scholarly journals Comparison of spatial classification rules with different conditional distributions of class label

2014 ◽  
Vol 19 (1) ◽  
pp. 109-117 ◽  
Author(s):  
Giedrius Stabingis ◽  
Kęstutis Dučinskas ◽  
Lijana Stabingienė
Keyword(s):  
Supervised Classification ◽  
Training Sample ◽  
Classification Rule ◽  
Correlated Noise ◽  
Classification Rules ◽  
Class Label ◽  
Spatial Classification ◽  
Spatially Correlated ◽  
Method Accuracy ◽  
Supervised Classification Methods

In this paper spatial classification rules based on Bayes discriminant functions are considered. The novelty of this work is that the statistical supervised classification method is improved by extending the influence of spatial correlation between observation to be classified and training sample. Such methods are used for data containing spatially correlated noise. Method accuracy is tested experimentally on artificially corrupted images. This classification rule with distance based conditional distribution for class label shows advantage against other classification rule ignoring such influence and against other commonly used supervised classification methods.

scholarly journals Application of spatial classification rules for remotely sensed images

2014 ◽  
Vol 55 ◽  
Author(s):  
Giedrius Stabingis ◽  
Lijana Stabingienė
Keyword(s):  
Classification Accuracy ◽  
Supervised Classification ◽  
Spatial Information ◽  
Gaussian Random Field ◽  
Remotely Sensed ◽  
Classification Rule ◽  
Classification Rules ◽  
Classification Methods ◽  
Remotely Sensed Images ◽  
Supervised Classification Methods

In this paper the remote sensed image classification example using spacial classification rule with distance (SCRD) is examined. This supervised classification method was first presented in paper [11]. This method is improved version of earlier method PBDF [4, 10, 9], during the classification it incorporates more spatial information. The advantage of this method is its ability to classify data which is corrupted by Gaussian random field and it is typical to remotely sensed images classified in this letter which are corrupted by clouds. Classification accuracy is compared with earlier method and with other commonly used supervised classification methods.

scholarly journals A New Classification Approach Based on Multiple Classification Rules

2014 ◽  
Vol 2014 ◽  
pp. 1-7 ◽  
Author(s):  
Zhongmei Zhou
Keyword(s):  
Classification Rule ◽  
Classification Rules ◽  
Associative Classification ◽  
New Classification ◽  
Class Label ◽  
Rule Based ◽  
Classification Approach ◽  
Minimum Support ◽  
Multiple Classification ◽  
Rule Set

A good classifier can correctly predict new data for which the class label is unknown, so it is important to construct a high accuracy classifier. Hence, classification techniques are much useful in ubiquitous computing. Associative classification achieves higher classification accuracy than some traditional rule-based classification approaches. However, the approach also has two major deficiencies. First, it generates a very large number of association classification rules, especially when the minimum support is set to be low. It is difficult to select a high quality rule set for classification. Second, the accuracy of associative classification depends on the setting of the minimum support and the minimum confidence. In comparison with associative classification, some improved traditional rule-based classification approaches often produce a classification rule set that plays an important role in prediction. Thus, some improved traditional rule-based classification approaches not only achieve better efficiency than associative classification but also get higher accuracy. In this paper, we put forward a new classification approach called CMR (classification based on multiple classification rules). CMR combines the advantages of both associative classification and rule-based classification. Our experimental results show that CMR gets higher accuracy than some traditional rule-based classification methods.

Self-Adaptive Weighting Text Association Categorization Algorithm Research

2010 ◽  
Vol 171-172 ◽  
pp. 246-251
Author(s):  
Liang Jun Li ◽  
Bin Zhang ◽  
Yuan Yuan Che ◽  
Ming Yang ◽  
Tie Nan Li
Keyword(s):  
Training Sample ◽  
Classification Rule ◽  
Classification Algorithms ◽  
Classification Rules ◽  
Sample Collection ◽  
Adaptive Weighting ◽  
Adjustment Factors ◽  
Weighing Method ◽  
The Stability ◽  
Self Adaptive

