scholarly journals A Method Combining CNN and ELM for Feature Extraction and Classification of SAR Image

2019 ◽  
Vol 2019 ◽  
pp. 1-8 ◽  
Author(s):  
Peng Wang ◽  
Xiaomin Zhang ◽  
Yan Hao
Keyword(s):  
Image Recognition ◽  
Recognition Rate ◽  
Activation Function ◽  
Recognition Algorithm ◽  
Sar Image ◽  
Stationary Target ◽  
Speed Up ◽  
Low Efficiency ◽  
Learning Machine ◽  
Sigmoid Activation Function

Due to the large number of Sigmoid activation function derivation in the traditional convolution neural network (CNN), it is difficult to solve the question of the low efficiency of extracting the feature of Synthetic Aperture Radar (SAR) images. The Sigmoid activation function in the CNN is improved to be a rectified linear unit (ReLU) activation function, and the classifier is modified by the Extreme Learning Machine (ELM). Finally, in this CNN model, the improved CNN works as the feature extractor and ELM performs as a recognizer. A SAR image recognition algorithm based on the CNN-ELM algorithm is proposed by combining the CNN and the ELM algorithm. The experiment is conducted on the Moving and Stationary Target Acquisition and Recognition (MSTAR) database which contains 10 kinds of target images. The experiment result shows that the algorithm can realize the sparsity of the network, alleviate the overfitting problem, and speed up the convergence speed of the network. It is worth mentioning that the running time of this experiment is very short. Compared with other experiment on the same database, it indicates that this experiment has generated a higher recognition rate. The accuracy of the SAR image recognition is 100%.

scholarly journals An Effective and Improved CNN-ELM Classifier for Handwritten Digits Recognition and Classification

Symmetry ◽  
2020 ◽  
Vol 12 (10) ◽  
pp. 1742
Author(s):  
Saqib Ali ◽  
Jianqiang Li ◽  
Yan Pei ◽  
Muhammad Saqlain Aslam ◽  
Zeeshan Shaukat ◽  
...  
Keyword(s):  
Character Recognition ◽  
Optical Character Recognition ◽  
Activation Function ◽  
Computational Time ◽  
Robust Model ◽  
Perfect Symmetry ◽  
Handwritten Digit ◽  
Low Efficiency ◽  
Learning Machine ◽  
Sigmoid Activation Function

Optical character recognition is gaining immense importance in the domain of deep learning. With each passing day, handwritten digits (0–9) data are increasing rapidly, and plenty of research has been conducted thus far. However, there is still a need to develop a robust model that can fetch useful information and investigate self-build handwritten digit data efficiently and effectively. The convolutional neural network (CNN) models incorporating a sigmoid activation function with a large number of derivatives have low efficiency in terms of feature extraction. Here, we designed a novel CNN model integrated with the extreme learning machine (ELM) algorithm. In this model, the sigmoid activation function is upgraded as the rectified linear unit (ReLU) activation function, and the CNN unit along with the ReLU activation function are used as a feature extractor. The ELM unit works as the image classifier, which makes the perfect symmetry for handwritten digit recognition. A deeplearning4j (DL4J) framework-based CNN-ELM model was developed and trained using the Modified National Institute of Standards and Technology (MNIST) database. Validation of the model was performed through self-build handwritten digits and USPS test datasets. Furthermore, we observed the variation of accuracies by adding various hidden layers in the architecture. Results reveal that the CNN-ELM-DL4J approach outperforms the conventional CNN models in terms of accuracy and computational time.

scholarly journals Extreme Learning Machine with sigmoid activation function on large data

2019 ◽  
Vol 8 (2S11) ◽  
pp. 3523-3526
Keyword(s):  
Efficient Algorithm ◽  
Large Data ◽  
Activation Function ◽  
Large Data Sets ◽  
Data Sets ◽  
Data Set ◽  
Learning Machine ◽  
Sigmoid Activation Function ◽  
State Of Art ◽  
Better Than

This paper describes an efficient algorithm for classification in large data set. While many algorithms exist for classification, they are not suitable for larger contents and different data sets. For working with large data sets various ELM algorithms are available in literature. However the existing algorithms using fixed activation function and it may lead deficiency in working with large data. In this paper, we proposed novel ELM comply with sigmoid activation function. The experimental evaluations demonstrate the our ELM-S algorithm is performing better than ELM,SVM and other state of art algorithms on large data sets.

