Outlier detection using linguistically quantified statements

Abstract

Automatic summary of databases is an important tool in strategic decision‐making. This paper applies the concept of linguistic summaries of databases to outlier detection. The definition of an outlier is closely related to the type of data analyzed and its context. Outlier detection is an important data‐mining technique, which finds applications in a wide range of domains. It can identify defects, remove impurities from the data, and, most of all, it is significant to decision‐making processes. The authors propose a novel definition of an outlier, based on linguistic quantifiers and linguistic summaries. Linguistic quantifiers are employed to express the cardinality of a set of outliers in a natural language. Thus, this paper demonstrates that linguistic summaries proposed by Yager, which provide the ability to model imprecise information, can serve as an effective tool for outlier detection.

Imputing Missing Values for Improved Statistical Inference Applied to Intrauterine Growth Restriction Problem

“…In high-dimensional datasets missing data may be more frequent [49] and appropriate feature selection technique [50], [51] may improve the imputation accuracy [10]. Novel solutions of outlier detection based on linguistically quantified statements may be also considered to remove impurities from the data [52].…”

Case‐Based Reasoning: The Search for Similar Solutions and Identification of Outliers

“…Then a subset of objects X out ∈ X will be called outliers in the set X if and only if for any subset of attributes s i ∈ S. The cardinality of subset X out is determined by the linguistic quantifier Q, that is, "little," "few," "very few," "very little," "almost no," and the like [20].…”

“…Cases of correct classification, that is, TP (true positive) and TN (true negative) as well as cases of incorrect classification, that is, FP (false positive) and FN (false positive), were taken into consideration in the matrices of errors. Sensitivity (SE), specificity (SP), and the accuracy were calculated, according to(20). The detection error was determined as the ratio of the number of misclassifications to the sum of all detections.…”

Detection of outlier information by the use of linguistic summaries based on classic and interval-valued fuzzy sets

“…In this paper, we clarify the concept of outlier detection based on linguistic summaries, proposed in Duraj et al, Duraj and Szczepaniak, Duraj et al, and Duraj . A review of the literature shows that linguistic summaries are very important in decision‐making.…”

“…Works related to the generation of linguistic summaries can be divided into those that deal with the creation of new summaries and those that seek to extend the existing ones to include more complex expressions. Novel approach to detection of outliers using linguistic summaries including definition of outliers was presented in Duraj et al, Duraj and Szczepaniak, and Duraj et al and medical application can be found in Duraj …”