Exploring ELM-based spatial–spectral classification of hyperspectral images

Heras, Dora B.; Argüello, Francisco; Quesada-Barriuso, Pablo

doi:10.1080/01431161.2013.869633

Cited by 52 publications

(18 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…2. Where input layer has J neurons, hidden layer has H neurons, and output layer has K neurons [18].…”

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

“…2. Where input layer has J neurons, hidden layer has H neurons, and output layer has K neurons [18].…”

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

show abstract

“…When satellite data have some noise or some atmospheric errors due to sensor problem as well as if the training samples are less in number, SVM algorithm gives the better and accurate results as compared to other conventional algorithms. Therefore, SVM has been a very popular method [7], [10], [11], [12] for last decade.…”

Section: B Hyperspectral Image Classification Using Svmmentioning

confidence: 99%

“…Development of new techniques has been the main objective [5], [6]. Recently, support vector machine based techniques have been used for Hyperspectral remote sensing data to various fields with minimum training pixels [7]. The present paper reports study based on SVM method to extract information related to soil using data acquired from Hyperspectral remote sensing.…”

Section: Introductionmentioning

confidence: 99%

Soil type classification and mapping using hyperspectral remote sensing data

Vibhute

Kale

Dhumal

et al. 2015

2015 International Conference on Man and Machine Interfacing (MAMI)

View full text Add to dashboard Cite

Hyperspectral remote sensing has been widely used for mapping of soil, its classification and also its texture description. It is beneficial in urban and rural management. The present work reports the study regarding classification soil analysis using Support Vector Machine (SVM). Hyperion Hyperspectral satellite data with 10nm fine spectral resolution of Phulambri region of Aurangabad district of Maharashtra (India) which lies between 20° 06' N latitude and 75° 25' E longitude was used for soil classification. Gaussian Radial Basis Function (RBF) kernel of SVM was used to extract five various soils types and achieved overall accuracy of 71.18% and with Kappa Value of 0.57 having sufficient training samples. It was found that the soil of the region may be classified in five categories. The maximum area (51 %) was covered by the brown sandy soil, whereas the minimum (.02%) by gray clay soil. The result is of great significance for soil analysis of very complex region without reduction of dimensionality in satellite data.

show abstract

“…While the pixel-based techniques, such as the classic Maximum Likelihood or Support Vector Machines (SVM) classifiers, primarily emphasize the independence of pixels, the spectral-spatial frameworks such as Geographic Object-Based Image Analysis (GEOBIA) (Blaschke et al, 2014) or Minimum Spanning Forest (MSF) (Tarabalka et al, 2010a) classifiers employ both the spectral characteristics and the spatial context of the pixels. Many researchers have demonstrated that the use of spectral-spatial information improves the classification results, compared to the use of spectral data alone, in hyperspectral imagery (Plaza et al, 2009;Li et al, 2010;Fauvel et al, 2012;Heras et al, 2014;Xu et al, 2014).…”

Section: Introductionmentioning

confidence: 99%

An Extended Spectral–spatial Classification Approach for Hyperspectral Data

Akbari

2017

ISPRS Ann. Photogramm. Remote Sens. Spatial Inf. Sci.

View full text Add to dashboard Cite

ABSTRACT:In this paper an extended classification approach for hyperspectral imagery based on both spectral and spatial information is proposed. The spatial information is obtained by an enhanced marker-based minimum spanning forest (MSF) algorithm. Three different methods of dimension reduction are first used to obtain the subspace of hyperspectral data: (1) unsupervised feature extraction methods including principal component analysis (PCA), independent component analysis (ICA), and minimum noise fraction (MNF); (2) supervised feature extraction including decision boundary feature extraction (DBFE), discriminate analysis feature extraction (DAFE), and nonparametric weighted feature extraction (NWFE); (3) genetic algorithm (GA). The spectral features obtained are then fed into the enhanced marker-based MSF classification algorithm. In the enhanced MSF algorithm, the markers are extracted from the classification maps obtained by both SVM and watershed segmentation algorithm. To evaluate the proposed approach, the Pavia University hyperspectral data is tested. Experimental results show that the proposed approach using GA achieves an approximately 8% overall accuracy higher than the original MSF-based algorithm.

show abstract

Exploring ELM-based spatial–spectral classification of hyperspectral images

Cited by 52 publications

References 35 publications

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

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

Soil type classification and mapping using hyperspectral remote sensing data

An Extended Spectral–spatial Classification Approach for Hyperspectral Data

Contact Info

Product

Resources

About