ELM based signature for texture classification

Sá, Jarbas Joaci de Mesquita; Backes, André Ricardo

doi:10.1016/j.patcog.2015.09.014

Cited by 47 publications

(12 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The summary of performance comparison of our technique with the models based on LBP descriptors, Extreme Learning Machine, and other statistical techniques [25][26][27][28][29] is represented by Tables 8,9 and 10. It is clear from the results that our method gives better results than most of the other existing models for the Kylberg and Outex TC-12 datasets, and gives competitive results for the Brodatz dataset.…”

Section: Resultsmentioning

confidence: 99%

“…There is immense scope for enhancing this research by applying our model to other pattern recognition tasks like traffic sign recognition, handwritten character recognition, gait recognition, medical image classification, etc. [27] RALBGC, RLBGC 100 [28] ELM based Signature ( ⃗ 19,39 ) 99.42 [29] Hybrid feature vector 89.28 Proposed method Modified CNN + WOA 97.43…”

Section: Conclusion and Future Enhancementmentioning

confidence: 99%

See 1 more Smart Citation

Texture classification using convolutional neural network optimized with whale optimization algorithm

et al. 2019

View full text Add to dashboard Cite

Texture classification is an active area of research in the field of pattern recognition. Convolutional neural networks (CNNs) have a remarkable capability of recognizing patterns and are one of the most efficient deep learning techniques. But, finding the optimal values of the different hyperparameters of the CNN is a major challenge. Nature-inspired algorithms (NIAs) are the meta-heuristic algorithms well-known for their optimizing capability. Whale optimization algorithm (WOA) is a recent nature-inspired algorithm (NIA) that is inspired by the hunting behaviour of the humpback whales. In this paper, we propose a novel deep learning technique for texture recognition using a CNN optimized through WOA. We apply WOA at the two different levels in the CNN: In the convolutional layer (for optimizing the values of the filters), and in the fully-connected layer (for optimizing the values of the weights and biases). For examining the performance of our technique, we apply it to the following three benchmark texture datasets: Kylberg v1.0, Brodatz, and Outex_TC_00012. Our model performs better than the most of the existing methods for the Kylberg and the Outex_TC_00012 datasets and gives competitive results for the Brodatz dataset. It is evident from the results that our model has the potential for application in the field of texture recognition.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Conclusion and Future Enhancementmentioning

confidence: 99%

Texture classification using convolutional neural network optimized with whale optimization algorithm

et al. 2019

View full text Add to dashboard Cite

show abstract

“…ELM has the advantages of easy parameter selection, fast learning speed and good generalization performance [17]. The structure of ELM is shown in Fig.…”

Section: Extreme Learning Machinementioning

confidence: 99%

Research of Planetary Gear Fault Diagnosis Based on Multi-Scale Fractal Box Dimension of CEEMD and ELM

Chen¹,

Li²,

Li³

2017

SV-JME

View full text Add to dashboard Cite

The planetary gear is the most critical part of a drive transmission system, and its faults will affect the reliability of the equipment, and even cause accidents. Therefore, it is of great significance to study the fault diagnosis of the planetary gear. A method of planetary gear fault diagnosis based on the multi-scale fractal box dimension of complementary ensemble empirical mode decomposition (CEEMD) and extreme learning machine (ELM) is proposed. The original vibration signal is decomposed by CEEMD, and a series of intrinsic mode functions (IMFs) are obtained. Some effective IMFs are extracted, and their reconstructed signal associated with the feature information is obtained. The reconstructed signal is analysed with multi-scale analysis, and the fault feature information contained in the signals with different scales is quantified and extracted via a fractal box dimension. The status recognition of planetary gear is achieved by combining ELM. The experiments show that the proposed method is effective at diagnosing planetary gear faults. Highlights • A method of planetary gear fault diagnosis based on the multi-scale fractal box dimensions of CEEMD and ELM is proposed.• The effective IMFs which associate with the shock feature information are selected by the kurtosis criterion.• The multi-scale fractal box dimension of the reconstructed signal is defined as the fault feature information.• The status recognition of a planetary gear is achieved by combining ELM.

show abstract

“…Extreme learning machine (ELM) [1], as a fast and effective solution of single hidden layer feed-forward networks (SLFNs), has been increasingly investigated in recent years. Because of its extremely fast training speed, good generalization ability and the proved universal approximation/classification capability, ELM has efficiently achieved excellent learning accuracy in many applied fields, such as face recognition [2,3,4], image classification [5,6,7], text categorization [8,9], nonlinear model identification [10] and time series prediction [11]. Many variants of ELM have been proposed in recent years, such as the regularized ELM [12], the kernelbased ELM [13], the ELM based on a regularized correntropy criterion [14] and the online sequential ELM [15], to name a few.…”

Section: Introductionmentioning

confidence: 99%

Correntropy-based robust multilayer extreme learning machines

Chen

Honeiné

et al. 2018

Pattern Recognition

View full text Add to dashboard Cite

In extreme learning machines (ELM), the hidden node parameters are randomly generated and the output weights can be analytically computed. To overcome the bad feature extraction ability of the shallow architecture of ELM, the hierarchical ELM has been extensively studied as a deep architecture with multilayer neural network. However, the commonly used mean square error (MSE) criterion is very sensitive to outliers and impulsive noises, generally existing in real world data. In this paper, we investigate the correntropy to improve the robustness of the multilayer ELM and provide sparser representation. The correntropy, as a nonlinear measure of similarity, is robust to outliers and can approximate different norms (from 0 to 2). A new full correntropy based multilayer extreme learning machine (FC-MELM) algorithm is proposed to handle the classification of datasets which are corrupted by impulsive noises or outliers. The contributions of this paper are three-folds: (1) The MSE based reconstruction loss is replaced by the correntropy based loss function; In this way, the robustness of the ELM based multilayer algorithms is enhanced. (2) The traditional 1-based sparsity penalty term is also replaced by a correntropy-based sparsity penalty term, which can further improve the performance of the proposed algorithm with a sparser representation of the data. The combination of (1) and (2) provides the correntropy-based ELM autoencoder. (3) The FC-MELM is proposed by using the correntropy-based ELM autoencoder as a building block. It is notable that the FC-MELM is trained in a forward manner, which means fine-tuning procedure is not required. Thus, the FC-MELM has great advantage in learning efficiently when compared with traditional deep learning algorithms. The good property of the proposed algorithm is confirmed by the experiments on well-known benchmark datasets, including the MNIST datasets, the NYU Object Recognition Benchmark dataset, and the Moore network traffic dataset. Finally, the proposed FC-MELM algorithm is applied to address Computer Aided Cancer Diagnosis. Experiments conducted on the well-known Wisconsin Breast Cancer Data (Diagnostic) dataset are presented and show that the proposed FC-MELM outperforms state-of-the-art methods in solving computer aided cancer diagnosis problems.

show abstract

ELM based signature for texture classification

Cited by 47 publications

References 33 publications

Texture classification using convolutional neural network optimized with whale optimization algorithm

Texture classification using convolutional neural network optimized with whale optimization algorithm

Research of Planetary Gear Fault Diagnosis Based on Multi-Scale Fractal Box Dimension of CEEMD and ELM

Correntropy-based robust multilayer extreme learning machines

Contact Info

Product

Resources

About