Agarwood Oil Quality Classification using Support Vector Classifier and Grid Search Cross Validation Hyperparameter Tuning

Clinicians and researchers utilize subjective classification systems based on clinical parameters to stratify lower extremity ulcer infections for treatment and research. This study compared clinical infection classifications (mild to severe) of lower extremity ulcers (n = 44) with transcriptomic profiles and direct measurement of bacterial RNA signatures by RNA-sequencing. Samples demonstrating similar transcriptomes were clustered and characterized by transcriptomic fingerprint. Clinical infection severity did not explain the major sources of variability among the samples and samples with the same clinical classification demonstrated high inter-sample variability. High proportions of bacterial RNA, however, resulted in a strong effect on transcription and increased expression of genes associated with immune response and inflammation. K-means clustering identified two clusters of samples, one of which contained all of the samples with high levels of bacterial RNA. A support vector classifier identified a fingerprint of 20 genes, including immune-associated genes such as CXCL8, GADD45B, and HILPDA, which accurately identified samples with signs of infection via cross-validation. This suggests that stratification of infection states based on a transcriptomic fingerprint may be a useful tool for studying host-bacterial interactions in these ulcers, as well as an objective classification method to identify the severity of infection.

Download Full-text

Agarwood oil quality classification using cascade-forward neural network

2015 IEEE 6th Control and System Graduate Research Colloquium (ICSGRC) ◽

10.1109/icsgrc.2015.7412475 ◽

2015 ◽

Cited By ~ 1

Author(s):

M.A. Abdul Aziz ◽

N. Ismail ◽

I.M. Yassin ◽

A. Zabidi ◽

M.S.A. Megat Ali

Keyword(s):

Neural Network ◽

Oil Quality ◽

Quality Classification ◽

Agarwood Oil

Download Full-text

Special Issue on Using Machine Learning Algorithms in the Prediction of Kyphosis Disease: A Comparative Study

Applied Sciences ◽

10.3390/app9163322 ◽

2019 ◽

Vol 9 (16) ◽

pp. 3322 ◽

Cited By ~ 2

Author(s):

Stephen Dankwa ◽

Wenfeng Zheng

Keyword(s):

Machine Learning ◽

Support Vector Machines ◽

Cross Validation ◽

Machine Learning Algorithms ◽

Support Vector ◽

Grid Search ◽

Baseline Model ◽

Vector Machines ◽

Ann Models ◽

Fold Cross Validation

Machine learning (ML) is the technology that allows a computer system to learn from the environment, through re-iterative processes, and improve itself from experience. Recently, machine learning has gained massive attention across numerous fields, and is making it easy to model data extremely well, without the importance of using strong assumptions about the modeled system. The rise of machine learning has proven to better describe data as a result of providing both engineering solutions and an important benchmark. Therefore, in this current research work, we applied three different machine learning algorithms, which were, the Random Forest (RF), Support Vector Machines (SVM), and Artificial Neural Network (ANN) to predict kyphosis disease based on a biomedical data. At the initial stage of the experiments, we performed 5- and 10-Fold Cross-Validation using Logistic Regression as a baseline model to compare with our ML models without performing grid search. We then evaluated the models and compared their performances based on 5- and 10-Fold Cross-Validation after running grid search algorithms on the ML models. Among the Support Vector Machines, we experimented with the three kernels (Linear, Radial Basis Function (RBF), Polynomial). We observed overall accuracies of the models between 79%–85%, and 77%–86% based on the 5- and 10-Fold Cross-Validation, after running grid search respectively. Based on the 5- and 10-Fold Cross-Validation as evaluation metrics, the RF, SVM-RBF, and ANN models achieved accuracies more than 80%. The RF, SVM-RBF and ANN models outperformed the baseline model based on the 10-Fold Cross-Validation with grid search. Overall, in terms of accuracies, the ANN model outperformed all the other ML models, achieving 85.19% and 86.42% based on the 5- and 10-Fold Cross-Validation. We proposed that RF, SVM-RBF and ANN models should be used to detect and predict kyphosis disease after a patient had undergone surgery or operation. We suggest that machine learning should be adopted and used as an essential and critical tool across the maximum spectrum of answering biomedical questions.

