Identification and Classification of Three Iranian Rice Varieties in Mixed Bulks Using Image Processing and MLP Neural Network

2017 ◽  
Vol 13 (5) ◽  
Author(s):  
Saeideh Fayyazi ◽  
Mohammad Hossein Abbaspour-Fard ◽  
Abbas Rohani ◽  
S. Amirhassan Monadjemi ◽  
Hassan Sadrnia
Keyword(s):  
Neural Network ◽  
Economic Value ◽  
Principal Component ◽  
Textural Features ◽  
Training Algorithms ◽  
Rice Varieties ◽  
Mlp Neural Network ◽  
Pca Method ◽  
Rice Seeds

Abstract Due to variation in economic value of different varieties of rice, reports indicating the possibility of mixing different varieties on the market. Applying machine vision techniques to classify rice varieties is a method which can increase the accuracy of classification process in real applications. In this study, several morphological and textural features of rice seeds’ images were examined to evaluate their efficacy in identification of three Iranian rice varieties (Tarom, Fajr, Shiroodi) in their mixed samples. On the whole, 666 images of rice seeds (222 images of each variety) were acquired at a stable illumination condition and totally, 17 morphological and 41 textural features were extracted from seeds images. Principal component analysis (PCA) method was employed to select and rank the most significant features for the classification. Subsequently, the MLP neural network classifier was employed for classification of rice varieties in the mixed bulks of three and two varieties, using top selected features. The network was three-layered feed forward type and trained using two training algorithms (BB and BDLRF). The classification accuracy of 55.93, 84.62 and 82.86 % for Fajr, Tarom and Shiroodi, 86.96 and 93.02 % for Fajr and Shiroodi, 86.84 and 96.08 % for Tarom and Shiroodi and 91.49 and 95.24 % for Fajr and Tarom were obtained in test phase, respectively.

Label-free non-invasive classification of rice seeds using optical coherence tomography assisted with deep neural network

2021 ◽  
Vol 137 ◽  
pp. 106861
Author(s):  
Deepa Joshi ◽  
Ankit Butola ◽  
Sheetal Raosaheb Kanade ◽  
Dilip K. Prasad ◽  
S.V. Amitha Mithra ◽  
...  
Keyword(s):  
Neural Network ◽  
Optical Coherence Tomography ◽  
Deep Neural Network ◽  
Optical Coherence ◽  
Label Free ◽  
Non Invasive ◽  
Rice Seeds

scholarly journals Deteksi Formalin Pada Buah Tomat (Lycopersicum esculentum Mill) Dengan Teknologi Hidung Elektronik (Electronic Nose)

2019 ◽  
Vol 4 (2) ◽  
pp. 359-366
Author(s):  
Irfan Maibriadi ◽  
Ratna Ratna ◽  
Agus Arip Munawar
Keyword(s):  
Principal Component Analysis ◽  
Electronic Nose ◽  
Principal Component ◽  
Component Analysis ◽  
Lycopersicum Esculentum ◽  
Olfactory Ability ◽  
Pca Method ◽  
The Difference ◽  
Electronic Nose Technology

Abstrak,  Tujuan dari penelitian ini adalah mendeteksi kandungan dan kadar formalin pada buah tomat dengan menggunakan instrument berbasis teknologi Electronic nose. Penelitian ini menggunakan buah tomat yang telah direndam dengan formalin dengan kadar 0.5%, 1%, 2%, 3%, 4%, dan buah tomat tanpa perendaman dengan formalin (0%). Jumlah sampel yang digunakan pada penelitian ini adalah sebanyak 18 sampel. Pengukuran spektrum beras menggunakan sensor Piezoelectric Tranducer. Klasifikasi data spektrum buah tomat menggunakan metode Principal Component Analysis (PCA) dengan pretreatment nya adalah Gap Reduction. Hasil penelitian ini diperoleh yaitu: Hidung elektronik mulai merespon aroma formalin pada buah tomat pada detik ke-8.14, dan dapat mengklasifikasikan kandungan dan kadar formalin pada buah tomat pada detik ke 25.77. Hidung elektronik yang dikombinasikan dengan metode principal component analysis (PCA) telah berhasil mendeteksikandungan dan kadar formalin pada buah tomat dengan tingkat keberhasilan sebesar 99% (PC-1 sebesar 93% dan PC-2 sebesar 6%). Perbedaan kadar formalin menjadi faktor utama yang menyebabkan Elektronik nose mampu membedakan sampel buah tomat yang diuji, karena semakin tinggi kadar formalin pada buah tomat maka aroma khas dari buah tomat pun semakin menghilang, sehingga Electronic nose yang berbasis kemampuan penciuman dapat membedakannya.Detect Formaldehyde on Tomato (Lycopersicum esculentum Mill) With Electronic Nose TechnologyAbstract, The purpose of this study is to detect the contents and levels of formalin in tomatoes by using instruments based on Electronic nose technology. This study used tomatoes that have been soaked in formalin with a concentration of 0.5%, 1%, 2%, 3%, 4%, 5% and tomatoes without soaking with formalin (0%). The samples in this study were 18 samples. The measurements of the intensity on tomatoes aroma were using Piezoelectric Transducer sensors. The classification of tomato spectrum data was using the Principal Component Analysis (PCA) method with Gap Reduction pretreatment. The results of this study were obtained: the Electronic nose began to respond the smell of formalin on tomatoes at 8.14 seconds, and it could classify the content and formalin levels in tomatoes at 25.77 seconds. Electronic nose combined with the principal component analysis (PCA) method have successfully detected the content and levels of formalin in tomatoes with a success rate at 99% (PC-1 of 93% and PC-2 of 6%). The difference of grade formalin levels is the main factor that causes Electronic nose to be able to distinguish the tomato samples tested, because the higher of formalin content in tomatoes, the distinctive of tomatoes aroma is increasingly disappearing. Thereby, the Electronic nose based on  the olfactory ability can distinguish them. 

