Architecture Selection of ELM Networks Based on Sensitivity of Hidden Nodes

Zhai, Junhai; Shao, Qingyan; Wang, Xizhao

doi:10.1007/s11063-015-9470-1

Cited by 13 publications

(2 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…ELM is noted to achieve good generalization performance in extremely fast learning speed. Figure 3 shows the basic architecture employed for image classification of ELM neural network [15,16]. The basic Extreme Learning Machine classifier algorithm [13] employed for classification application is as given below, Consider N different samples (x i ,y i ) ∈R n × R m , where x i = [x i1 , x i2 .…”

Section: Figure 3: Architecture Of the Elm Network (Singlementioning

confidence: 99%

Proposed Self – Regulated Gray Wolf Optimizer based Extreme Learning Machine Neural Network Classifier for Lung Cancer Classification

2019

IJRTE

View full text Add to dashboard Cite

The major issue in the development of pattern recognition towards lung cancer classification is the formation of feature extraction process and the proposed classifier model. In the proposed approach, a self-regulated gray wolf optimizer based extreme learning machine classifier is proposed to carry out lung cancer classification along with the statistical feature extraction methods. Simulation shows that the proposed approach works well and produces higher classification accuracy than the conventional classifier methods. The modeled SelfRegulated Gray Wolf Optimizer (SRGWO) and Extreme Learning Machine (ELM) along with feature and segmentation process shows highest improvement in comparison with the other existing literature studies in neural networks. In particular, the significant finding of this work employing ELM, SRGWO and feature analysis validates the correlation of Computed Tomography (CT) measures as well as classification pathological parameters. Thus, the proposed SRGWO and ELM classifier is developed in the present approach for lung cancer classification of CT images reducing the computational cost and time of all the earlier classifiers and as well increasing the classification accuracy. On performing trial runs for the proposed SRGWO – ELM to compute the classification results for the considered real time and Lung Image Database Consortium (LIDC) lung images, it has been noted that at certain trials, the extreme learning machine neuronal classifier is noted to get stuck up with the local minima problem and it is necessary to restart the generation process to achieve classification solutions.

show abstract

Section: Figure 3: Architecture Of the Elm Network (Singlementioning

confidence: 99%

Proposed Self – Regulated Gray Wolf Optimizer based Extreme Learning Machine Neural Network Classifier for Lung Cancer Classification

2019

IJRTE

View full text Add to dashboard Cite

show abstract

“…In [28], a dynamic forgetting factor is utilised to adjust OS-ELM parameters, and the corresponding DOS-ELM algorithm is proposed. Up to now, many other algorithms have been considered to extend the basic ELM to make it more efficient [29][30][31][32][33][34][35].…”

Section: Introductionmentioning

confidence: 99%

A Hybrid Method Based on Extreme Learning Machine and Self Organizing Map for Pattern Classification

Jammoussi¹,

Nasr²

2020

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

Extreme learning machine is a fast learning algorithm for single hidden layer feedforward neural network. However, an improper number of hidden neurons and random parameters have a great effect on the performance of the extreme learning machine. In order to select a suitable number of hidden neurons, this paper proposes a novel hybrid learning based on a two-step process. First, the parameters of hidden layer are adjusted by a self-organized learning algorithm. Next, the weights matrix of the output layer is determined using the Moore–Penrose inverse method. Nine classification datasets are considered to demonstrate the efficiency of the proposed approach compared with original extreme learning machine, Tikhonov regularization optimally pruned extreme learning machine, and backpropagation algorithms. The results show that the proposed method is fast and produces better accuracy and generalization performances.

show abstract

A Revisit of Reducing Hidden Nodes in a Radial Basis Function Neural Network with Histogram

Goh

Tan

Cheah

2018

Neural Information Processing

View full text Add to dashboard Cite

Architecture Selection of ELM Networks Based on Sensitivity of Hidden Nodes

Cited by 13 publications

References 32 publications

Proposed Self – Regulated Gray Wolf Optimizer based Extreme Learning Machine Neural Network Classifier for Lung Cancer Classification

Proposed Self – Regulated Gray Wolf Optimizer based Extreme Learning Machine Neural Network Classifier for Lung Cancer Classification

A Hybrid Method Based on Extreme Learning Machine and Self Organizing Map for Pattern Classification

A Revisit of Reducing Hidden Nodes in a Radial Basis Function Neural Network with Histogram

Contact Info

Product

Resources

About