XCS and GALE: A Comparative Study of Two Learning Classifier Systems on Data Mining

Mansilla, Ester Bernadó i; Llorà, Xavier; Guiu, Josep Maria Garrell i

doi:10.1007/3-540-48104-4_8

Cited by 92 publications

(42 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The common approach used by many researchers in such cases is to use pairwise comparisons between all the classifiers using commonly used statistical tests such as paired t-test or wilcoxon signed rank test and to report significant differences between the pairs [6] [8]. Demsar has criticized the misuse of these approaches for multiple classifier comparisons because: (1) none of them reasons about comparing the means of more than two random variables, and (2) a certain portion of null hypothesis is always rejected due to a random chance by doing so [25].…”

Section: Statistical Analysis Of Resultsmentioning

confidence: 99%

“…In [7], the authors compared the Pittsburgh and Michigan style classifier using XCS and GAssist on 13 publicly available datasets to reveal important differences between the two systems. The comparative study performed in [8] between evolutionary algorithms (XCS and Gale) and non-evolutionary algorithms (instance based, decision trees, rule-learning, statistical models and support vector machines) on several datasets suggests evolutionary algorithms as more suitable for data mining and classification. The results of the experiments carried in [9] show better classification accuracy for well-known ant colony inspired, Ant-Miner, compared with C4.5 on 4 biomedical datasets.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Classification Potential vs. Classification Accuracy: A Comprehensive Study of Evolutionary Algorithms with Biomedical Datasets

Tanwani

Farooq

2010

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract. Biomedical datasets pose a unique challenge for machine learning and data mining techniques to extract accurate, comprehensible and hidden knowledge from them. In this paper, we investigate the role of a biomedical dataset on the classification accuracy of an algorithm. To this end, we quantify the complexity of a biomedical dataset in terms of its missing values, imbalance ratio, noise and information gain. We have performed our experiments using six wellknown evolutionary rule learning algorithms -XCS, UCS, GAssist, cAnt-Miner, SLAVE and Ishibuchi -on 31 publicly available biomedical datasets. The results of our experiments and statistical analysis show that GAssist gives better classification results on majority of biomedical datasets among the compared schemes but cannot be categorized as the best classifier. Moreover, our analysis reveals that the nature of a biomedical dataset -not the selection of evolutionary algorithm -plays a major role in determining the classification accuracy of a dataset. We further show that noise is a dominating factor in determining the complexity of a dataset and it is inversely proportional to the classification accuracy of all evaluated algorithms. Towards the end, we provide researchers with a metaclassification model that can be used to determine the classification potential of a dataset on the basis of its complexity measures.

show abstract

Section: Statistical Analysis Of Resultsmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Classification Potential vs. Classification Accuracy: A Comprehensive Study of Evolutionary Algorithms with Biomedical Datasets

Tanwani

Farooq

2010

Lecture Notes in Computer Science

View full text Add to dashboard Cite

show abstract

“…Soon after, John Holmes initiated a lineage of LCS designed for epidemiological surveillance and knowledge discovery which included BOOLE++ [81], EpiCS [82], and most recently EpiXCS [143]. Similar applications include [93,95,130,142,[185][186][187], all of which examined the Wisconsin breast cancer data taken from the UCI repository [188]. LCSs have also been applied to protein structure prediction [131,149,154], diagnostic image classification [158,189], and promoter region identification [190].…”

Section: Biological Applicationsmentioning

confidence: 99%

Learning Classifier Systems: A Complete Introduction, Review, and Roadmap

Urbanowicz

Moore

2009

Journal of Artificial Evolution and Applications

223

131

View full text Add to dashboard Cite

If complexity is your problem, learning classifier systems (LCSs) may offer a solution. These rule-based, multifaceted, machine learning algorithms originated and have evolved in the cradle of evolutionary biology and artificial intelligence. The LCS concept has inspired a multitude of implementations adapted to manage the different problem domains to which it has been applied (e.g., autonomous robotics, classification, knowledge discovery, and modeling). One field that is taking increasing notice of LCS is epidemiology, where there is a growing demand for powerful tools to facilitate etiological discovery. Unfortunately, implementation optimization is nontrivial, and a cohesive encapsulation of implementation alternatives seems to be lacking. This paper aims to provide an accessible foundation for researchers of different backgrounds interested in selecting or developing their own LCS. Included is a simple yet thorough introduction, a historical review, and a roadmap of algorithmic components, emphasizing differences in alternative LCS implementations.

show abstract

“…Also, each attribute ranges between 1 and 10. Table 3 [21] shows an example of the results of XCS prediction accuracy over the WBC dataset. It is clear that the result of 96.4±2.5 (the average accuracy and standard deviation) compared to other learning algorithms illustrates the efficiency and ability of XCS to tackle real complex problems.…”

Section: Wbc Datasetmentioning

confidence: 99%