RETRACTED ARTICLE: Empowering an IoT platform with  advance quantum computing and a Customized deep residual technique

• Published in: Optical and quantum electronics Vol. 55; no. 10
• Main Authors: Ashok, P., Ragunthar, T., James, T. Prabahar Godwin, Sahayaraj, K. Kishore Anthuvan, Suganthi, P., Somasundaram, K., Ananthi, S.
• Format: Journal Article
• Language: English
• Published: New York Springer US 2023; Springer Nature B.V
• Subjects: Accuracy; Characterization and Evaluation of Materials; Computer Communication Networks; Cost function; Data analysis; Data collection; Data exchange; Datasets; Decision analysis; Decision making; Electrical Engineering; Internet of Things; Lasers; Neural networks; Optical Devices; Optics; Photonics; Physics; Physics and Astronomy; Quantum computing; R-QCNN; Deep residual learning technique; Quantum neural network; IoT
• ISSN: 0306-8919; 1572-817X
• DOI: 10.1007/s11082-023-05154-4

All over the world, millions of devices are wirelessly connected and exchanging data as part of the Internet of Things (IoT). As more and more information is hoped to be monitored by means of a single platform, the importance of accuracy assessment in the pursuit of the perfect IoT platform has grown. To keep up with the ever-increasing data analysis needs for crucial, real-time decision making, IoT data collection is becoming increasingly crucial. In this study, we utilized the "IoT Sensor Data" dataset, consisting of sensor readings collected from various IoT devices. The proposed R-QCNN model, which combines a quantum neural network with a deep residual learning technique, was trained and evaluated on this dataset. Experimental results show that the R-QCNN achieved an accuracy of 95% in classifying the IoT sensor data, outperforming existing methods. Thus, our approach demonstrates promising results in optimizing the cost function routine for IoT platforms.