# Transport Choice Modeling for the Evaluation of New Transport Policies

^{1}

^{2}

^{*}

## Abstract

**:**

## 1. Introduction

**Trip generation:**Generate a specific, whether fixed or approximated, amount of vehicles that represents the population.**Trip distribution:**Spread the population along the scenario in a realistic distribution.**Transport choice:**Schedule their transport mode and itineraries throughout the city to reach their destination.**Traffic simulation:**Estimate the global impact derived from the configuration of a single scenario and compare the results with those obtained from others.

**Micro-simulation models:**These models describe traffic with a high level of detail and distinguish separate elements in the traffic flow, such as types of vehicles and pedestrians. Though the use of this high level of detail entails very precise analysis, it must be limited to a small area or intersection due to its complexity. The most popular micro-simulation tools are PTV Vissim [14], Aimsun [15], and Corsim [16].**Meso-simulation models:**These models describe traffic with an intermediate level of detail, distinguishing separate elements in the traffic flow but not taking into account the interactions between them. They are less precise and can be applied to cover larger areas than those of the micro-simulation. The most popular meso-simulation tools are Dynasmart [17] and Transims [18].**Macro-simulation models:**These models describe traffic with a high level of aggregation, as a uniform traffic flow. They are based on deterministic relationships between the parameters characterizing the traffic flow, such as volume, speed, or density. Macroscopic simulation has been developed to model an entire transport network and/or system. The most popular macro-simulation tools are Emme/2 [19], PTV Visum [20], and Transcad [21].

## 2. Materials and Methods

#### 2.1. Trip Generation and Distribution

^{2}. The census also details the points of origin and destination of traveling for the most populated 11 municipalities of the region, with a total population of about 1,100,000 citizens. This data set will be used to train the different models. On the other hand, Silesia commutes (depicted in Figure 1b and Figure 2b) were extracted from the green traveling project’s surveys [26]. The data set covers 19 municipalities of the central part of Silesian Voivodeship with a population of 4,710,000 citizens. This data set will be used to validate the results.

#### 2.2. Transport Mode Choice

#### 2.2.1. Multinomial Logit Models

#### 2.2.2. Support Vector Machines

#### 2.2.3. Neural Networks

#### 2.2.4. The Naïve Bayes (B) model

#### 2.2.5. k-Nearest Neighbours

#### 2.2.6. Fuzzy Logic

**Inputs, terms, and membership functions:**For the engine to translate from linguistic terms to numbers, inputs are composed of a name that identifies the input, the possible terms or values that the input can take, and a membership function that limits the extent to which each term can be classified. The inputs of the model presented here are built from the four previously mentioned itinerary features: DURATION, PRICE, LENGTH, and ENVIRONMENTAL IMPACT. Each of these inputs feature a fixed set of three terms: LOW, MEDIUM, and HIGH, shaped as triangles. The anchors of these triangles ($\alpha $, $\beta $, $\gamma $, and $\delta $), shown in Figure 5, are key values that describe how citizens understand these qualitative variables.**Outputs, terms, and membership functions:**Similarly to the inputs, the outputs are composed of a name that identifies the output, the possible terms or values the output can take, and a membership function for each term. The model presented here features a single output with five fixed, non-overlapping terms that represent the transport modes among which to choose: CAR, MOTORCYCLE, PUBLIC TRANSPORT, BICYCLE, and WALK, as represented in Figure 6.**Rules:**Rules follow the following structure: if INPUT is INPUT_TERM and … then OUTPUT is OUTPUT_TERM. The engine needs a set of rules, each with one output but with one or more terms, as depicted in Table 3. Additionally, the engine provides fuzzy value modifiers or hedges through natural language keywords to help describe border cases without the need to include additional terms: ANY, NOT, EXTREMELY, SELDOM, SOMEWHAT, or VERY. The defuzzifier will be the maximum value between the three terms, that is, the term that receives the maximum value and thus the one chosen by the citizen. Please note that only AND conjunctions will be used between rule terms, since disjunctions can be represented by splitting a rule in two or using the NOT hedge.

#### Expert Fuzzy Knowledge (EK)

#### A Co-Evolutionary Fuzzy Logic Algorithm (CE)

**Input-evolving sub-component:**This is composed of a population of 200 input sets. Each input set features the four input variables already mentioned—DURATION, PRICE, LENGTH, and ENVIRONMENT. Each input has three fixed and ordered terms—LOW, MEDIUM, and HIGH—whose triangle anchors $\alpha $, $\beta $, $\gamma $, and $\delta $ (see Figure 5 for details) can be modified in search of limits that better fit the citizens’ appreciation for these qualitative terms.**Rule evolving sub-component:**This is composed of a population of 200 rule sets. Each rule set features a list with a variable number of rules, and, for each rule, its terms and output are modified to extract the combination of rules that more faithfully represents citizens’ transport choice from the census.

**Operators used for Rules:****rule set slice crossover**Given two rule sets, this operator creates a new rule set, taking the first to n rules from the first set and the n to last rules from the second set.**rule set combine crossover**Given two rule sets, this operator creates a new rule set, appending for each position a randomly selected rule from the same position of the two provided rule sets.**rule set slice terms crossover**Given two rule sets, this operator clones the first rule set and selects a p rule in the set. The p rule’s terms are replaced by the first to n terms from the p rule of the first set and n to last from the p rule of the second provided set.

