Hybrid Learning Enhancement of RBF Network Based on Particle Swarm Optimization

2009 ◽  
pp. 19-29 ◽  
Author(s):  
Sultan Noman Qasem ◽  
Siti Mariyam Shamsuddin
Keyword(s):  
Particle Swarm Optimization ◽  
Particle Swarm ◽  
Hybrid Learning ◽  
Learning Enhancement ◽  
Swarm Optimization ◽  
Rbf Network

scholarly journals Improved SpikeProp for Using Particle Swarm Optimization

2013 ◽  
Vol 2013 ◽  
pp. 1-13 ◽  
Author(s):  
Falah Y. H. Ahmed ◽  
Siti Mariyam Shamsuddin ◽  
Siti Zaiton Mohd Hashim
Keyword(s):  
Particle Swarm Optimization ◽  
Supervised Learning ◽  
Learning Algorithm ◽  
Particle Swarm ◽  
Learning Rule ◽  
Temporal Coding ◽  
Spiking Neurons ◽  
Learning Enhancement ◽  
Swarm Optimization ◽  
Spiking Networks

A spiking neurons network encodes information in the timing of individual spike times. A novel supervised learning rule for SpikeProp is derived to overcome the discontinuities introduced by the spiking thresholding. This algorithm is based on an error-backpropagation learning rule suited for supervised learning of spiking neurons that use exact spike time coding. The SpikeProp is able to demonstrate the spiking neurons that can perform complex nonlinear classification in fast temporal coding. This study proposes enhancements of SpikeProp learning algorithm for supervised training of spiking networks which can deal with complex patterns. The proposed methods include the SpikeProp particle swarm optimization (PSO) and angle driven dependency learning rate. These methods are presented to SpikeProp network for multilayer learning enhancement and weights optimization. Input and output patterns are encoded as spike trains of precisely timed spikes, and the network learns to transform the input trains into target output trains. With these enhancements, our proposed methods outperformed other conventional neural network architectures.

Integrative optimization by RBF network and particle swarm optimization

2009 ◽  
Vol 92 (12) ◽  
pp. 31-42 ◽  
Author(s):  
Satoshi Kitayama ◽  
Keiichiro Yasuda ◽  
Koetsu Yamazaki
Keyword(s):  
Particle Swarm Optimization ◽  
Particle Swarm ◽  
Swarm Optimization ◽  
Rbf Network

scholarly journals Research on Adaptive Suppression of LCL Converter Resonance Grid-Connected System

2020 ◽  
Vol 2020 ◽  
pp. 1-9
Author(s):  
Junwei Li ◽  
Yafang Tang ◽  
Junke Li
Keyword(s):  
Particle Swarm Optimization ◽  
Particle Swarm ◽  
Stability Margin ◽  
System Stability ◽  
Current Feedback ◽  
Swarm Optimization ◽  
Lcl Filter ◽  
Rbf Network ◽  
Grid Impedance ◽  
Suppression Method

LCL-type converters are widely used in grid-connected systems due to their small size and good filtering performance. However, the resonance suppression problem brought by the LCL filter cannot be ignored. The capacitive current feedback is a commonly used resonance suppression method. In applications, the grid impedance can cause LCL filter resonance. Thus, this paper presents an adaptive resonance suppression method based on the RBF network optimized by particle swarm optimization. This method optimizes the initial parameters of the RBF network through particle swarm optimization, identifies the parameters of the PI controller by RBF neural network’s own identification capability, and updates the active damping coefficient based on constraints such as stability margin, thereby realizing the LCL-type inverter to maintain the system stability when the grid impedance changes. The effectiveness of the method is verified by experiments.

Particle Swarm Optimization For Neural Network Learning Enhancement

2008 ◽  
Vol 49 (1) ◽  
Author(s):  
Haza Nuzly Abdull Hamed ◽  
Siti Mariyam Shamsuddin ◽  
Naomie Salim
Keyword(s):  
Neural Network ◽  
Particle Swarm Optimization ◽  
Particle Swarm ◽  
Learning Enhancement ◽  
Swarm Optimization ◽  
Neural Network Learning ◽  
Network Learning

Self-Adaptive two roles hybrid learning strategies-based particle swarm optimization

2021 ◽  
Author(s):  
Xinmin Tao ◽  
Xiangke Li ◽  
Wei Chen ◽  
Tian Liang ◽  
Yetong Li ◽  
...  
Keyword(s):  
Particle Swarm Optimization ◽  
Learning Strategies ◽  
Particle Swarm ◽  
Hybrid Learning ◽  
Swarm Optimization ◽  
Self Adaptive

scholarly journals Hybrid Learning of Hand-Crafted and Deep-Activated Features Using Particle Swarm Optimization and Optimized Support Vector Machine for Tuberculosis Screening

2020 ◽  
Vol 10 (17) ◽  
pp. 5749
Author(s):  
Khin Yadanar Win ◽  
Noppadol Maneerat ◽  
Kazuhiko Hamamoto ◽  
Syna Sreng
Keyword(s):  
Support Vector Machine ◽  
Particle Swarm Optimization ◽  
Learning Algorithm ◽  
Particle Swarm ◽  
Hybrid Learning ◽  
Support Vector ◽  
X Rays ◽  
Histogram Of Oriented Gradients ◽  
Hybrid Features ◽  
Swarm Optimization

Tuberculosis (TB) is a leading infectious killer, especially for people with Human Immunodeficiency Virus (HIV) and Acquired Immunodeficiency Syndrome (AIDS). Early diagnosis of TB is crucial for disease treatment and control. Radiology is a fundamental diagnostic tool used to screen or triage TB. Automated chest x-rays analysis can facilitate and expedite TB screening with fast and accurate reports of radiological findings and can rapidly screen large populations and alleviate a shortage of skilled experts in remote areas. We describe a hybrid feature-learning algorithm for automatic screening of TB in chest x-rays: it first segmented the lung regions using the DeepLabv3+ model. Then, six sets of hand-crafted features from statistical textures, local binary pattern, GIST, histogram of oriented gradients (HOG), pyramid histogram of oriented gradients and bags of visual words (BoVW), and nine sets of deep-activated features from AlexNet, GoogLeNet, InceptionV3, XceptionNet, ResNet-50, SqueezeNet, ShuffleNet, MobileNet, and DenseNet, were extracted. The dominant features of each feature set were selected using particle swarm optimization, and then separately input to an optimized support vector machine classifier to label ‘normal’ and ‘TB’ x-rays. GIST, HOG, BoVW from hand-crafted features, and MobileNet and DenseNet from deep-activated features performed better than the others. Finally, we combined these five best-performing feature sets to build a hybrid-learning algorithm. Using the Montgomery County (MC) and Shenzen datasets, we found that the hybrid features of GIST, HOG, BoVW, MobileNet and DenseNet, performed best, achieving an accuracy of 92.5% for the MC dataset and 95.5% for the Shenzen dataset.

Sign in / Sign up

Export Citation Format

Share Document