scholarly journals Design of Improved Version of Sigmoidal Function with Biases for Classification Task in ELM Domain

2021 ◽  
Vol 3 (2) ◽  
pp. 70-82
Author(s):  
Mugunthan S. R. ◽  
Vijayakumar T.
Keyword(s):  
Learning Algorithm ◽  
Mathematical Proof ◽  
Stochastic Matrix ◽  
Recognition Rate ◽  
Computation Time ◽  
Classification Task ◽  
Classification Error ◽  
Sigmoidal Function ◽  
Research Article ◽  
Hidden Nodes

Extreme Learning Machine (ELM) is one of the latest trends in learning algorithm, which can provide a good recognition rate within less computation time. Therefore, the algorithm can sustain for a faster response application by utilizing a feed-forward neural network. In this research article, the ELM method has been designed with the presence of sigmoidal function of biases in the hidden nodes to perform the classification task. The classification task is very challenging with the existing learning algorithm and increased computation time due to the huge amount of dataset. While handling of the stochastic matrix for hidden layer, output provides the lower performance for learning rate and robustness in the determination. To address these issues, the modified version of ELM has been developed to obtain better accuracy and minimize the classification error. This research article includes the mathematical proof of sigmoidal activation function with biases of the hidden nodes present in the networks. The output matrix maintains the column rank in order to improve the speed of the training output weights (β). The proposed improved version of ELM leverages better accuracy and efficacy in classification and regression problems as well. Due to the inclusion of matrix column ranking in mathematical proof, the proposed improved version of ELM solves the slow training speed and over-fitting problems present in the existing learning approach.

scholarly journals Study of Variants of Extreme Learning Machine (ELM) Brands and its Performance Measure on Classification Algorithm

2021 ◽  
Vol 3 (2) ◽  
pp. 83-95
Keyword(s):  
Neural Network ◽  
Computation Time ◽  
Performance Measure ◽  
Feed Forward Neural Network ◽  
Forward Algorithm ◽  
Feed Forward ◽  
Research Article ◽  
The Neural Network ◽  
Real Essence ◽  
Hidden Nodes

Recently, the feed-forward neural network is functioning with slow computation time and increased gain. The weight vector and biases in the neural network can be tuned based on performing intelligent assignment for simple generalized operation. This drawback of FFNN is solved by using various ELM algorithms based on the applications issues. ELM algorithms have redesigned the existing neural networks with network components such as hidden nodes, weights, and biases. The selection of hidden nodes is randomly determined and leverages good accuracy than conservative methods. The main aim of this research article is to explain variants of ELM advances for different applications. This procedure can be improved and optimized by using the neural network with novel feed-forward algorithm. The nodes will mainly perform due to the above factors, which are tuning for inverse operation. The ELM essence should be incorporated to reach a faster learning speed and less computation time with minimum human intervention. This research article consists of the real essence of ELM and a briefly explained algorithm for classification purpose. This research article provides clear information on the variants of ELM for different classification tasks. Finally, this research article has discussed the future extension of ELM for several applications based on the function approximation.

A Robust and Efficient Face Recognition System Based on Luminance Distribution Using Maximum Likelihood

2012 ◽  
Vol 241-244 ◽  
pp. 1705-1709
Author(s):  
Ching Tang Hsieh ◽  
Chia Shing Hu
Keyword(s):  
Face Recognition ◽  
Maximum Likelihood ◽  
Recognition Rate ◽  
Computation Time ◽  
Likelihood Estimation ◽  
Recognition System ◽  
Luminance Distribution ◽  
Face Region ◽  
Face Recognition System ◽  
The Face

In this paper, a robust and efficient face recognition system based on luminance distribution by using maximum likelihood estimation is proposed. The distribution of luminance components of the face region is acquired and applied to maximum likelihood test for face matching. The experimental results showed that the proposed method has a high recognition rate and requires less computation time.

