Data Preprocessing Technique for Neural Networks Based on Image Represented by a Fuzzy Function

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F61988987%3A17610%2F20%3AA2101VJP" target="_blank" >RIV/61988987:17610/20:A2101VJP - isvavai.cz</a>

Výsledek na webu

<a href="https://ieeexplore.ieee.org/document/8691766" target="_blank" >https://ieeexplore.ieee.org/document/8691766</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/TFUZZ.2019.2911494" target="_blank" >10.1109/TFUZZ.2019.2911494</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Data Preprocessing Technique for Neural Networks Based on Image Represented by a Fuzzy Function

Popis výsledku v původním jazyce

Although data preprocessing is a universal technique that can be widely used in neural networks, most research in this area is focused on designing new neural network architectures. In our work, we propose a preprocessing technique that enriches the original image data using local intensity information; this technique is motivated by human perception. To encode this information into an image, we introduce a new image structure named Image Represented by a Fuzzy Function. When using this structure, a crisp intensity value of each pixel is replaced by a fuzzy set given by a membership function constructed with the usage of extremal values from the particular neighborhood of that pixel. We describe this structure and its properties and propose a way in which it can be used as an input into existing neural networks without any modifications. Based on our benchmark consisting of three well-known datasets and five neural network architectures, we show that the proposed preprocessing can, in most cases, decrease classification error compared with a baseline and two other preprocessing methods. To support our claim, we have also selected several publicly available projects and tested the impact of the preprocessing with a positive result.

Název v anglickém jazyce

Data Preprocessing Technique for Neural Networks Based on Image Represented by a Fuzzy Function

Popis výsledku anglicky

Although data preprocessing is a universal technique that can be widely used in neural networks, most research in this area is focused on designing new neural network architectures. In our work, we propose a preprocessing technique that enriches the original image data using local intensity information; this technique is motivated by human perception. To encode this information into an image, we introduce a new image structure named Image Represented by a Fuzzy Function. When using this structure, a crisp intensity value of each pixel is replaced by a fuzzy set given by a membership function constructed with the usage of extremal values from the particular neighborhood of that pixel. We describe this structure and its properties and propose a way in which it can be used as an input into existing neural networks without any modifications. Based on our benchmark consisting of three well-known datasets and five neural network architectures, we show that the proposed preprocessing can, in most cases, decrease classification error compared with a baseline and two other preprocessing methods. To support our claim, we have also selected several publicly available projects and tested the impact of the preprocessing with a positive result.

Druh

J_imp - Článek v periodiku v databázi Web of Science

CEP obor

—

OECD FORD obor

10102 - Applied mathematics

Projekt

<a href="/cs/project/EF17_049%2F0008414" target="_blank" >EF17_049/0008414: Centrum pro výzkum a vývoj metod umělé intelligence v automobilovém průmyslu regionu</a><br>

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)<br>S - Specificky vyzkum na vysokych skolach

Rok uplatnění

2020

Kód důvěrnosti údajů

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

Název periodika

IEEE Transactions on Fuzzy Systems

ISSN

1063-6706

e-ISSN

1941-0034

Svazek periodika

28

Číslo periodika v rámci svazku

7

Stát vydavatele periodika

US - Spojené státy americké

Počet stran výsledku

10

Strana od-do

1195-1204

Kód UT WoS článku

000545205300002

EID výsledku v databázi Scopus

2-s2.0-85087805973