scholarly journals Navel Orange Maturity Classification by Multispectral Indexes Based on Hyperspectral Diffuse Transmittance Imaging

2017 ◽  
Vol 2017 ◽  
pp. 1-7
Author(s):  
Xuan Wei ◽  
Jin-Cheng He ◽  
Da-Peng Ye ◽  
Deng-Fei Jie
Keyword(s):  
Multispectral Imaging ◽  
Nearest Neighbor ◽  
Hyperspectral Image ◽  
Low Cost ◽  
Imaging Systems ◽  
Correct Classification Rate ◽  
Discriminate Analysis ◽  
Classification Rate

Maturity grading is important for the quality of fruits. Nondestructive maturity detection can be greatly beneficial to the consumer and fruit industry. In this paper, a hyperspectral image of navel oranges was obtained using a diffuse transmittance imaging based system. Multispectral indexes were built to identify the maturity with the hyperspectral technique. Five indexes were proposed to combine the spectra at wavelengths of 640, 760 nm (red edges), and 670 nm (for chlorophyll content) to grade the navel oranges into three maturity stages. The index of (T670+T760-T640)/(T670+T760+T640) seemed to be more appropriate to classify maturity, especially to distinguish immature oranges that can be straightly identified in accordance with the value of this index ((T670+T760-T640)/(T670+T760+T640)). Different indexes were used as the input of linear discriminate analysis (LDA) and of k-nearest neighbor (k-NN) algorithm to identify the maturity, and it was found that k-NN with (T670+T760-T640)/(T670+T760+T640) could reach the highest correct classification rate of 96.0%. The results showed that the built index was feasible and accurate in the nondestructive classification of oranges based on the hyperspectral diffuse transmittance imaging. It will greatly help to develop low-cost and real-time multispectral imaging systems for the nondestructive detection of fruit quality in the industry.

Alzheimer's Disease Classification Based on Multi-feature Fusion

2019 ◽  
Vol 15 (2) ◽  
pp. 161-169 ◽  
Author(s):  
Nuwan Madusanka ◽  
Heung-Kook Choi ◽  
Jae-Hong So ◽  
Boo-Kyeong Choi
Keyword(s):  
Alzheimer’S Disease ◽  
Alzheimer's Disease ◽  
Feature Fusion ◽  
Biological Data ◽  
Correct Classification ◽  
Mr Images ◽  
Correct Classification Rate ◽  
Classification Rate ◽  
Morphometric Features

Background: In this study, we investigated the fusion of texture and morphometric features as a possible diagnostic biomarker for Alzheimer’s Disease (AD). Methods: In particular, we classified subjects with Alzheimer’s disease, Mild Cognitive Impairment (MCI) and Normal Control (NC) based on texture and morphometric features. Currently, neuropsychiatric categorization provides the ground truth for AD and MCI diagnosis. This can then be supported by biological data such as the results of imaging studies. Cerebral atrophy has been shown to correlate strongly with cognitive symptoms. Hence, Magnetic Resonance (MR) images of the brain are important resources for AD diagnosis. In the proposed method, we used three different types of features identified from structural MR images: Gabor, hippocampus morphometric, and Two Dimensional (2D) and Three Dimensional (3D) Gray Level Co-occurrence Matrix (GLCM). The experimental results, obtained using a 5-fold cross-validated Support Vector Machine (SVM) with 2DGLCM and 3DGLCM multi-feature fusion approaches, indicate that we achieved 81.05% ±1.34, 86.61% ±1.25 correct classification rate with 95% Confidence Interval (CI) falls between (80.75-81.35) and (86.33-86.89) respectively, 83.33%±2.15, 84.21%±1.42 sensitivity and 80.95%±1.52, 85.00%±1.24 specificity in our classification of AD against NC subjects, thus outperforming recent works found in the literature. For the classification of MCI against AD, the SVM achieved a 76.31% ± 2.18, 78.95% ±2.26 correct classification rate, 75.00% ±1.34, 76.19%±1.84 sensitivity and 77.78% ±1.14, 82.35% ±1.34 specificity. Results and Conclusion: The results of the third experiment, with MCI against NC, also showed that the multiclass SVM provided highly accurate classification results. These findings suggest that this approach is efficient and may be a promising strategy for obtaining better AD, MCI and NC classification performance.