scholarly journals Tree crown size as a measure of tree biosocial position in 135-year-old oak (Quercus L.) stand

2016 ◽  
Vol 58 (1) ◽  
pp. 31-42 ◽  
Author(s):  
Katarzyna Kaźmierczak ◽  
Bogna Zawieja
Keyword(s):  
Principal Component ◽  
Tree Height ◽  
Projection Area ◽  
Tree Crown ◽  
Diameter At Breast Height ◽  
Breast Height ◽  
Crown Length ◽  
Pca Method ◽  
Crown Projection Area

AbstractThe paper presents an attempt to apply measurable traits of a tree – crown projection area, crown length, diameter at breast height and tree height for classification of 135-year-old oak (QuercusL.) trees into Kraft classes. Statistical multivariate analysis was applied to reach the aim. Empirical material was collected on sample plot area of 0.75 ha, located in 135-year-old oak stand. Analysis of dimensional traits of oaks from 135-year-old stand allows quite certain classification of trees into three groups: pre-dominant, dominant and co-dominant and dominated ones. This seems to be quite promising, providing a tool for the approximation of the biosocial position of tree with no need for assessment in forest. Applied analyses do not allow distinguishing trees belonging to II and III Kraft classes. Unless the eye-estimation-based classification is completed, principal component analysis (PCA) method provided simple, provisional solution for grouping trees from 135-year-old stand into three over-mentioned groups. Discriminant analysis gives more precise results compared with PCA. In the analysed stand, the most important traits for the evaluation of biosocial position were diameter at breast height, crown projection area and height.

Implementation of Reduce AI-NN Model for Highly Accurate Blood Pressure Measurement

2020 ◽  
Author(s):  
Jerry Lin ◽  
Rajeev Kumar Pandey ◽  
Paul C.-P. Chao
Keyword(s):  
Neural Network ◽  
Blood Pressure ◽  
Measurement Accuracy ◽  
Blood Pressure Measurement ◽  
Principal Component ◽  
Data Sets ◽  
British Hypertension Society ◽  
The Neural Network ◽  
Pca Method ◽  
Highly Correlated

Abstract This study proposes a reduce AI model for the accurate measurement of the blood pressure (BP). In this study varied temporal periods of photoplethysmography (PPG) waveforms is used as the features for the artificial neural networks to estimate blood pressure. A nonlinear Principal component analysis (PCA) method is used herein to remove the redundant features and determine a set of dominant features which is highly correlated to the Blood pressure (BP). The reduce features-set not only helps to minimize the size of the neural network but also improve the measurement accuracy of the systolic blood pressure (SBP) and diastolic blood pressure (DBP). The designed Neural Network has the 5-input layer, 2 hidden layers (32 nodes each) and 2 output nodes for SBP and DBP, respectively. The NN model is trained by the PPG data sets, acquired from the 96 subjects. The testing regression for the SBP and DBP estimation is obtained as 0.81. The resultant errors for the SBP and DBP measurement are 2.00±6.08 mmHg and 1.87±4.09 mmHg, respectively. According to the Advancement of Medical Instrumentation (AAMI) and British Hypertension Society (BHS) standard, the measured error of ±6.08 mmHg is less than 8 mmHg, which shows that the device performance is in grade “A”.

