Prediction of Benzene Concentration of Air in Urban Area Using Deep Neural Network Radhika Ray, Siddhartha Haldar, Subhadeep Biswas, Ruptirtha Mukherjee, Shayan Banerjee and Sankhadeep Chatterjee Abstract Recent studies have revealed the adverse effect of benzene as an air pol- lutant. Benzene has been proved to be causing several health hazards in unbar areas. Researchers have employed machine learning methods to predict the available ben- zene concentration in a particular area. Motivated by the recent advancements in the field of machine learning, the authors have proposed a deep learning-based model to predict benzene quantity in order to determine the quality of air as well. Benzene quantity prediction in the atmosphere has been accomplished with respect to certain specified elements (like carbon monoxide, PT08.S1, PT08.S2) that coexist along with benzene (C 6 H 6 ). A feature selection stage has been employed using correlation analysis to find the most suitable set of features. Six features have been selected for the experimental purpose. Further, the proposed model has been compared with well-known machine learning models such as linear regression, polynomial regres- sion, K-nearest neighbor, multilayer perceptron feedforward network (MLP-FFN) in terms of RMSE. Experimental results have suggested that the proposed deep learning-based model is superior to the other models under current study. Keywords Deep learning · Benzene prediction · Air quality R. Ray · S. Haldar · S. Biswas · R. Mukherjee · S. Banerjee (B ) · S. Chatterjee (B ) Department of Computer Science & Engineering, University of Engineering & Management, Kolkata, India e-mail: shayanbanerjee96@gmail.com S. Chatterjee e-mail: chatterjeesankhadeep.cu@gmail.com R. Ray e-mail: rray6797@gmail.com S. Haldar e-mail: sidhaldar98@gmail.com S. Biswas e-mail: subhadeepbiswas250@gmail.com R. Mukherjee e-mail: rupje65@gmail.com © Springer Nature Singapore Pte Ltd. 2019 M. Chakraborty et al. (eds.), Proceedings of International Ethical Hacking Conference 2018, Advances in Intelligent Systems and Computing 811, https://doi.org/10.1007/978-981-13-1544-2_38 465