scholarly journals Robust Automatic Target Recognition Algorithm for Large-Scene SAR Images and Its Adaptability Analysis on Speckle

2016 ◽  
Vol 2016 ◽  
pp. 1-11 ◽  
Author(s):  
Hongqiao Wang ◽  
Yanning Cai ◽  
Guangyuan Fu ◽  
Shicheng Wang
Keyword(s):  
Target Recognition ◽  
Low Frequency ◽  
Automatic Target Recognition ◽  
Recognition Algorithm ◽  
Scale Transformation ◽  
Sar Image ◽  
Sar Images ◽  
Stationary Target ◽  
Multilevel Sampling ◽  
Process Method

Aiming at the multiple target recognition problems in large-scene SAR image with strong speckle, a robust full-process method from target detection, feature extraction to target recognition is studied in this paper. By introducing a simple 8-neighborhood orthogonal basis, a local multiscale decomposition method from the center of gravity of the target is presented. Using this method, an image can be processed with a multilevel sampling filter and the target’s multiscale features in eight directions and one low frequency filtering feature can be derived directly by the key pixels sampling. At the same time, a recognition algorithm organically integrating the local multiscale features and the multiscale wavelet kernel classifier is studied, which realizes the quick classification with robustness and high accuracy for multiclass image targets. The results of classification and adaptability analysis on speckle show that the robust algorithm is effective not only for the MSTAR (Moving and Stationary Target Automatic Recognition) target chips but also for the automatic target recognition of multiclass/multitarget in large-scene SAR image with strong speckle; meanwhile, the method has good robustness to target’s rotation and scale transformation.

SAR Image Recognition Combined Bidirectional 2DPCA with PCA

2013 ◽  
Vol 756-759 ◽  
pp. 4041-4044 ◽  
Author(s):  
De Gong Wang ◽  
Zuo Long Yang ◽  
Shuo Chang
Keyword(s):  
Experimental Data ◽  
Principal Component Analysis ◽  
Feature Extraction ◽  
Image Recognition ◽  
Recognition Rate ◽  
Principal Component ◽  
Column Vector ◽  
Experimental Result ◽  
High Dimensional ◽  
Sar Image

The method of Principal Component Analysis (PCA) needs to convert image matrix to high-dimensional column vector used in feature extraction. The 2-dimensional PCA (2DPCA) offsets disadvantages of PCA. However, 2DPCA compresses image along the rows or columns only, the number of features is still large. In order to solve the above problems, bidirectional 2DPCA was used to compress image matrix along row and column meanwhile, then use PCA reduce the number of computations and feature dimensions. Three kinds of ground static military targets images acquired by SAR were used as the experimental data. The experimental result shows that, the method of SAR image recognition presented by this paper reduced the dimensions of feature matrix and raised the recognition rate.

Automatic Calibration System for Digital-Display Vibrometers Based on Machine Vision

2014 ◽  
Vol 21 (2) ◽  
pp. 317-328 ◽  
Author(s):  
Wen He ◽  
Guanhua Xu ◽  
Zuochao Rong ◽  
Gen Li ◽  
Min Liu
Keyword(s):  
Machine Vision ◽  
Image Recognition ◽  
Recognition Rate ◽  
Digital Camera ◽  
Automatic Calibration ◽  
Vibration Exciter ◽  
Digital Display ◽  
Vibration Level ◽  
Calibration System ◽  
Low Efficiency

Abstract Considering the low efficiency during the process of traditional calibration for digital-display vibrometers, an automatic calibration system for vibrometers based on machine vision is developed. First, an automatic vibration control system is established on the basis of a personal computer, and the output of a vibration exciter on which a digital-display vibrometer to be calibrated is installed, is automatically adjusted to vibrate at a preset vibration level and a preset frequency. Then the display of the vibrometer is captured by a digital camera and identified by means of image recognition. According to the vibration level of the exciter measured by a laser interferometer and the recognized display of the vibrometer, the properties of the vibrometer are calculated and output by the computer. Image recognition algorithms for the display of the vibrometer with a high recognition rate are presented, and the recognition for vibrating digits and alternating digits is especially analyzed in detail. Experimental results on the built-up system show that the prposed image recognition methods are very effective and the system could liberate operators from boring and intense calibration work for digital-display vibrometers

scholarly journals Dual-channel convolutional neural network for power edge image recognition

