Premium
Improved Particle Swarm Optimization Based Adaptive Neuro‐Fuzzy Inference System for Benzene Detection
Author(s) -
Pannu Husanbir S.,
Singh Dilbag,
Malhi Avleen K.
Publication year - 2018
Publication title -
clean – soil, air, water
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.444
H-Index - 66
eISSN - 1863-0669
pISSN - 1863-0650
DOI - 10.1002/clen.201700162
Subject(s) - particle swarm optimization , adaptive neuro fuzzy inference system , mean squared error , computer science , heuristic , fuzzy logic , data mining , mathematical optimization , artificial intelligence , machine learning , fuzzy control system , mathematics , statistics
Benzene is a carcinogen and employing hardware sensors to detect its concentration is expensive, along with limited operational efficiency. There is a relation among various atmospheric gas concentrations and therefore, some heuristic regression approaches can be applied for benzene forecasting, if given the concentration level of other gases. This paper proposes a new adaptive benzene prediction model using an improved particle swarm optimization (PSO) based adaptive neuro fuzzy inference system (ANFIS). Improved PSO enhances the performance of ANFIS by considering the multi‐objective fitness function involving accuracy, root mean squared error (RMSE), and coefficient of determination ( r 2 ). The proposed technique has been tested on both publicly available air quality datasets and a real world dataset of Patiala City in India. Extensive analysis reveals that the proposed technique outperforms other state‐of‐the‐art techniques, making it well suited for building effective and economical benzene prediction models.