A Fuzzy–Expert System For Classification Of Short Duration Voltage Disturbances

2012 ◽  
Author(s):  
Ghafour Amouzad Mahdiraji ◽  
Azah Mohamed
Keyword(s):  
Expert System ◽  
Power Quality ◽  
Short Duration ◽  
Automated Detection ◽  
Voltage Sag ◽  
Fuzzy Expert System ◽  
Correct Classification Rate ◽  
Classification Rate ◽  
Fast Fourier Transform Analysis

Satu aspek penting dalam penilaian kualiti kuasa adalah pengesanan dan pengkelasan gangguan kualiti kuasa secara automatik yang memerlukan penggunaan teknik kepintaran buatan. Kertas kerja ini membentangkan penggunaan sistem pakar-kabur untuk pengkelasan gangguan voltan jangka masa pendek yang termasuk lendut voltan, ampul dan sampukan. Untuk memperolehi sifat unik bagi gangguan voltan, analisis jelmaan Fourier pantas dan teknik purataan punca min kuasa dua digunakan untuk menentukan parameter gangguan seperti tempoh masa, magnitud voltan pmk maksimum dan minimum. Berasaskan pada parameter ini, sebuah sistem pakar–kabur telah dibangunkan dengan mengset aturan kabur yang menimbangkan lima masukan dan tiga keluaran. Sistem ini direka bentuk untuk mengesan dan mengkelaskan tiga jenis gangguan voltan tempoh masa pendek dengan menentukan sama ada gangguan adalah gangguan ketika, gangguan seketika dan bukan gangguan lendut, ampul dan sampukan. Untuk mengesahkan kejituan sistem yang dicadangkan, ia telah diuji dengan gangguan voltan yang diperolehi dari pengawasan. Keputusan ujian menunjukkan bahawa sistem pakar–kabur yang dibangunkan telah memberikan kadar pengkelasan yang betul sebanyak 98.4 %. Kata kunci: Kualiti kuasa, sistem pakar–kabur, lendut, ampul dan sampukan One of the important aspects in power quality assessment is automated detection and classification of power quality disturbances which requires the use of artificial intelligent techniques. This paper presents the application of fuzzy–expert system for classification of short duration voltage disturbances which include voltage sag, swell and interruption. To obtain unique features of the voltage disturbances, fast Fourier transform analysis and root mean square averaging technique are utilized so as to determine the disturbance parameters such as duration, maximum and minimum rms voltage magnitudes. Based on these parameters, a fuzzy-expert system has been developed to set the fuzzy rules incorporating five inputs and three outputs. The system is designed for detecting and classifying the three types of short duration voltage disturbances, so as to determine whether the disturbance is instantaneous, momentary and non sag, swell and interruption. To verify the accuracy of the proposed system, it has been tested with recorded voltage disturbances obtained from monitoring. Tests results showed that the developed fuzzy–expert system gives a correct classification rate of 98.4 %. Key words: Power quality, fuzzy–expert system, sag, swell and interruption.

scholarly journals Natural Agents that Act in the Prevention and Treatment of Oral Mucositis: Literature Review

2020 ◽  
Vol 22 (4) ◽  
pp. 214-221
Author(s):  
Tamires Ribeiro Avelino ◽  
Ana Carla Barletta Sanches ◽  
Tila Fortuna Costa Freire ◽  
Gabriela Botelho Martins ◽  
Juliana Borges de Lima Dantas
Keyword(s):  
Literature Review ◽  
Low Cost ◽  
Aloe Vera ◽  
Signs And Symptoms ◽  
Natural Agents ◽  
De Se ◽  
Prevention And Treatment ◽  
No Gold Standard

