Agarwood oil quality classifier using machine learning

Abas, Muhamad Azahar; Zubir, N. S. A.; Ismail, Nordinah; Yassin, Ihsan Mohd; Ali, Nor Azah Mohd; Rahiman, Mohd Hezri Fazalul; Saiful, N. T.; Taib, Mohd Nasir

doi:10.4314/jfas.v9i4s.4

Cited by 7 publications

(2 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Currently, kaffir lime oil quality grading is evaluated using human sensory organs and human perception based on the long-lasting aroma, odor and color of this oil. This method is less accurate because every human has different perceptions, and their noses are prone to getting fatigued [6]- [8]. To overcome this problem, the quality of kaffir lime oil can be grad by using significant chemical compounds.…”

Section: Introductionmentioning

confidence: 99%

Intelligent grading of kaffir lime oil quality using non-linear support vector machine

Jailani

Muhammad

Rahiman

et al. 2022

IJECE

View full text Add to dashboard Cite

<span lang="EN-US">This paper presents kaffir lime oil quality grading using the intelligent system classification method, a non-linear support vector machine (NSVM). This method classifies the quality kaffir lime oil into two groups: high and low quality, based on their significant chemical compounds. The 90 data of kaffir lime oil were used in this project from high to low quality. The abundance (%) of significant chemical compounds will act as the input and high or low quality as an output. The 90 data will be divided into two sets: training and testing data sets with a ratio of 8:2. The radial basis function (RBF) optimization kernel parameters in NSVM. Using the implementation of MATLAB software version R2020a, all data and analysis work was performed automatically. The results showed that the NSVM model met all performance criteria for 100% accuracy, sensitivity, specificity, and precision.</span>

show abstract

Section: Introductionmentioning

confidence: 99%

Intelligent grading of kaffir lime oil quality using non-linear support vector machine

Jailani

Muhammad

Rahiman

et al. 2022

IJECE

View full text Add to dashboard Cite

show abstract

“…However, it suffers from disadvantage of moderate adsorption capacity. This drawback makes it unsuitable for practical applications, in the field of industrial effluents management [17,18].…”

mentioning

confidence: 99%