Investigating pedestrian behaviour in urban environments: A Wi-Fi tracking and machine learning approach

Stanitsa, Avgousta; Hallett, Stephen R; Jude, Simon

doi:10.1016/j.multra.2022.100049

Cited by 15 publications

(5 citation statements)

References 58 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Clustering individuals based on their walking speed, direction, and time enables the precise classification of walking behavior. K-means clustering aids in identifying clusters [ 9 ]. Mapping identifies locations with high levels of pedestrian traffic and their distribution.…”

Section: Methodsmentioning

confidence: 99%

“…Shoval et al [ 6 ] utilized psychological mapping to generate real-time maps of subjective and objective emotions to analyze Jerusalem’s urban surroundings for the first time. Building upon that study, there is currently a growing interest in mapping behavior across several fields [ 7 , 8 , 9 ].…”

Section: Introductionmentioning

confidence: 99%

“…The availability of technology for the establishment of the geographic coordinates of mobile phones and other devices has significantly increased, leading to the emergence of a wide range of applications of location-based services (LBS) [ 11 ]. Similarly, Wi-Fi signals were also utilized in these studies [ 9 ]. The incorporation of LBS improves the quantitative metrics, offering significant spatial observation of the pattern of pedestrian movement.…”

Section: Introductionmentioning

confidence: 99%

“…Multiple authors identify the following five essential components in the observation process: 1. a visual representation of the observed areas; 2. a precise explanation of the human behavior observed, tracked, described, or outlined; 3. a timetable of recurring intervals for observation and recording; 4. a methodological observation process; and 5. a system for programming analysis that reduces the recording workload [ 1 ]. While walkability studies highlight the complexity of walking activities, there is still a lack of systematic categorization of pedestrian actions, creating a knowledge gap [ 9 ]. Further, research on walking patterns disregards the individual travel direction and time of the day.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Real-Time Tracking Data and Machine Learning Approaches for Mapping Pedestrian Walking Behavior: A Case Study at the University of Moratuwa

Sawandi,

Jayasinghe,

Retscher

2024

Sensors

View full text Add to dashboard Cite

The growing urban population and traffic congestion underline the importance of building pedestrian-friendly environments to encourage walking as a preferred mode of transportation. However, a major challenge remains, which is the absence of such pedestrian-friendly walking environments. Identifying locations and routes with high pedestrian concentration is critical for improving pedestrian-friendly walking environments. This paper presents a quantitative method to map pedestrian walking behavior by utilizing real-time data from mobile phone sensors, focusing on the University of Moratuwa, Sri Lanka, as a case study. This holistic method integrates new urban data, such as location-based service (LBS) positioning data, and data clustering with unsupervised machine learning techniques. This study focused on the following three criteria for quantifying walking behavior: walking speed, walking time, and walking direction inside the experimental research context. A novel signal processing method has been used to evaluate speed signals, resulting in the identification of 622 speed clusters using K-means clustering techniques during specific morning and evening hours. This project uses mobile GPS signals and machine learning algorithms to track and classify pedestrian walking activity in crucial sites and routes, potentially improving urban walking through mapping.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Real-Time Tracking Data and Machine Learning Approaches for Mapping Pedestrian Walking Behavior: A Case Study at the University of Moratuwa

Sawandi,

Jayasinghe,

Retscher

2024

Sensors

View full text Add to dashboard Cite

show abstract

“…The study followed a deductive qualitative content analysis, where the interview guide was predefined based on previous research and the desire to explore topics based on these findings (Barton et al, 2021). The research that Stanitsa et al (2022aStanitsa et al ( , 2022b conducted defined the structure of the data framework presented in Figure 3, while it informed the selection of participants, as described in Section 2.2.…”

Section: Research Methodology 21 Data Collection Via Semi-structured ...mentioning

confidence: 99%

The challenges of implementing evidence-based strategies to inform building and urban design decisions: a view from current practice

Stanitsa

Hallett

Jude

2022

JEDT

Self Cite

View full text Add to dashboard Cite

Purpose This study aims to raise awareness of the key challenges, opportunities and priorities for evidence-based strategies’ application to inform building and urban design decisions. Design/methodology/approach This study uses deductive qualitative content and manifest analysis, using semi-structured interviews undertaken with building and urban design professionals who represent a UK-based organisation. Findings The challenges associated with the practical implementation of frameworks, potential application areas and perceived areas of concern have been identified. These not only include the need to practically test their use, but also to identify the most appropriate forums for their use. Participant responses indicate the need to further develop engagement strategies for their practical implementation, clearly communicating the benefits and efficiencies to all stakeholders. Research limitations/implications Implications/ limitations of this study come with the fact that some of the respondents may possess inadequate professional experience in properly evaluating all the questions. Additionally, the information gathered is restricted to the UK geographical context, as well as coming from one organisation, because of data accessibility. Practical implications The findings of the study can be adopted by designers in the strategic definition level to overcome the key challenges associated with the use of evidence-based strategies, enhancing their decision-making processes. Originality/value As a theoretical contribution to knowledge, this study enhances the body of knowledge by identifying the challenges associated with the practical implementation of evidence-based strategies to inform building and urban design decisions. In practice, the findings aid urban planners, designers and academics in embedding and adopting strategies that enhance decision-making processes.

show abstract

Exploring passengers’ choice of transfer city in air-to-rail intermodal travel using an interpretable ensemble machine learning approach

et al. 2023

View full text Add to dashboard Cite

Investigating pedestrian behaviour in urban environments: A Wi-Fi tracking and machine learning approach

Cited by 15 publications

References 58 publications

Real-Time Tracking Data and Machine Learning Approaches for Mapping Pedestrian Walking Behavior: A Case Study at the University of Moratuwa

Real-Time Tracking Data and Machine Learning Approaches for Mapping Pedestrian Walking Behavior: A Case Study at the University of Moratuwa

The challenges of implementing evidence-based strategies to inform building and urban design decisions: a view from current practice

Exploring passengers’ choice of transfer city in air-to-rail intermodal travel using an interpretable ensemble machine learning approach

Contact Info

Product

Resources

About