AbstractOral mucositis (OM) is one of the most frequent and painful problems caused by head and neck radiotherapy and/or chemotherapy. Because there is no gold standard therapy for this disruptive conditions management, the therapeutic approach promotes palliative action, which consists of the signs and symptoms relief, in addition to preventing further complications. The present study aims to identify the main natural agents that act in the prevention and treatment of MO, as well as to describe the pathophysiology and classification of this condition. This is a literature review of qualitative and exploratory nature through survey of scientific articles in the database SciELO, Lilacs, Medline and Pubmed. The results demonstrated that chamomile, propolis, aloe and honey have been widely used in dentistry, being pointed out in the scientific literature as promising strategies, as they present analgesic and anti-inflammatory effects, besides being well tolerated by the patients and have a low cost. It can be considered that the use of these agents for the prevention and treatment of OM provides a clinical lesions improvement, with consequent advance in the quality of life of these patients. However, more studies need to be carried out in an attempt to obtain more information about the most appropriate posology and presentation form, besides evaluating the toxicity of these natural agents. Keywords: Stomatitis. Chamomile. Propolis. Aloe. Honey. ResumoA mucosite oral (MO) consiste em um dos problemas mais frequentes e dolorosos provocados pela radioterapia em região de cabeça e pescoço e/ou quimioterapia. Por não existir terapia considerada padrão ouro para o manejo desta condição perturbadora, a abordagem terapêutica promove ação paliativa, que consiste no alívio de sinais e sintomas, além de prevenir maiores complicações. O presente estudo teve como objetivo identificar os principais agentes naturais que atuam na prevenção e tratamento da MO, bem como descrever a fisiopatologia e classificação desta afecção. Trata-se de uma revisão de literatura de natureza qualitativa e exploratória através de levantamento de artigos científicos na base de dados SciELO, Lilacs, Medline e Pubmed. Os resultados demonstraram que a camomila, a aloe vera, a própolis e o mel têm sido amplamente utilizados na Odontologia,sendo apontados na literatura científica como estratégias de tratamento promissoras, pois apresentam efeito analgésico e antiinflamatório, além de serem bem tolerados pelos pacientes e possuirem baixo custo.Pode-se considerar que a utilização desses agentes para a prevenção e o tratamento da MO proporciona uma melhora clínica das lesões, com conseqüente melhora na qualidade de vida desses pacientes. Todavia, mais estudos precisam ser realizados na tentativa de se obter maiores informações acerca da posologia e forma de apresentação mais indicadas, além de avaliar a toxicidade desses agentes naturais. Palavras-chave: Estomatite. Camomila. Própolis. Aloe. Mel.

scholarly journals Automatic Classification of Chickpea Varieties Using Computer Vision Techniques

Agronomy ◽  
2019 ◽  
Vol 9 (11) ◽  
pp. 672 ◽  
Author(s):  
Pourdarbani ◽  
Sabzi ◽  
García-Amicis ◽  
García-Mateos ◽  
Molina-Martínez ◽  
...  
Keyword(s):  
Computer Vision ◽  
Morphological Characteristics ◽  
Texture Features ◽  
Correct Classification Rate ◽  
Classification Rate ◽  
Swarm Optimization ◽  
Visual Classification ◽  
Image Patches ◽  
Selection Of

There are about 90 different varieties of chickpeas around the world. In Iran, where this study takes place, there are five species that are the most popular (Adel, Arman, Azad, Bevanij and Hashem), with different properties and prices. However, distinguishing them manually is difficult because they have very similar morphological characteristics. In this research, two different computer vision methods for the classification of the variety of chickpeas are proposed and compared. The images were captured with an industrial camera in Kermanshah, Iran. The first method is based on color and texture features extraction, followed by a selection of the most effective features, and classification with a hybrid of artificial neural networks and particle swarm optimization (ANN-PSO). The second method is not based on an explicit extraction of features; instead, image patches (RGB pixel values) are directly used as input for a three-layered backpropagation ANN. The first method achieved a correct classification rate (CCR) of 97.0%, while the second approach achieved a CCR of 99.3%. These results prove that visual classification of fruit varieties in agriculture can be done in a very precise way using a suitable method. Although both techniques are feasible, the second method is generic and more easily applicable to other types of crops, since it is not based on a set of given features.

scholarly journals Unsupervised Clustering of Hyperspectral Paper Data Using t-SNE

2020 ◽  
Vol 6 (5) ◽  
pp. 29
Author(s):  
Binu Melit Devassy ◽  
Sony George ◽  
Peter Nussbaum
Keyword(s):  
Imaging Systems ◽  
High Dimensional ◽  
Electromagnetic Spectrum ◽  
Discrimination Power ◽  
Vast Number ◽  
Clustering Quality ◽  
The Subject ◽  
Non Destructive

