Abstract
This article presents the operational analysis of urban signalized segments, the most fundamental entity of road networks, operating under heterogeneous traffic conditions. Geometric, traffic, and built-environmental data were collected from mid-block sections and downstream intersections of 45 well-diversified segments. Besides, the socio-demographic details, travel characteristics, and perceived satisfaction scores (varying from 1 \(=\) excellent to 6 \(=\) worst) were collected from 9000 on-street automobile drivers. Subsequently, the variables having significant (\(p < 0.001\)) influences on the perceived satisfaction scores were identified by Spearman’s correlation analysis. As observed, the array of significant variables included six quantitative road attributes and the age group of motorists. By incorporating these variables, highly reliable but less complex automobile level of service (ALOS) models were developed with the help of two novel artificial intelligence techniques namely, multi-gene genetic programming (MGGP) and functional network (FN). Both models exhibited excellent prediction efficiencies in the present context and produced high coefficient of determination (\(R^{2}\)) values of above 0.86 under the prevailing site conditions. The model comparison showed that the MGGP model is more reliable and easier for field implementations as compared to the FN model. The sensitivity analyses of modeled attributes revealed that traffic volume, travel speed, and automobile stop rate have by far the most significant influences on the ALOS of urban streets. The crucial outcomes of this study would largely help the transportation planners and engineers in quantifying the operational efficiencies of urban roadways and in taking efficient decisions for the better management of automobile traffic.
Similar content being viewed by others
Abbreviations
- AAE:
-
Average absolute error
- AI:
-
Artificial intelligence
- ALOS:
-
Automobile level of service
- ANN:
-
Artificial neural network
- AP:
-
Affinity propagation
- CAF:
-
Coordination adjustment factor
- CBD:
-
Central business district
- CCF:
-
Cyclic coordination function
- FCM:
-
Fuzzy c-means
- FFS:
-
Free flow speed
- FN:
-
Functional networks
- GA:
-
Genetic algorithm
- GP:
-
Genetic programming
- GPS:
-
Global positioning system
- Hardcl:
-
Hard competitive learning
- HCM:
-
Highway Capacity Manual
- IRC:
-
Indian Road Congress
- LOS:
-
Level of service
- MAPE:
-
Mean absolute percentage error
- MGGP:
-
Multi-gene genetic programming
- OR:
-
Overfitting ratio
- QOP:
-
Quality of progression
- RMSE:
-
Root-mean-square error
- SF:
-
Shape function
- SSE:
-
Sum of squared error
- AG :
-
Age group
- \(a_{i}\) :
-
Coefficient of \(\phi \)(x) at ith degree
- \({\textit{ALOS}}_{{\mathrm{Max}}}\) :
-
Maximum value of overall perceived ALOS score
- \({\textit{ALOS}}_{{\mathrm{Min}}}\) :
-
Minimum value of overall perceived ALOS score
- \({\textit{ALOS}}_{{\mathrm{Norm}}}\) :
-
Normalized value of overall perceived ALOS score
- \({\textit{ALOS}}_{{\mathrm{Overall}}}\) :
-
Overall perceived ALOS score
- \(\alpha _{k}\), \(x_{0}\) :
-
Constant terms
- C :
-
Cycle length
- D :
-
Maximum deviation in the model output
- \(D_{{\mathrm{Avg}}}\) :
-
Average delay
- \(D_{{\mathrm{Freq}}}\) :
-
Frequency of driveways carrying high traffic volume
- \(d_{{\mathrm{max}}}\) :
-
Maximum depth of GP tree
- E :
-
Nash–Sutcliffe efficiency coefficient
