Integrating multi-source big data to infer building functions

Niu, Ning; Li, Xiaoping; Jin, He; Ye, Xinyue; Liu, Yu; Li, Xia; Chen, Yi-Min; Li, Shaoying

doi:10.1080/13658816.2017.1325489

Cited by 56 publications

(44 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Some studies adopted concepts from time geography to develop analytical approaches for social media data. Others applied clustering or spatial association to identify points of interest (POI) locations (e.g., home or shopping centers), building functions (Niu et al, ), urban zoning (e.g., residential vs. office buildings), population fluctuations across regions over time, or human activity space of individuals or groups. The popularity of POI types over time echoes the pulses of activity within a city (McKenzie, Janowicz, Gao, & Gong, ), and, when compared across areas, reflects the regional variability of geosocial temporal signatures (McKenzie, Janowicz, Gao, Yang, & Hu, ).…”

Section: Spacing Time and Timing Spacementioning

confidence: 99%

Section: S Pacing Time and Timing S Pacementioning

confidence: 99%

See 1 more Smart Citation

Human dynamics in space and time: A brief history and a view forward

Yuan

2018

Transactions in GIS

View full text Add to dashboard Cite

This article highlights the key intellectual development in human dynamics research, examines the modeling emphases in publications, and argues for research directions in need. Human dynamics research is discussed in two broad directions: spacing time and timing space, to model human activities and interactions. Time is essential to human dynamics research. Space, while often being overlooked, in complement with time is critical to understanding human dynamics because knowing where activities take place is essential to knowing how and why people act and interact. Some interactions allow remote or asynchronized participations, and others require movement to collocate individuals for participating in synchronized activities. A spacing time approach examines the temporal gaps between interactions. A timing space approach investigates the spatial pulses between interactions. Primary research in the spacing time of human dynamics established queueing theories to explain the bursts and heavy‐tailed distribution of human interactions. Although research on the timing space of human dynamics enjoys growing popularity with data from geo‐tagged social media and location‐aware social internet of things (SIoT), its publications remain mostly exploratory. This article suggests a hierarchical framework to systematically study human dynamics and relate findings to build the body of knowledge about human dynamics.

show abstract

Section: Spacing Time and Timing Spacementioning

confidence: 99%

Section: S Pacing Time and Timing S Pacementioning

confidence: 99%

Human dynamics in space and time: A brief history and a view forward

Yuan

2018

Transactions in GIS

View full text Add to dashboard Cite

show abstract

“…Social media data has been utilized extensively to delineate human activities in land use analyses. Related applications include land use classification (Frias‐Martinez & Frias‐Martinez, ), urban functional region detection (Chen et al, ; Niu et al, ), population estimation (Yao, Liu, et al, ), and mixed land use evaluation (Liu et al, ; Yue et al, ). Compared with other sources of data [such as points of interest (POI)], social media data can reveal regular patterns of dynamic human activities at the individual scale, instead of simply capturing the static distribution of land use forms.…”

Section: Literature Reviewmentioning

confidence: 99%

A dynamic human activity‐driven model for mixed land use evaluation using social media data

Xing

Meng

Shi

2018

Transactions in GIS

View full text Add to dashboard Cite

Massive amounts of social media data have enabled the evaluation of mixed land use from the human activities perspective. While most studies have focused on approaches to better measure mixed land use, the dynamic activity patterns used to distinguish land use types have seldom been discussed. In light of this, in this study, a mixed land use evaluation model is constructed, which is driven by dynamic human activities hidden in social media data. Specifically, temporal topics related to human activities are first extracted from Twitter messages. On this basis, these topics are clustered with successive measurements of both temporal and semantic similarities, and then, they are further transformed into dynamic features. In addition, the dynamic feature‐based Shannon entropy is employed for mixed land use evaluation. For verification, the building classes from OpenStreetMap are referenced to investigate their correlations with dynamic features in mixed land uses. Finally, a strong correlation demonstrates the effectiveness and power of the proposed method in the evaluation of mixed land uses.

show abstract

“…Semantic information from POIs has been used in a myriad of studies and applications, such as mobile POI recommendation [10,11], spatial analyses of socio-economic processes [12,13], land-use estimation from individual buildings [14,15], grid cells [16] and urban parcels [17,18], neighbourhood vibrancy description [19], semantic enrichment of streets segments [19,20], urban mobility modelling [21,22] and pedestrian navigation [23,24], to name a few. These and other studies and applications can benefit a lot from the conflation of POI semantic information dispersed across different VGI sources.…”

Section: Steps In the Matching Of Pois From Different Datasetsmentioning

confidence: 99%

Graph-Based Matching of Points-of-Interest from Collaborative Geo-Datasets

Novack

Peters

Zipf

2018

IJGI

View full text Add to dashboard Cite

Several geospatial studies and applications require comprehensive semantic information from points-of-interest (POIs). However, this information is frequently dispersed across different collaborative mapping platforms. Surprisingly, there is still a research gap on the conflation of POIs from this type of geo-dataset. In this paper, we focus on the matching aspect of POI data conflation by proposing two matching strategies based on a graph whose nodes represent POIs and edges represent matching possibilities. We demonstrate how the graph is used for (1) dynamically defining the weights of the different POI similarity measures we consider; (2) tackling the issue that POIs should be left unmatched when they do not have a corresponding POI on the other dataset and (3) detecting multiple POIs from the same place in the same dataset and jointly matching these to the corresponding POI(s) from the other dataset. The strategies we propose do not require the collection of training samples or extensive parameter tuning. They were statistically compared with a "naive", though commonly applied, matching approach considering POIs collected from OpenStreetMap and Foursquare from the city of London (England). In our experiments, we sequentially included each of our methodological suggestions in the matching procedure and each of them led to an increase in the accuracy in comparison to the previous results. Our best matching result achieved an overall accuracy of 91%, which is more than 10% higher than the accuracy achieved by the baseline method.

show abstract

Integrating multi-source big data to infer building functions

Cited by 56 publications

References 28 publications

Human dynamics in space and time: A brief history and a view forward

Human dynamics in space and time: A brief history and a view forward

A dynamic human activity‐driven model for mixed land use evaluation using social media data

Graph-Based Matching of Points-of-Interest from Collaborative Geo-Datasets

Contact Info

Product

Resources

About