Modified singular spectrum analysis in identifying rainfall trend over peninsular Malaysia

Shaharudin, Shazlyn Milleana; Ahmad, Norhaiza; Zainuddin, Nurul Hila

doi:10.11591/ijeecs.v15.i1.pp283-293

Cited by 9 publications

(9 citation statements)

References 3 publications

(6 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Hence, it was important to select some criteria to lead and establish a threshold to find a certain distinction between what does or does not constitute a day of torrential rainfall in the Peninsular Malaysia regions. The most common and applicable threshold in a tropical climate for this was 60 mm/day [18]. The filtered days with rainfall that exceeded 60 mm in at least 2% of the stations were used [19].…”

Section: Research Methods 21 Datamentioning

confidence: 99%

An Efficient Method to Improve the Clustering Performance using Hybrid Robust Principal Component Analysis-Spectral biclustering in Rainfall Patterns Identification

Shaharudin

Ismail

Nor

et al. 2019

IJ-AI

View full text Add to dashboard Cite

<p>In this study, hybrid RPCA-spectral biclustering model is proposed in identifying the Peninsular Malaysia rainfall pattern. This model is a combination between Robust Principal Component Analysis (RPCA) and bi-clustering in order to overcome the skewness problem that existed in the Peninsular Malaysia rainfall data. The ability of Robust PCA is more resilient to outlier given that it assesses every observation and downweights the ones which deviate from the data center compared to classical PCA. Meanwhile, two way-clustering able to simultaneously cluster along two variables and exhibit a high correlation compared to one-way cluster analysis. The experimental results showed that the best cumulative percentage of variation in between 65% - 70% for both Robust and classical PCA. Meanwhile, the number of clusters has improved from six disjointed cluster in Robust PCA-kMeans to eight disjointed cluster for the proposed model. Further analysis shows that the proposed model has smaller variation with the values of 0.0034 compared to 0.030 in Robust PCA-kMeans model. Evident from this analysis, it is proven that the proposed RPCA-spectral biclustering model is predominantly acclimatized to the identifying rainfall patterns in Peninsular Malaysia due to the small variation of the clustering result.</p>

show abstract

Section: Research Methods 21 Datamentioning

confidence: 99%

An Efficient Method to Improve the Clustering Performance using Hybrid Robust Principal Component Analysis-Spectral biclustering in Rainfall Patterns Identification

Shaharudin

Ismail

Nor

et al. 2019

IJ-AI

View full text Add to dashboard Cite

show abstract

“…The SSA is a model-free approach that can be applied to all types of data, regardless of Gaussian or non-Gaussian, linear or nonlinear, and stationary or nonstationary [19]. The student GPA can be decomposed into several additive components via SSA, which could be defined in the forms of trend, seasonal, and noise components [20]. The possible application areas of SSA are diverse [21−23].…”

Section: 1data Collectionmentioning

confidence: 99%

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

Fuad¹,

Shaharudin²,

Ismail³

et al. 2021

IJATEE

View full text Add to dashboard Cite

On 31 December 2019, the Wuhan Municipal Health Commission wrote in their website about the discovery of the novel corona virus which was later confirmed by the World Health Organization (WHO) that the virus originated from Republic of China. The contagious virus namely COVID-19 can cause respiratory problems to humans infected by it. Since then, almost all countries around the world have had cases of this virus. Malaysia's first case of COVID-19 was detected on January 24, 2020 [1]. Until November 9, 2020 the total number of confirmed cases are 50,030,121 that infected in 219 countries [2]. *Author for correspondenceAs a precaution in the dangerous virus spreading control, Tan Sri Muhyiddin bin Yassin, Malaysia's prime minister has imposed the Movement Control Order (MCO) from 18th of March, 2020 until year end. This order strictly prohibits Malaysians from engaging in any religious, sports, social and cultural activities involving many people.Due to the MCO, all educational institutions such as preschools, primary schools, secondary schools, and higher educational institutions had to be temporarily closed. On May 27, 2020, Malaysian Ministry of Higher Education (MOHE) recommended that all higher educational institutions to continue teaching and learning activities via online platforms until the end of 2020 [3]. Online learning is any form of teaching and learning delivered through digital technology such as Google Meet, MOOC, Zoom, YouTube and etc [4]. Teaching and learning

show abstract

“…It is therefore necessary to choose some criteria that would lead to the establishment of a threshold in order to allow for a clear distinction between what constitutes a day of torrential rainfall in the Peninsular Malaysia region and what does not. The range of threshold for torrential rainfall data in Peninsular Malaysia is 60 mm/day [14]. This threshold is chosen based on the categorization of rainfall intensity by Jabatan Pengairan dan Saliran (JPS).…”

Section: Rainfall Datamentioning

confidence: 99%

Fitting statistical distribution of extreme rainfall data for the purpose of simulation

Shaharudin

Ahmad

Mohamed

et al. 2020

IJEECS

Self Cite

View full text Add to dashboard Cite

<span>In this study, several types of probability distributions were used to fit the daily torrential rainfall data from 15 monitoring stations of Peninsular Malaysia from the period of 1975 to 2007. The study of fitting statistical distribution is important to find the most suitable model that could anticipate extreme events of certain natural phenomena such as flood and tsunamis. The aim of the study is to determine which distribution fits well with the daily torrential Malaysian rainfall data. Generalized Pareto, Lognormal and Gamma distributions were the distributions that had been tested to fit the daily torrential rainfall amount in Peninsular Malaysia. First, the appropriate distribution of the daily torrential rainfall was identified within the selected distributions for rainfall stations. Then, data sets were generated based on probability distributions that mimic a daily torrential rainfall data. Graphical representation and goodness of fit tests were used in finding the best fit model. The Generalized Pareto was found to be the most appropriate distribution in describing the daily torrential rainfall amounts of Peninsular Malaysia. The outputs can be beneficial for the purpose of generating several sets of simulated data matrices that mimic the same characteristics of rainfall data in order to assess the performance of the modification method compared to classical method. </span>

show abstract

Modified singular spectrum analysis in identifying rainfall trend over peninsular Malaysia

Cited by 9 publications

References 3 publications

An Efficient Method to Improve the Clustering Performance using Hybrid Robust Principal Component Analysis-Spectral biclustering in Rainfall Patterns Identification

An Efficient Method to Improve the Clustering Performance using Hybrid Robust Principal Component Analysis-Spectral biclustering in Rainfall Patterns Identification

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

Fitting statistical distribution of extreme rainfall data for the purpose of simulation

Contact Info

Product

Resources

About