Agarwood Oil Quality Grading using OVO Multiclass Support Vector Machine

Amidon, Aqib Fawwaz Mohd; Mahabob, Noratikah Zawani; Haron, Mohamad Hushnie; Ismail, Nurlaila; Yusoff, Zakiah Mohd; Taib, Mohd Nasir; Tajuddin, Saıful Nizam; Ali, Nor Azah Mohd

doi:10.1109/aidas53897.2021.9574320

Cited by 4 publications

(5 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Agarwood oil's market value is determined by its inherent quality with higherquality variants commanding premium prices [17], [18]. As previously stated, human sensory panels are used to evaluate the quality of Agarwood oil, a practice fraught with inefficiencies, fatigue and time consumption [13], [14], [19]. Consequently, doubts may arise and the grading process varies between exporting countries [7], [20].…”

Section: Introductionmentioning

confidence: 99%

Agarwood oil quality identification using artificial neural network modelling for five grades

Mohd Huzir,

Tajuddin,

Mohd Yusoff

et al. 2024

IJECE

View full text Add to dashboard Cite

Agarwood (Aquilaria Malaccensis) oil stands out as one of the most valuable and highly sought-after oils with a hefty price tag due to its widespread use of fragrances, incense, perfumes, ceremonial practices, medicinal applications and as a symbol of luxury. However, nowadays the conventional method that rely on color alone has its limitations as it yields varying results depending on individual panelists' experiences. Hence, the quality identification system of Agarwood oil using its chemical compounds had been proposed in this study to enhance the precision of the Agarwood oil grades thus addressing the shortcomings of traditional methods. This study indicates that the primary chemical compounds of Agarwood oil encompass ɤ-Eudesmol, ar-curcumene, β-dihydroagarofuran, ϒ-cadinene, α-agarofuran, allo-aromadendrene epoxide, valerianol, α-guaiene, 10-epi-ɤ-eudesmol, β-agarofuran and dihydrocollumellarin. This study employed artificial neural network analysis with the implementation of Levenberg-Marquardt algorithm to identify the Agarwood oil grades. The study's findings revealed that this modeling system of five grades got 100% accuracies with mean square error of 0.14338×10-08. Notably, this lowest mean square error (MSE) value falls within the best hidden neuron 3. These study outcomes play a pivotal role in highlighting the Levenberg Marquardt- artificial neural network (LM-ANN) modeling that contribute to the successful of Agarwood oil quality identification using its chemical compounds.

show abstract

Section: Introductionmentioning

confidence: 99%

Agarwood oil quality identification using artificial neural network modelling for five grades

Mohd Huzir,

Tajuddin,

Mohd Yusoff

et al. 2024

IJECE

View full text Add to dashboard Cite

show abstract

“…Agarwood oil is particularly valuable as natural products used as incense, fragrant, shampoo, traditional medicine (healing stomach complaints, diarrhoea, lungs and liver pain), and for perfumery (especially the dark colors) [1]- [5]. In fact, the infected heartwood of Aqualaria species is the most expensive oil in the market [3], [5], [6].…”

Section: Introductionmentioning

confidence: 99%

“…There is no guarantee that grading essential oils depending on human sensory evaluation can guarantee its purity or quality. The human trained grader technique has a considerable disadvantage in terms of objectivity and consistency when working with multiple samples at once, resulting in a labor-intensive and time-consuming procedure [1], [11], [13]. Many innovative technologies for enhancing the stability and availability of essential oils have emerged to address these inadequacies of essential oil products [14], [15].…”

Section: Introductionmentioning

confidence: 99%

“…With new development of data analysis, there is several platforms where agarwood oil quality classification can be done solely based on their chemical profiles using intelligent methods, enabling essential oils to be classified into their respective classes (low, medium low, medium high, or high quality) and the findings to be measured accurately. Several researchers have been proposed machine learning techniques to verify the quality of agarwood oil such as artificial neural network (ANN), linear regression, k-Nearest Neighbor (k-NN), selforganizing map (SOM) and OVO multiclass support vector machine (SVM) [1], [13], [16]- [18]. Studies on the agarwood oil seven chemical compounds (β-agarofuran, 10-epi-ϒeudesmol, ϒ-Eudesmol, Eudesmol, Hexadecanol, α-agarofuran and Longifolol) have reported value of correlation coefficient, R is equal to 1 at hidden neurons number 2 outperforms shows the best performance since the mean squared error (MSE) value is the lowest compared to other neurons with 7.69x10 -15 [16].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Stepwise regression of agarwood oil significant chemical compounds into four quality differentiation

Huzir

Amidon²,

Al-Hadi³

et al. 2023

IJEECS

View full text Add to dashboard Cite

<span>This paper gives precise summary on the application of stepwise regression model based upon the pre-process analysis of boxplot for four chemical compounds into four different qualities of agarwood oil. In the global market, agarwood oil is acknowledged as a pricey and valuable nature product owing to its benefits. Unfortunately, there is no standard grading method for agarwood oil grade classification. Intelligent model in grading the quality of agarwood oil is crucial as one of the efforts to classify the agarwood quality. The main model chosen in this study is stepwise regression by concerned specific parameter which is the value of correlation coefficient, R2. To achieve this goal, four out of eleven significant compounds of agarwood oil that consist of 660 data samples from low, medium low, medium high and high quality are representing the input. The independent variables are X1, X2, X3 and X4 which refer to the ɤ-Eudesmol, 10-epi-ɤ-eudesmol, β-agarofuran and dihydrocollumellarin compounds, respectively. MATLAB software version r2015a has been chosen as the simulation platform for this research work. The result showed that the stepwise regression model has a correlation coefficient of 0.756 and p-value less than 0.05 significance level which successfully passed the performance criteria toward regression value.</span>

show abstract

“…There is no guarantee that grading using human sensory evaluation can secure the purity or quality of the essential oils. Human trained grader technique has a significant disadvantage in terms of objectivity and repeatability due to the continuous process when deal with a bulk of samples at once, contribute to the high labor-intensive process and time-consuming [8]- [10]. As a result, several methods have been proposed and implemented to verify essential oil quality using intelligent techniques [8], [9], [11]- [17].…”

Section: Introductionmentioning

confidence: 99%

A Ppreliminary study on the intelligent model of k-nearest neighbor for agarwood oil quality grading

Huzir

Mahabob

Amidon

et al. 2022

IJEECS

View full text Add to dashboard Cite

Essential <span>oils extracted from trees has various usages like perfumes, incense, aromatherapy and traditional medicine which increase their popularity in global market. In Malaysia, the recognition system for identifying the essential oil quality still does not reach its standard since mostly graded by using human sensory evaluation. However, previous researchers discovered new modern techniques to present the quality of essential oils by analyse the chemical compounds. Agarwood essential oil had been chosen for the proposed integrated intelligent models with the implementation of k-nearest neighbor (k-NN) due to the high demand and an expensive natural raw world resource. k-NN with Euclidean distance metrics had better performance in terms of its confusion matrix, sensitivity, precision accuracy and specificity. This paper presents an overview of essential oils as well as their previous analysis technique. The review on k-NN is done to prove the technique is compatible for future research studies based on its performance.</span>

show abstract

Agarwood Oil Quality Grading using OVO Multiclass Support Vector Machine

Cited by 4 publications

References 23 publications

Agarwood oil quality identification using artificial neural network modelling for five grades

Agarwood oil quality identification using artificial neural network modelling for five grades

Stepwise regression of agarwood oil significant chemical compounds into four quality differentiation

A Ppreliminary study on the intelligent model of k-nearest neighbor for agarwood oil quality grading

Contact Info

Product

Resources

About