Using evolutionary algorithms as instance selection for data reduction in KDD: an experimental study

Cano, José-Ramón; Herrera, F.; Lozano, Manuel

doi:10.1109/tevc.2003.819265

Cited by 292 publications

(205 citation statements)

References 27 publications

Supporting

Mentioning

202

Contrasting

Unclassified

Order By: Relevance

“…Although the approach is promising, it is unclear when to stop the optimization for multi-class tasks (the authors terminated the evolution once 60 vectors from each category have been retrieved). Verbiest et al (2016) recently investigated the performance of different evolutionary techniques for selection of SVM training sets: (i) a standard genetic algorithm, (ii) the adaptive genetic algorithm, which dynamically updates the crossover threshold [only notably different parents can be crossed over (Eshelman 1991)], and (iii) the steady state genetic algorithm [two parents are selected to generate offspring (Cano et al 2003)]. Interestingly, the fitness involved not only the classification accuracy of the SVM classifier, but also the reduction ratio, indicating how much the input T has been shrunk.…”

Section: Evolutionary Methodsmentioning

confidence: 99%

Selecting training sets for support vector machines: a review

2018

View full text Add to dashboard Cite

Support vector machines (SVMs) are a supervised classifier successfully applied in a plethora of real-life applications. However, they suffer from the important shortcomings of their high time and memory training complexities, which depend on the training set size. This issue is especially challenging nowadays, since the amount of data generated every second becomes tremendously large in many domains. This review provides an extensive survey on existing methods for selecting SVM training data from large datasets. We divide the state-of-the-art techniques into several categories. They help understand the underlying ideas behind these algorithms, which may be useful in designing new methods to deal with this important problem. The review is complemented with the discussion on the future research pathways which can make SVMs easier to exploit in practice.

show abstract

Section: Evolutionary Methodsmentioning

confidence: 99%

Selecting training sets for support vector machines: a review

2018

View full text Add to dashboard Cite

show abstract

“…Another method related to the associates concept was the Iterative Case Filtering algorithm (ICF) proposed by [32]. In addition, evolutionary algorithms have been used for instance selection [54] [74] [37] [24] [138]. In [76] it was proposed a memetic algorithm, combining evolutionary algorithms and local search in the evolutive process, and [73] proposed the Clonal selection Algorithm (CSA), which is based on the artificial immune system approach.…”

Section: Wrapper Instance Selectionmentioning

confidence: 99%

A survey on pre-processing techniques: Relevant issues in the context of environmental data mining

Gibert

Sànchez–Marrè

Izquierdo

2016

AIC

View full text Add to dashboard Cite

One of the important issues related with all types of data analysis, either statistical data analysis, machine learning, data mining, data science or whatever form of data-driven modeling, is data quality. The more complex the reality to be analyzed is, the higher the risk of getting low quality data. Unfortunately real data often contain noise, uncertainty, errors, redundancies or even irrelevant information. Useless models will be obtained when built over incorrect or incomplete data. As a consequence, the quality of decisions made over these models, also depends on data quality. This is why pre-processing is one of the most critical steps of data analysis in any of its forms. However, pre-processing has not been properly systematized yet, and little research is focused on this. In this paper a survey on most popular pre-processing steps required in environmental data analysis is presented, together with a proposal to systematize it. Rather than providing technical details on specific pre-processing techniques, the paper focus on providing general ideas to a non-expert user, who, after reading them, can decide which one is the more suitable technique required to solve his/her problem.

show abstract

“…Due to the high complexity of the optimization procedure involved, it is often preferred to use randomized (Pkalska et al 2006) or greedy methods (Battiti 1994;Wilson and Martinez 2000). Over the years, EL solutions have been proposed using nearest neighbors (Aha et al 1991), genetic algorithms (Cano et al 2003), vector quantization (Jankowski and Grochowski 2005) and density estimation based classification techniques (Fukunaga and Hayes 1989).…”

Section: Exemplar Learning On Embedded Devicesmentioning

confidence: 99%

Incremental exemplar learning schemes for classification on embedded devices

Jain

Nikovski

2008

Mach Learn

View full text Add to dashboard Cite

Although memory-based classifiers offer robust classification performance, their widespread usage on embedded devices is hindered due to the device's limited memory resources. Moreover, embedded devices often operate in an environment where data exhibits evolutionary changes which entails frequent update of the in-memory training data. A viable option for dealing with the memory constraint is to use Exemplar Learning (EL) schemes that learn a small memory set (called the exemplar set) of high functional information that fits in memory. However, traditional EL schemes have several drawbacks that make them inapplicable for embedded devices; (1) they have high memory overheads and are unable to handle incremental updates to the exemplar set, (2) they cannot be customized to obtain exemplar sets of any user-defined size that fits in the memory and (3) they learn exemplar sets based on local neighborhood structures that do not offer robust classification performance. In this paper, we propose two novel EL schemes, EBEL (Entropy-Based Exemplar Learning) and ABEL (AUC-Based Exemplar Learning) that overcome the aforementioned short-comings of traditional EL algorithms. We show that our schemes efficiently incorporate new training datasets while maintaining high quality exemplar sets of any user-defined size. We present a comprehensive experimental analysis showing excellent classificationaccuracy versus memory-usage tradeoffs using our proposed methods.

show abstract

Using evolutionary algorithms as instance selection for data reduction in KDD: an experimental study

Cited by 292 publications

References 27 publications

Selecting training sets for support vector machines: a review

Selecting training sets for support vector machines: a review

A survey on pre-processing techniques: Relevant issues in the context of environmental data mining

Incremental exemplar learning schemes for classification on embedded devices

Contact Info

Product

Resources

About