Improved Cluster Partition in Principal Component Analysis Guided Clustering

Shaharudin, Shazlyn Milleana; Ahmad, Norhaiza; Yusof, Fadhilah

doi:10.5120/13156-0839

Cited by 5 publications

(4 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The algorithm of SVM has been proven effectively to be used in regression and classification methods. Based on previous studies from [19], the study reported that the SVM is generally able to result the best accuracy of classification compare than other methods. Also, SVM can performs linear and nonlinear classification with high efficiently.…”

Section: B Support Vector Machine (Svm)mentioning

confidence: 99%

Improving Support Vector Machine Rainfall Classification Accuracy based on Kernel Parameters Optimization for Statistical Downscaling Approach

Sulaiman¹

2020

IJATCSE

View full text Add to dashboard Cite

This study proposed a statistical downscaling model to find the best accuracy model of daily rainfall data in east-coast Peninsular Malaysia. Statistical downscaling is an approach to build relationship between the gap of climate change data from GCM and local climate by applying various mathematical model. The current studies don't contain a detailed investigation on selection the best accuracy model of statistical downscaling in study area. The proposed statistical downscaling having a main step which is classification-based Support Vector Machine (SVM). Predictor for this classification model was selected from large scale weather variables in NCEP reanalysis data. Methodologies involve in this proposed study are Principle Component Analysis (PCA) as preprocessing steps of data and SVM as classification model. The result was found that the best accuracy achieved by SVM are 65.28% by using radial basis function kernel and pair of parameter which is gamma ( =0.5) and penalty term ( =10000).

show abstract

Section: B Support Vector Machine (Svm)mentioning

confidence: 99%

Improving Support Vector Machine Rainfall Classification Accuracy based on Kernel Parameters Optimization for Statistical Downscaling Approach

Sulaiman¹

2020

IJATCSE

View full text Add to dashboard Cite

show abstract

“…The PCA was carried out with the software Statistica 7.0. PCA was used to reveal interrelationships among the ten species of the genus Beilschmiedia based on the essential oil common constituents of these species (Wickramagamage, 2010;Shaharudin et al, 2013;Shaharudin et al, 2018).…”

Section: Multivariate Data Analysismentioning

confidence: 99%

Multivariate statistical analysis of the essential oils of five Beilschmiediaspecies from Peninsular Malaysia

Salleh¹,

Shaharudin²

2021

BLACPMA

View full text Add to dashboard Cite

Identification of the chemical compositionof essential oils is very important for ensuring the quality of finished herbal products. The objective of the study was to analyze the chemical components present in the essential oils of five Beilschmiediaspecies (i.e. B. kunstleri, B. maingayi, B. penangiana, B. madang, and B. glabra) by multivariate data analysis using principal component analysis (PCA) and hierarchical clustering analysis (HCA) methods. The essential oils were obtained by hydrodistillation and fully characterized by gas chromatography (GC) and gas chromatography-mass spectrometry (GC-MS). A total of 108 chemical components were successfully identified from the essential oils of five Beilschmiediaspecies. The essential oils were characterized by high proportions of β-caryophyllene (B.kunstleri), δ-cadinene (B. penangianaand B. madang), and β-eudesmol (B. maingayiand B. glabra). Principal component analysis (PCA) and hierarchical cluster analysis (HCA) revealed that chemical similarity was highest for all samples, except for B. madang. The multivariate data analysis may be used for the identification and characterization of essential oils from different Beilschmiediaspecies that are to be used as raw materials of traditional herbal products.

show abstract

“…The PCA was carried out with the software Statistica 7.0. PCA was used to reveal interrelationships among the ten species of the genus Goniothalamus based on the essential oil common components of these species (Wickramagamage, 2010;Shaharudin et al, 2013Shaharudin et al, , 2018.…”

Section: Speciesmentioning

confidence: 99%

Review on Malaysian Goniothalamus essential oils and their comparative study using multivariate statistical analysis

Shakri

Salleh

Shaharudin

2021

Natural Volatiles and Essential Oils

View full text Add to dashboard Cite

The genus Goniothalamus is belonging to the Annonaceae family, consists of ca. 2500 species and found in tropical Southeast Asia. The Goniothalamus essential oils were recognized to possess considerable biological activities with varied chemical composition. This article aims to overview the medicinal uses, chemical compositions, and biological activities of Malaysian Goniothalamus essential oils considered as a medicinal plants, widely used as traditional herbal medicines in the treatment of various diseases. The data were collected from the scientific electronic databases including SciFinder, Scopus, Elsevier, PubMed and Google Scholar. Ten Goniothalamus species have been reported for their essential oils and biological activities. It can be observed that the major components were α-cadinol, terpinen-4-ol, β-eudesmol, β-selinene, linalool, limonene, α-copaene, 1,8-cineole and β-cubebene. In addition, the selected chemical components from the bark, leaf and root oils were analysed using Principal Component Analysis (PCA) and Hierarchical Cluster Analysis (HCA) and were able to cluster in four groups based on relationships and chemical patterns in essential oils. This multivariate data analysis may be used for the identification and characterization of essential oils from different Goniothalamus species that are to be used as raw materials of traditional herbal products.

show abstract

Improved Cluster Partition in Principal Component Analysis Guided Clustering

Cited by 5 publications

References 22 publications

Improving Support Vector Machine Rainfall Classification Accuracy based on Kernel Parameters Optimization for Statistical Downscaling Approach

Improving Support Vector Machine Rainfall Classification Accuracy based on Kernel Parameters Optimization for Statistical Downscaling Approach

Multivariate statistical analysis of the essential oils of five Beilschmiediaspecies from Peninsular Malaysia

Review on Malaysian Goniothalamus essential oils and their comparative study using multivariate statistical analysis

Contact Info

Product

Resources

About