Video Semantic Analysis

2021 ◽  
Vol 11 (2) ◽  
pp. 1-21
Author(s):  
Daniel Danso Essel ◽  
Ben-Bright Benuwa ◽  
Benjamin Ghansah
Keyword(s):  
Dictionary Learning ◽  
Semantic Analysis ◽  
Learning Algorithm ◽  
Recognition Rate ◽  
Image Data ◽  
Video Data ◽  
The Novel ◽  
Video Feature ◽  
Novel Approach ◽  
Video Semantic Analysis

Sparse Representation (SR) and Dictionary Learning (DL) based Classifier have shown promising results in classification tasks, with impressive recognition rate on image data. In Video Semantic Analysis (VSA) however, the local structure of video data contains significant discriminative information required for classification. To the best of our knowledge, this has not been fully explored by recent DL-based approaches. Further, similar coding findings are not being realized from video features with the same video category. Based on the foregoing, a novel learning algorithm, Sparsity based Locality-Sensitive Discriminative Dictionary Learning (SLSDDL) for VSA is proposed in this paper. In the proposed algorithm, a discriminant loss function for the category based on sparse coding of the sparse coefficients is introduced into structure of Locality-Sensitive Dictionary Learning (LSDL) algorithm. Finally, the sparse coefficients for the testing video feature sample are solved by the optimized method of SLSDDL and the classification result for video semantic is obtained by minimizing the error between the original and reconstructed samples. The experimental results show that, the proposed SLSDDL significantly improves the performance of video semantic detection compared with state-of-the-art approaches. The proposed approach also shows robustness to diverse video environments, proving the universality of the novel approach.

Electrocardiogram stream level correlated patterns as features to classify heartbeats for arrhythmia prediction

2020 ◽  
Vol 54 (5) ◽  
pp. 685-701
Author(s):  
Fuad Ali Mohammed Al-Yarimi ◽  
Nabil Mohammed Ali Munassar ◽  
Fahd N. Al-Wesabi
Keyword(s):  
Supervised Learning ◽  
Computation Time ◽  
Classification Error ◽  
Clinical Practices ◽  
Content Type ◽  
A Value ◽  
Correlated Patterns ◽  
Constructive Models ◽  
Minimum Classification Error ◽  
Supervised Learning And Classification

PurposeDigital computing and machine learning-driven predictive analysis in the diagnosis of non-communicable diseases are gaining significance. Globally many research studies are focusing on developing comprehensive models for such detection. Categorically in the proposed diagnosis for arrhythmia, which is a critical diagnosis to prevent cardiac-related deaths, any constructive models can be a value proposition. In this study, the focus is on developing a holistic system that predicts the scope of arrhythmia from the given electrocardiogram report. The proposed method is using the sequential patterns of the electrocardiogram elements as features.Design/methodology/approachConsidering the decision accuracy of the contemporary classification methods, which is not adequate to use in clinical practices, this manuscript coined a new dimension of features to perform supervised learning and classification using the AdaBoost classifier. The proposed method has titled “Electrocardiogram stream level correlated patterns as features (ESCPFs),” which takes electrocardiograms (ECGs) signal streams as input records to perform supervised learning-based classification to detect the arrhythmia scope in given ECG record.FindingsFrom the results and comparative reports generated for the study, it is evident that the model is performing with higher accuracy compared to some of the earlier models. However, focusing on the emerging solutions and technologies, if the accuracy factors for the model can be improved, it can lead to compelling predictions and accurate outcome from the process.Originality/valueThe authors represent complete automatic and rapid arrhythmia as classifier, which could be applied online and examine long ECG records sequence efficiently. By releasing the needs for extraction of features, the authors project an application based on raw signals, one result to heart rates date, whose objective is to lessen computation time when attaining minimum classification error outcomes.

