61 research outputs found
A comparison of differential evolution and Harmony Search methods for SVM model selection in hyperspectral image classification
No full text36th IEEE International Geoscience and Remote Sensing Symposium (IGARSS) -- JUL 10-15, 2016 -- Beijing, PEOPLES R CHINACeylan, O/0000-0002-0892-6380; Kaya, Gulsen Taskin/0000-0002-2294-4462Support vector machines is a very popular method in classification of hyperspectral images due to their good generalization capability even with a limited number of training datasets. However, the performance of SVM strongly depends on selection of kernel parameters when RBF kernel is used. In order to achieve a high classification performance, the kernel parameters, that are the value of regularization term and kernel width, should optimally be chosen. In this work, the use of recently developed evolutionary optimization methods, harmony search and differential evolution methods, are investigated in the context of hyperspectral image classification for the first time in this paper. The experimental results showed that these methods provide fast and accurate results in comparison to classical grid search approach.Inst Elect & Elect Engineers, Inst Elect & Elect Engineers, Geoscience & Remote Sensing Soc, NSS
Comparison of Psychometric Properties of the Dual-Task Timed Up-And Test (Cognitive) and the 3-M Walk Backward Test in Community-Dwelling Stroke Patients
No full textBaskan, Emre/0000-0001-7069-0658; Taskin, Gulsen/0000-0002-2016-4147; Yesil, Hilal/0000-0002-8291-1515; Eken, Fatma/0000-0003-2975-7480Background: There is a need for practical, easy-to-use and accurately assessing balance tools in stroke patients. Objectives: This study aimed to compare the psychometric properties of the dual-task Timed Up-and-Go test (cognitive) (DTUG) and the 3-m walk backward test (3MBWT) in stroke patients. Methods: This study evaluated the practicality, validity, and reliability of the DTUG and the 3MBWT. The test-retest method was used for reliability. The Modified Four Square Step Test (MFSST), the Timed Up-and-Go (TUG), and Berg Balance Scale (BBS) were administered for concurrent validity. A cutoff value was calculated to discriminate between fallers and non-fallers. Results: The mean practicality times of the tests were 63.58 +/- 47.32 sec for DTUG and 37.42 +/- 24.036 sec for 3MBWT. Intraclass correlation coefficient of the DTUG and 3MBWT were 0.977, 0.964, respectively which showed excellent test - retest reliability. The DTUG demonstrated strong/very strong correlations with the MFSST (r = 0.724, p 0.001), TUG (r = 0.909, p 0.001), and BBS (r = -0.740, p 0.001). The 3MBWT showed strong correlations with the MFSST (r = 0.835, p 0.001), the TUG (r = 0.799, p 0.001), and the BBS (r = -0.740, p 0.001). The cutoff point was 36.945 s for DTUG and 14.605 s for 3MBWT. Conclusions: The 3MBWT was a more practical test than the DTUG; however, the DTUG was more discriminative than the 3MBWT in identifying fallers after stroke
A Feature Selection Method via Graph Embedding and Global Sensitivity Analysis
No full textFeature selection (FS) has been a prominent research topic for a long time, not only in hyperspectral image (HSI) classification but also in other related fields. It has gained even more popularity recently, especially with the growing interest in explainable artificial intelligence (AI) studies. The literature on FS is extensively studied not only in remote sensing but also in the domain of computer science. However, most of the conventional approaches ignore information about the manifold structure of the data, which might be critical, especially for the analysis of hyperspectral data due to their complex nonlinear structure. This study introduces an FS approach based on graph embedding (GE) and global sensitivity analysis, utilizing the first-order terms of the high dimensional model representation (HDMR). The effectiveness of the proposed method is analyzed on four hyperspectral datasets utilizing some evaluation criteria, including classification accuracy and clustering quality, and compared to seven state-of-the-art FS methods. The results show that the proposed method typically outperforms the others and is notably more computationally efficient
A comprehensive evaluation of feature selection algorithms in hyperspectral image classification
No full textNowadays, hyperspectral images have been an attractive subject for many researches in remote sensing area since they provide abundant information due to their wide range of spectral bands. On the one hand, classification plays a significant role in extraction of information for different applications. On the other hand, providing a huge amount of data by hyperspectral images may lead to complexity and bring some redundancy due to high correlation among the hyperspectral bands. In order to reduce the redundancy, feature selection algorithms have been carried out to remove irrelevant features to efficiently use the classifier and to achieve a significant accuracy with minimum costs. In this work, a comprehensive analysis of weil known feature selection algorithms will be conducted with different classifiers on some commonly used hyperspectral datasets. The contribution of this paper is to present an extensive benchmark study on using feature selection algorithms with hyperspectral dataset. The analysis of feature selection algorithms will be carried out by considering number of training sampies, classification accuracy and computational time
