Rhythm of the streets: a street classification framework based on street activity patterns

Abstract

As the living tissue connecting urban places, streets play significant roles in driving city development, providing essential access, and promoting human interactions. Understanding street activities and how these activities vary across different streets is critical for designing both efficient and livable streets. However, current street classification frameworks primarily focus on either streets’ functions in transportation networks or their adjacent land uses rather than actual activity patterns, resulting in coarse classifications. This research proposes an activity-based street classification framework to categorize street segments based on their temporal street activity patterns, which is derived from high-resolution de-identified and privacy-enhanced mobility data. We then apply the proposed framework to 18,023 street segments in the City of Boston and reveal 10 distinct activity-based street types (ASTs). These ASTs highlight dynamic street activities on streets, which complements existing street classification frameworks, which focus on the static or transportation characteristics of the street segments. Our results show that a street classification framework based on temporal street activity patterns can identify street categories at a finer granularity than current methods, which can offer useful implications for state-of-the-art urban management and planning. In particular, we find that our classification distinguishes better those streets where crime is more prevalent than current functional or contextual classifications of streets.

Future workspace needs flexibility and diversity: A machine learning-driven behavioural analysis of co-working space

“…It represents a combination of spatial and temporal attributes at a particular moment. While the application of this analysis in the interior environment is relatively less common compared to other scenarios like urban transport, tourism, climate environment and public health [52][53][54][55], there exists significant potential for employing this method to analyse spatial and temporal patterns of human behaviour within indoor environments, as demonstrated in this study.…”

Integrative Analysis of Rhythmicity: From Biology to Urban Environments and Sustainability

“…Šveda et al [37] explored the hourly mobile phone records of signalling exchanges by all major mobile network operators present in a certain urban area to monitor the spatiotemporal activities of the urban population and distinguish the typical rhythms of diurnal and nocturnal activity, resulting in the division of the urban area into relatively consistent territory types (chronopoles). Similarly, Su et al [38] classified the streets according to the observed activity patterns based on the insights derived from high-resolution, anonymous and privacy-enhanced mobility data of street segments, and they revealed 10 distinct activity-based street types. Their examination of the activity rhythms showed that a street classification framework based on temporal street activity patterns can identify street categories at a finer granularity than other current methods, which can offer useful implications for state-of-the-art urban management and planning.…”

Segmentation using large language models: A new typology of American neighborhoods

“…Social Scientific practise has not fully adapted to this new operating environment where data are more abundant but lower quality. However, the growing availability of spatially referenced data about populations and their local contexts has led to an upsurge of interest in these high-dimensional descriptive models of places [5,6]. Commonly referred to as segmentation or geodemographic classification [7,8], they represent a collection of methodological approaches that utilise unsupervised classification techniques to group geographic areas based on the similarity of their characteristics in the socioeconomic, demographic, and built environment [9].…”

“…This process of description is often error prone; [14] noted that a major research endeavor in the 1970s was undermined by misleading interpretation of multivariate groupings of data. This paper addresses these challenges by developing an open and reproducible geodemographic classification at the block group scale for the United States using the ACS, and further demonstrates how by coupling this classification with Generative Pre-trained Transformer 4 (GPT4 5 ) one can generate intuitive descriptions and names for high dimensional clusters. Integration of GPT4 into geodemographic typologies represents a novel application of natural language processing techniques in the interpretation of high-dimensional cluster analyses.…”