STICC: a multivariate spatial clustering method for repeated geographic pattern discovery with consideration of spatial contiguity

Kang, Yuhao; Wu, Kunlin; Gao, Song; Ng, Ignavier; Rao, Jinmeng; Ye, Shan; Zhang, Fan; Fei, Teng

doi:10.1080/13658816.2022.2053980

Cited by 9 publications

(1 citation statement)

References 64 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Based on location information about social networks, we can perceive the relationship between human activities and urban spaces from multiple perspectives. Examples include the geotagging and tagging classification of POIs from take-out data [9] and Twitter data [10]; the relationship between Airbnb locations and urban elements [11]; over-commuting [12]; separation of the workplace and residence [13]; the application of spatial clustering in spatial partitioning [14]; and the location and colocation associations of economic activities [15].…”

Section: Introductionmentioning

confidence: 99%

Mining the Spatial Distribution Pattern of the Typical Fast-Food Industry Based on Point-of-Interest Data: The Case Study of Hangzhou, China

Shen

Wang

Liao

et al. 2022

IJGI

View full text Add to dashboard Cite

There is a Chinese proverb which states “Where there are Shaxian Snacks, there are generally Lanzhou Ramen nearby”. This proverb reflects the characteristics of spatial clustering in the catering industry. Since the proverbs are rarely elucidated from the perspective of geographical proximity and mutual attraction, we aimed to explore the spatial clustering characteristics of the fast food industry from the proverb perspective. Point-of-interest, OSM road network, population, and other types of data from the typical fast-food industry in Hangzhou were used as examples. The spatial pattern of the overall catering industry in Hangzhou was analyzed, while the spatial distribution of the four types of fast food selected in Hangzhou was identified and evaluated. The “core-edge” circle structure characteristics of Hangzhou’s catering industry were fitted by the inverse S function. The common location connection between the Western fast-food KFC and McDonald’s and the Chinese fast-food Lanzhou Ramen and Shaxian Snacks and the spatial aggregation were elucidated, being supported by correlation analysis. The degree of mutual attraction between the two was applied to express the spatial correlation. The analysis demonstrated that (1) the distribution of the catering industry in Hangzhou was northeast–southwest. The center of the catering industry in Hangzhou was located near the economic center of the main city rather than in the center of urban geography. (2) The four types of fast food were distributed in densely populated areas and exhibited an anti-S law, which first increased but then decreased as the distance from the center increased. Among these, the number of four typical fast foods was the highest within a distance of 4–10 km from the center. (3) It was concluded that 81.6% of KFCs had a McDonald’s nearby within 2500 m, and 68.5% of Shaxian Snacks had a Lanzhou Ramen nearby within 400 m. McDonald’s attractiveness to KFC was calculated as 0.928448. KFC’s attractiveness to McDonald’s was 0.908902. The attractiveness of the Shaxian Snacks to Lanzhou Ramen was 0.826835. The attractiveness of Lanzhou Ramen to Shaxian Snacks was 0.854509. McDonald’s was found to be dependent on KFC in the main urban area. Shaxian Snacks were strongly attributed to Lanzhou Ramen in commercial centers and streets, while Shaxian Snacks were distributed independently in the eastern Xiaoshan and Yuhang Districts. This study also helped us to optimize the spatial distribution of a typical fast-food industry, while providing case references and decision-making assistance with respect to the locations of catering industries.

show abstract