Agarwood oil quality classification using cascade-forward neural network

<span>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 <span>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</span> benefit for future works of agarwood oil research areas, especially in terms of oil quality classification.</span>

Download Full-text

A Mobile Deep Convolutional Neural Network Combined with Grad-CAM Visual Explanations for Real Time Tomato Quality Classification System

2020 5th International Conference on Green Technology and Sustainable Development (GTSD) ◽

10.1109/gtsd50082.2020.9303079 ◽

2020 ◽

Author(s):

Loc-Phat Truong ◽

Bach-Duong Pham ◽

Quang-Huy Vu

Keyword(s):

Neural Network ◽

Convolutional Neural Network ◽

Real Time ◽

Classification System ◽

Deep Convolutional Neural Network ◽

Tomato Quality ◽

Quality Classification

Download Full-text

Agarwood Oil Quality Grading using OVO Multiclass Support Vector Machine

10.1109/aidas53897.2021.9574320 ◽

2021 ◽

Author(s):

A. F. M. Amidon ◽

N. Z. Mahabob ◽

M. H. Haron ◽

N. Ismail ◽

Z. M. Yusoff ◽

...

Keyword(s):

Support Vector Machine ◽

Oil Quality ◽

Support Vector ◽

Quality Grading ◽

Multiclass Support Vector Machine ◽

Agarwood Oil

Download Full-text

Pork Quality Classification Using a Hyperspectral Imaging System and Neural Network

International Journal of Food Engineering ◽

10.2202/1556-3758.1089 ◽

2007 ◽

Vol 3 (1) ◽

Cited By ~ 9

Author(s):

Qiao Jun ◽

Michael Ngadi ◽

Ning Wang ◽

Aynur Gunenc ◽

Mariana Monroy ◽

...

Keyword(s):

Neural Network ◽

Hyperspectral Imaging ◽

Imaging System ◽

Objective Assessment ◽

Principal Component ◽

Pork Quality ◽

Pca Analysis ◽

Error Frequency ◽

Quality Classification ◽

Average Reflectance

Pork quality is usually determined subjectively as PSE, PFN, RFN, RSE and DFD based on color, texture and exudation of the meat. In this study, a hyperspectral-imaging-based technique was developed to achieve rapid, accurate and objective assessment of pork quality. The principal component analysis (PCA) and stepwise operation methods were used to select feature waveband from the entire spectral wavelengths (430 to 980 nm). Then the feature waveband images were extracted at the selected feature wavebands from raw hyperspectral images, and the average reflectance (R) was calculated within the whole loin-eye area. Artificial neural network was used to classify these groups. Results showed that PCA analysis had a better performance than that of stepwise operation for feature waveband images selection. The 1st derivative data gave a better result than that of mean reflectance spectra data. The best classified result was 87.5% correction. The error frequency showed that RSE samples were easier to classify. The PFN and PSE samples were difficult to separate from each other.

Download Full-text

Pengaruh Latar Belakang Warna pada Objek Gambar terhadap Hasil Ekstraksi Sinyal EEG

IJEIS (Indonesian Journal of Electronics and Instrumentation Systems) ◽

10.22146/ijeis.22893 ◽

2017 ◽

Vol 7 (2) ◽

pp. 161 ◽

Cited By ~ 1

Author(s):

Catur Atmaji ◽

Zandy Yudha Perwira

Keyword(s):

Neural Network ◽

Artificial Neural Network ◽

Training System ◽

Training Data ◽

Spectrum Estimation ◽

Quality Classification ◽

Eeg Data ◽

Two Systems ◽

Artificial Neural ◽

Color Background

In this study, observation on the differences in features quality of EEG records as a result of training on subjects has been made. The features of EEG records were extracted using two different methods, the root mean square which is acquired from the range between 0.5 and 5 seconds and the average of power spectrum estimation from the frequency range between 20 and 40Hz. All of the data consists of a 4-channel recording and produce good quality classification on artificial neural network, with each of which generates training data accuracy over 90%. However, different results are occured when the trained system is tested on other test data. The test results show that the two systems which are trained using training data with object with color background produce higher accuracy than the other two systems which are trained using training data with object without background color, 63.98% and 60.22% compared to 59.68% and 56.45% accuracy respectively. From the use of the features on the artificial neural network classification system, it can be concluded that the training system using EEG data records derived from the visualization of object with color background produces better features than the visualization of object without color background.

Download Full-text