A New Urban Functional Regions Minig Method with MPETM

Urban functional regions mining plays an important role in Smart Cities. At present, the main approaches to deal with this problem are probabilistic topic models. Some researchers also use deep learning methods to solve this problem. In this paper, we present a new method for urban functional regions mining called MPETM which combines deep learning and probabilistic topic models. Experiment results show that the MPETM framework has superior accuracy than other current popular methods.

[1]  Krzysztof Janowicz,et al.  Extracting and understanding urban areas of interest using geotagged photos , 2015, Comput. Environ. Urban Syst..

[2]  David M. Blei,et al.  Exponential Family Embeddings , 2016, NIPS.

[3]  Francisco C. Pereira,et al.  Mining point-of-interest data from social networks for urban land use classification and disaggregation , 2015, Comput. Environ. Urban Syst..

[4]  Thomas Hofmann,et al.  Probabilistic Latent Semantic Analysis , 1999, UAI.

[5]  Andrew McCallum,et al.  Topic Models Conditioned on Arbitrary Features with Dirichlet-multinomial Regression , 2008, UAI.

[6]  Xing Xie,et al.  Discovering regions of different functions in a city using human mobility and POIs , 2012, KDD.

[7]  Quoc V. Le,et al.  Distributed Representations of Sentences and Documents , 2014, ICML.

[8]  Hugo Larochelle,et al.  A Neural Autoregressive Topic Model , 2012, NIPS.

[9]  Thomas Hofmann,et al.  Unsupervised Learning by Probabilistic Latent Semantic Analysis , 2004, Machine Learning.

[10]  Jayant Kalagnanam,et al.  Foundations for Smarter Cities , 2010, IBM J. Res. Dev..

[11]  Licia Capra,et al.  Urban Computing: Concepts, Methodologies, and Applications , 2014, TIST.

[12]  Charlie Karlsson,et al.  The identification of functional regions: theory, methods, and applications , 2006 .

[13]  David M. Blei,et al.  Deep Exponential Families , 2014, AISTATS.

[14]  Krzysztof Janowicz,et al.  A data-synthesis-driven method for detecting and extracting vague cognitive regions , 2017, Int. J. Geogr. Inf. Sci..