<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>

No abstract

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>

No abstract

Agarwood oil quality is often separated into two or three categories. This makes classifying agarwood oil quality using current methods difficult. Current approaches rely solely on human perception to determine the quality of agarwood, whether in raw material or oil. This technique has other undesirable implications. It can affect the human sensory system, particularly the eyes and nose. Categorization takes time, which is a considerable expense to succeed in this method. As a result, a new classification system should be devised. The chemical components in agarwood oil are used to classify it in this study. In this study, samples with preprocessing data from two to five quality levels were used. The purpose is to categorize this data based on its qualities and analyze whether this new quality group is acceptable. The K-nearest neighbours (KNN) approach was used to classify all samples and their properties for this dataset. All samples may be correctly classified by grade without any errors. This shows the chemical compound-based classification of agarwood oil can be retained. With these findings, future agarwood oil research may focus on building a new classification.