- \(e_{j}\) :
-
Error in the jth data
- \(E_{n}\) :
-
Sum of squared errors for n data sets
- \(E_{\lambda }\) :
-
An auxiliary function
- \(f'\) :
-
Functional element
- F :
-
Model function
- f, g :
-
Any function
- \(f_{{\mathrm{max}}}(x_{i})\) :
-
Maximum value of the predicted output over ith input
- \(f_{{\mathrm{min}}}(x_{i})\) :
-
Minimum value of the predicted output over ith input
- g :
-
Green period
- g / C :
-
Green time over cycle length
- \(G_{{\mathrm{max}}}\) :
-
Maximum number of genes
- L :
-
Number of lanes
- LU :
-
Roadside land use pattern
- m :
-
Degree of shape functions
- n :
-
Number of genes in the target expression
- p :
-
Significance level
- PHV :
-
Peak hour volume
- \(R^{2}\) :
-
Coefficient of determination
- S :
-
Average traffic speed
- s :
-
Number of independent variables
- \(S_{i}\) :
-
Percentage contribution ith input
- SR :
-
Spatial stop rate
- v :
-
Variable
- \(w_{0}\) :
-
Bias parameter
- \(w_{i}\) :
-
Weight of ith gene
- x :
-
Input unit or output unit
- X :
-
Vector of influencing variables
- \(x_{1}, x_{2},{\ldots }, x_{\mathrm{s}}\) :
-
FN model inputs
- \(x_{{\mathrm{s}}+1}\) :
-
FN model output
- y :
-
MGGP model output
- \(\rho \) :
-
Rho
- \(\phi _{i}\) :
-
Shape function of an input variable at ith degree
References
Transportation Research Board (TRB): Highway Capacity Manual, Transportation Research Board of the National Academies, Washington, DC (2000)
TRB: Highway Capacity Manual, Transportation Research Board of the National Academies, Washington, DC (2010)
Science Applications International Corporation (SAIC): Quality of service and customer satisfaction on arterial streets: final report. FHWA, US Department of Transportation (USDOT) (2003). www.itsdocs.fhwa.dot.gov//JPODOCS/REPTS_TE//13849.html
Pécheux, K.; Flannery, A.; Wochinger, K.; Rephlo, J.; Lappin, J.: Automobile drivers’ perceptions of service quality on urban streets. Transp. Res. Rec. 1883, 167–175 (2004). https://doi.org/10.3141/1883-19
Flannery, A.; Wochinger, K.; Martin, A.: Driver assessment of service quality on urban streets. Transp. Res. Rec. 1920, 25–31 (2005). https://doi.org/10.3141/1920-03
Flannery, A.; Rouphail, N.; Reinke, D.: Analysis and modeling of automobile users’ perceptions of quality of service on urban streets. Transp. Res. Rec. 2071, 26–34 (2008). https://doi.org/10.3141/2071-04
Dowling, R.; Flannery, A.; Landis, B.; Petritsch, T.; Rouphail, N.; Ryus, P.: Multimodal level of service for urban streets. Transp. Res. Rec. 2071, 1–7 (2008). https://doi.org/10.3141/2071-01
Deshpande, R.; Gartner, N.; Zarrillo, M.: Urban street performance: level of service and quality of progression analysis. Transp. Res. Rec. 2173, 57–63 (2010). https://doi.org/10.3141/2173-07
Faezi, S.F.; Hamid, H.; Arintono, S.; Davoodi, S.R.: Level of service model for exclusive motorcycle lane. Indian. J. Sci. Technol. 4(4), 387–393 (2011)
Bonneson, J.A.; Pratt, M.; Vandehey. M.: Predicting the performance of automobile traffic on urban streets. NCHRP Project 3–79, Transportation Research Board of the National Academies, Washington, DC (2008)
Dowling, R.: Multimodal level of service analysis for urban streets: users guide. NCHRP Project 3–70, Transportation Research Board of the National Academies, Washington, DC (2009)
Ozkul, S.; Washburn, S.; McLeod, D.: Revised version of the automobile level-of-service methodology for urban streets in the highway capacity manual 2010. Transp. Res. Rec. 2395, 66–72 (2013). https://doi.org/10.3141/2395-08
