An Integrated Approach of Belief Rule Base and Deep Learning to Predict Air Pollution

Abstract

Sensor data are gaining increasing global attention due to the advent of Internet of Things (IoT). Reasoning is applied on such sensor data in order to compute prediction. Generating a health warning that is based on prediction of atmospheric pollution, planning timely evacuation of people from vulnerable areas with respect to prediction of natural disasters, etc., are the use cases of sensor data stream where prediction is vital to protect people and assets. Thus, prediction accuracy is of paramount importance to take preventive steps and avert any untoward situation. Uncertainties of sensor data is a severe factor which hampers prediction accuracy. Belief Rule Based Expert System (BRBES), a knowledge-driven approach, is a widely employed prediction algorithm to deal with such uncertainties based on knowledge base and inference engine. In connection with handling uncertainties, it offers higher accuracy than other such knowledge-driven techniques, e.g., fuzzy logic and Bayesian probability theory. Contrarily, Deep Learning is a data-driven technique, which constitutes a part of Artificial Intelligence (AI). By applying analytics on huge amount of data, Deep Learning learns the hidden representation of data. Thus, Deep Learning can infer prediction by reasoning over available data, such as historical data and sensor data streams. Combined application of BRBES and Deep Learning can compute prediction with improved accuracy by addressing sensor data uncertainties while utilizing its discovered data pattern. Hence, this paper proposes a novel predictive model that is based on the integrated approach of BRBES and Deep Learning. The uniqueness of this model lies in the development of a mathematical model to combine Deep Learning with BRBES and capture the nonlinear dependencies among the relevant variables. We optimized BRBES further by applying parameter and structure optimization on it. Air pollution prediction has been taken as use case of our proposed combined approach. This model has been evaluated against two different datasets. One dataset contains synthetic images with a corresponding label of PM2.5 concentrations. The other one contains real images, PM2.5 concentrations, and numerical weather data of Shanghai, China. We also distinguished a hazy image between polluted air and fog through our proposed model. Our approach has outperformed only BRBES and only Deep Learning in terms of prediction accuracy.

A Deep Learning Inspired Belief Rule-Based Expert System

“…Kabir et al [30] proposed integration of a Deep Learning method with BRBES to predict air pollution using outdoor images of Beijing city. They have used Convolutional Neural Networks (CNN) to predict PM2.5 values from outdoor images.…”

“…Different learning methodologies like fmincon [24], DE [26], and eBRBaDE [27] have been used to improve the prediction accuracy of BRBES. On the other hand, various methods like CGMV [28], PCA [29], and CNN [30] have been integrated as a separate box to improve the performance of BRBES. However, there have been no attempts to incorporate associative memory with the BRBES inference procedure to improve the BRBES's accuracy of prediction for large amounts of data.…”

An Empirical Mode Decomposition Fuzzy Forecast Model for Air Quality

“…Peng et al proposed a learning method based on an extremum learning machine, which learns continuously as the data increases, combined with multiple linear regressions and multi-layer perceptron networks, to predict air quality 18 . Kabi et al combined the confidence expert system with deep learning, and optimized the confidence expert system so as to find the nonlinear dependence among the relevant variables, so as to predict air quality 19 . Bai et al proposed a seasonal stacked automatic encoder model combining seasonal analysis and deep feature learning 20 .…”

Self-Powered Wireless Sensor Matrix for Air Pollution Detection with a Neural Predictor

“…Indirect methods are a very interesting solution, and are mostly based on image analysis and using Deep Learning (DL) neural networks [33]. In this case, two datasets are applied to the model.…”

“…The second set contains actual images and numerical weather data from a weather station. The authors [33] present a parameter optimization model to distinguish fog from smog and improve the accuracy of smog occurrence prediction. Other neural methods for image analysis are also used.…”