For a suspected forgery that involves the falsification of a document or its contents, the investigator will primarily analyze the document’s paper and ink in order to establish the authenticity of the subject under investigation. As a non-destructive and contactless technique, Hyperspectral Imaging (HSI) is gaining popularity in the field of forensic document analysis. HSI returns more information compared to conventional three channel imaging systems due to the vast number of narrowband images recorded across the electromagnetic spectrum. As a result, HSI can provide better classification results. In this publication, we present results of an approach known as the t-Distributed Stochastic Neighbor Embedding (t-SNE) algorithm, which we have applied to HSI paper data analysis. Even though t-SNE has been widely accepted as a method for dimensionality reduction and visualization of high dimensional data, its usefulness has not yet been evaluated for the classification of paper data. In this research, we present a hyperspectral dataset of paper samples, and evaluate the clustering quality of the proposed method both visually and quantitatively. The t-SNE algorithm shows exceptional discrimination power when compared to traditional PCA with k-means clustering, in both visual and quantitative evaluations.

Evaluation of stereo imaging capabilities and parameters when using personal computers: Defining a low-cost high-quality system

1992 ◽  
Vol 50 (2) ◽  
pp. 1048-1049
Author(s):  
John M. Mackenzie
Keyword(s):  
Low Cost ◽  
Evaluation Criteria ◽  
Imaging Systems ◽  
Personal Computers ◽  
Stereo Imaging ◽  
High Quality ◽  
Display Devices ◽  
The One ◽  
The Cost

Over the past several years the capabilities of personal computers have advanced at a staggering rate. At the same time, the cost of the hardware has dropped to such a degree that one wonders whether such inexpensive hardware can perform adequately.The purpose of this discussion is to look at the minimum hardware necessary to do quality stereo imaging on CRT display devices and to discuss several important evaluation criteria in producing these stereo images.The most important criteria for producing high quality stereo pairs lies in the quality of the digitization of the image. Most TV rate imaging systems even after multiple frames are averaged are quite distorted and lack sufficient image detail. Slow scan imaging systems such as the one developed in this laboratory which use a gated integrator and can digitize at over one thousand pixels square with 256 gray levels produce images which are extremely close to photographic quality.

scholarly journals Classification of soybean tempe quality using deep learning

2021 ◽  
Vol 924 (1) ◽  
pp. 012022
Author(s):  
Y Hendrawan ◽  
B Rohmatulloh ◽  
I Prakoso ◽  
V Liana ◽  
M R Fauzy ◽  
...  
Keyword(s):  
Deep Learning ◽  
Classification Accuracy ◽  
Low Cost ◽  
Confusion Matrix ◽  
Learning Rate ◽  
Traditional Food ◽  
Quality Classification ◽  
Non Destructive

Abstract Tempe is a traditional food originating from Indonesia, which is made from the fermentation process of soybean using Rhizopus mold. The purpose of this study was to classify three quality levels of soybean tempe i.e., fresh, consumable, and non-consumable using a convolutional neural network (CNN) based deep learning. Four types of pre-trained networks CNN were used in this study i.e. SqueezeNet, GoogLeNet, ResNet50, and AlexNet. The sensitivity analysis showed the highest quality classification accuracy of soybean tempe was 100% can be achieved when using AlexNet with SGDm optimizer and learning rate of 0.0001; GoogLeNet with Adam optimizer and learning rate 0.0001, GoogLeNet with RMSProp optimizer, and learning rate 0.0001, ResNet50 with Adam optimizer and learning rate 0.00005, ResNet50 with Adam optimizer and learning rate 0.0001, and SqueezeNet with RSMProp optimizer and learning rate 0.0001. In further testing using testing-set data, the classification accuracy based on the confusion matrix reached 98.33%. The combination of the CNN model and the low-cost digital commercial camera can later be used to detect the quality of soybean tempe with the advantages of being non-destructive, rapid, accurate, low-cost, and real-time.

Sign in / Sign up

Export Citation Format

Share Document