We study the relationship between the distribution of data, on the one hand, and classifier performance, on the other, for non-parametric classifiers. It is shown that predictable factors such as the available amount of training data (relative to the dimensionality of the feature space), the spatial variability of the effective average distance between data samples, and the type and amount of n...

Evaluating the performance of classifiers is not as trivial as it would seem at a first glance. Even the most widely used methods such as measuring accuracy or error rate on a test set has severe limitations. Two of the most prominent limitations of these measures are that they do not consider misclassification costs and can be misleading when the classes have very different prior probabilities...

Classification requirements for real-world classification problems are often constrained by a given true positive or false positive rate to ensure that the classification error for the most important class is within a desired limit. For a sufficiently high true positive rate, this may result in the set-point being located somewhere in the flat portion of the ROC curve where the associated false...

Automatic signal type identification (ASTI) is an important topic for both the civilian and military domains. Most of the proposed identifiers can only recognize a few types of digital signal and usually need high levels of SNRs. This paper presents a new high efficient technique that includes a variety of digital signal types. In this technique, a combination of higher order moments and hi...

In this paper, several two-dimensional extensions of principal component analysis (PCA) and linear discriminant analysis (LDA) techniques has been applied in a lossless dimensionality reduction framework, for face recognition application. In this framework, the benefits of dimensionality reduction were used to improve the performance of its predictive model, which was a support vector machine (...

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...

An imbalanced class on a dataset is common classification problem. The effect of using datasets can cause decrease in the performance classifier. Resampling one solutions to this This study used 100 from 3 websites: UCI Machine Learning, Kaggle, and OpenML. Each will go through processing stages: resampling process, significance testing process between evaluation values combination classifier p...

Educational Data Mining (EDM) is gaining great importance as a new interdisciplinary research field related to some other areas. It directly data mining (DM), the latter being fundamental part of knowledge discovery in databases (KDD). This growing more and contains hidden that could be very useful for users (both teachers students). convenient identify such form models, patterns, or any repres...

in this paper, the performance of 11 different distances for image retrieval and classification, based on color, shape and texture, is evaluated. the precision-recall measure and the correct classification rate of the k-nn classifier are used to evaluate retrieval and classification performances, respectively. the experimental results for a database of 1000 images from 10 different semantic gro...

Classification is a widely used technique in data mining. Thereby achieving a reasonable classifier performance is an increasingly important goal. This paper aims to empirically show how classifier performance can be improved by knowledge-driven data preparation using business, data and methodological know-how. To point out the variety of knowledge-driven approaches, we firstly introduce an adv...