Assessing the quality of heathland vegetation by classification of hyperspectral data using spatial information

2009 ◽  
Author(s):  
G. Thoonen ◽  
J. Vanden Borre ◽  
S. De Backer ◽  
P. Scheunders
Keyword(s):  
Spatial Information ◽  
Hyperspectral Data ◽  
Heathland Vegetation

scholarly journals SPECTRAL-SPATIAL CLASSIFICATION OF HYPERSPECTRAL IMAGERY USING NEURAL NETWORK ALGORITHM AND HIERARCHICAL SEGMENTATION

2019 ◽  
Vol XLII-2/W12 ◽  
pp. 1-5
Author(s):  
D. Akbari ◽  
M. Moradizadeh ◽  
M. Akbari
Keyword(s):  
Neural Network ◽  
Spatial Information ◽  
Hyperspectral Data ◽  
Support Vector ◽  
Washington Dc ◽  
Hierarchical Segmentation ◽  
Vector Machines ◽  
Neural Network Algorithm ◽  
New Framework

<p><strong>Abstract.</strong> This paper describes a new framework for classification of hyperspectral images, based on both spectral and spatial information. The spatial information is obtained by an enhanced Marker-based Hierarchical Segmentation (MHS) algorithm. The hyperspectral data is first fed into the Multi-Layer Perceptron (MLP) neural network classification algorithm. Then, the MHS algorithm is applied in order to increase the accuracy of less-accurately classified land-cover types. In the proposed approach, the markers are extracted from the classification maps obtained by MLP and Support Vector Machines (SVM) classifiers. Experimental results on Washington DC Mall hyperspectral dataset, demonstrate the superiority of proposed approach compared to the MLP and the original MHS algorithms.</p>

scholarly journals SPECTRAL-SPATIAL CLASSIFICATION OF HYPERSPECTRAL IMAGERY USING A HYBRID FRAMEWORK

2019 ◽  
Vol XLII-4/W18 ◽  
pp. 41-44
Author(s):  
D. Akbari ◽  
M. Moradizadeh
Keyword(s):  
Spatial Information ◽  
Hyperspectral Data ◽  
Hyperspectral Images ◽  
Support Vector ◽  
Quebec City ◽  
Spectral Variability ◽  
Hierarchical Segmentation ◽  
Spectral Identification ◽  
Vector Machines

Abstract. Hyperspectral Images are worthwhile data for many processing algorithms (e.g. Dimensionality Reduction, Target Detection, Change Detection, Classification and Unmixing). Classification is a key issue in processing hyperspectral images. Spectral-identification-based algorithms are sensitive to spectral variability and noise in acquisition. There are many algorithms for classification. This paper describes a new framework for classification of hyperspectral images, based on both spectral and spatial information. The spatial information is obtained by an enhanced Marker-based Hierarchical Segmentation (MHS) algorithm. The hyperspectral data is first fed into the Multi-Layer Perceptron (MLP) neural network classification algorithm. Then, the MHS algorithm is applied in order to increase the accuracy of less-accurately classified land-cover types. In the proposed approach, the markers are extracted from the classification maps obtained by MLP and Support Vector Machines (SVM) classifiers. Experimental results on Quebec City hyperspectral dataset, demonstrate that the proposed approach achieves approximately 9% and 5% better overall accuracy than the MLP and the original MHS algorithms respectively.

scholarly journals A NEW SPECTRAL-SPATIAL FRAMEWORK FOR CLASSIFICATION OF HYPERSPECTRAL DATA

2017 ◽  
Vol IV-4/W4 ◽  
pp. 43-46
Author(s):  
D. Akbari
Keyword(s):  
Spatial Information ◽  
Hyperspectral Data ◽  
Hyperspectral Images ◽  
Land Cover Mapping ◽  
Binary Classifier ◽  
Accuracy Class ◽  
Acceptable Accuracy ◽  
Svm Algorithm ◽  
Minimum Spanning Forest