**Fuzzy Logic Input Membership Functions:****input set combine crossover**Given two input sets, this function creates a new input set, appending for each position a randomly selected element from the same position of the two provided input sets.**input set shape mutation**Given an input set, this function modifies one of the $\alpha $, $\beta $, $\gamma $, or $\delta $ values from the shapes in Figure 5. It will displace at the same time the first term’s triangle’s third point, the second term’s triangle’s mid-point, and the third term’s triangle’s first point.

- initialize the population of rule sets and input sets that will take part in the co-evolutionary process, and
- initialize the co-evolutionary process itself where the rule sets and input sets evolve together through the application of the evolutionary operators, the calculation of the fuzzy experiments’ fitness on each iteration, and the update of the percentage of census being used for evaluation.

#### Random Search (RA)

#### 2.3. Transport Simulation

## 3. Experimental Results

## 4. Conclusions and Future Work

- Some of the models produce unbalanced predictions, like M, SVM and NN, which completely ignore some of the transport modes. Therefore, given the similar prediction capabilities, the models with more balanced predictions should be used, namely, the EK, CE, and KNN models.
- The number of parameters and complexity of the models are not the same either. In this sense, simpler models should be preferred to more complex models. However, EK, CE, and KNN are non-parametric, and their complexity is difficult to assess. On the one hand, the number of parameters of KNN is indeed the amount of points in the training data set, but the complexity of the model is quite low (understanding here the complexity in terms of its VC dimension or similar measures [53]). On the other hand, the amount of parameters in the EK and CE models is quite low (compared to the number of parameters of KNN), but the complexity of the model is higher [54].
- Comparing the EK and CE fuzzy rule sets, both have similar amounts of rules (EK has 33 and CE has 30). However, the EK rules are only composed of one or two terms, which makes it easy to follow and modify, while the CE evolved rules usually have about 10 or more terms with a relation between them that is not very clear.
- It is always better to use a model that is easy to be understood than a data-driven model. Following this advice, EK and M should be preferred to the rest of the models.

## Acknowledgments

## Author Contributions

## Conflicts of Interest

## Appendix A. Result tables

Biscay | Silesia | ||||||||||
---|---|---|---|---|---|---|---|---|---|---|---|

Observed | Observed | ||||||||||

B | C | M | T | W | B | C | M | T | W | ||

Forecast | B | 20.9302 | 25.9588 | 13.5483 | 16.9042 | 22.9138 | 39.8180 | 6.3235 | 0 | 0.0005 | 0.0051 |

C | 14.3410 | 19.8004 | 11.6129 | 18.5639 | 6.8561 | 3.597 | 23.9876 | 8.5339 | 5.12764 | 53.5860 | |

M | 18.9922 | 14.4995 | 23.8709 | 21.0896 | 23.0491 | 13.3028 | 8.1699 | 20.8480 | 1.726741 | 12.15994 | |

T | 12.7906 | 17.5709 | 14.8387 | 14.0898 | 4.2399 | 16.4029 | 12.1599 | 60.1307 | 24.0259 | 33.56175 | |

W | 32.9457 | 22.1702 | 36.1290 | 29.3523 | 42.9409 | 26.8792 | 49.3589 | 10.4874 | 69.1292 | 0.6872 |

Biscay | Silesia | ||||||||||
---|---|---|---|---|---|---|---|---|---|---|---|

Observed | Observed | ||||||||||

B | C | M | T | W | B | C | M | T | W | ||

Forecast | B | 25.5814 | 18.45266 | 28.70968 | 22.90614 | 20.75812 | 4.3421 | 3.6566 | 3.2258 | 4.0652 | 5.2098 |