2021 ◽  
Vol 10 (1) ◽  
Author(s):  
Fangrong Zhou ◽  
Yi Ma ◽  
Bo Wang ◽  
Gang Lin
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Image Recognition ◽  
Recognition Rate ◽  
Recognition Algorithm ◽  
Classification Method ◽  
Power Equipment ◽  
Recognition Method ◽  
Edge Image ◽  
Dual Channel

AbstractIn view of the low accuracy and poor processing capacity of traditional power equipment image recognition methods, this paper proposes a power equipment image recognition method based on a dual-channel convolutional neural network (DC-CNN) model and random forest (RF) classification. In the aspect of feature extraction, the DC-CNN model extracts the characteristics of power equipment through two independent CNN models. In the aspect of the recognition algorithm, by referring to the advantages of the traditional machine learning method and incorporating the advantages of the RF, an RF classification method incorporating deep learning is proposed. Finally, the proposed DC-CNN model and RF classification method are used to classify images of various types of power equipment. The results show that the proposed methods can be effectively applied to the image recognition of various types of power equipment, and they greatly improve the recognition rate of power equipment images.

scholarly journals Speeding up quantum perceptron via shortcuts to adiabaticity

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Yue Ban ◽  
Xi Chen ◽  
E. Torrontegui ◽  
E. Solano ◽  
J. Casanova
Keyword(s):  
Machine Learning ◽  
Nonlinear Response ◽  
Activation Function ◽  
Control Field ◽  
Fundamental Building Block ◽  
Shortcuts To Adiabaticity ◽  
Quantum Machine Learning ◽  
Speed Up ◽  
Sigmoid Activation Function ◽  
Learning Schemes

AbstractThe quantum perceptron is a fundamental building block for quantum machine learning. This is a multidisciplinary field that incorporates abilities of quantum computing, such as state superposition and entanglement, to classical machine learning schemes. Motivated by the techniques of shortcuts to adiabaticity, we propose a speed-up quantum perceptron where a control field on the perceptron is inversely engineered leading to a rapid nonlinear response with a sigmoid activation function. This results in faster overall perceptron performance compared to quasi-adiabatic protocols, as well as in enhanced robustness against imperfections in the controls.

SCORING MODELING BASED ON NEURAL NETWORKS FOR DETERMINING A BANK BORROWER'S RATING

2020 ◽  
Vol 2020 (10) ◽  
pp. 54-62
Author(s):  
Oleksii VASYLIEV ◽  
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Network Architecture ◽  
Statistical Data ◽  
Activation Function ◽  
Decision Making Process ◽  
Neural Network Architecture ◽  
Acceptable Accuracy ◽  
The Neural Network ◽  
Sigmoid Activation Function

The problem of applying neural networks to calculate ratings used in banking in the decision-making process on granting or not granting loans to borrowers is considered. The task is to determine the rating function of the borrower based on a set of statistical data on the effectiveness of loans provided by the bank. When constructing a regression model to calculate the rating function, it is necessary to know its general form. If so, the task is to calculate the parameters that are included in the expression for the rating function. In contrast to this approach, in the case of using neural networks, there is no need to specify the general form for the rating function. Instead, certain neural network architecture is chosen and parameters are calculated for it on the basis of statistical data. Importantly, the same neural network architecture can be used to process different sets of statistical data. The disadvantages of using neural networks include the need to calculate a large number of parameters. There is also no universal algorithm that would determine the optimal neural network architecture. As an example of the use of neural networks to determine the borrower's rating, a model system is considered, in which the borrower's rating is determined by a known non-analytical rating function. A neural network with two inner layers, which contain, respectively, three and two neurons and have a sigmoid activation function, is used for modeling. It is shown that the use of the neural network allows restoring the borrower's rating function with quite acceptable accuracy.

Sign in / Sign up

Export Citation Format

Share Document