Diversity of individual mobility patterns and emergence of aggregated scaling laws

Yan, Xiao-Yong; Xiao, Han; Wang, Bing–Hong; Zhou, Tao

doi:10.1038/srep02678

Cited by 136 publications

(125 citation statements)

References 54 publications

Supporting

Mentioning

114

Contrasting

Order By: Relevance

“…For another example, by analyzing the flow trajectories of 464,670 dollar bills, Brockmann [8] uncovered the knowledge of dynamic and statistical properties of human travel on a large scale, and discovered the dispersal of bank notes matches a continuous time random walk process incorporating scale free jumps as well as long waiting times between displacements. Likewise, Gonzalez [22], Yan [54] and Peng [39] reached some valuable conclusions by analysing the trajectories of over 100 thousand mobile users, 230 volunteers' 6-week travel diaries and the movement paths of 15.8 thousand Shanghai taxies respectively.…”

Section: Scientific Progress and Research Paradigm Of Big Data Based mentioning

confidence: 99%

Universal knowledge discovery from big data using combined dual-cycle

Shen

2015

Int. J. Mach. Learn. & Cyber.

View full text Add to dashboard Cite

Many people hold a vision that big data will provide big insights and have a big impact in the future. However, how to turn big data into deep insights with tremendous value still remains obscure. Here I highlight universal knowledge discovery from big data. The new concept focuses on discovering universal knowledge, which exists in the statistical analyses of big data and provides valuable insights into big data. Universal knowledge comes in different forms, e.g., universal patterns, rules, correlations, models and mechanisms. To accelerate big data assisted scientific discovery, a unified research paradigm should be built based on techniques and paradigms from related research domains, especially big data mining and complex systems science. Therefore, I propose a dual-cycle methodology with three types of cycle-driven UKD process, i.e., big-data-cycle-driven, mechanism-cycle-driven and combined-dual-cycle-driven mining. A case study is also given to illustrate the effectiveness of the proposed processes. This paper lays a foundation for the future development of universal knowledge discovery, and offers a pathway to the discovery of ''treasure-trove'' hidden in big data.

show abstract

Section: Scientific Progress and Research Paradigm Of Big Data Based mentioning

confidence: 99%

Universal knowledge discovery from big data using combined dual-cycle

Shen

2015

Int. J. Mach. Learn. & Cyber.

View full text Add to dashboard Cite

show abstract

“…Social network data and social media data, i.e., geo-tagged image, message, and video, are very sparse in both space and time (Zhou et al, 2015). They tell us different stories about urban human movements (Yan et al, 2013). Therefore, there are some questions before using them in urban applications.…”

Section: * Corresponding Authormentioning

confidence: 99%

Comparison of Urban Human Movements Inferring From Multi-Source Spatial-Temporal Data

Cao¹,

Tu²,

Cao³

et al. 2016

Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci.

View full text Add to dashboard Cite

ABSTRACT:The quantification of human movements is very hard because of the sparsity of traditional data and the labour intensive of the data collecting process. Recently, much spatial-temporal data give us an opportunity to observe human movement. This research investigates the relationship of city-wide human movements inferring from two types of spatial-temporal data at traffic analysis zone (TAZ) level. The first type of human movement is inferred from long-time smart card transaction data recording the boarding actions. The second type of human movement is extracted from citywide time sequenced mobile phone data with 30 minutes interval. Travel volume, travel distance and travel time are used to measure aggregated human movements in the city. To further examine the relationship between the two types of inferred movements, the linear correlation analysis is conducted on the hourly travel volume. The obtained results show that human movements inferred from smart card data and mobile phone data have a correlation of 0.635. However, there are still some non-ignorable differences in some special areas. This research not only reveals the citywide spatialtemporal human dynamic but also benefits the understanding of the reliability of the inference of human movements with big spatialtemporal data.

show abstract

“…On the other hand, in our experiment, we only used three baseline methods, implying that we may neglect some latest POI recommendation approaches. Third, as mentioned in some previous works (Song et al, 2010;Yan et al, 2013;Liu et al, 2014), individual heterogeneity (Gonzalez et al, 2008) requires the variability in mobility prediction at the individual level. It is worth noting that our proposed model, as a preliminary attempt to investigate crossurban human mobility, also possesses the potential of more accurate personalized recommendation with sophisticated machine learning techniques such as deep learning.…”

Section: Threats To Validitymentioning

confidence: 99%

“…It is vitally significant to understand socioeconomic phenomena embodying spatiality and human movement by unfolding human mobility patterns (Yan et al, 2013). Therefore, numerous researchers have attempted to uncover and model human mobility patterns (Gonzalez et al, 2008;Noulas et al, 2012;Hasan et al, 2013a;Schneider et al, 2013;Barchiesi et al, 2015;Pappalardo et al, 2015;Gallotti et al, 2016), to provide a deeper understanding of individual and collective mobility behaviors.…”

Section: Introductionmentioning

confidence: 99%

Cross-Urban Point-of-Interest Recommendation for Non-Natives

Wang

2018

International Journal of Web Services Research

View full text Add to dashboard Cite

This article describes how understanding human mobility behavior is of great significance for predicting a broad range of socioeconomic phenomena in contemporary society. Although many studies have been conducted to uncover behavioral patterns of intra-urban and inter-urban human mobility, a fundamental question remains unanswered: To what degree is human mobility behavior predictable in new cities-a person has never visited before? Location-based social networks with a large volume of check-in records provide an unprecedented opportunity to investigate cross-urban human mobility. The authors' empirical study on millions of records from Foursquare reveals the motives and behavioral patterns of non-natives in 59 cities across the United States. Inspired by the ideology of transfer learning, the authors also propose a machine learning model, which is designed based on the regularities that they found in this study, to predict cross-urban human whereabouts after non-natives move to new cities. The experimental results validate the effectiveness and efficiency of the proposed model, thus allowing us to predict and control activities driven by cross-urban human mobility, such as mobile recommendation, visual (personal) assistant, and epidemic prevention.

show abstract

Diversity of individual mobility patterns and emergence of aggregated scaling laws

Cited by 136 publications

References 54 publications

Universal knowledge discovery from big data using combined dual-cycle

Universal knowledge discovery from big data using combined dual-cycle

Comparison of Urban Human Movements Inferring From Multi-Source Spatial-Temporal Data

Cross-Urban Point-of-Interest Recommendation for Non-Natives

Contact Info

Product

Resources

About