Wireless Spatial Analysis-Based Predictive Analysis and Environmental Data Optimisation Using Machine Learning Model

A significant quantity of sensor data has been used recently to construct a variety of Internet of Things (IoT)-based methods as well as applications. They have been extensively employed in urban sustainable development and in mobile data reception for WSN (wireless sensor networks), for instance. Correct interpretation as well as reuse of sensor data from many domains is essential for maximising the use of data from numerous sources for decision-making. The purpose of this project is to provide new methods for predictive analysis based on spatial data modelling and machine learning-based environment data optimisation. Predictive Bayesian spatial Markov neural network is used for the environment spatial data predictive analysis. Then, lion grey moath binary optimisation is used to optimise the data. Environmental data is subjected to an experimental examination in terms of F-1 score, recall, accuracy and precision. The results of the study showed that optimizing models for precise water quality prediction may be achieved by combining artificial intelligence models with optimisation routines.