A Comparison of Ranking Methods for Classification Algorithm Selection
نویسندگان
چکیده
We investigate the problem of using past performance information to select an algorithm for a given classiication problem. We present three ranking methods for that purpose: average ranks, success rate ratios and signiicant wins. We also analyze the problem of evaluating and comparing these methods. The evaluation technique used is based on a leave-one-out procedure. On each iteration, the method generates a ranking using the results obtained by the algorithms on the training datasets. This ranking is then evaluated by calculating its distance from the ideal ranking built using the performance information on the test dataset. The distance measure adopted here, average correlation, is based on Spearman's rank correlation coeecient. To compare ranking methods, a combination of Friedman's test and Dunn's multiple comparison procedure is adopted. When applied to the methods presented here, these tests indicate that the success rate ratios and average ranks methods perform better than signiicant wins.
منابع مشابه
SFLA Based Gene Selection Approach for Improving Cancer Classification Accuracy
In this paper, we propose a new gene selection algorithm based on Shuffled Frog Leaping Algorithm that is called SFLA-FS. The proposed algorithm is used for improving cancer classification accuracy. Most of the biological datasets such as cancer datasets have a large number of genes and few samples. However, most of these genes are not usable in some tasks for example in cancer classification....
متن کاملOnline Streaming Feature Selection Using Geometric Series of the Adjacency Matrix of Features
Feature Selection (FS) is an important pre-processing step in machine learning and data mining. All the traditional feature selection methods assume that the entire feature space is available from the beginning. However, online streaming features (OSF) are an integral part of many real-world applications. In OSF, the number of training examples is fixed while the number of features grows with t...
متن کاملA new approach for Robot selection in manufacturing using the ellipsoid algorithm
The choice of suitable robots in manufacturing, to improve product quality and to increase productivity, is a complicated decision due to the increase in robot manufacturers and configurations. In this article, a novel approach is proposed to choose among alternatives, differently assessed by decision makers on different criteria, to make the final evaluation for decision-making. The approach i...
متن کاملNegative Selection Based Data Classification with Flexible Boundaries
One of the most important artificial immune algorithms is negative selection algorithm, which is an anomaly detection and pattern recognition technique; however, recent research has shown the successful application of this algorithm in data classification. Most of the negative selection methods consider deterministic boundaries to distinguish between self and non-self-spaces. In this paper, two...
متن کاملA Novel Approach to Feature Selection Using PageRank algorithm for Web Page Classification
In this paper, a novel filter-based approach is proposed using the PageRank algorithm to select the optimal subset of features as well as to compute their weights for web page classification. To evaluate the proposed approach multiple experiments are performed using accuracy score as the main criterion on four different datasets, namely WebKB, Reuters-R8, Reuters-R52, and 20NewsGroups. By analy...
متن کاملA Classification Method for E-mail Spam Using a Hybrid Approach for Feature Selection Optimization
Spam is an unwanted email that is harmful to communications around the world. Spam leads to a growing problem in a personal email, so it would be essential to detect it. Machine learning is very useful to solve this problem as it shows good results in order to learn all the requisite patterns for classification due to its adaptive existence. Nonetheless, in spam detection, there are a large num...
متن کامل