An Enhanced Extreme Learning Machine for Efficient Small Sample Classification

2016 ◽  
pp. 501-509 ◽  
Author(s):  
Ying Yin ◽  
Yuhai Zhao ◽  
Ming Li ◽  
Bin Zhang
Keyword(s):  
Extreme Learning Machine ◽  
Small Sample ◽  
Sample Classification ◽  
Learning Machine

scholarly journals Parcel-Based Crop Classification Using Multi-Temporal TerraSAR-X Dual Polarimetric Data

2019 ◽  
Vol 11 (10) ◽  
pp. 1148 ◽  
Author(s):  
Rei Sonobe
Keyword(s):  
Extreme Learning Machine ◽  
Local Governments ◽  
Multiple Kernel Learning ◽  
Small Sample ◽  
Machine Learning Algorithms ◽  
Support Vector ◽  
Multiple Kernel ◽  
Crop Classification ◽  
Learning Machine ◽  
Simple Ratio

Cropland maps are useful for the management of agricultural fields and the estimation of harvest yield. Some local governments have documented field properties, including crop type and location, based on site investigations. This process, which is generally done manually, is labor-intensive, and remote-sensing techniques can be used as alternatives. In this study, eight crop types (beans, beetroot, grass, maize, potatoes, squash, winter wheat, and yams) were identified using gamma naught values and polarimetric parameters calculated from TerraSAR-X (or TanDEM-X) dual-polarimetric (HH/VV) data. Three indices (difference (D-type), simple ratio (SR), and normalized difference (ND)) were calculated using gamma naught values and m-chi decomposition parameters and were evaluated in terms of crop classification. We also evaluated the classification accuracy of four widely used machine-learning algorithms (kernel-based extreme learning machine, support vector machine, multilayer feedforward neural network (FNN), and random forest) and two multiple-kernel methods (multiple kernel extreme learning machine (MKELM) and multiple kernel learning (MKL)). MKL performed best, achieving an overall accuracy of 92.1%, and proved useful for the identification of crops with small sample sizes. The difference (raw or normalized) between double-bounce scattering and odd-bounce scattering helped to improve the identification of squash and yams fields.

A Hybrid Kernel Extreme Learning Machine and Improved Cat Swarm Optimization for Microarray Medical Data Classification

2016 ◽  
Vol 7 (3) ◽  
pp. 71-100 ◽  
Author(s):  
S. Chakravarty ◽  
R. Bisoi ◽  
P. K. Dash
Keyword(s):  
Gene Expression ◽  
Support Vector Machine ◽  
Extreme Learning Machine ◽  
Medical Data ◽  
Small Sample ◽  
Support Vector ◽  
Swarm Optimization ◽  
Cat Swarm Optimization ◽  
Kernel Extreme Learning Machine ◽  
Learning Machine

This paper presents the pattern classification of the binary microarray gene expression based medical data using extreme learning machine (ELM) and its variants like on-line sequential ELM (OSELM) and kernel based extreme learning machine (KELM). In the KELM category two variants namely the wavelet based kernel (WKELM) extreme learning machine and radial basis kernel extreme learning machine (RKELM) along with support vector machine (SVMRBF) and support vector machine polynomial (SVMPoly) are used to classify microarray medical datasets. Further to reduce the high dimensionality of Microarray medical datasets giving rise to high number of gene expression and small sample sizes, a modified evolutionary cat swarm optimization (MCSO) technique is adopted. The efficiency of the proposed algorithm is verified using a set of performance metrics for four binary medical datasets belonging to breast cancer, prostate cancer, colon tumor, and leukemia, respectively.

scholarly journals A study of extreme learning machine on small sample-sized classification problems

2021 ◽  
Vol 2107 (1) ◽  
pp. 012013
Author(s):  
Boon Pin Ooi ◽  
Norasmadi Abdul Rahim ◽  
Maz Jamilah Masnan ◽  
Ammar Zakaria
Keyword(s):  
Extreme Learning Machine ◽  
Small Sample ◽  
Majority Voting ◽  
Training Data ◽  
Ensemble Model ◽  
Classification Problems ◽  
Total Data ◽  
Learning Machine ◽  
Hidden Layer ◽  
Mlp Model

Abstract Extreme learning machine (ELM) is a special type of single hidden layer feedforward neural network that emphasizes training speed and optimal generalization. The ELM model proposes that the weights of hidden neurons need not be tuned, and the weights of output neurons can be calculated by finding the Moore-Penrose generalized inverse method. Thus, the ELM classifier is suitable to use in a homogeneous ensemble model due to the untuned random hidden weights which promote diversity even with the same training data. This paper studies the effectiveness of the ELM ensemble models in solving small sample-sized classification problems. The research involves two variants of the ensemble model: the normal ELM ensemble with majority voting (ELE), and the random subspace method (RS-ELM). To simulate the small sample cases, only 30% of the total data will be used as the training data. Experiment results show that the RS-ELM model can outperform a multi-layer perceptron (MLP) model under the assumptions of a Friedman test. Furthermore, the ELE model has similar performance as an MLP model under the same assumptions.

Sign in / Sign up

Export Citation Format

Share Document