Framework to forecast environment changes by optimized predictive modelling based on rough set and Elman neural network

The techniques pertaining to soft computing are the base for commencement, model and organization of intelligent systems in order to offer more perfect, economical and realistic solution which has minimal complexity levels. The concept of intelligent systems has for long supported objectives on sustainability, improvisation of efficiency and symbolized various kinds of activities like creation of jobs, earning profits, providing services and improvement in capacities in ICT. The applications based on this system are widespread in the technological market because of massive development in grid, cloud, mobile and big data applications and its corresponding connectivity advantages. ICT triggers data scientists to satisfy technical-based demands of intelligent systems around data analytics and big data applications. The major features of big data like that of reservation of designs on information and knowledge have offered the public undertaking an opportunity to enhance production levels, improved efficiency and its effectiveness. The main objective of this paper is to enhance the accuracy of predictive modelling using an optimized predictive modelling based on rough set (RS) and Elman neural network (ElNN). These advanced predictive models are designed on the basis of RS approach in initial stages and in later processes enhanced with the support of Elman-NN. RS has an excellent feature selection capability, and Elman-NN is the best at nonlinear system modelling. By integrating them, the proposed method can limit the input dimension and optimize the structure for ElNN modelling. This can reduce the mathematical computation complexity with the progress of predictive models. The experimental results indicate that through RS feature selection and the structure of Elman-NN, the predictive model can be simplified significantly with enhanced model performance. The predictive accuracy of data sets, namely air quality in Northern Taiwan, hazardous air pollutants, historical hourly weather data and US pollutants through optimization, is above 99%, and this model proves that the results of optimized predictive error are far better than those obtained by other neural networks like PCA-RBF, PCA-NN, FFNN-BP with PCA, MLR, FFNN-BP, ELM, SOM, RBF and ART2.