A dynamic mixed logit model with agent effect for pedestrian next location choice using ubiquitous Wi-Fi network data

Beaulieu, Alexandra; Farooq, Bilal

doi:10.1016/j.ijtst.2019.02.003

Cited by 6 publications

(10 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Another study applied a nested logit model to generate the activity schedules by dividing the activity choice at the airport into three periods: before-check-in, before-security, and before-boarding [16]. Additionally, several studies have demonstrated that the application of dynamic models for the activity choice is more representative when compared to the static models such as the multinomial logit models [17,18]. However, these studies only determined the order of the activities and did not consider the allocation of the activity time.…”

Section: Activity Scheduling Models For Pedestriansmentioning

confidence: 99%

“…The utility maximization models are based on microeconomics and are most applicable for general activity-based models, owing to their mathematical rigor, regardless of the pedestrian models. The applications of the activity scheduling models based on the utility maximization models include nested logit-based activity-choice models [16] and dynamic activity choice models [17,18].…”

Section: Introductionmentioning

confidence: 99%

“…Additionally, recent studies have demonstrated that the combination of positive utility and space-time constraints can better explain the pedestrian-specific behavior such as detours and short stays in the path choice [22]. Moreover, several studies have shown that the application of dynamic models with agent effects for the activity choice outperforms the static models such as multinomial logit models [17,18]. Although these studies can determine the order of activities, they do not consider the allocation of the activity time.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Activity Scheduling Behavior of the Visitors to an Outdoor Recreational Facility Using GPS Data

Hidaka

Yamamoto

2021

Sustainability

View full text Add to dashboard Cite

Understanding the decision-making behavior of pedestrians is essential for urban designers and developers in enhancing the commercial and aesthetic value of streets and other urban spaces. However, limited research has been conducted on the activity scheduling behavior of pedestrians. The majority of the studies conducted on outdoor facilities utilize spatial representations by links and are unable to sufficiently represent the highly flexible behavior of pedestrians. This study proposes a new method to discretize data from the global positioning system (GPS) into a two-dimensional grid-based spatial representation with a high spatial resolution. The information regarding the stay at the point of interests (POIs) is extracted from the discretized data, and the activity scheduling model is estimated. The estimation results indicate that the visitors’ attributes, such as the age of the representative and number of children, affect the probability of the activity choice and the time spent at the POI. The probability of choosing the main gate increases in the latter half of the stay, confirming the existence of time pressure. The information on the decision-making behavior of the visitors to a facility, obtained from the GPS data, can be applied to the data-oriented spatial design process to create attractive and lively spaces.

show abstract

Section: Activity Scheduling Models For Pedestriansmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Activity Scheduling Behavior of the Visitors to an Outdoor Recreational Facility Using GPS Data

Hidaka

Yamamoto

2021

Sustainability

View full text Add to dashboard Cite

show abstract

“…This study also did not consider transportation modes other than walking. Beaulieu and Farooq (2019) used Wi-Fi data collected on a 14 blocks pedestrianized street in Montreal to develop the next location choice model. They developed a dynamic mixed logit model with agent effects to achieve a maximum prediction performance of 70%.…”

Section: Literature Reviewmentioning

confidence: 99%

A Semi-Supervised Deep Residual Network for Mode Detection in Wi-Fi Signals

Kalatian

Farooq

2020

J. Big Data Anal. Transp.

Self Cite

View full text Add to dashboard Cite

Inferring transportation mode of users in a network is of paramount importance in planning, designing, and operating intelligent transportation systems. Previous studies in the literature have mainly utilized GPS data. However, albeit the successful performances of models built upon such data, being limited to certain participants and the requirement of their involvement makes large scale implementations difficult. Due to their ubiquitous and pervasive nature, Wi-Fi networks have the potential to collect large scale, low-cost, passive and disaggregate data on multimodal transportation. In this study, by a passive collection of Wi-Fi network data on a congested urban road in downtown Toronto, we attempt to tackle the aforementioned problems. We develop a semi-supervised deep residual network (ResNet) framework to utilize Wi-Fi communications obtained from smartphones. Our semi-supervised framework enables utilization of an ample amount of easily collected low-cost unlabelled data, coupled with a relatively small-sized labelled data. By incorporating a ResNet architecture as the core of the framework, we take advantage of the high-level features not considered in the traditional machine learning frameworks. The proposed framework shows a promising performance on the collected data, with a prediction precision of 81.4% for walking, 80.5% for biking and 84.9% for the driving mode.

show abstract

“…The broad mechanism for pedestrian destination choice is considered to be based on individuals trading off different factors against each other when making decisions (e.g. [1][2][3]). For example, pedestrians who seek to complete an activity at a destination quickly may want to avoid busy destinations, and, to minimize their effort, they may generally prefer nearby destinations.…”

Section: Introductionmentioning

confidence: 99%

A virtual experiment on pedestrian destination choice: the role of schedules, the environment and behavioural categories

King

Bode

2022

R. Soc. open sci.

View full text Add to dashboard Cite

Which locations pedestrians decide to visit and in what order drives circulation patterns in pedestrian infrastructure. Destination choice is understood to arise from individuals trading off different factors, such as the proximity and busyness of destinations. Here, a virtual experiment is used to investigate whether this behaviour depends on the layout of buildings, whether planned or imposed destination schedules influence decisions and whether it is possible to distinguish different choice behaviour strategies in pedestrian populations. Findings suggest that virtual experiments can consistently elicit a range of destination choice behaviours indicating the flexibility of this experimental paradigm. The experimental approach facilitates changing the environment layout while controlling for other factors and illustrates this in itself can be important in determining destination choice. Destination schedules are found to be relevant both when imposed or generated by individuals, but adherence to them varies across individuals and depends on prevailing environmental conditions, such as destination busyness. Different destination choice behaviour strategies can be identified, but their properties are sensitive to the detection methods used, and it is suggested such behaviour classification should be informed by specific use-cases. It is suggested that these contributions present useful starting points for future research into pedestrian destination choice.

show abstract

A dynamic mixed logit model with agent effect for pedestrian next location choice using ubiquitous Wi-Fi network data

Cited by 6 publications

References 11 publications

Activity Scheduling Behavior of the Visitors to an Outdoor Recreational Facility Using GPS Data

Activity Scheduling Behavior of the Visitors to an Outdoor Recreational Facility Using GPS Data

A Semi-Supervised Deep Residual Network for Mode Detection in Wi-Fi Signals

A virtual experiment on pedestrian destination choice: the role of schedules, the environment and behavioural categories

Contact Info

Product

Resources

About