C | 5.03876 | 26.15817 | 3.870968 | 5.018051 | 3.745487 | 43.2894 | 55.6609 | 20.9677 | 50.0042 | 14.4617 | |

M | 0 | 0 | 0 | 0 | 0 | 46.3157 | 35.6888 | 64.5161 | 40.3782 | 48.2227 | |

T | 24.03101 | 31.14959 | 24.51613 | 29.07942 | 5.685921 | 0.3947 | 0.1415 | 0 | 0.1385 | 0.5517 | |

W | 45.34884 | 24.23959 | 42.90323 | 42.99639 | 69.81047 | 5.6578 | 4.8519 | 11.2903 | 5.4137 | 31.5539 |

Biscay | Silesia | ||||||||||
---|---|---|---|---|---|---|---|---|---|---|---|

Observed | Observed | ||||||||||

B | C | M | T | W | B | C | M | T | W | ||

Forecast | B | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 |

C | 34.1085 | 63.6576 | 36.7741 | 38.2283 | 11.1411 | 61.7693 | 68.9583 | 43.7908 | 65.7117 | 77.1642 | |

M | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | |

T | 65.8914 | 36.3423 | 63.2258 | 61.7716 | 88.8588 | 38.2306 | 31.0416 | 56.2091 | 34.2882 | 22.8357 | |

W | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 |

Biscay | Silesia | ||||||||||
---|---|---|---|---|---|---|---|---|---|---|---|

Observed | Observed | ||||||||||

B | C | M | T | W | B | C | M | T | W | ||

Forecast | B | 3.0076 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 |

C | 34.2105 | 64.5774 | 118 | 2306 | 248 | 63.1384 | 71.4683 | 44.117 | 68.3363 | 15.8941 | |

M | 0 | 0 | 0 | 0 | 0 | 0.1843 | 0.6491 | 0 | 0.5331 | 0.0051 | |

T | 62.7819 | 35.3445 | 192 | 3236 | 1969 | 36.5718 | 27.8083 | 55.8823 | 31.0581 | 83.6567 | |

W | 0 | 0.0779 | 0 | 1 | 0 | 0.1053 | 0.0742 | 0 | 0.0723 | 0.4439 |

Biscay | Silesia | ||||||||||
---|---|---|---|---|---|---|---|---|---|---|---|

Observed | Observed | ||||||||||

B | C | M | T | W | B | C | M | T | W | ||

Forecast | B | 0 | 0.0155 | 0 | 0 | 0 | 0.0263 | 0.0233 | 0 | 0.0316 | 0.0487 |

C | 33.0827 | 63.5640 | 115 | 2250 | 298 | 42.7330 | 52.2078 | 26.1437 | 48.8802 | 17.4520 | |

M | 0 | 0 | 0 | 0 | 0 | 0.1053 | 0.0623 | 0 | 0.0593 | 0.2540 | |

T | 62.4060 | 36.0773 | 193 | 3257 | 1883 | 56.7667 | 47.2574 | 72.8758 | 50.5170 | 81.1723 | |

W | 1.5037 | 0.3429 | 2 | 36 | 36 | 0.3686 | 0.4490 | 0.9803 | 0.5116 | 1.0727 |

Biscay | Silesia | ||||||||||
---|---|---|---|---|---|---|---|---|---|---|---|

Observed | Observed | ||||||||||

B | C | M | T | W | B | C | M | T | W | ||

Forecast | B | 3.3835 | 0.2806 | 0.3225 | 0.2164 | 0 | 0.9215 | 2.4044 | 1.6339 | 1.0844 | 0.8469 |

