[HTML][HTML] Recent Applications of Explainable AI (XAI): A Systematic Literature Review

M Saarela, V Podgorelec - Applied Sciences, 2024‏ - mdpi.com
This systematic literature review employs the Preferred Reporting Items for Systematic
Reviews and Meta-Analyses (PRISMA) methodology to investigate recent applications of …

Brightbox—a rough set based technology for diagnosing mistakes of machine learning models

A Janusz, A Zalewska, Ł Wawrowski, P Biczyk… - Applied Soft …, 2023‏ - Elsevier
The paper presents a novel approach to investigating mistakes in machine learning model
operations. The considered approach is the basis for BrightBox–a diagnostic technology that …

[HTML][HTML] RuleXAI—A package for rule-based explanations of machine learning model

D Macha, M Kozielski, Ł Wróbel, M Sikora - SoftwareX, 2022‏ - Elsevier
The ability to use eXplainable Artificial Intelligence (XAI) methods is very important for both
AI users and AI developers. This paper presents the RuleXAI library, which provides XAI …

COVIDSensing: social sensing strategy for the management of the COVID-19 crisis

A Sepúlveda, C Periñán-Pascual, A Muñoz… - Electronics, 2021‏ - mdpi.com
The management of the COVID-19 pandemic has been shown to be critical for reducing its
dramatic effects. Social sensing can analyse user-contributed data posted daily in social …

Detecting and Isolating Adversarial Attacks Using Characteristics of the Surrogate Model Framework

P Biczyk, Ł Wawrowski - Applied Sciences, 2023‏ - mdpi.com
The paper introduces a novel framework for detecting adversarial attacks on machine
learning models that classify tabular data. Its purpose is to provide a robust method for the …

[PDF][PDF] Machine learning methods in support of multiomics signature identification for breast cancer patient subpopulations

J Polańska, C Hatzis‏ - repolis.bg.polsl.pl
Breast cancer is a highly heterogeneous disease with a diverse molecular portrait. The
commonly used clinical classification of breast cancer subtypes relies on levels of several …

[PDF][PDF] 1 Motivation, aims, and thesis

J Tobiasz‏ - delibra.bg.polsl.pl
2 Background Currently used, four clinical breast cancer subtypes are determined based on
the presence of three key markers: estrogen receptor (ER), progesterone receptor (PR), and …