Data preprocessing using banded structure and image morphology enhancing Boolean matrix factorization

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F61989592%3A15310%2F25%3A73633773" target="_blank" >RIV/61989592:15310/25:73633773 - isvavai.cz</a>

Výsledek na webu

<a href="https://www.sciencedirect.com/science/article/pii/S0950705125014054" target="_blank" >https://www.sciencedirect.com/science/article/pii/S0950705125014054</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1016/j.knosys.2025.114366" target="_blank" >10.1016/j.knosys.2025.114366</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Data preprocessing using banded structure and image morphology enhancing Boolean matrix factorization

Popis výsledku v původním jazyce

Boolean Matrix Factorization (BMF) is a widely used method for revealing underlying patterns, called factors, in data. In the paper, we propose a novel data preprocessing method that makes patterns more visible, thus simplifying the overall BMF process. The method first reorders the data to reveal a banded structure. Then, it applies image morphology to enhance this structure by emphasizing important information and suppressing less relevant information. We demonstrate the efficacy of our approach through various experimental evaluations, showing that it effectively modifies the data, resulting in fewer, more interpretable factors. The proposed method also allows using more straightforward and faster BMF algorithms while maintaining high-quality results.

Název v anglickém jazyce

Data preprocessing using banded structure and image morphology enhancing Boolean matrix factorization

Popis výsledku anglicky

Boolean Matrix Factorization (BMF) is a widely used method for revealing underlying patterns, called factors, in data. In the paper, we propose a novel data preprocessing method that makes patterns more visible, thus simplifying the overall BMF process. The method first reorders the data to reveal a banded structure. Then, it applies image morphology to enhance this structure by emphasizing important information and suppressing less relevant information. We demonstrate the efficacy of our approach through various experimental evaluations, showing that it effectively modifies the data, resulting in fewer, more interpretable factors. The proposed method also allows using more straightforward and faster BMF algorithms while maintaining high-quality results.

Druh

J_imp - Článek v periodiku v databázi Web of Science

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

—

Návaznosti

I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace

Rok uplatnění

2025

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název periodika

KNOWLEDGE-BASED SYSTEMS

ISSN

0950-7051

e-ISSN

1872-7409

Svazek periodika

329B

Číslo periodika v rámci svazku

NOV

Stát vydavatele periodika

NL - Nizozemsko

Počet stran výsledku

9

Strana od-do

"114366-1"-"114366-9"

Kód UT WoS článku

001567119200003

EID výsledku v databázi Scopus

2-s2.0-105015039733