section: Introductionmentioning

confidence: 99%

Individual student key performance using mobile web apps based on knowledge profile and cumulative grade point average

Khamis¹,

Sulong²,

Apandi³

et al. 2023

IJERE

View full text Add to dashboard Cite

This study investigated the performance of individual students toward the knowledge profile and cumulative grade point average or known as CGPA. The proposal of this paper involves two major components. The first component is investigating the individual student performance based on the knowledge profile and CGPA. The performance of students from cohort 2017 for the program Bachelor of Electrical Engineering (BEKG) courses in the Faculty of Electrical Engineering, Universiti Teknikal Malaysia Melaka (UTeM) was used as the dataset. The case study separates into various groups (excellent, honors and pass). Secondly, the study proposed a responsive web application leveraging a Google Visualization Feature to self-check individual academic performance. The goal of this app is to assist users in evaluating individual student performance and assist management in planning for continual quality improvement using the web and mobile apps. The marketing segments include students, academics, university, and school administration for analysis and evaluate the individual student’s performance.

show abstract

“…Although SSA lacks parametric description and highly relies on the length of time series, these flexible SSA models can recreate the asymmetric shapes of a trend, hence allowing better prediction of seasonal peaks than can harmonic models. This model, when compared to others, is easy to use, dismisses specification of models of time series and trend, enables extraction of trend in the presence of noise and oscillations, and involves only two parameters to determine the accuracy and flexibility in predicting outcomes ( 22 ).…”

Section: Introductionmentioning

confidence: 99%

Short-Term Forecasting of Daily Confirmed COVID-19 Cases in Malaysia Using RF-SSA Model

Shaharudin

Ismail

Hassan

et al. 2021

Front. Public Health

Self Cite

View full text Add to dashboard Cite

Novel coronavirus (COVID-19) was discovered in Wuhan, China in December 2019, and has affected millions of lives worldwide. On 29th April 2020, Malaysia reported more than 5,000 COVID-19 cases; the second highest in the Southeast Asian region after Singapore. Recently, a forecasting model was developed to measure and predict COVID-19 cases in Malaysia on daily basis for the next 10 days using previously-confirmed cases. A Recurrent Forecasting-Singular Spectrum Analysis (RF-SSA) is proposed by establishing L and ET parameters via several tests. The advantage of using this forecasting model is it would discriminate noise in a time series trend and produce significant forecasting results. The RF-SSA model assessment was based on the official COVID-19 data released by the World Health Organization (WHO) to predict daily confirmed cases between 30th April and 31st May, 2020. These results revealed that parameter L = 5 (T/20) for the RF-SSA model was indeed suitable for short-time series outbreak data, while the appropriate number of eigentriples was integral as it influenced the forecasting results. Evidently, the RF-SSA had over-forecasted the cases by 0.36%. This signifies the competence of RF-SSA in predicting the impending number of COVID-19 cases. Nonetheless, an enhanced RF-SSA algorithm should be developed for higher effectivity of capturing any extreme data changes.

show abstract

Comparison of singular spectrum analysis forecasting algorithms for student’s academic performance during COVID-19 outbreak

Cited by 5 publications

References 20 publications

Mapping of Students’ Academic Performance in Online Learning Environment during Pandemic Using Multiple Correspondence Analysis

Mapping of Students’ Academic Performance in Online Learning Environment during Pandemic Using Multiple Correspondence Analysis

Individual student key performance using mobile web apps based on knowledge profile and cumulative grade point average

Short-Term Forecasting of Daily Confirmed COVID-19 Cases in Malaysia Using RF-SSA Model

Contact Info

Product

Resources

About