C | 9.3984 | 29.7006 | 7.7419 | 7.4688 | 4.1948 | 26.5139 | 31.6341 | 17.9738 | 30.5481 | 17.5213 | |

M | 0 | 0 | 0 | 0 | 0 | 0.7635 | 0.5622 | 0 | 0.6038 | 0.6980 | |

T | 18.7969 | 27.2840 | 20.3225 | 26.3575 | 5.1420 | 18.6677 | 24.3470 | 7.8431 | 21.9218 | 0.1154 | |

W | 68.4210 | 42.7346 | 71.6129 | 65.9570 | 90.6630 | 53.1332 | 41.0521 | 72.5490 | 45.8417 | 80.8181 |

Biscay | Silesia | ||||||||||
---|---|---|---|---|---|---|---|---|---|---|---|

Observed | Observed | ||||||||||

B | C | M | T | W | B | C | M | T | W | ||

Forecast | B | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 |

C | 33.4586 | 64.4839 | 37.0967 | 33.1048 | 21.2449 | 52.9489 | 61.7642 | 38.2352 | 58.5322 | 26.5013 | |

M | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | |

T | 54.1353 | 31.6027 | 54.8387 | 60.7793 | 60.9833 | 44.7077 | 36.1090 | 58.8235 | 39.1705 | 61.8109 | |

W | 12.406 | 3.9133 | 8.0645 | 6.1158 | 17.7717 | 2.3433 | 2.1267 | 2.9411 | 2.2972 | 11.6877 |

Biscay | Silesia | ||||||||||
---|---|---|---|---|---|---|---|---|---|---|---|

Observed | Observed | ||||||||||

B | C | M | T | W | B | C | M | T | W | ||

Forecast | B | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 |

C | 100 | 100 | 100 | 100 | 100 | 0 | 0.1434 | 1.9608 | 5.1742 | 23.0056 | |

M | 0 | 0 | 0 | 0 | 0 | 100 | 85.717 | 98.0392 | 91.1507 | 76.2244 | |

T | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3.6751 | 0 | |

W | 0 | 0 | 0 | 0 | 0 | 0 | 14.1396 | 0 | 0 | 0.7699 |

Biscay | Silesia | ||||||
---|---|---|---|---|---|---|---|

Observed | Observed | ||||||

P | T | W | P | T | W | ||

Forecast | P | 27.2306 | 8.5771 | 10.8617 | 64.3052 | 60.4932 | 32.9044 |

T | 47.6867 | 51.6633 | 27.5583 | 0.0528 | 0.0587 | 0.4739 | |

W | 25.0826 | 39.7595 | 61.5798 | 35.6419 | 39.4479 | 66.6216 |

Biscay | Silesia | ||||||
---|---|---|---|---|---|---|---|

Observed | Observed | ||||||

P | T | W | P | T | W | ||

Forecast | P | 27.8851 | 6.9637 | 5.2929 | 23.3397 | 26.4874 | 15.1919 |

T | 44.8245 | 46.1122 | 21.0505 | 40.5583 | 55.2673 | 59.8538 | |

W | 27.2903 | 46.9240 | 73.6565 | 36.102 | 18.2453 | 24.9543 |

Biscay | Silesia | ||||||
---|---|---|---|---|---|---|---|

Observed | Observed | ||||||

P | T | W | P | T | W | ||

Forecast | P | 63.9797 | 40.0144 | 14.1414 | 63.9771 | 60.4658 | 20.4924 |

T | 36.0202 | 59.9855 | 85.7373 | 36.0228 | 39.5341 | 79.5075 | |

W | 0 | 0 | 0.1212 | 0 | 0 | 0 |

Biscay | Silesia | ||||||
---|---|---|---|---|---|---|---|

Observed | Observed | ||||||

P | T | W | P | T | W | ||

Forecast | P | 65.9131 | 44.1096 | 15.1919 | 76.5456 | 74.0214 | 22.5083 |

T | 34.0124 | 55.8722 | 84.8080 | 23.3329 | 25.8451 | 77.0076 | |

W | 0.0743 | 0.0180 | 0 | 0.1214 | 0.1334 | 0.4840 |

Biscay | Silesia | ||||||
---|---|---|---|---|---|---|---|

Observed | Observed | ||||||

P | T | W | P | T | W | ||

Forecast | P | 58.0011 | 36.3882 | 14.9090 | 47.2961 | 47.0370 | 24.9403 |

T | 41.6121 | 63.1968 | 83.9595 | 51.6283 | 51.9418 | 70.7169 | |

W | 0.3866 | 0.4149 | 1.1313 | 1.0754 | 1.0211 | 4.3426 |

Biscay | Silesia | ||||||
---|---|---|---|---|---|---|---|

Observed | Observed | ||||||

P | T | W | P | T | W | ||

Forecast | P | 28.9708 | 7.6853 | 4.8080 | 34.6062 | 32.2438 | 19.8774 |

T | 26.9333 | 26.3575 | 6.6262 | 24.3029 | 21.9127 | 1.7585 | |

W | 44.0957 | 65.9570 | 88.5656 | 41.0908 | 45.8434 | 78.3639 |

Biscay | Silesia | ||||||
---|---|---|---|---|---|---|---|

Observed | Observed | ||||||

P | T | W | P | T | W | ||

Forecast | P | 99.9366 | 99.9431 | 100 | 22.3468 | 100 | 100 |

T | 0 | 0 | 0 | 77.6532 | 0 | 0 | |

W | 0.0633 | 0.0568 | 0 | 0 | 0 | 0 |

Biscay | Silesia | ||||||
---|---|---|---|---|---|---|---|

Observed | Observed | ||||||

P | T | W | P | T | W | ||

Forecast | P | 65.9875 | 36.4604 | 25.3737 | 64.2006 | 61.2099 | 31.7244 |

T | 29.0898 | 55.9985 | 53.4949 | 33.0386 | 35.7617 | 54.8664 | |

W | 4.9226 | 7.5410 | 21.1313 | 2.7607 | 3.0282 | 13.4091 |

## References

- De Donnea, F.X. The Determinants of Transport Mode Choice in Dutch Cities: Some Disaggregate Stochastic Models; Universitaire Pers Rotterdam: Rotterdam, The Netherlands, 1971. [Google Scholar]
- Holtsmark, B.; Skonhoft, A. The Norwegian support and subsidy policy of electric cars. Should it be adopted by other countries? Environ. Sci. Policy
**2014**, 42, 160–168. [Google Scholar] [CrossRef] - Karlaftis, M.G.; Vlahogianni, E.I. Statistical methods versus neural networks in transportation research: Differences, similarities and some insights. Transp. Res. Part C Emerg. Technol.
**2011**, 19, 387–399. [Google Scholar] [CrossRef] - Fernández-Isabel, A.; Fuentes-Fernández, R. An agent-based platform for traffic simulation. In Soft Computing Models in Industrial and Environmental Applications, 6th International Conference SOCO 2011; Springer: Berlin/Heidelberg, Germany, 2011; pp. 505–514. [Google Scholar]
- Bazzan, A.L.; Klügl, F. A review on agent-based technology for traffic and transportation. Knowl. Eng. Rev.
