Optimizing the IoT PAYLOAD Encryption Watermarking-Oriented Applying Computational Intelligence and Visual Quality Coding to Improve the Vehicular Speed Controller Platform's Features

In this article, we'll outline a road transportation Internet of Things platform that enables real-time road flow data collection, adaptation, and encryption to enhance user experience, communicate in excellent quality at a bit rate appropriate for cloud storage, processing, and decision-making. The recommended approach entails compiling all the crucial road data, which include: the speed of movement, the geolocation of the vehicle, the vehicle picture, the detection of the license plate, the detection and recognition of the driver's face, as well as suspicious situations like telephone use, strange driving, failure to obey traffic signals, and so on. A relative QR code is produced by this solution. With the help of an advanced object recognition technology, our solution creates a relative QR code that contains all of the vehicle's data and ensures that it is appropriate for the car being recognized. The recommended approach demonstrates how psychovisual optimization tools affect watermarking coding quality in comparison with reference yields by SPIHT standard coder, how computational intelligence predicts lost data, and seeks to optimize platform data features in terms of CoAP payload time transportation duration, ECC encryption bandwidth storage and space occupation, and communication energy consumption to finally provide a high-quality and time/energy lossless watermarked content to enhance the security of the QR code during its transmission. To achieve these goals, the proposed system incorporates real-time data collection from the various nodes in the IoT network topology, data compression, synchronized handshaking between the cloud and the IoT nodes, and missing data prediction in the event of node failure to accomplish these aims.