In this paper, an innovative framework, based on both spectral and spatial information, is proposed. The objective is to improve the classification of hyperspectral images for high resolution land cover mapping. The spatial information is obtained by a marker-based Minimum Spanning Forest (MSF) algorithm. A pixel-based SVM algorithm is first used to classify the image. Then, the marker-based MSF spectral-spatial algorithm is applied to improve the accuracy for classes with low accuracy. The marker-based MSF algorithm is used as a binary classifier. These two classes are the low accuracy class and the remaining classes. Finally, the SVM algorithm is trained for classes with acceptable accuracy. To evaluate the proposed approach, the Berlin hyperspectral dataset is tested. Experimental results demonstrate the superiority of the proposed method compared to the original MSF-based approach. It achieves approximately 5&amp;thinsp;% higher rates in kappa coefficients of agreement, in comparison to the original MSF-based method.

scholarly journals SPECTRAL-SPATIAL CLASSIFICATION OF HYPERSPECTRAL IMAGERY USING A HYBRID FRAMEWORK

2019 ◽  
Vol XLII-3/W6 ◽  
pp. 541-544
Author(s):  
D. Akbari
Keyword(s):  
Spatial Information ◽  
Hyperspectral Data ◽  
Support Vector ◽  
Washington Dc ◽  
Hierarchical Segmentation ◽  
Neural Network Classification ◽  
Vector Machines ◽  
Hybrid Framework ◽  
New Framework

<p><strong>Abstract.</strong> This paper describes a new framework for classification of hyperspectral images, based on both spectral and spatial information. The spatial information is obtained by an enhanced Marker-based Hierarchical Segmentation (MHS) algorithm. The hyperspectral data is first fed into the Multi-Layer Perceptron (MLP) neural network classification algorithm. Then, the MHS algorithm is applied in order to increase the accuracy of less-accurately classified land-cover types. In the proposed approach, the markers are extracted from the classification maps obtained by MLP and Support Vector Machines (SVM) classifiers. Experimental results on Washington DC Mall hyperspectral dataset, demonstrate the superiority of proposed approach compared to the MLP and the original MHS algorithms.</p>

scholarly journals A NEW SPECTRAL-SPATIAL FRAMEWORK FOR CLASSIFICATION OF HYPERSPECTRAL DATA

2017 ◽  
Vol XLII-4/W5 ◽  
pp. 7-10
Author(s):  
D. Akbari
Keyword(s):  
Spatial Information ◽  
Hyperspectral Data ◽  
Hyperspectral Images ◽  
Land Cover Mapping ◽  
Binary Classifier ◽  
Accuracy Class ◽  
Acceptable Accuracy ◽  
Svm Algorithm ◽  
Minimum Spanning Forest

In this paper, an innovative framework, based on both spectral and spatial information, is proposed. The objective is to improve the classification of hyperspectral images for high resolution land cover mapping. The spatial information is obtained by a marker-based Minimum Spanning Forest (MSF) algorithm. A pixel-based SVM algorithm is first used to classify the image. Then, the marker- based MSF spectral-spatial algorithm is applied to improve the accuracy for classes with low accuracy. The marker-based MSF algorithm is used as a binary classifier. These two classes are the low accuracy class and the remaining classes. Finally, the SVM algorithm is trained for classes with acceptable accuracy. To evaluate the proposed approach, the Berlin hyperspectral dataset is tested. Experimental results demonstrate the superiority of the proposed method compared to the original MSF-based approach. It achieves approximately 5&amp;thinsp;% higher rates in kappa coefficients of agreement, in comparison to the original MSF-based method.

Automatic tumor tissue classification of oncological esophageal resectates based on hyperspectral data

2019 ◽  
Author(s):  
M Maktabi ◽  
H Köhler ◽  
R Thieme ◽  
JP Takoh ◽  
SM Rabe ◽  
...  
Keyword(s):  
Tumor Tissue ◽  
Hyperspectral Data ◽  
Tissue Classification

Dynamics of the processes in metal machining

1998 ◽  
Vol 2 ◽  
pp. 115-122
Author(s):  
Donatas Švitra ◽  
Jolanta Janutėnienė
Keyword(s):  
High Frequency ◽  
Machine Tools ◽  
Metal Cutting ◽  
Cutting Tool ◽  
Low Frequency ◽  
Metal Cutting Machine ◽  
Cutting Machine ◽  
Metal Machining

