Genus and Species-Level Classification of Wrasse Fishes Using Multidomain Features and Extreme Learning Machine Classifier

2020 ◽  
Vol 34 (11) ◽  
pp. 2050028 ◽  
Author(s):  
Jisha Anu Jose ◽  
C. Sathish Kumar
Keyword(s):  
Extreme Learning Machine ◽  
Species Level ◽  
Feature Reduction ◽  
Polynomial Kernel ◽  
Automated Recognition ◽  
Background Elimination ◽  
Frequency Domains ◽  
Kernel Extreme Learning Machine ◽  
Learning Machine

Automated recognition and classification of fishes are useful for studies dealing with counting of fishes for population assessments, discovering association between fishes and ecosystem, and monitoring of the ecosystem. This paper proposes a model which classifies the fishes belonging to the family Labridae in the genus and the species level. Features computed in the spatial and frequency domains are used in this work. All the images are preprocessed before feature extraction. Preprocessing step involves image segmentation for background elimination, de-noising and image enhancement. A combination of color, local binary pattern (LBP), histogram of oriented gradients (HOG), and wavelet features forms the feature vector. An ensemble feature reduction technique is used to reduce the attribute size. Performances of the system using combined as well as reduced feature sets are evaluated using seven popular classifiers. Among the classifiers, wavelet kernel extreme learning machine (ELM) showed higher classification accuracy of 96.65% in genus level and polynomial kernel ELM showed an accuracy of 92.42% in species level with the reduced feature set.

Efficient Kernel Extreme Learning Machine and Neutrosophic C-means-based Attribute Weighting Method for Medical Data Classification

2020 ◽  
Vol 29 (16) ◽  
pp. 2050260 ◽  
Author(s):  
D. Shiny Irene ◽  
T. Sethukarasi
Keyword(s):  
Extreme Learning Machine ◽  
Data Classification ◽  
Medical Data ◽  
Integrated System ◽  
Weighting Method ◽  
Attribute Weighting ◽  
Kernel Extreme Learning Machine ◽  
Medical Data Classification ◽  
Learning Machine

This paper proposes an integrated system neutrosophic C-means-based attribute weighting-kernel extreme learning machine (NCMAW-KELM) for medical data classification using NCM clustering and KELM. To do that, NCMAW is developed, and then combined with classification method in classification of medical data. The proposed approach contains two steps. In the first step, input attributes are weighted using NCMAW method. The purpose of the weighting method is twofold: (i) to improve the classification performance in the classification of the medical data, (ii) to transform from nonlinearly separable dataset to linearly separable dataset. Finally, KELM algorithm is used for medical data classification purpose. In KELM algorithm, four types of kernels, such as Polynomial, Sigmoid, Radial basis function and Linear, are used. The simulation result on our three datasets demonstrates that the sigmoid kernel is outperformed to ELM in most cases. From the results, NCMAW-KELM approach may be a promising method in medical data classification problem.

Reproducing Polynomial Kernel Extreme Learning Machine

2017 ◽  
Vol 21 (5) ◽  
pp. 795-802 ◽  
Author(s):  
Yibo Li ◽  
Chao Liu ◽  
Senyue Zhang ◽  
Wenan Tan ◽  
Yanyan Ding ◽  
...  
Keyword(s):  
Extreme Learning Machine ◽  
Reproducing Kernel ◽  
Search Algorithm ◽  
Cuckoo Search ◽  
Cuckoo Search Algorithm ◽  
Polynomial Kernel ◽  
Support Vector ◽  
Fast Training ◽  
Kernel Extreme Learning Machine ◽  
Learning Machine

Conventional kernel support vector machine (KSVM) has the problem of slow training speed, and single kernel extreme learning machine (KELM) also has some performance limitations, for which this paper proposes a new combined KELM model that build by the polynomial kernel and reproducing kernel on Sobolev Hilbert space. This model combines the advantages of global and local kernel function and has fast training speed. At the same time, an efficient optimization algorithm called cuckoo search algorithm is adopted to avoid blindness and inaccuracy in parameter selection. Experiments were performed on bi-spiral benchmark dataset, Banana dataset, as well as a number of classification and regression datasets from the UCI benchmark repository illustrate the feasibility of the proposed model. It achieves the better robustness and generalization performance when compared to other conventional KELM and KSVM, which demonstrates its effectiveness and usefulness.

scholarly journals Exploring the Extreme Learning Machine for Classification of Brain MRIs

2019 ◽  
Vol 9 (2) ◽  
pp. 3654-3657
Keyword(s):  
Extreme Learning Machine ◽  
Principal Component ◽  
Classification Performance ◽  
Feature Reduction ◽  
Brain Diseases ◽  
Discrete Wavelet ◽  
Learning Machine ◽  
Hidden Layer ◽  
Method Accuracy

Magnetic Resonance Imaging (MRI) technique of brain is the most important aspect of diagnosis of brain diseases. The manual analysis of MR images and identifying the brain diseases is tedious and error prone task for the radiologists and physicians. In this paper 2-Dimensional Discrete Wavelet Transformation (2D DWT) is used for feature extraction and Principal Component Analysis (PCA) is used for feature reduction. The three types of brain diseases i.e. Alzheimer, Glioma and Multiple Sclerosis are considered for this work. The Two Hidden layer Extreme learning Machine (TELM) is used for classification of samples into normal or pathological. The performance of the TELM is compared with basic ELM and the simulation results indicate that TELM outperformed the basic ELM method. Accuracy, Recall, Sensitivity and F-score are considered as the classification performance measures in this paper

Sign in / Sign up

Export Citation Format

Share Document