Asheesh Sharma

Development of a traffic noise prediction model for an urban environment

The objective of this study is to develop a traffic noise model under diverse traffic conditions in metropolitan cities. The model has been developed to calculate equivalent traffic noise based on four input variables i.e. equivalent traffic flow (Q e ), equivalent vehicle speed (S e ) and distance (d) and honking (h). The traffic data is collected and statistically analyzed in three different cases for 15-min during morning and evening rush hours. Case I represents congested traffic where equivalent vehicle speed is <30 km/h while case II represents free-flowing traffic where equivalent vehicle speed is >30 km/h and case III represents calm traffic where no honking is recorded. The noise model showed better results than earlier developed noise model for Indian traffic conditions. A comparative assessment between present and earlier developed noise model has also been presented in the study. The model is validated with measured noise levels and the correlation coefficients between measured and predicted noise levels were found to be 0.75, 0.83 and 0.86 for case I, II and III respectively. The noise model performs reasonably well under different traffic conditions and could be implemented for traffic noise prediction at other region as well.

Adoptive Neuro-Fuzzy Inference System for Traffic Noise Prediction

An adaptive neuro-fuzzy inference system (ANFIS) is implemented to evaluate traffic noise under heterogeneous traffic conditions of Nagpur city, India. The major factors which affect the traffic noise are traffic flow, vehicle speed and honking. These factors are considered as input parameters to ANFIS model for traffic noise estimation. The proposed ANFIS model has implemented for traffic noise estimation at eight locations. The results have been compared and analyzed with observed noise levels and the coefficient of co-relation between observed and predicted noise level was found to be in range of 0.70 to 0.95. The model performance has also been compared with Federal Highway Administration (FHWA), Calculation of road traffic noise (CRTN) and regression noise models and it is observed that the model performs better than conventional statistical noise model. The proposed noise model is completely generalized and problem independent so it can be easily modified to prediction traffic noise under various traffic criteria and serve as first hand tool for traffic noise assessment. General Terms Back propagation algorithm

An adaptive neuro-fuzzy interface system model for traffic classification and noise prediction

In present study, two adaptive neuro-fuzzy models have been developed for traffic classification and noise prediction, respectively. The traffic classification model (ANFIS-TC) classifies extracted sound features of different categories of vehicles based on their acoustic signatures. The model also compute total number of vehicles passes through a particular sampling point. The results have been used for the estimation of the equivalent traffic flow (

Development of GIS based noise simulation model: A case study of Mumbai India Development of GIS-NSM

Q_\mathrm{E})

Development of computer automated decision support system for surface water quality assessment

QE). The noise prediction model (ANFIS-TNP) has three inputs, namely equivalent traffic flow (

Evaluation and analysis of noise levels at traffic intersections of Nagpur city, India.

Q_\mathrm{E})