Construction of fuzzy classification systems with rectangular fuzzy rules using genetic algorithms

Ishibuchi, Hisao; Nozaki, Kengo; Yamamoto, Naohisa; Tanaka, Hideo

doi:10.1016/0165-0114(94)90022-1

Cited by 158 publications

(53 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…A large number of supervised classification methods have been developed, and they include Maximum Likelihood Classifier (MLC) [Settle and Briggs, 1987;Shalaby and Tateishi, 2007], Minimum Distance-to-Means Classifier [Atkinson and Lewis, 2000;Dwivedi et al, 2004], Mahalanobis Distance Classifier [Deer and Eklund, 2003;Dwivedi et al, 2004], Parallelepiped [Perakis et al, 2000] and K-Nearest Neighbors Classifier [Zhu and Basir, 2005;Zhang et al, 2008], etc. Recently, machine learning techniques have also been developed to refine the knowledge learning process [Mountrakis et al, 2011], and these methods include artificial neural network [Kavzoglu and Mather, 2003], classification tree [Friedl and Brodley, 1997;Mclver and Friedl, 2002;Jiang et al, 2012], random forests [Gislason et al, 2006], support vector machine [Gualtieri and Cromp, 1999;Huang et al, 2002;Pal and Mather, 2005;Marconcini et al, 2009], and genetic algorithms [Ishibuchi et al, 1994;Tseng et al, 2008].…”

Section: Pixel-wise Image Classificationmentioning

confidence: 99%

A Review of Remote Sensing Image Classification Techniques: the Role of Spatio-contextual Information

Zang

Zhang

et al. 2014

European Journal of Remote Sensing

403

234

View full text Add to dashboard Cite

This paper reviewed major remote sensing image classification techniques, including pixel-wise, sub-pixel-wise, and object-based image classification methods, and highlighted the importance of incorporating spatio-contextual information in remote sensing image classification. Further, this paper grouped spatio-contextual analysis techniques into three major categories, including 1) texture extraction, 2) Markov random fields (MRFs) modeling, and 3) image segmentation and object-based image analysis. Finally, this paper argued the necessity of developing geographic information analysis models for spatial-contextual classifications using two case studies.

show abstract

Section: Pixel-wise Image Classificationmentioning

confidence: 99%

A Review of Remote Sensing Image Classification Techniques: the Role of Spatio-contextual Information

Zang

Zhang

et al. 2014

European Journal of Remote Sensing

403

234

View full text Add to dashboard Cite

show abstract

“…In this paper, a certainty degree measure is proposed which extends the one presented in [9], adapted to rules with fuzzy consequents.…”

Section: Learning Maximal Structure Fuzzy Rulesmentioning

confidence: 99%

FRIwE: Fuzzy Rule Identification With Exceptions

Carmona

Castro

Zurita

2004

IEEE Trans. Fuzzy Syst.

View full text Add to dashboard Cite

Abstract-In this paper, the FRIwE method is proposed to identify fuzzy models from examples. Such a method has been developed trying to achieve a double goal:accuracy and interpretability. In order to do that, maximal structure fuzzy rules are firstly obtained based on a method proposed by Castro et al. In a second stage, the conflicts generated by the maximal rules are solved, thus increasing the model accuracy. The resolution of conflicts are carried out by including exceptions in the rules. This strategy has been identified by psychologists with the learning mechanism employed by the human being, thus improving the model interpretability. Besides, in order to improve the interpretability even more, several methods are presented based on reducing and merging rules and exceptions in the model. The exhaustive use of the training examples gives the method a special suitability for problems with small training sets or high dimensionality. Finally, the method is applied to an example in order to analyze the achievement of the goals.

show abstract

“…The class predicted by the rule is assigned to the attributes. If fatality is high and DRI is medium, then severity is extreme And If fatality is low and DRI is low then severity is severe In a more complex space with more dimensions, if we have K fuzzy subsets , … , , a triangular membership function [21] can be calculated based on formula (4) where (a) and (b) respectively are the upper and lower bound in each categories of input (table 1).…”

Section: Fuzzy Classification Systemmentioning

confidence: 99%

A disaster severity assessment decision support tool for reducing the risk of failure in response operations

2014

View full text Add to dashboard Cite

After a disaster strikes, the disaster severity needs to be estimated in order to provide an adequate humanitarian response. The decision makers need to decide quickly about the requisite supplies and bespoke teams based on the scale and nature of the disruption. The failure of the severity assessment may impose risk to the success of the response operations, leading to the loss of lives at worst. The existing severity assessment tools employ various criteria such as intensity, frequency, vulnerability and capability. However a framework which differentiates between the impact of disasters on communities with different coping capabilities, is missing. For example, an equally intense earthquake affects Japan differently from Haiti, due to the difference in the coping capabilities of the two nations. To that end this paper investigates the records of previous disasters to provide a holistic Disaster Severity Assessment (DSA) tool. This decision support tool accommodates physical and socio-economic impacts of the disaster on the affected population. The assessment is based on six criteria including impact time, fatality, casualty, relative financial damage, Human Development Index (HDI) and Disaster Risk Index (DRI). The resulting decision support tool may be used to diagnose the severity of the disaster immediately after it strikes. It also is capable of accommodating the imprecise data by the means of a fuzzy classification system. This characteristic allows the decision maker to draw a realistic picture of the disaster response required based on the affected population capabilities and reduce the risk of failure in disaster response operations.

show abstract

Construction of fuzzy classification systems with rectangular fuzzy rules using genetic algorithms

Cited by 158 publications

References 15 publications

A Review of Remote Sensing Image Classification Techniques: the Role of Spatio-contextual Information

A Review of Remote Sensing Image Classification Techniques: the Role of Spatio-contextual Information

FRIwE: Fuzzy Rule Identification With Exceptions

A disaster severity assessment decision support tool for reducing the risk of failure in response operations

Contact Info

Product

Resources

About