Abstract:Palavras-chave: Comportamento individual relativo a viagens. Coleta de dados passiva. Smartphones. Análise de Clusters. K-médias. Análise espacial. Indicadores globais. Geoestatística.
“…It constituted an essential contribution, taking into account the importance of representing spatial dependence through an independent variable. This stage followed the process proposed in previous study (Assirati, 2018).…”
Section: Proposal Of Spatial Covariatesmentioning
confidence: 99%
“…For the comparison of the Binomial Logit models (spatial and non-spatial), three metrics will be used: The adjusted rho-square values; the Akaike criterion value; the hit rate by cross-validation and likelihood values for validation sample. Such metrics are well known, however, the reader who seeks more details can consult Hosmer and Lemeshow (2000) and Assirati (2018). Equation 9defines the adjusted rho-square metric.…”
Section: Comparison Of the Two Modelsmentioning
confidence: 99%
“…Finally, the main contribution of this paper is related to a methodological demonstration on how to take into account the spatial characteristics of the data, along with the usual variables. Assirati (2018) applicated this methodology considering a real data and a trip-chaining study case regarding panel data collected by smartphones. This application corroborates that the methodological procedure is feasible to real data, with different urban configuration.…”
Section: Conclusion and Research Contributionsmentioning
confidence: 99%
“…So, the spatial analysis of travel demand has become a potential line of research, especially given the requirement of including spatial effects on mathematical models (Páez et al 2013). Hence, many studies (Miyamoto et al, 2004;Zhou, 2012;Páez et al, 2013;Pitombo et al, 2015;Lindner and Pitombo, 2018;Assirati, 2018;Lindner et al, 2021) started to incorporate variables related to geographic location to travel demand forecasting studies, promoting the improvement of estimates. So, this paper mainly proposes to model the spatial effect on travel mode choice, taking into account the spatial analysis of the travel demand research field.…”
Urban dynamics can be characterized more effectively by considering spatial aspects in studies. This paper, using a synthetic spatially correlated data set, aims to model the spatial effect on travel mode choice based on geostatistics precepts. A method was proposed based on three main steps. The first step consists of building synthetic spatially correlated data, using the intrinsic spatial dependence on travel demand data and mathematical principles of bilinear interpolation. The following two steps correspond to the modeling approach. The Exploratory Spatial Data Analysis stage aimed to attest the existence of spatial autocorrelation of the data set using two indicators: Moran and G-SIVAR (Global Spatial Indicator Based on Variogram). The Confirmatory Spatial Data Analysis stage proposed the calibration of two Binomial Logit models. The first model includes only the original database variables (nonspatial model). The second one is analogous to the original but added to spatial covariates obtained by geostatistical concepts (spatial model). A 15% increase in cross-validation hit rates is achieved when spatial variables are included. This paper presents three significant research contributions: (1) The methodological procedure to model spatial effect on travel mode choice; (2) The proposal of spatial covariates based on geostatistical assumptions; and (3) The suggestion of a simple procedure to propose a simulation of a spatially correlated database.
“…It constituted an essential contribution, taking into account the importance of representing spatial dependence through an independent variable. This stage followed the process proposed in previous study (Assirati, 2018).…”
Section: Proposal Of Spatial Covariatesmentioning
confidence: 99%
“…For the comparison of the Binomial Logit models (spatial and non-spatial), three metrics will be used: The adjusted rho-square values; the Akaike criterion value; the hit rate by cross-validation and likelihood values for validation sample. Such metrics are well known, however, the reader who seeks more details can consult Hosmer and Lemeshow (2000) and Assirati (2018). Equation 9defines the adjusted rho-square metric.…”
Section: Comparison Of the Two Modelsmentioning
confidence: 99%
“…Finally, the main contribution of this paper is related to a methodological demonstration on how to take into account the spatial characteristics of the data, along with the usual variables. Assirati (2018) applicated this methodology considering a real data and a trip-chaining study case regarding panel data collected by smartphones. This application corroborates that the methodological procedure is feasible to real data, with different urban configuration.…”
Section: Conclusion and Research Contributionsmentioning
confidence: 99%
“…So, the spatial analysis of travel demand has become a potential line of research, especially given the requirement of including spatial effects on mathematical models (Páez et al 2013). Hence, many studies (Miyamoto et al, 2004;Zhou, 2012;Páez et al, 2013;Pitombo et al, 2015;Lindner and Pitombo, 2018;Assirati, 2018;Lindner et al, 2021) started to incorporate variables related to geographic location to travel demand forecasting studies, promoting the improvement of estimates. So, this paper mainly proposes to model the spatial effect on travel mode choice, taking into account the spatial analysis of the travel demand research field.…”
Urban dynamics can be characterized more effectively by considering spatial aspects in studies. This paper, using a synthetic spatially correlated data set, aims to model the spatial effect on travel mode choice based on geostatistics precepts. A method was proposed based on three main steps. The first step consists of building synthetic spatially correlated data, using the intrinsic spatial dependence on travel demand data and mathematical principles of bilinear interpolation. The following two steps correspond to the modeling approach. The Exploratory Spatial Data Analysis stage aimed to attest the existence of spatial autocorrelation of the data set using two indicators: Moran and G-SIVAR (Global Spatial Indicator Based on Variogram). The Confirmatory Spatial Data Analysis stage proposed the calibration of two Binomial Logit models. The first model includes only the original database variables (nonspatial model). The second one is analogous to the original but added to spatial covariates obtained by geostatistical concepts (spatial model). A 15% increase in cross-validation hit rates is achieved when spatial variables are included. This paper presents three significant research contributions: (1) The methodological procedure to model spatial effect on travel mode choice; (2) The proposal of spatial covariates based on geostatistical assumptions; and (3) The suggestion of a simple procedure to propose a simulation of a spatially correlated database.
“…A cidade abriga dúas grandes institúiço es de ensino súperior: A Universidade de Sa o Paúlo (USP) qúe conta com dois campi e a Universidade Federal de Sa o Carlos (UFSCar). Júntas, as institúiço es possúem cerca de 40 mil estúdantes o qúe representa aproximadamente 18% da popúlaça o do múnicí pio (Assirati, 2018).…”
A caracterização comportamental relativa a viagens é uma questão importante nas análises baseadas em atividades e, comumente, é a variável dependente nos modelos de estimativa de demanda por transportes. A classificação individual, segundo comportamentos relacionados aos deslocamentos, pode ser realizada com dados seccionais, considerando diferentes fatores como distâncias, modos utilizados e atividades realizadas, ou com dados em painel, através de valores médios nos múltiplos dias ou atividades frequentes, por exemplo. Dados em painel constituem importante ferramenta em análises comportamentais relativas às viagens urbanas, propiciando dimensão analítica extra relativo à heterogeneidade temporal individual. Todavia, a obtenção desses dados não é trivial, demandando recursos monetários e de tempo. Assim, o objetivo principal deste trabalho é classificar indivíduos segundo comportamento relativo a viagens a partir de dados em painel. O objetivo secundário associa-se à obtenção do painel através de smartphones. A potencialidade da proposta é validada por um estudo de caso contemplando estudantes universitários em São Carlos – SP, Brasil. Mediante dados fornecidos pelos estudantes, utilizou-se o algoritmo k-médias considerando quatro variáveis associadas às viagens realizadas em três dias úteis consecutivos. Obtiveram-se três grupos comportamentais distintos com diferenças quanto ao grau de motorização, recorrência de localidades, número de viagens realizadas e distâncias médias percorridas.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.