18 July 2024 in Journal of Advanced Research in Applied Sciences and Engineering Technology
AAAqib Fawwaz Mohd Amidon
Agarwood is a highly prized and useful forest product. In Southeast Asia, Aquilaria Malaccensis species are typically the most prevalent. This agarwood is usually used in the manufacture of medicine, the production of high-quality perfumes, and is also used in religious and ethnic ceremonies. According to the study, the agarwood grading process entirely relies on human senses. The graders will evaluate the agarwood oil's color concentration with their unaided eyes and evaluate the amount of scent emitted with their noses. This approach has been proven to have several limitations, including that the graders' health will suffer, the grading procedure will take a very long time, and will consume high operating expenses. Therefore, an established standard grading model that is faster, easier, and more accurate needs to be introduced. Previous researchers found that chemical compounds contained in agarwood oil can be used to grade the quality of agarwood oil. Therefore, this study has used the data obtained that contains significant chemical compounds as input to develop a grading model with the support of machine learning and artificial intelligence, which is the k-Nearest Neighbor (KNN) technique. The output of this grading model is the classification of agarwood oil according to its quality, which includes four different grades. The results of the implementation of KNN grading of this model found that this model has very excellent performance by obtaining 100% for each measurement for the performance evaluator of the classifier.
1 December 2022 in International Journal of Electrical and Computer Engineering (IJECE)
This work studies the agarwood oil classification into high and low quality by using two different techniques. Initially, the Forest Research Institute Malaysia (FRIM) and Universiti Malaysia Pahang (UMP) are where the sample preparation and compound extraction of agarwood oil is collected. The data collections were done from the previous researcher consists of 96 samples from seven significant agarwood oil compounds. The artificial neural network (ANN) and the proposed stepwise regression technique were used in this study. The stepwise regression was done the feature selection and successfully reduced agarwood oil compounds from seven to four. Then, the ANN technique was used to classify agarwood oil into high and low using input from seven and four compounds separately. The performance of ANN with different inputs is compared (ANN with seven inputs compared with ANN with four inputs). All the experimental work was performed using the MATLAB R2017b using the “patternet” implemented Levenberg Marquardt algorithm and ten hidden neurons. It was found that the ANN technique using seven compounds obtained the best performance according to high accuracy and lower mean square error (MSE) value. Finally, 1 hidden neuron in ANN with seven inputs selected as the best neuron for grading the agarwood oil compounds.
1 February 2023 in Indonesian Journal of Electrical Engineering and Computer Science
AAAnis Hazirah ‘iZzati Hasnu Al-Hadi
Anis Hazirah ‘iZzati Hasnu Al-Hadi
+1
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.
1 August 2024 in International Journal of Electrical and Computer Engineering (IJECE)
The paper examines the characterization of Aquilaria essential oils from different species, namely Aquilaria malaccensis, Aquilaria beccariana, Aquilaria crassna, and Aquilaria subintegra, renowned for agarwood production in Malaysia. Gas chromatography-mass spectrometry (GC-MS) and gas chromatography-flame ionization detector (GC-FID) were employed for extracting essential oil data, facilitating compound identification. Subsequently, a preliminary analysis focused on classifying significant chemical compounds in the samples. The study then utilized boxplot pre-processing for visualizing and interpreting data distribution. The statistical analyses were performed using MATLAB software version R2021b, considering two key parameters which are the peak area (%) of significant chemical compounds and the classification of Aquilaria species (A. beccariana, A. malaccensis, A. crassna, and A. subintegra) based on their chemical composition. The results, presented through boxplot analyses, demonstrated a clear representation of the parameters and their distribution in the data. This method not only confirmed the potential of boxplot analysis in statistical evaluation of significant compounds in Aquilaria essential oil but also suggested its applicability for further classification work.
26 October 2019 in International Journal of Online and Biomedical Engineering (iJOE)
To supplement conventional teaching methods, use of new technology have recently being adapted in the current education system. Such examples are implementing simulators and quiz kits in a classroom session to assist teachers in providing standardized evaluation or practical and more direct examples of concepts that are being taught. Additionally, the well-known issue of attracting student interest in a so-called uninteresting conventional lecture may be solved by using this technological method. The objective of this works to provide methods on developing a prototype training kit (named as e-Logic trainer kit or e-LTK) which comprises of an electronic simulator and quiz assessment module to evaluate subject knowledge on logic gates. The e-LTK is developed by using Arduino Mega 2560 as the base microcontroller, equipped with keypad and display module as the user input/output interface. The quiz assessment module contained in the prototype also allows conversion of inputs by combinatorial logic circuits into output in the form of timing diagram. This equipment enables electrical engineering students to simulate several combinations of logic circuit, reinforcing the understanding of logic circuit operation. The effectiveness of using this prototype in educational settings have been evaluated through a survey on students and instructors at Faculty of Technology in Engineering (FTK) in Universiti Teknikal Malaysia Melaka (UTeM). Response has been positive, with 60% of the correspondence has shown positive feedbacks, indicating the usefulness of the prototype kit.