Enhanced Quantum Convolutional Neural Network for Signature Authentication in Consumer Products

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216305%3A26220%2F26%3A0193456" target="_blank" >RIV/00216305:26220/26:0193456 - isvavai.cz</a>

Výsledek na webu

<a href="https://ieeexplore.ieee.org/document/10771968" target="_blank" >https://ieeexplore.ieee.org/document/10771968</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/TCE.2024.3509624" target="_blank" >10.1109/TCE.2024.3509624</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Enhanced Quantum Convolutional Neural Network for Signature Authentication in Consumer Products

Popis výsledku v původním jazyce

Product tracking applications utilize the Internet of Things and cyber-physical systems to identify permitted or unauthorized user intrusions into the system. Classical machine learning algorithms cannot detect every risk in an environment that evolves constantly and where new abnormalities are visible. This article investigates the potential of quantum machine learning (QML) for real-time product purchase monitoring and intrusion detection using an enhanced quantum convolutional neural network (EQCNN) with signature-based detection over a massive volume of search space data (qubits). We suggest a three-stage technique to effectively handle the sensitive content: Pre-processing, EQCNN-based feature extraction, and syntactic pattern recognition. Signature-based identification is a feature of the EQCNN architecture that helps detect particular patterns linked to goods purchases or invasions. The model can minimize product tracking mistakes by utilizing the QML-based EQCNN with signature-based detection, resulting in a more efficient supply chain.

Název v anglickém jazyce

Enhanced Quantum Convolutional Neural Network for Signature Authentication in Consumer Products

Popis výsledku anglicky

Product tracking applications utilize the Internet of Things and cyber-physical systems to identify permitted or unauthorized user intrusions into the system. Classical machine learning algorithms cannot detect every risk in an environment that evolves constantly and where new abnormalities are visible. This article investigates the potential of quantum machine learning (QML) for real-time product purchase monitoring and intrusion detection using an enhanced quantum convolutional neural network (EQCNN) with signature-based detection over a massive volume of search space data (qubits). We suggest a three-stage technique to effectively handle the sensitive content: Pre-processing, EQCNN-based feature extraction, and syntactic pattern recognition. Signature-based identification is a feature of the EQCNN architecture that helps detect particular patterns linked to goods purchases or invasions. The model can minimize product tracking mistakes by utilizing the QML-based EQCNN with signature-based detection, resulting in a more efficient supply chain.

Druh

J_imp - Článek v periodiku v databázi Web of Science

CEP obor

—

OECD FORD obor

20200 - Electrical engineering, Electronic engineering, Information engineering

Projekt

—

Návaznosti

S - Specificky vyzkum na vysokych skolach

Rok uplatnění

2025

Kód důvěrnosti údajů

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

Název periodika

IEEE TRANSACTIONS ON CONSUMER ELECTRONICS

ISSN

0098-3063

e-ISSN

1558-4127

Svazek periodika

71

Číslo periodika v rámci svazku

1

Stát vydavatele periodika

US - Spojené státy americké

Počet stran výsledku

13

Strana od-do

2309-2321

Kód UT WoS článku

001511069500038

EID výsledku v databázi Scopus

2-s2.0-85210773967