**2014**, 29, 375–403. [Google Scholar] [CrossRef] - Rubinstein, R.Y.; Kroese, D.P. Simulation and the Monte Carlo Method; John Wiley & Sons: Hoboken, NJ, USA, 2016; Volume 10. [Google Scholar]
- Keilson, J. Markov Chain Models—Rarity and Exponentiality; Springer Science & Business Media: Berlin, Germany, 2012; Volume 28. [Google Scholar]
- Allen, A.O. Probability, Statistics, and Queueing Theory; Academic Press: Cambridge, MA, USA, 2014. [Google Scholar]
- Meyer, M.D.; Miller, E.J. Urban Transportation Planning: A Decision-Oriented Approach; McGraw-Hill: New York, NY, USA, 1984. [Google Scholar]
- McNally, M.G. The four-step model. In Handbook of Transport Modelling, 2nd ed.; Emerald Group Publishing Limited: Bingley, UK, 2007; pp. 35–53. [Google Scholar]
- Wooldridge, M.; Jennings, N.R. Intelligent Agents: Theory and Practice; Cambridge University Press: Cambridge, UK, 1995. [Google Scholar]
- Owen, L.E.; Zhang, Y.; Rao, L.; McHale, G. Street and traffic simulation: Traffic flow simulation using CORSIM. In Proceedings of the 32nd conference on Winter simulation, Orlando, FL, USA, 10–13 December 2000; pp. 1143–1147. [Google Scholar]
- Saad, F. In-depth analysis of interactions between drivers and the road environment: Contribution of on-board observations and subsequent verbal report. In Proceedings of the 4th Workshop of ICTCT, University of Lund, Vienna, Austria, November 1992. [Google Scholar]
- PTV AG. PTV Vissim 7—USER MANUAL; PTV AG: Karlsruhe, Njemačka, 2015. [Google Scholar]
- Barceló, J.; Casas, J. Dynamic network simulation with AIMSUN. In Simulation Approaches in Transportation Analysis; Springer: Boston, MA, USA, 2005; pp. 57–98. [Google Scholar]
- Halati, A.; Lieu, H.; Walker, S. CORSIM-corridor traffic simulation model. In Proceedings of the Traffic Congestion and Traffic Safety in the 21st Century: Challenges, Innovations, and Opportunities, Chicago, IL, USA, 8–11 June 1997. [Google Scholar]
- Mahmassani, H. Dynamic traffic assignment and simulation for advanced network informatics (DYNASMART). In Proceedings of the 2nd International Seminar on Urban Traffic Networks, Capri, Italy, 5–8 July 1992. [Google Scholar]
- Smith, L.; Beckman, R.; Anson, D.; Nagel, K.; Williams, M. TRANSIMS: Transportation Analysis and Simulation System; Technical Report; Los Alamos National Lab.: Los Alamos, NM, USA, 1995.
- Babin, A.; Florian, M.; James-Lefebvre, L.; Spiess, H. Emme/2 an interactive graphic method for road and transit planning. In Proceedings of the RTAC Annual Conference Preprints, Washington, DC, USA, 18–22 January 1981; Volume 1. [Google Scholar]
- PTV Group Ptv Visum. 2016. Available online: http://your.visum.ptvgroup.com/FreeDemoVersion (accessed on 4 November 2016).
- Ji, M.; Yu-long, P. Development and application of TransCAD for urban traffic planning. J. Harbin Univ. Civ. Eng. Archit.
**2002**, 5, 028. [Google Scholar] - Balcombe, R.; Mackett, R.; Paulley, N.; Preston, J.; Shires, J.; Titheridge, H.; Wardman, M.; White, P. The Demand for Public Transport: A Practical Guide; Transportation Research Laboratory: Wokingham, UK, 2004. [Google Scholar]
- Train, K. Qualitative Choice Analysis: Theory, Econometrics, and an Application to Automobile Demand, 1st ed.; The MIT Press: Cambridge, MA, USA, 1985; Volume 1. [Google Scholar]
- Rich, J.; Holmblad, P.; Hansen, C. A weighted logit freight mode-choice model. Transp. Res. Part E Logist. Transp. Rev.
**2009**, 45, 1006–1019. [Google Scholar] [CrossRef] - Instituto Nacional de Estadística. Censos 2011. 2011. Available online: http://www.ine.es/censos2011_datos/cen11_datos_resultados.html (accessed on 13 April 2018).
- Green Travelling Consortium. A Platform to Analyse and Foster the Use of Green Travelling Options; Technical Report, Project Proposal, The ERA-NET Transport III: Future Travelling; Avda. Universidades: Bilbao, Spain, 2013. [Google Scholar]
- Domencich, T.A.; McFadden, D. Urban Travel Demand—A Behavioral Analysis; North-Holland Publishing Co.: Amsterdam, The Netherlands, 1975. [Google Scholar]
- Chiu Chuen, O.; Karim, M.R.; Yusoff, S. Mode Choice between Private and Public Transport in Klang Valley, Malaysia. Sci. World J.
