scholarly journals Passenger Flows Estimation of Light Rail Transit (LRT) System in Izmir, Turkey Using Multiple Regression and ANN Methods

1970 ◽  
Vol 24 (1) ◽  
pp. 1-14
Author(s):  
Mustafa Özuysal ◽  
Gökmen Tayfur ◽  
Serhan Tanyel
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Multiple Regression ◽  
Public Transportation ◽  
Light Rail ◽  
Rail Transit ◽  
Light Rail Transit ◽  
Passenger Flow ◽  
Feed Forward Back Propagation ◽  
Artificial Neural

Passenger flow estimation of transit systems is essential for new decisions about additional facilities and feeder lines. For increasing the efficiency of an existing transit line, stations which are insufficient for trip production and attraction should be examined first. Such investigation supports decisions for feeder line projects which may seem necessary or futile according to the findings. In this study, passenger flow of a light rail transit (LRT) system in Izmir, Turkey is estimated by using multiple regression and feed-forward back-propagation type of artificial neural networks (ANN). The number of alighting passengers at each station is estimated as a function of boarding passengers from other stations. It is found that ANN approach produced significantly better estimations specifically for the low passenger attractive stations. In addition, ANN is found to be more capable for the determination of trip-attractive parts of LRT lines.   Keywords: light rail transit, multiple regression, artificial neural networks, public transportation

Application of Artificial Neural Networks in Predicting the Degradation of Tram Tracks Using Maintenance Data

2020 ◽  
pp. 845-864
Author(s):  
Sara Moridpour ◽  
Ehsan Mazloumi ◽  
Reyhaneh Hesami
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Asset Management ◽  
Management Strategies ◽  
Operating Cost ◽  
Light Rail ◽  
Ann Model ◽  
Track Geometry ◽  
Artificial Neural ◽  
And Performance

The increase in number of passengers and tramcars will wear down existing rail structures faster. This is forcing the rail infrastructure asset owners to incorporate asset management strategies to reduce total operating cost of maintenance whilst improving safety and performance. Analysing track geometry defects is critical to plan a proactive maintenance strategy in short and long term. Repairing and maintaining the correctly selected tram tracks can effectively reduce the cost of maintenance operations. The main contribution of this chapter is to explore the factors influencing the degradation of tram tracks (light rail tracks) using existing geometric data, inspection data, load data and repair data. This chapter also presents an Artificial Neural Networks (ANN) model to predict the degradation of tram tracks. Predicting the degradation of tram tracks will assist in understanding the maintenance needs of tram system and reduce the operating costs of the system.

Estimation of the Environmental Load Caused by Introducing Light Rail Transit Using an Urban Transportation Simulator

2013 ◽  
Vol 295-298 ◽  
pp. 669-672
Author(s):  
Nozomi Kudo ◽  
Hideo Nakamura
Keyword(s):  
Public Transportation ◽  
Urban Transportation ◽  
Light Rail ◽  
Rail Transit ◽  
Environmental Load ◽  
Light Rail Transit ◽  
Low Carbon ◽  
Modal Shift

A modal shift from automobiles is imperative in the transportation field for realizing a low-carbon society. We have developed a simulator that can quantitatively assess the effect of a modal shift by simulating track-based public transportation, such as LRT (Light Rail Transit), and automobile transportation. This paper presents an example in which we used the simulator to calculate the effect in a case where track-based transportation is implemented.

scholarly journals Artificial neural networks predictive models. A case study: carbon and bromine concentrations prediction based on chlorination time

2013 ◽  
Vol 14 (1) ◽  
pp. 10-17
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Potable Water ◽  
Back Propagation ◽  
Ann Model ◽  
Data Set ◽  
Test Set ◽  
Feed Forward Back Propagation ◽  
Artificial Neural ◽  
Comparison Of The Results

Artificial neural networks (ANNs) are being used increasingly to predict water variables. This study offers an alternative approach to quantify the relationship between time of chlorination in potable water (due to convectional treatment procedure) and chlorination by-products concentration (expressed as carbon and bromine) with an ANN model, i.e., capturing non-linear relationships among the water quality variables. Thus, carbon and bromine concentrations in potable water (the second chosen due to the toxicity of brominated trihalomethanes, THMs) were predicted using artificial neural networks (ANNs) based mainly on multi-layer perceptrons (MLPs) architecture. The chlorination (detention) time as much as 58 hours in Athens distributed network, comprised the input variables to the ANNs models. Moreover, to develop an ANN model for estimating carbon and bromine, the available data set was partitioned into training, validation and test set. In order to reach an optimum amount of hidden layers or nodes, different architectures were tested. The quality of the ANN simulations was evaluated in terms of the error in the validation sample set for the proper interpretation of the results. The calculated sum-squared errors for training, validation and test set were 0.056, 0.039 and 0.060 respectively for the best model selected. Comparison of the results showed that a two-layer feed-forward back propagation ANN model could be used as an acceptable model for predicting carbon and bromine contained in potable water THMs.

Sign in / Sign up

Export Citation Format

Share Document