PCA–Based Human Posture Classification

2012 ◽  
Author(s):  
Nooritawati Md Tahir ◽  
Aini Hussain ◽  
Salina Abdul Samad ◽  
Hafizah Husain
Keyword(s):  
Neural Network ◽  
Principal Component Analysis ◽  
Artificial Neural Network ◽  
Multilayer Perceptron ◽  
Principal Component ◽  
Optimal Choice ◽  
Correct Classification ◽  
Human Posture ◽  
Posture Classification

Kertas kerja ini membentangkan suatu mekanisme untuk pengelasan susuk tubuh manusia berdasarkan kombinasi pelbagai jelmaan ruang eigen yang dinamakan sebagai eigenposture dan Multilayer Perceptron (MLP) sebagai pengelas. Penjelmaan komponen utama telah digunakan untuk menyari sifat pada bayang-bayang bentuk badan manusia. Gabungan sarian sifat ini digunakan untuk pengelasan susuk tubuh manusia sebagai berdiri atau sebaliknya berasaskan bentuk badan yang diperoleh selepas proses peruasan. Uji kaji telah dijalankan dengan mengubah bilangan vektor eigen yang dijadikan perwakilan untuk tujuan pengelasan. Keputusan yang diperoleh menunjukkan gabungan eigenposture kedua dan keempat memberi keputusan pengelasan bentuk badan manusia yang agak baik iaitu 98% dan boleh dijadikan sebagai pilihan optimal masukan bagi tujuan pengelasan menggunakan bilangan input minima. Kata kunci: Analisa komponen utama, vektor eigen, pengelasan, rangkaian neural tiruan, susuk tubuh manusia This paper outlines a mechanism for human body posture classification based on various combination of eigenspace transform, which we named as eigenposture, and using Multilayer Perceptron (MLP) as classifier. We apply principal component transformation to extract the features from human shape silhouettes. Combinations of the extracted features were used to classify the posture of standing and non-standing based on the human shape obtained from the segmentation process. We experiment by using various combinations of eigenvectors as input representations for classification purpose. Results showed that the second and fourth eigenpostures combination gives reasonably good result with 98% correct classification of human posture and can be adopted as the optimal choice of input for classification using a minimal combination. Key words: Principal component analysis (PCA), eigenvectors, classification, artificial neural network, human posture

The selection of adaptive region of geomagnetic map based on PCA and GA-BP neural network

2020 ◽  
Author(s):  
Yang Chong ◽  
Dongqing Zhao ◽  
Guorui Xiao ◽  
Minzhi Xiang ◽  
Linyang Li ◽  
...  
Keyword(s):  
Neural Network ◽  
Bp Neural Network ◽  
Principal Component ◽  
Background Field ◽  
Characteristic Parameters ◽  
Positioning Accuracy ◽  
Matching Performance ◽  
Bp Neural Network Model ◽  
Selection Of

<p>The selection of adaptive region of geomagnetic map is an important factor that affects the positioning accuracy of geomagnetic navigation. An automatic recognition and classification method of adaptive region of geomagnetic background field based on Principal Component Analysis (PCA) and GA-BP neural network is proposed. Firstly, PCA is used to analyze the geomagnetic characteristic parameters, and the independent characteristic parameters containing principal components are selected. Then, the GA-BP neural network model is constructed, and the correspondence between the geomagnetic characteristic parameters and matching performance is established, so as to realize the recognition and classification of adaptive region. Finally, Simulation results show that the method is feasible and efficient, and the positioning accuracy of geomagnetic navigation is improved.</p>

scholarly journals REAL-TIME CLASSIFICATION OF FACIAL EXPRESSIONS USING A PRINCIPAL COMPONENT ANALYSIS AND CONVOLUTIONAL NEURAL NETWORK

SINERGI ◽  
2019 ◽  
Vol 23 (3) ◽  
pp. 239
Author(s):  
Dwi Lydia Zuharah Astuti ◽  
Samsuryadi Samsuryadi ◽  
Dian Palupi Rini
Keyword(s):  
Neural Network ◽  
Principal Component Analysis ◽  
Convolutional Neural Network ◽  
Customer Service ◽  
Facial Expressions ◽  
Principal Component ◽  
Component Analysis ◽  
Point Of View ◽  
In The Wild

Classification of facial expressions has become an essential part of computer systems and human-computer fast interaction. It is employed in various applications such as digital entertainment, customer service, driver monitoring, and emotional robots. Moreover, it has been studied through several aspects related to the face itself when facial expressions change based on the point of view or perspective. Facial curves such as eyebrows, nose, lips, and mouth will automatically change. Most of the proposed methods have limited frontal Face Expressions Recognition (FER), and their performance decrease when handling non-frontal and multi-view FER cases.  This study combined both methods in the classification of facial expressions, namely the Principal Component Analysis (PCA) and Convolutional Neural Network (CNN) methods. The results of this study proved to be more accurate than that of previous studies. The combination of PCA and CNN methods in the Static Facial Expressions in The Wild (SFEW) 2.0 dataset obtained an accuracy amounting to 70.4%; the CNN method alone only obtained an accuracy amounting to 60.9%.

Sign in / Sign up

Export Citation Format

Share Document