In text association classification research, feature distribution of the training sample collection impacts greatly on the classification results, even with a same classification algorithm classification results will have obvious differences using different sample collections. In order to solve the problem, the stability of association classification is improved by the weighing method in the paper, the design realizes the association classification algorithms (WARC) based on rule weight. In the WARC algorithm, this paper proposes the concept of classification rule intensity and gives the concrete formula. Using rule intensity defines the rule adjustment factors that adjust uneven classification rules. Experimental results show the accuracy of text classification can be improved obviously by self-adaptive weighting.

scholarly journals New Workflow of Plastic-Mulched Farmland Mapping using Multi-Temporal Sentinel-2 data

2019 ◽  
Vol 11 (11) ◽  
pp. 1353 ◽  
Author(s):  
Pengyu Hao ◽  
Zhongxin Chen ◽  
Huajun Tang ◽  
Dandan Li ◽  
He Li
Keyword(s):  
Supervised Classification ◽  
Vegetation Index ◽  
Near Infrared ◽  
Normalized Difference Vegetation Index ◽  
Training Sample ◽  
Plastic Film ◽  
Training Samples ◽  
Bare Land ◽  
Multi Temporal ◽  
Supervised Classification Methods

Using plastic film mulch on cropland improves crop yield in water-deficient areas, but the use of plastic film on cropland leads to soil pollution. The accurate mapping of plastic-mulched land (PML) is valuable for monitoring the environmental problems caused by the use of plastic film. The drawback of PML mapping is that the detectable period of PML changes among the fields, which causes uncertainty when supervised classification methods are used to identify PML. In this study, a new workflow which merging PML of multiple temporal phases (MTPML) is proposed. For each temporal phase, the “possible PML” is firstly generated, these “temporal possible PML” layers are then combined to generate the “possible PML” layer. Finally, the maximum normalized difference vegetation index (NDVI) of the growing season is used to remove the non-cropland pixels from the “possible PML layer,” and then generate PML images. When generating “temporal possible PML layers,” three new PML indices (PMLI with near-infrared bands known as PMLI_NIR, PMLI with shortwave infrared bands known as PMLI_SWIR, and Normalized Difference PMLI known as PMLI_ND) are proposed to separate PML from bare land at plastic film cover stage; and the “temporal possible PML layer” are identified by the threshold based method. To estimate the performance of the three PML indices, two other approaches, PMLI threshold and Random Forest (RF) are used to generate “temporal possible PML layer.” Finally, PML images generated from the five MTPML approaches are compared with the image time series supervised classification (SUPML) result. Two study regions, Hengshui (HS) and Guyuan (GY), are used in this study. PML identification models are generated using training samples in HS and the models are used for PML mapping in both study regions. The results showed that MTPML workflow outperformed SUPML with 3%–5% higher classification accuracy. The three proposed PML indices had higher separability and importance score for bare land and PML discrimination. Among the five approaches used to generate the “temporal possible PML layer,” PMLI_SWIR is the recommended approach because the PMLI_SWIR threshold approach is easy to implement and the accuracy is only slightly lower than the RF approach. It is notable that no training sample was used in GY and the accuracy of the MTPML approach was higher than 85%, which indicated that the rules proposed in this study are suitable for other study regions.

scholarly journals SEMI-SUPERVISED SPECTRAL-TEXTURE IMAGE CLASSIFICATION ALGORITHM

2019 ◽  
Vol 4 (1) ◽  
pp. 37-43
Author(s):  
Sergey Rylov
Keyword(s):  
Supervised Classification ◽  
Satellite Images ◽  
Spatial Information ◽  
Spectral Characteristics ◽  
Texture Features ◽  
Training Sample ◽  
Classification Algorithm ◽  
High Resolution Satellite Images ◽  
Texture Image Classification ◽  
Supervised Classification Methods

When classifying satellite images, training sample often turns out to be unrepresentative. This leads to low segmentation quality. In such conditions, it is advisable to use semi-supervised classification methods, which simultaneously utilize both training sample and unclassified data. At the same time, high resolution satellite images are characterized by high interclass heterogeneity of spectral characteristics, which demands to take spatial information into account. We propose a new semi-supervised classification algorithm for multispectral images, that utilizes both spectral and texture features. The use of the semi-supervised concept allows improving the classification quality when the amount of training sample is small. The results of experiments on model and satellite images confirming the effectiveness of the proposed algorithm are given.