Optimization of Graph Affinity Matrix with Heuristic Methods in Dimensionality Reduction of Hypespectral Images
No full textFeature Selection Using Self Organizing Map Oriented Evolutionary Approach
No full textHyperspectral images are the multidimensional matrices consisting of hundreds of spectral feature vectors. Thanks to these large number of features, the objects on the Earth having similar spectral characteristics can easily be distinguished from each other. However, the high correlation and the noise between these features cause a significant decrease in the classification performances, especially in the supervised classification tasks. In order to overcome these problems, which is known in the literature as Hughes's effects or curse of dimensionality, dimensionality reduction techniques have frequently been used. Feature selection and feature extraction methods are the ones used for this purpose. The feature selection methods aim to remove the features, including high correlation and noise, out of the original feature set. In other words, a subset of relevant features that have the ability to distinguish the objects is determined. The feature extraction methods project the high dimensional space into a lower-dimensional feature space based on some optimization criterion, and hence they distort the original characteristic of the dataset. Therefore, the feature selection methods are more preferred than the feature extraction methods since they preserve the originality of the dataset. Based on this motivation, an evolutionary based optimization algorithm utilizing self organizing map was accordingly modified to provide a new feature selection method for the classification of hyperspectral images. The proposed method was compared to well-known feature selection methods in the classification of two hyperspectral datasets: Botswana and Indian Pines. According to the preliminary results, the proposed method achieves higher performance over other feature selection methods with a very less number of features.Conference Proceedings Citation Index - Scienc
EXTENDING OUT-OF-SAMPLE MANIFOLD LEARNING VIA META-MODELLING TECHNIQUES
No full textUnsupervised manifold learning has become accepted as an important tool for reducing dimensionality of a data set by finding its meaningful low dimensional representation lying on an unknown nonlinear subspace. Most manifold learning methods only embed an existing data set, but do not provide an explicit mapping function for novel out-of-sample data, thereby potentially resulting in an ineffective tool for classification purposes. To address this issue, out-of-sample extension methods have been introduced to generalize an existing embedding to new samples. In this work, a meta-modelling method called High Dimensional Model Representation (HDMR) is firstly implemented as a nonlinear multivariate regression for the out-of-sample problem for non-parametric unsupervised manifold learning algorithms. Several experiments show that the proposed method outperforms several state-of-the-art out-of-sample extension methods in terms of generalization to new samples for classification experiments on two remote sensing hyperspectral data sets
An Out-of-Sample Extension to Manifold Learning via Meta-Modeling
No full textUnsupervised manifold learning has become accepted as an important tool for reducing dimensionality of a dataset by finding its meaningful low-dimensional representation lying on an unknown nonlinear subspace. Most manifold learning methods only embed an existing dataset but do not provide an explicit mapping function for novel out-of-sample data, thereby potentially resulting in an ineffective tool for classification purposes, particularly for iterative methods, such as active learning. To address this issue, out-of-sample extension methods have been introduced to generalize an existing embedding of new samples. In this paper, a novel out-of-sample method is introduced by utilizing high dimensional model representation (HDMR) as a nonlinear multivariate regression with the Tikhonov regularizer for unsupervised manifold learning algorithms. The proposed method was extensively analyzed using illustrative datasets sampled from known manifolds. Several experiments with 3D synthetic datasets and face recognition datasets were also conducted, and the performance of the proposed method was compared to several well-known out-of-sample methods. The results obtained with locally linear embedding (LLE), Laplacian Eigenmaps (LE), and t-distributed stochastic neighbor embedding (t-SNE) showed that the proposed method achieves competitive even better performance than the other out-of-sample methods
- …