**2014**, 2014, 394587. [Google Scholar] [CrossRef] [PubMed] - Clauss, T.; Döppe, S. Why do urban travelers select multimodal travel options: A repertory grid analysis. Transp. Res. Part A Policy Pract.
**2016**, 93, 93–116. [Google Scholar] [CrossRef] - Pijoan, A.; Borges, C.E.; Oribe-Garcia, I.; Martin, C.; Alonso-Vicario, A. Agent Based Simulations for the Estimation of Sustainability Indicators. Procedia Comput. Sci.
**2015**, 51, 2943–2947. [Google Scholar] [CrossRef] - Altman, N.S. An introduction to kernel and nearest-neighbor nonparametric regression. Am. Stat.
**1992**, 46, 175–185. [Google Scholar] - Lemeshow, S.; Sturdivant, R.X.; Hosmer, D.W. Applied Logistic Regression; Wiley: Hoboken, NJ, USA, 2013. [Google Scholar]
- Cristianini, N.; Shawe-Taylor, J. An Introduction to Support Vector Machines and Other Kernel-Based Learning Methods; Cambridge University Press: Cambridge, UK, 2000. [Google Scholar]
- Schalkoff, R.J. Artificial Neural Networks; McGraw-Hill: New York, NY, USA, 1997; Volume 1. [Google Scholar]
- Lewis, D.D. Naive (Bayes) at forty: The independence assumption in information retrieval. In Machine Learning: ECML-98; Springer: Berlin/Heidelberg, Germany, 1998; pp. 4–15. [Google Scholar]
- Mendel, J.M. Uncertain Rule-Based Fuzzy Logic Systems: Introduction and New Directions; Prentice Hall PTR: Upper Saddle River, NJ, USA, 2001. [Google Scholar]
- Souche, S. Measuring the structural determinants of urban travel demand. Transp. Policy
**2010**, 17, 127–134. [Google Scholar] [CrossRef] [Green Version] - Chang, C.C.; Lin, C.J. LIBSVM: A Library for Support Vector Machines. ACM Trans. Intell. Syst. Technol.
**2011**, 2, 27:1–27:27. [Google Scholar] [CrossRef] - Von Seggern, D.H. CRC Standard Curves and Surfaces with Mathematica; CRC Press: Boca Raton, FL, USA, 2006. [Google Scholar]
- Kumar, M.; Sarkar, P.; Madhu, E. Development of fuzzy logic based mode choice model considering various public transport policy options. Int. J. Traffic Transp. Eng.
**2013**, 3, 408–425. [Google Scholar] [CrossRef] - Tuzkaya, U.R.; Önüt, S. A fuzzy analytic network process based approach to transportation-mode selection between Turkey and Germany: A case study. Inf. Sci.
**2008**, 178, 3133–3146. [Google Scholar] [CrossRef] - Berkan, R.C.; Trubatch, S. Fuzzy System Design Principles; Wiley-IEEE Press: Hoboken, NJ, USA, 1997. [Google Scholar]
- Staniek, M.; Sierpiński, G. Cost Criteria as a Means to Support Travelling Mode Related Decisions—A Case Study for the Central Part of Silesian Voivodeship (Poland). In Sustainable Transport Development, Innovation and Technology; Springer: Cham, Switzerland, 2016; pp. 137–150. [Google Scholar]
- Sierpiński, G.; Staniek, M.; Celiński, I. Travel behavior profiling using a trip planner. Transp. Res. Procedia
**2016**, 14, 1743–1752. [Google Scholar] [CrossRef] - Herrera, F. Genetic fuzzy systems: Taxonomy, current research trends and prospects. Evolut. Intell.
**2008**, 1, 27–46. [Google Scholar] [CrossRef] - Potter, M.A.; De Jong, K.A. A cooperative coevolutionary approach to function optimization. In Parallel Problem Solving from Nature; Springer: Berlin/Heidelberg, Germany, 1994; pp. 249–257. [Google Scholar]
- Pijoan, A.; Kamara-Esteban, O.; Borges, C.E. Environment modelling for spatial load forecasting. In Agent Environments for Multi-Agent Systems IV; Springer: Verlag, New York, 2014; pp. 188–206. [Google Scholar]
- Rada-Vilela, J. Fuzzylite: A Fuzzy Logic Control Library. 2017. Available online: https://www.fuzzylite.com/ (accessed on 13 April 2018).
- Kuhn, M. caret: Classification and Regression Training; R Package Version 6.0-78; ASCL: Leicester, UK, 2017. [Google Scholar]
- R Core Team. R: A Language and Environment for Statistical Computing; R Foundation for Statistical Computing: Vienna, Austria, 2017. [Google Scholar]
- Efron, B. Bootstrap Methods: Another Look at the Jackknife. Ann. Stat.
**1979**, 7, 1–26. [Google Scholar] [CrossRef] - Piepho, H.P. An Algorithm for a Letter-Based Representation of All-Pairwise Comparisons. J. Comput. Graph. Stat.
**2004**, 13, 456–466. [Google Scholar] [CrossRef] - Vapnik, V.N.; Chervonenkis, A.Y. On the Uniform Convergence of Relative Frequencies of Events to Their Probabilities. Theory Probab. Appl.
**1971**, 16, 264–280. [Google Scholar] [CrossRef] - Chen, Y.; Wang, J.Z. Support vector learning for fuzzy rule-based classification systems. IEEE Trans. Fuzzy Syst.
**2003**, 11, 716–728. [Google Scholar] [CrossRef] - Khattak, Z.H.; Magalotti, M.J.; Miller, J.S.; Fontaine, M.D. Using New Mode Choice Model Nesting Structures to Address Emerging Policy Questions: A Case Study of the Pittsburgh Central Business District. Sustainability
**2017**, 9, 2120. [Google Scholar] [CrossRef] - Ding, L.; Zhang, N. A travel mode choice model using individual grouping based on cluster analysis. Procedia Eng.
**2016**, 137, 786–795. [Google Scholar] [CrossRef]

