Prediction of Protein Structural Class by Functional Link Artificial Neural Network Using Hybrid Feature Extraction Method

2013 ◽  
pp. 298-307 ◽  
Author(s):  
Bishnupriya Panda ◽  
Ambika Prasad Mishra ◽  
Babita Majhi ◽  
Minakhi Rout
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Feature Extraction ◽  
Extraction Method ◽  
Functional Link ◽  
Structural Class ◽  
Protein Structural Class ◽  
Feature Extraction Method ◽  
Hybrid Feature Extraction ◽  
Artificial Neural

scholarly journals THE IMPLEMENTATION OF EXTRACTION FEATURE USING GLCM AND BACK-PROPAGATION ARTIFICIAL NEURAL NETWORK TO CLASIFY LOMBOK SONGKET WOVEN CLOTH

2020 ◽  
Vol 17 (2) ◽  
pp. 131-136
Author(s):  
Bahtiar Imran ◽  
Muhamad Masjun Efendi
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Feature Extraction ◽  
Extraction Method ◽  
Back Propagation ◽  
Training Data ◽  
Feature Extraction Method ◽  
Good Classification ◽  
Artificial Neural ◽  
Artificial Neural Network Ann

The aimed of this study was to apply the feature extraction method of GLCM and Back-propagation Artificial Neural Network (ANN) to classify Lombok's typical Songket woven cloth by classifying based on the texture of the Songket woven cloth. Songket woven cloth in Lombok in terms of weaving and texture are vary from region to region. For example the songket woven cloth in Pringgasela Village, Sukarara Village and Sade Village has differences in texture and motifs. For this reason, this study focuses on classifying Lombok's typical Songket woven cloth by performing feature extraction on woven cloth using the GLCM method and the classification method uses Back-propagation Artificial Neural Network (ANN). For data collection, the data was taken directly from the Songket weaving centers in Pringgasela, Sade and Sukarara. In the classification stage the training data used were 64 data and 11 test data. Then the epoch used was 41 iterations with a time of 0:00:04, with neurons 80 and 100. The use of neurons 80 generated 18% which was successful in the classification. While using 100 neurons generated 100% successful which was can be classified. Based on the classification results obtained, the use of 100 neurons gained good classification results.

scholarly journals Deteksi Api Pada Video Menggunakan Metode Artificial Neural Network

2021 ◽  
Vol 3 (1) ◽  
pp. 96-107
Author(s):  
Budiman Rabbani
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Feature Extraction ◽  
Extraction Method ◽  
Gray Level ◽  
Backpropagation Neural Network ◽  
Validation Process ◽  
Feature Extraction Method ◽  
Time Value ◽  
Occurrence Matrix

Abstract The camera is one of the tools used to collect images. Cameras are often used for the safety of homes, highways and others. Then in this study camera captures are used to support fire objects because fire is one of the causes of safety that can be controlled. Therefore, by utilizing a capture camera will see the best model of backpropagation neural network by combining the local binary patern (LBP) feature extraction method and the Gray Level Co-occurrence Matrix (GLCM) to access the fire. Then to evaluate the performance of the model created using three parameters that contain accuracy, recall, precision. The data in this study consisted of videos with variations of fire and non-fire videos. Based on the final results of the study, accuracy, remember, the best precision obtained simultaneously 96%, 97%, 97%. Then the validation process was done using 30 videos with a variation of 15 fire videos and 15 non-fire videos and obtained an accuracy of 86.6% with an average time value of 6.029 minutes.

On-Line Quality Detection of Ultrasonic Wire Bonding via Refining Analysis of Electrical Signal From Ultrasonic Generator

2010 ◽  
Vol 132 (4) ◽  
Author(s):  
Wuwei Feng ◽  
Qingfeng Meng ◽  
Youbo Xie ◽  
Hong Fan
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Feature Extraction ◽  
Extraction Method ◽  
Wire Bonding ◽  
Bond Quality ◽  
Feature Extraction Method ◽  
Quality Detection ◽  
On Line ◽  
Ultrasonic Wire Bonding

A technique for on-line quality detection of ultrasonic wire bonding is developed. The electrical signals from the ultrasonic generator supply, namely, voltage and current, are picked up by a measuring circuit and transformed into digital signals by a data acquisition system. A new feature extraction method is presented to characterize the transient property of the electrical signals and further evaluate the bond quality. The method includes three steps. First, the captured voltage and current are filtered by digital bandpass filter banks to obtain the corresponding subband signals such as fundamental signal, second harmonic, and third harmonic. Second, each subband envelope is obtained using the Hilbert transform for further feature extraction. Third, the subband envelopes are, respectively, separated into three phases, namely, envelope rising, stable, and damping phases, to extract the tiny waveform changes. The different waveform features are extracted from each phase of these subband envelopes. The principal components analysis method is used for the feature selection in order to remove the relevant information and reduce the dimension of original feature variables. Using the selected features as inputs, an artificial neural network is constructed to identify the complex bond fault pattern. By analyzing experimental data with the proposed feature extraction method and neural network, the results demonstrate the advantages of the proposed feature extraction method and the constructed artificial neural network in detecting and identifying bond quality.

Sign in / Sign up

Export Citation Format

Share Document