scholarly journals Spatial classification rule with distance in three dimensional space

2016 ◽  
Vol 57 ◽  
Author(s):  
Giedrius Stabingis
Keyword(s):  
Spatial Information ◽  
Dimensional Space ◽  
Three Dimensional ◽  
Training Sample ◽  
Classification Rule ◽  
Coordinate Space ◽  
Spatial Classification ◽  
Similar Images ◽  
Three Dimensional Coordinate ◽  
Three Dimensional Space

Spatial Classification Rule with Distance (SCRD) method is used in two dimensional coordinate system, which limits the usage of existing spatial information in MRI, CT and other three dimensional (layered) images. The SCRD method is extended to be applied in three dimensional coordinate space. Artificial experiment is performed in order to show ability to use SCRD method with three dimensional medical or other similar images where training sample is available.

Quadratic Discriminant Analysis of Spatially Correlated Data

2001 ◽  
Vol 6 (2) ◽  
pp. 15-28 ◽  
Author(s):  
K. Dučinskas ◽  
J. Šaltytė
Keyword(s):  
Discriminant Function ◽  
Error Rate ◽  
Gaussian Random Field ◽  
Correlated Data ◽  
Covariance Matrices ◽  
Classification Rule ◽  
Spatial Correlations ◽  
Linear Quadratic ◽  
Spatial Correlation Function ◽  
Spatially Correlated

The problem of classification of the realisation of the stationary univariate Gaussian random field into one of two populations with different means and different factorised covariance matrices is considered. In such a case optimal classification rule in the sense of minimum probability of misclassification is associated with non-linear (quadratic) discriminant function. Unknown means and the covariance matrices of the feature vector components are estimated from spatially correlated training samples using the maximum likelihood approach and assuming spatial correlations to be known. Explicit formula of Bayes error rate and the first-order asymptotic expansion of the expected error rate associated with quadratic plug-in discriminant function are presented. A set of numerical calculations for the spherical spatial correlation function is performed and two different spatial sampling designs are compared.

AUTOMATIC ESTIMATION OF SPATIALLY CORRELATED NOISE VARIANCE IN SPECTRAL DOMAIN FOR IMAGES

2014 ◽  
Vol 73 (6) ◽  
pp. 511-527 ◽  
Author(s):  
V.V. Abramova ◽  
S. K. Abramov ◽  
V. V. Lukin ◽  
A. A. Roenko ◽  
Benoit Vozel
Keyword(s):  
Spectral Domain ◽  
Correlated Noise ◽  
Noise Variance ◽  
Spatially Correlated ◽  
Automatic Estimation ◽  
Spatially Correlated Noise

scholarly journals gbt-HIPS: Explaining the Classifications of Gradient Boosted Tree Ensembles

2021 ◽  
Vol 11 (6) ◽  
pp. 2511
Author(s):  
Julian Hatwell ◽  
Mohamed Medhat Gaber ◽  
R. Muhammad Atif Azad
Keyword(s):  
State Of The Art ◽  
Heuristic Method ◽  
Good Explanation ◽  
Classification Rule ◽  
Data Sets ◽  
Classification Models ◽  
Boundary Values ◽  
Class Label ◽  
Input Space ◽  
Boosted Tree

This research presents Gradient Boosted Tree High Importance Path Snippets (gbt-HIPS), a novel, heuristic method for explaining gradient boosted tree (GBT) classification models by extracting a single classification rule (CR) from the ensemble of decision trees that make up the GBT model. This CR contains the most statistically important boundary values of the input space as antecedent terms. The CR represents a hyper-rectangle of the input space inside which the GBT model is, very reliably, classifying all instances with the same class label as the explanandum instance. In a benchmark test using nine data sets and five competing state-of-the-art methods, gbt-HIPS offered the best trade-off between coverage (0.16–0.75) and precision (0.85–0.98). Unlike competing methods, gbt-HIPS is also demonstrably guarded against under- and over-fitting. A further distinguishing feature of our method is that, unlike much prior work, our explanations also provide counterfactual detail in accordance with widely accepted recommendations for what makes a good explanation.

Sign in / Sign up

Export Citation Format

Share Document