**Figure 1.**Area and transport links of Biscay (Spain) and Silesia (Poland) data sets. Source: own research generated from real boundaries and transport networks.

**Figure 3.**Distribution of time (

**left**) and length (

**right**) for CAR and BICYCLE transport modes in Silesian Voivodeship.

**Figure 5.**Fuzzy engine input membership functions, with the configurable anchors that modify the shape of the terms. Source: own research for better understanding the input membership functions.

**Figure 6.**Fuzzy engine output. Each term represents a mode of transport one may choose. Source: own research for better understanding the fuzzy logic output membership function.

**Figure 7.**Iterations of the co-evolutive fuzzy algorithm. Source: own research by plotting the evolution in time of the algorithm.

**Figure 8.**Pseudocode of the co-evolutionary fuzzy logic algorithm. Source: own research simplification of the real code programmed in the algorithm.

**Figure 9.**Box plot of the distribution of the models’ accuracy of the three transport modes on 100 bootstrapping samples. In Biscay, the probability of using BICYCLE, CAR, MOTORCYCLE, TRANSIT, and WALK is 1.75%, 43.51%, 2.1%, 37.6%, and 15.04%, respectively. In Silesia, the probability of using BICYCLE, CAR, MOTORCYCLE, TRANSIT, and WALK is 0.82%, 53.96%, 0.12%, 36.33%, and 8.75%, respectively. Therefore, if a model can produce such a forecast, it will achieve an accuracy of 100 %. Source: own research generated from R Statistical Suite [50].

**Figure 10.**Results of an ALL vs. ALL post-hoc analysis of the accuracy of the models. Source: own research by plotting the results from R Statistical Suite [50].

**Table 1.**Itinerary features used for transport choice. Source: Adapted from [29].

Feature | Description | Encompasses |
---|---|---|

Duration | Time necessary (in seconds) to complete the itinerary from the departure point until arriving at the destination. | Closeness to public transport stop and parking spaces. |

Frequency and reliability of public transport. | ||

In-journey traveling time. | ||

Traffic congestion. | ||

Transfer waiting time between two means of transport. | ||

Waiting environment. | ||

Poor waiting time. | ||

Price | Monetary cost (in euros) of the itinerary including public transport tickets, parking fares and private vehicle costs. | Public transport fares. |

Private vehicle purchase, maintenance, and fuel costs. | ||

Tolls and congestion charges. | ||

Economic incentives. | ||

Length | Distance of the itinerary (in kilometers). For long- and medium-length travels, this is not a determinant factor. This is only when walking or cycling are an option. | Walking distance. |

Cycling distance. | ||

Environmental impact | Contribution to climate change (measured in CO_{2} emissions). Regarding short distance and itineraries, where transports compete in similar conditions, environmental awareness can be the trigger that determines user decisions. | Environmental impact of the trip. |

**Table 2.**Itinerary features are not present in the data sets and are beyond the scope of the study. Source: own research, conducted by analyzing the features mentioned in [27], which are not present in the data sets.

Feature | Description | Encompasses |
---|---|---|

Profile | Personal demographic, socio-economical, and cultural attributes of the user. | Citizen age |

Citizen gender | ||

Socio-economic profile | ||

Cultural profile | ||

Family size | ||

Trip type | ||

Ownership | Vehicle(s) under the property of the user. | Car ownership |

Motorcycle ownership | ||

Bicycle ownership | ||

Climatology | Variables that may have a direct impact on the physical variables of the trip, i.e., if it rains, the duration of a trip may take longer than usual. | Environment climatology |

**Table 3.**Example of fuzzy engine rule sets. Source: own research for explaining the structure and examples of fuzzy logic rules.

if TRANSIT_DURATION is HIGH and TRANSIT_PRICE is HIGH then TRANSPORT is PRIVATE |

if TRANSIT_DURATION is HIGH and PRIVATE_DURATION is LOW then TRANSPORT is PRIVATE |

if PRIVATE_PRICE is HIGH and TRANSIT_PRICE is LOW and TRANSIT_DURATION is MEDIUM then TRANSPORT is TRANSIT |

