Haytham Assem
ABSTRACT
During the past few years, the analysis of data generated from Location-Based Social Networks (LBSNs) have aided in the identification of urban patterns, understanding activity behaviours in urban areas, as well as producing novel recommender systems that facilitate users' choices. However, the recent advancement in machine learning techniques promises new deeper insights with the possibility of finding new spatio-temporal patterns in cities. In this paper, we show that one of the recent advancements in machine learning, Deep Belief Networks (DBNs), can discover a new type of pattern, which we refer to in the paper as the Socio-demographic Regional Pattern. This pattern illustrates the ability of predicting the district of a city given a set of weekly activities captured from LBSNs. Specifically, we have found instances of this embedded pattern for the boroughs in New York City by training a DBN model that can classify with nearly 70% accuracy the location of weekly region-footprints. We further validated the existence and complexity of this type of pattern by applying a probabilistic topic model, namely Latent Dirichlet Allocation (LDA). We believe that this research can yield to a deeper understanding about social commonalities and the geographical evolution of different regions and areas, between cities across the globe.
- 5 boroughs: Compare and contrast. http://www.newyork.com/articles/real-estate/5-boroughs-compare-and-contrast-17601/. Accessed: 16-01-2016.Google Scholar
- Foursquare application. http://www.foursquare.com/.Google Scholar
- Y. Anzai. Pattern Recognition & Machine Learning. Elsevier, 2012. Google ScholarDigital Library
- R. Arun, V. Suresh, C. V. Madhavan, and M. N. Murthy. On finding the natural number of topics with latent dirichlet allocation: Some observations. In KDD. 2010. Google ScholarDigital Library
- H. Assem and D. O'Sullivan. Towards bridging the gap between machine learning researchers and practitioners. In 2015 IEEE International Conference on Smart City/SocialCom/SustainCom (SmartCity), pages 702--708. IEEE, 2015.Google ScholarCross Ref
- H. Assem, L. Xu, T. S. Buda, and D. O'Sullivan. Machine learning as a service for enabling internet of things and people. Personal and Ubiquitous Computing, pages 1--16. Google ScholarDigital Library
- H. Assem, L. Xu, T. S. Buda, and D. O'Sullivan. Spatio-temporal clustering approach for detecting functional regions in cities. In ICTAI, 2016.Google ScholarCross Ref
- Y. Bengio. Learning deep architectures for ai. Foundations and trends® in Machine Learning, 2(1):1--127, 2009. Google ScholarDigital Library
- Y. Bengio, P. Lamblin, D. Popovici, H. Larochelle, et al. Greedy layer-wise training of deep networks. In NIPS, 2007. Google ScholarDigital Library
- N. Bicocchi, G. Castelli, M. Mamei, A. Rosi, and F. Zambonelli. Supporting location-aware services for mobile users with the whereabouts diary. In MobilWare, 2008. Google ScholarDigital Library
- D. M. Blei, A. Y. Ng, and M. I. Jordan. Latent dirichlet allocation. the Journal of machine Learning research, 3:993--1022, 2003. Google ScholarDigital Library
- J. Cao, T. Xia, J. Li, Y. Zhang, and S. Tang. A density-based method for adaptive lda model selection. Neurocomputing, 72(7):1775--1781, 2009. Google ScholarDigital Library
- Z. Cheng, J. Caverlee, K. Lee, and D. Z. Sui. Exploring millions of footprints in location sharing services. 2011.Google Scholar
- C. Collins, S. Hasan, and S. V. Ukkusuri. A novel transit rider satisfaction metric: Rider sentiments measured from online social media data. Journal of Public Transportation, 16(2):2, 2013.Google ScholarCross Ref
- R. Collobert and J. Weston. A unified architecture for natural language processing: Deep neural networks with multitask learning. In ICML, 2008. Google ScholarDigital Library
- N. Eagle and A. S. Pentland. Eigenbehaviors: Identifying structure in routine. Behavioral Ecology and Sociobiology, 63(7):1057--1066, 2009.Google ScholarCross Ref
- K. Farrahi and D. Gatica-Perez. Discovering routines from large-scale human locations using probabilistic topic models. ACM Transactions on Intelligent Systems and Technology (TIST), 2(1):3, 2011. Google ScholarDigital Library
- L. Ferrari and M. Mamei. Discovering daily routines from google latitude with topic models. In PERCOM, 2011.Google ScholarCross Ref
- L. Ferrari, A. Rosi, M. Mamei, and F. Zambonelli. Extracting urban patterns from location-based social networks. In SIGSPATIAL, 2011. Google ScholarDigital Library
- Y. Freund and D. Haussler. Unsupervised learning of distributions of binary vectors using two layer networks, 1994.Google Scholar
- Y. Fu, H. Xiong, Y. Ge, Z. Yao, Y. Zheng, and Z.-H. Zhou. Exploiting geographic dependencies for real estate appraisal: A mutual perspective of ranking and clustering. In Proceedings of the 20th ACM SIGKDD international conference on Knowledge discovery and data mining, pages 1047--1056. ACM, 2014. Google ScholarDigital Library