Feature Selection for Fatigue Segment Classification System Using Elitist Non-Dominated Sorting in Genetic Algorithm

2012 ◽  
Vol 165 ◽  
pp. 232-236 ◽  
Author(s):  
Mohd Haniff Osman ◽  
Z.M. Nopiah ◽  
S. Abdullah
Keyword(s):  
Genetic Algorithm ◽  
Feature Selection ◽  
Classification System ◽  
Learning Algorithm ◽  
Selection Procedure ◽  
Classification Error ◽  
Algorithm Selection ◽  
Nsga Ii ◽  
Nearest Neighbours ◽  
Good Set

Having relevant features for representing dataset would motivate such algorithms to provide a highly accurate classification system in less-consuming time. Unfortunately, one good set of features is sometimes not fit to all learning algorithms. To confirm that learning algorithm selection does not weights system accuracy user has to validate that the given dataset is a feature-oriented dataset. Thus, in this study we propose a simple verification procedure based on multi objective approach by means of elitist Non-dominated Sorting in Genetic Algorithm (NSGA-II). The way NSGA-II performs in this work is quite similar to the feature selection procedure except on interpretation of the results i.e. set of optimal solutions. Two conflicting minimization elements namely classification error and number of used features are taken as objective functions. A case study of fatigue segment classification was chosen for the purpose of this study where simulations were repeated using four single classifiers such as Naive-Bayes, k nearest neighbours, decision tree and radial basis function. The proposed procedure demonstrates that only two features are needed for classifying a fatigue segment task without having to place concern on learning algorithm

Reduction Models in Competitive Learning Founded on Distortion Standards

2008 ◽  
Vol 12 (3) ◽  
pp. 314-323 ◽  
Author(s):  
Michiharu Maeda ◽  
◽  
Noritaka Shigei ◽  
Hiromi Miyajima ◽  
Kenichi Suzaki ◽  
...  
Keyword(s):  
Image Coding ◽  
Learning Algorithm ◽  
Computation Time ◽  
Competitive Learning ◽  
Experimental Results ◽  
Error Criterion ◽  
General Reduction ◽  
Predetermined Number

Two reductions in competitive learning founded on distortion standards are discussed from the viewpoint of generating necessary and appropriate reference vectors under the condition of their predetermined number. The first approach is termed the segmental reduction and competitive learning algorithm. The algorithm is presented as follows: First, numerous reference vectors are prepared and the algorithm is processed under competitive learning. Next, reference vectors are sequentially eliminated to reach their prespecified number based on the partition error criterion. The second approach is termed the general reduction and competitive learning algorithm. The algorithm is presented as follows: First, numerous reference vectors are prepared and the algorithm is processed under competitive learning. Next, reference vectors are sequentially erased based on the average distortion criterion. Experimental results demonstrate the effectiveness of our approaches compared to conventional techniques in average distortion. The two approaches are applied to image coding to determine their feasibility in quality and computation time.

scholarly journals Convergence Analysis of An Improved Extreme Learning Machine Based on Gradient Descent Method

2016 ◽  
Vol 8 (1) ◽  
pp. 5-15
Author(s):  
Liu Yusong ◽  
Su Zhixun ◽  
Zhang Bingjie ◽  
Gong Xiaoling ◽  
Sang Zhaoyang
Keyword(s):  
Extreme Learning Machine ◽  
Learning Algorithm ◽  
Error Function ◽  
Gradient Descent Method ◽  
Testing Time ◽  
Training Procedure ◽  
Feed Forward Neural Network ◽  
Learning Machine ◽  
Theoretical Results ◽  
Hidden Nodes

Abstract Extreme learning machine (ELM) is an efficient algorithm, but it requires more hidden nodes than the BP algorithms to reach the matched performance. Recently, an efficient learning algorithm, the upper-layer-solution-unaware algorithm (USUA), is proposed for the single-hidden layer feed-forward neural network. It needs less number of hidden nodes and testing time than ELM. In this paper, we mainly give the theoretical analysis for USUA. Theoretical results show that the error function monotonously decreases in the training procedure, the gradient of the error function with respect to weights tends to zero (the weak convergence), and the weight sequence goes to a fixed point (the strong convergence) when the iterations approach positive infinity. An illustrated simulation has been implemented on the MNIST database of handwritten digits which effectively verifies the theoretical results..