if WALK_LENGTH is LOW and TRANSIT_PRICE is HIGH then TRANSPORT is WALK |

if CAR_PRICE is LOW then TRANSPORT is CAR |

if CAR_TIME is LOW and TRANSIT_TIME is HIGH then TRANSPORT is CAR |

if CAR_TIME is MEDIUM and TRANSIT_TIME is HIGH then TRANSPORT is CAR |

if CAR_TIME is LOW and MOTORCYCLE_TIME is MEDIUM then TRANSPORT is CAR |

if CAR_TIME is LOW and MOTORCYCLE_TIME is HIGH then TRANSPORT is CAR |

if CAR_PRICE is LOW and TRANSIT_PRICE is LOW then TRANSPORT is CAR |

if CAR_PRICE is LOW and TRANSIT_PRICE is MEDIUM then TRANSPORT is CAR |

if CAR_PRICE is LOW and TRANSIT_PRICE is HIGH then TRANSPORT is CAR |

if CAR_PRICE is MEDIUM and TRANSIT_PRICE is MEDIUM then TRANSPORT is CAR |

if CAR_PRICE is MEDIUM and TRANSIT_PRICE is HIGH then TRANSPORT is CAR |

if CAR_PRICE is HIGH and TRANSIT_PRICE is HIGH then TRANSPORT is CAR |

if CAR_DISTANCE is MEDIUM and BICYCLE_DISTANCE is HIGH then TRANSPORT is CAR |

if TRANSIT_PRICE is LOW and CAR_PRICE is MEDIUM then TRANSPORT is TRANSIT |

if TRANSIT_PRICE is LOW and CAR_PRICE is HIGH then TRANSPORT is TRANSIT |

if TRANSIT_PRICE is MEDIUM and CAR_PRICE is HIGH then TRANSPORT is TRANSIT |

if TRANSIT_TIME is MEDIUM and CAR_TIME is MEDIUM then TRANSPORT is TRANSIT |

if TRANSIT_TIME is MEDIUM and CAR_TIME is HIGH then TRANSPORT is TRANSIT |

if TRANSIT_TIME is HIGH and CAR_TIME is HIGH then TRANSPORT is TRANSIT |

if MOTORCYCLE_DISTANCE is LOW and CAR_PRICE is HIGH then TRANSPORT is MOTORCYCLE |

if MOTORCYCLE_PRICE is MEDIUM and CAR_PRICE is HIGH then TRANSPORT is MOTORCYCLE |

if WALK_DISTANCE is LOW then TRANSPORT is WALK |

if BICYCLE_DISTANCE is LOW then TRANSPORT is BICYCLE |

if BICYCLE_TIME is LOW then TRANSPORT is BICYCLE |

**Table 5.**Global accuracy (%) of the algorithm. Column T (testing) shows the results for Biscay’s data set and Column V (validation) for Silesia. Source: own research by extracting the forecast accuracy of the different models in Table A1. EK: expert knowledge; CE: fuzzy logic; SVM: support vector machine; M: multinomial logit; NN: neural network; B: naive Bayes; KNN: knearest neighbor; RA: random search.

EK | CE | SVM | M | NN | B | KNN | RA | |||||||||
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|

T | V | T | V | T | V | T | V | T | V | T | V | T | V | T | V | |

5-TM | 24.3265 | 22.0289 | 37.0689 | 39.9139 | 50.6600 | 50.05 | 50.1700 | 49.47 | 49.9950 | 47.62 | 36.0300 | 28.13 | 62.6800 | 47.22 | 14.1254 | 2.700535 |

3-TM | 46.8343 | 44.87867 | 49.218 | 45.72521 | 50.8800 | 49.32 | 51.0700 | 50.61 | 50.9500 | 45.73 | 37.9900 | 33.68 | 64.2500 | 47.50 | 31.276 | 26.26114 |

**Table 6.**Bootstraping values (in %) for the modal split forecast by the different models. Source: own research.

Model | Transport Mean | Real | L.C.I | U.C.I. |
---|---|---|---|---|

EK | WALK | 9.57 | 31.10 | 31.12 |

EK | TRANSIT | 36.33 | 0.08 | 0.08 |

EK | PRIVATE | 54.10 | 68.80 | 68.85 |

CE | WALK | 9.57 | 6.89 | 6.90 |

CE | TRANSIT | 36.33 | 19.20 | 19.23 |

CE | PRIVATE | 54.10 | 73.87 | 73.91 |

SVM | WALK | 9.57 | 0.00 | 0.00 |

SVM | TRANSIT | 36.33 | 41.15 | 41.17 |

SVM | PRIVATE | 54.10 | 58.81 | 58.85 |

M | WALK | 9.57 | 0.11 | 0.11 |

M | TRANSIT | 36.33 | 33.11 | 33.16 |

M | PRIVATE | 54.10 | 66.75 | 66.77 |

NN | WALK | 9.57 | 4.36 | 4.38 |

NN | TRANSIT | 36.33 | 49.63 | 49.65 |

NN | PRIVATE | 54.10 | 45.99 | 46.01 |

B | WALK | 9.57 | 46.14 | 46.16 |

B | TRANSIT | 36.33 | 21.79 | 21.81 |

B | PRIVATE | 54.10 | 32.05 | 32.08 |

KNN | WALK | 9.57 | 7.47 | 7.48 |

KNN | TRANSIT | 36.33 | 35.61 | 35.65 |

KNN | PRIVATE | 54.10 | 56.88 | 56.92 |

RA | WALK | 9.57 | 44.46 | 44.48 |

RA | TRANSIT | 36.33 | 35.57 | 35.59 |

RA | PRIVATE | 54.10 | 19.94 | 19.96 |

© 2018 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (http://creativecommons.org/licenses/by/4.0/).

## Share and Cite

**MDPI and ACS Style**

Pijoan, A.; Kamara-Esteban, O.; Alonso-Vicario, A.; Borges, C.E.
Transport Choice Modeling for the Evaluation of New Transport Policies. *Sustainability* **2018**, *10*, 1230.
https://doi.org/10.3390/su10041230

**AMA Style**

Pijoan A, Kamara-Esteban O, Alonso-Vicario A, Borges CE.
Transport Choice Modeling for the Evaluation of New Transport Policies. *Sustainability*. 2018; 10(4):1230.
https://doi.org/10.3390/su10041230

**Chicago/Turabian Style**

Pijoan, Ander, Oihane Kamara-Esteban, Ainhoa Alonso-Vicario, and Cruz E. Borges.
2018. "Transport Choice Modeling for the Evaluation of New Transport Policies" *Sustainability* 10, no. 4: 1230.
https://doi.org/10.3390/su10041230