In the practice of processing of metals by cutting it is necessary to overcome the vibration of the cutting tool, the processed detail and units of the machine tool. These vibrations in many cases are an obstacle to increase the productivity and quality of treatment of details on metal-cutting machine tools. Vibration at cutting of metals is a very diverse phenomenon due to both it’s nature and the form of oscillatory motion. The most general classification of vibrations at cutting is a division them into forced vibration and autovibrations. The most difficult to remove and poorly investigated are the autovibrations, i.e. vibrations arising at the absence of external periodic forces. The autovibrations, stipulated by the process of cutting on metalcutting machine are of two types: the low-frequency autovibrations and high-frequency autovibrations. When the low-frequency autovibration there appear, the cutting process ought to be terminated and the cause of the vibrations eliminated. Otherwise, there is a danger of a break of both machine and tool. In the case of high-frequency vibration the machine operates apparently quiently, but the processed surface feature small-sized roughness. The frequency of autovibrations can reach 5000 Hz and more.

Paepalanthus fabianeae (Eriocaulaceae): A New Microendemic Species from a Morphologically Coherent Clade

2020 ◽  
Vol 45 (4) ◽  
pp. 794-801
Author(s):  
Caroline Oliveira Andrino ◽  
Marcelo Fragomeni Simon ◽  
Jair Eustáquio Quintino Faria ◽  
André Luiz da Costa Moreira ◽  
Paulo Takeo Sano
Keyword(s):  
New Species ◽  
Iucn Red List ◽  
Phylogenetic Position ◽  
Similar Species ◽  
Infrageneric Classification ◽  
Espinhaço Range ◽  
Nuclear Its ◽  
Two Populations

Abstract—We describe and illustrate Paepalanthus fabianeae, a new species of Eriocaulaceae from the central portion of the Espinhaço Range in Minas Gerais, Brazil. Previous phylogenetic evidence based on analyses of nuclear (ITS and ETS) and plastid (trnL-trnF and psba-trnH) sequences revealed P. fabianeae as belonging to a strongly supported and morphologically coherent clade containing five other species, all of them microendemic, restricted to the Espinhaço range. Due to the infrageneric classification of Paepalanthus being highly artificial, we preferred not assigning P. fabianeae to any infrageneric group. Paepalanthus fabianeae is known from two populations growing in campos rupestres (highland rocky fields) in the meridional Espinhaço Range. The species is characterized by pseudodichotomously branched stems, small, linear, recurved, and reflexed leaves, urceolate capitula, and bifid stigmas. Illustrations, photos, the phylogenetic position, and a detailed description, as well as comments on habitat, morphology, and affinities with similar species are provided. The restricted area of occurrence allied with threats to the quality of the habitat, mainly due to quartzite mining, justifies the preliminary classification of the new species in the Critically Endangered (CR) category using the guidelines and criteria of the IUCN Red List.

MEDIATEXT IS A TOOL THAT DETERMINES THE QUALITY OF INFORMATION

2020 ◽  
Vol 6 (3) ◽  
pp. 158-164
Author(s):  
Navruza Yakhyayeva ◽  
Keyword(s):  
Functional Properties ◽  
Linguistic Features ◽  
Text Linguistics ◽  
Quality Of Information ◽  
The Creation ◽  
Linguistic Units ◽  
Scientific Classification

The quality and content of information in the article media text is based on scientific classification of linguistic features. The study of functional styles of speech, the identification of their linguistic signs, the discovery of the functional properties of linguistic units and their separation on the basis of linguistic facts is one of thetasks that modern linguistics is waiting for a solution. Text Linguistics, which deals with the creation, modeling of its structure and the study of the process of such activity, is of interest to journalists today as a science.

IMPROVEMENT OF CLASSIFICATION OF FACTORS AFFECTING THE QUALITY OF SILICON CONNECTIONS IN SEWING PRODUCTS

2019 ◽  
pp. 86-88
Author(s):  
R. H. Batirova ◽  
S. S. Tashpulatov ◽  
I. V. Cherunova ◽  
M. A. Mansurova ◽  
S. L. Matismailov
Keyword(s):  
Factors Affecting
Sign in / Sign up

Export Citation Format

Share Document