An Identification Method of Library Identifiers Based on Computer Vision

2013 ◽  
Vol 380-384 ◽  
pp. 3534-3537
Author(s):  
Li Ya Liu
Keyword(s):  
Neural Network ◽  
Computer Vision ◽  
Network Model ◽  
Neural Network Model ◽  
Recognition Rate ◽  
Computation Time ◽  
Principal Component ◽  
Structural Features ◽  
Traditional Methods ◽  
Quantum Neural Network

For traditional methods of library identifies based on the two-dimensional code characteristics, these methods are time consuming and a lot of prior experience is required. A method of library identifies based on computer vision technology is proposed. In this method, a preprocessing, such as image equalization, binarization and wavelet change, is first performed on the acquired library label images. Then on the basis of the structural features of the character, the features of library identifiers are obtained by applying PCA for a principal component analysis. A quantum neural network model is designed to have an optimization analysis and calculation on the extracted features, to avoid the drawbacks which need a lot of prior knowledge for the traditional methods. At the same time, an optimization is carried out for the neural network model saving a large amount of computation time. The experimental results show that a recognition rate, up to 98.13%, is obtained by using this method. With a high recognition speed, the method can meet the actual needs to be applied in a practical system.

scholarly journals A Novel Algorithm for Feature Level Fusion Using SVM Classifier for Multibiometrics-Based Person Identification

2013 ◽  
Vol 2013 ◽  
pp. 1-11 ◽  
Author(s):  
Ujwalla Gawande ◽  
Mukesh Zaveri ◽  
Avichal Kapur
Keyword(s):  
Learning Algorithm ◽  
Recognition Performance ◽  
Recognition Rate ◽  
Rejection Rate ◽  
Support Vector ◽  
Svm Classifier ◽  
Fusion Algorithm ◽  
Biometric Systems ◽  
Feature Level Fusion ◽  
Level Fusion

Recent times witnessed many advancements in the field of biometric and ultimodal biometric fields. This is typically observed in the area, of security, privacy, and forensics. Even for the best of unimodal biometric systems, it is often not possible to achieve a higher recognition rate. Multimodal biometric systems overcome various limitations of unimodal biometric systems, such as nonuniversality, lower false acceptance, and higher genuine acceptance rates. More reliable recognition performance is achievable as multiple pieces of evidence of the same identity are available. The work presented in this paper is focused on multimodal biometric system using fingerprint and iris. Distinct textual features of the iris and fingerprint are extracted using the Haar wavelet-based technique. A novel feature level fusion algorithm is developed to combine these unimodal features using the Mahalanobis distance technique. A support-vector-machine-based learning algorithm is used to train the system using the feature extracted. The performance of the proposed algorithms is validated and compared with other algorithms using the CASIA iris database and real fingerprint database. From the simulation results, it is evident that our algorithm has higher recognition rate and very less false rejection rate compared to existing approaches.

Improved Algorithm Base on Locally Linear Embedding

2014 ◽  
Vol 644-650 ◽  
pp. 2160-2163 ◽  
Author(s):  
Shi Min Liu ◽  
Yan Ni Deng ◽  
Yuan Xing Lv
Keyword(s):  
Learning Algorithm ◽  
Recognition Rate ◽  
Feature Space ◽  
Locally Linear Embedding ◽  
Dispersion Matrix ◽  
Redundant Information ◽  
Training Samples ◽  
Linear Embedding ◽  
Low Dimensional ◽  
Locally Linear

Locally linear embedding algorithm (LLE) , It makes up the shortcomings that the manifold learning algorithm can be only applied to training samples but not be extended to test samples . However, due to the presence of its Low-dimensional feature space redundant information,and its sample category information does not integrate into a low-dimensional embedding. For this shortcoming, here we introduce the two improved algorithms:the local linear maximum dispersion matrix algorithm (FSLLE) and the adaptive algorithm (ALLE), and the combinations of the above two algorithms.With this experience,combined Garbol and locally linear embedding algorithm (LLE) to compare each conclusion. The results proved to be effective elimination of redundant information among basis vectors and improve the recognition rate.

Sign in / Sign up

Export Citation Format

Share Document