- H. Gao, J. Tang, and H. Liu. gscorr: modeling geo-social correlations for new check-ins on location-based social networks. In CIKM, 2012. Google ScholarDigital Library
- A. Halevy, P. Norvig, and F. Pereira. The unreasonable effectiveness of data. Intelligent Systems, IEEE, 24(2):8--12, 2009. Google ScholarDigital Library
- S. Hasan and S. V. Ukkusuri. Urban activity pattern classification using topic models from online geo-location data. Transportation Research Part C: Emerging Technologies, 44:363--381, 2014.Google ScholarCross Ref
- G. Hinton. A practical guide to training restricted boltzmann machines. Momentum, 9(1):926, 2010.Google Scholar
- G. E. Hinton. Training products of experts by minimizing contrastive divergence. Neural computation, 14(8):1771--1800, 2002. Google ScholarDigital Library
- G. E. Hinton and R. R. Salakhutdinov. Reducing the dimensionality of data with neural networks. Science, 313(5786):504--507, 2006.Google ScholarCross Ref
- J. J. Hopfield. Neural networks and physical systems with emergent collective computational abilities. Proceedings of the national academy of sciences, 79(8):2554--2558, 1982.Google ScholarCross Ref
- F. Kling and A. Pozdnoukhov. When a city tells a story: urban topic analysis. In SIGSPATIAL, 2012. Google ScholarDigital Library
- H. Larochelle, D. Erhan, A. Courville, J. Bergstra, and Y. Bengio. An empirical evaluation of deep architectures on problems with many factors of variation. In ICML, 2007. Google ScholarDigital Library
- Y. LeCun, S. Chopra, R. Hadsell, M. Ranzato, and F. Huang. A tutorial on energy-based learning. Predicting structured data, 1:0, 2006.Google Scholar
- L. Maaloe, M. Arngren, and O. Winther. Deep belief nets for topic modeling. arXiv preprint arXiv:1501.04325, 2015.Google Scholar
- H. Mobahi, R. Collobert, and J. Weston. Deep learning from temporal coherence in video. In ICML, 2009. Google ScholarDigital Library
- A. Noulas, S. Scellato, C. Mascolo, and M. Pontil. Exploiting semantic annotations for clustering geographic areas and users in location-based social networks. 2011.Google Scholar
- R. Salakhutdinov, A. Mnih, and G. Hinton. Restricted boltzmann machines for collaborative filtering. In ICML, 2007. Google ScholarDigital Library
- J. Shang, Y. Zheng, W. Tong, E. Chang, and Y. Yu. Inferring gas consumption and pollution emission of vehicles throughout a city. In SIGKDD, 2014. Google ScholarDigital Library
- S. Sigg, S. Haseloff, and K. David. An alignment approach for context prediction tasks in ubicomp environments. PERCOM, 2010.Google ScholarDigital Library
- D. Yang, D. Zhang, V. W. Zheng, and Z. Yu. Modeling user activity preference by leveraging user spatial temporal characteristics in lbsns. Systems, Man, and Cybernetics: Systems, IEEE Transactions on, 45(1):129--142, 2015.Google Scholar
- N. J. Yuan, Y. Zheng, X. Xie, Y. Wang, K. Zheng, and H. Xiong. Discovering urban functional zones using latent activity trajectories. Knowledge and Data Engineering, IEEE Transactions on, 27(3):712--725, 2015.Google Scholar
- E. Zavitsanos, S. Petridis, G. Paliouras, and G. A. Vouros. Determining automatically the size of learned ontologies. In ECAI, 2008. Google ScholarDigital Library
- F. Zhang, D. Wilkie, Y. Zheng, and X. Xie. Sensing the pulse of urban refueling behavior. In UbiComp, 2013. Google ScholarDigital Library
Recommendations
Smart and Fermented Cities: An Approach to Placemaking in Urban Informatics
CHI '19: Proceedings of the 2019 CHI Conference on Human Factors in Computing SystemsWhat makes a city meaningful to its residents? What attracts people to live in a city and to care for it? Today, we might see such questions as concerns for HCI, given the emerging agendas of smart and connected cities, IoT, and ubiquitous computing: ...
A Tale of Three Cities: Looking at the Trending Feature on Foursquare
SOCIALCOM-PASSAT '12: Proceedings of the 2012 ASE/IEEE International Conference on Social Computing and 2012 ASE/IEEE International Conference on Privacy, Security, Risk and TrustThis study examines and compares the temporal patterns and categorical trends of Foursquare's trending feature in three cities in the U.S. The three cities in our experiment are New York City, NY, Pittsburgh, PA and Erie, PA. We show that large cities ...
Using an Online Spatial Analytics Workbench for Understanding Changing Housing Markets across Australian Cities
UCUI '15: Proceedings of the ACM First International Workshop on Understanding the City with Urban InformaticsWe live in an era of unprecedented global population growth where cities are expected to accommodate a significant proportion of this growth. In the context of Australia we have Sydney and Melbourne each approaching a population of 8 million people and ...
Comments