Wyniki wyszukiwania - BazTech

Ograniczanie wyników

Znaleziono wyników: 2

Liczba wyników na stronie

Wyniki wyszukiwania

Wyszukiwano:
w słowach kluczowych: zestaw testowy

Sortuj według:

Ogranicz wyniki do:

Data irregularities in discretisation of test sets used for evaluation of classification systems: A case study on authorship attribution

Stańczyk Urszula, Zielosko Beata

Bulletin of the Polish Academy of Sciences. Technical Sciences

2021

Vol. 69, nr 4

art. no. e137629

When patterns to be recognised are described by features of continuous type, discretisation becomes either an optional or necessary step in the initial data pre-processing stage. Characteristics of data, distribution of data points in the input space, can significantly influence the process of transformation from real-valued into nominal attributes, and the resulting performance of classification systems employing them. If data include several separate sets, their discretisation becomes more complex, as varying numbers of intervals and different ranges can be constructed for the same variables. The paper presents research on irregularities in data distribution, observed in the context of discretisation processes. Selected discretisation methods were used and their effect on the performance of decision algorithms, induced in classical rough set approach, was investigated. The studied input space was defined by measurable style-markers, which, exploited as characteristic features, facilitate treating a task of stylometric authorship attribution as classification.

Data Quality Model-based Testing of Information Systems

Bicevskis Janis, Bicevska Zane, Nikiforova Anastasija, Oditis Ivo

Annals of Computer Science and Information Systems

2020

Vol. 21

595--602

This paper proposes a model-based testing approach by offering to use the data quality model (DQ-model) instead of the program's control flow graph as a testing model. The DQ-model contains definitions and conditions for data objects to consider the data object as correct. The study proposes to automatically generate a complete test set (CTS) using a DQ-model that allows all data quality conditions to be tested, resulting in a full coverage of DQ-model. In addition, the possibility to check the conformity of the data to be entered and already stored in the database is ensured. The proposed alternative approach changes the testing process: (1) CTS can be generated prior to software development; (2) CTS contains not only input data, but also database content required for complete testing of the system; (3) CTS generation from DQ-model provides values against which the system can be further tested. If the test results correspond to the values obtained during CTS generation, the system under test shall be considered to have been tested according to DQ-model. Otherwise, the user can verify the cause of the differences that may occur due incorrect software, as well as an inaccurate specification.