Download Full-text

Evaluation of RBF and MLP in SVM kernel tuned parameters for agarwood oil quality classification

2018 IEEE 14th International Colloquium on Signal Processing & Its Applications (CSPA) ◽

10.1109/cspa.2018.8368721 ◽

2018 ◽

Cited By ~ 2

Author(s):

Khairul Anis Athirah Kamarulzaini ◽

Nurlaila Ismail ◽

Mohd Hezri Fazalul Rahiman ◽

Mohd Nasir Taib ◽

Nor Azah Mohd Ali ◽

...

Keyword(s):

Oil Quality ◽

Quality Classification ◽

Agarwood Oil

Download Full-text

Quadratic tuned kernel parameter in Non-linear support vector machine (SVM) for agarwood oil compounds quality classification

Indonesian Journal of Electrical Engineering and Computer Science ◽

10.11591/ijeecs.v17.i3.pp1371-1376 ◽

2020 ◽

Vol 17 (3) ◽

pp. 1371

Author(s):

Muhamad Addin Akmal Bin Mohd Raif ◽

Nurlaila Ismail ◽

Nor Azah Mohd Ali ◽

Mohd Hezri Fazalul Rahiman ◽

Saiful Nizam Tajuddin ◽

...

Keyword(s):

Support Vector Machine ◽

Confusion Matrix ◽

Research Area ◽

Training Dataset ◽

Support Vector ◽

Testing Dataset ◽

Quality Classification ◽

Kernel Parameter ◽

Svm Model ◽

Agarwood Oil

This paper presents the analysis of agarwood oil compounds quality classification by tuning quadratic kernel parameter in Support Vector Machine (SVM). The experimental work involved of agarwood oil samples from low and high qualities. The input is abundances (%) of the agarwood oil compounds and the output is the quality of the oil either high or low. The input and output data were processed by following tasks; i) data processing which covers normalization, randomization and data splitting into two parts in which training and testing database (ratio of 80%:20%), and ii) data analysis which covers SVM development by tuning quadratic kernel parameter. The training dataset was used to be train the SVM model and the testing dataset was used to test the developed SVM model. All the analytical works are performed via MATLAB software version R2013a. The result showed that, quadratic tuned kernel parameter in SVM model was successful since it passed all the performance criteria’s in which accuracy, precision, confusion matrix, sensitivity and specificity. The finding obtained in this paper is vital to the agarwood oil and its research area especially to the agarwood oil compounds classification system.

Download Full-text

Modeling of agarwood oil compounds based on linear regression and ANN for oil quality classification

International Journal of Electrical and Computer Engineering (IJECE) ◽

10.11591/ijece.v11i6.pp5505-5514 ◽

2021 ◽

Vol 11 (6) ◽

pp. 5505

Author(s):

Noratikah Zawani Mahabob ◽

Zakiah Mohd Yusoff ◽

Aqib Fawwaz Mohd Amidon ◽

Nurlaila Ismail ◽

Mohd Nasir Taib

Keyword(s):

Linear Regression ◽

Multilayer Perceptron ◽

Mean Squared Error ◽

Oil Quality ◽

Study Data ◽

Research Centre ◽

Training Algorithms ◽

Research Areas ◽

Quality Classification ◽

Agarwood Oil

Agarwood oil is in increasing demand in Malaysia throughout the world for use in incense, traditional medicine, and perfumes. However, there is still no standardized grading method for agarwood oil. It is vital to grade agarwood oil into high and low quality so that both qualities can be properly differentiated. In the present study, data were obtained from the Forest Research Institute Malaysia (FRIM), Selangor Malaysia and Bioaromatic Research Centre of Excellence (BARCE), Universiti Malaysia Pahang (UMP). The work involves the data from a previous researcher. As a part of on-going research, the stepwise linear regression and multilayer perceptron have been proposed for grading agarwood oil. The output features of the stepwise regression were the input features for modeling agarwood oil in a multilayer perceptron (MLP) network. A three layer MLP with 10 hidden neurons was used with three different training algorithms, namely resilient backpropagation (RBP), levenberg marquardt (LM) and scaled-conjugate gradient (SCG). All analytical work was performed using MATLAB software version R2017a. It was found that one hidden neuron in LM algorithm performed the most accurate result in the classification of agarwood oil with the lowest mean squared error (MSE) as compared to SCG and RBP algorithms. The findings in this research will be a benefit for future works of agarwood oil research areas, especially in terms of oil quality classification.

Download Full-text