Enhanced Quantum Convolutional Neural Network for Signature Authentication in Consumer Products

Enhanced Quantum Convolutional Neural Network for Signature Authentication in Consumer Products

Článek WoS

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.

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.

Quantum computing; Qubit; Quantum circuit; Feature extraction; Computers; Logic gates; Consumer electronics; Machine learning; Kernel; Data models; Convolutional neural network; quantum machine learning; RFID product tracking; SBD; signature-based detection

Quantum computing; Qubit; Quantum circuit; Feature extraction; Computers; Logic gates; Consumer electronics; Machine learning; Kernel; Data models; Convolutional neural network; quantum machine learning; RFID product tracking; SBD; signature-based detection

RAGHUPATHY, B. K.; VAIRAVASUNDRAM, S.; GANESAN, M.; NAMACHIVAYAM, R. K.; KOTECHA, K.; HERENCSÁR, N.

29.11.2024

IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC

PISCATAWAY

0098-3063

IEEE TRANSACTIONS ON CONSUMER ELECTRONICS

71

1

Spojené státy americké

2309

2321

13

https://ieeexplore.ieee.org/document/10771968

http://hdl.handle.net/11012/249750

TCE-2024-07-2141.R1
TCE.2024.3509624-accepted