Sustainable Urbanization-Based Data Analysis by Remote Sensing with Cyber-Physical Systems and Wireless Internet of Things Integrated Machine Learning

Abstract

The Processing data from remote sensing has practical uses with high social worth. For example, the use of remotely sensed multispectral or radar imagery for urban monitoring, fire detection, or flood prediction can have a significant influence on both environmental and economic concerns. Remote sensing has developed into a diverse discipline that relies heavily on machine learning and signal processing techniques to handle the collected data effectively and provide accurate outputs. Some towns have been able to lessen the issue by using the various advantages provided by digitalization, which is facilitated by the internet of things and wireless connectivity. These are cyber-physical systems (CPS), which are systems in which many gadgets work together to control tangible objects. This study offers a unique method for analysing remote sensing data in metropolitan areas while modelling cyber-physical systems with wireless IoT as well as machine learning. Here, wireless IoT model in cyber-physical system has been studied using remote sensing data from metropolitan areas. Next, the environment data from the metropolitan zone was examined and categorised using regressive stochastic Gaussian modelling with Quantile adversarial neural networks (RSG-QANN). The experimental study is done in terms of precision, packet delivery ratio, end-to-end latency, recall, and accuracy of categorization. The findings demonstrate that social activity perceived signatures and physically sensed picture data, which at first glance appear to be unrelated, can in fact work in concert to improve accuracy of urban region function detection.