Shao, M.; Sun, L.: United evaluation model of traffic operation level for different types of urban road. J. Tongji. Univ. (Nat. Sci.) 11, 007 (2010)
Bhuyan, P.K.; Mohapatra, S.S.: Affinity propagation clustering in defining level of service criteria of urban streets. Transport 29(4), 401–411 (2014)
Patnaik, A.K.; Bhuyan, P.K.: Application of genetic programming clustering in defining LOS criteria of urban street in Indian context. Travel. Behav. Soc. 3, 38–50 (2016). https://doi.org/10.1016/j.tbs.2015.08.003
Das, A.K.; Bhuyan, P.K.: Hardcl method for defining los criteria of urban streets. Int. J. Civ. Eng. 1–10 (2017). https://doi.org/10.1007/s40999-017-0207-6
Searson, D.P.; Leahy, D.E.; Willis, M.J.: GPTIPS: An open source genetic programming toolbox from multi-gene symbolic regression. In: International Multi-Conference of Engineers and Computer Scientists I, Hong Kong, pp. 77–80 (2010)
Koza, J.R.: Genetic Programming: on the Programming of Computers by Means of Natural Selection. MIT Press, Cambridge (1992)
McPhee, N.F.; Poli, R.; Langdon, W.B.: A Field Guide to Genetic Programming, Lulu Enterprises, UK Ltd. (2008)
Castillo, E.; Ruiz-Cobo, R.: Functional Equations in Science and Engineering. Marcel Decker, New York (1992)
Castillo, E.; Cobo, A.; Gutiérrez, J.M.; Pruneda, E.: Functional networks: a new network-based methodology. Comput.-Aided. Civ. Infrastruct. 15(2), 90–106 (2000a). https://doi.org/10.1111/0885-9507.00175
Castillo, E.; Cobo, A.; Gómez-Nesterkin, R.; Hadi, A.S.: A general framework for functional networks. Networks 35(1), 70–82 (2000b). https://doi.org/10.1002/(SICI)1097-0037(200001)35:1%3c70::AID-NET6%3e3.0.CO;2-Q
Beura, S.K.; Chellapilla, H.; Bhuyan, P.K.: Urban road segment level of service based on bicycle users’ perception under mixed traffic conditions. J. Mod. Transp. 25(2), 90–105 (2017a). https://doi.org/10.1007/s40534-017-0127-9
Beura, S.K.; Kumar, N.K.; Bhuyan, P.K.: Level of service for bicycle through movement at signalized intersections operating under heterogeneous traffic flow conditions. Transp. Dev. Econ. 3(2), 21p (2017b). https://doi.org/10.1007/s40890-017-0051-z
Bai, L.; Liu, P.; Chan, C.Y.; Li, Z.: Estimating level of service of mid-block bicycle lanes considering mixed traffic flow. Transp. Res. A: Policy Pract. 101, 203–217 (2017). https://doi.org/10.1016/j.tra.2017.04.031
Cochran, W.G.: Sampling Techniques. Wiley, New York (1997)
Bian, Y.; Ma, J.; Rong, J.; Wang, W.; Lu, J.: Pedestrians’ level of service at signalized intersections in China. Transp. Res. Rec. 2114, 83–89 (2009). https://doi.org/10.3141/2114-10
Beura, S.K.; Bhuyan, P.K.: Modeling quality of bicycle accommodations on urban road segments using functional networks and multivariate adaptive regression splines techniques. In: Transportation Research Board’s 96th Annual Meeting, Washington, DC, 20 p (2017)
Gandomi, A.H.; Yun, G.J.; Alavi, A.H.: An evolutionary approach for modeling of shear strength of RC deep beams. Mater. Struct. 46(12), 2109–2119 (2013). https://doi.org/10.1617/s11527-013-0039-z
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Beura, S.K., Bhuyan, P.K. Operational Analysis of Signalized Street Segments Using Multi-gene Genetic Programming and Functional Network Techniques. Arab J Sci Eng 43, 5365–5386 (2018). https://doi.org/10.1007/s13369-018-3176-4
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s13369-018-3176-4