Sensing Urban with Wi-Fi and Satellite: Functional Region Discovery across Cities

Modern urbanization is featured with rapid development and collective intelligence, for which how to effectively utilize multimodal urban sensory data is a hot topic. In this paper, we focus on automatically recognizing functional urban regions by fusing two important sensory media, including collective behavioral information reflected by Wi-Fi accessing records collected from large populations as well as high-resolution satellite urban imaging. An aggregation algorithm is firstly applied to identify candidate functional regions characterized by geographical clusters of Wi-Fi access points. Semantic behavioral and visual features are extracted from two heterogeneous sensory data respectively, from which multi-functional properties are recognized by combining decision trees with boosting method. Finally, a transfer learning algorithm derived from AdaBoost is proposed to adapt the trained model to other cities with different feature distribution. Experimental results on real data sets demonstrate the efficacy of the proposed model in terms of recognition accuracy.

[1]  Krzysztof Janowicz,et al.  On the semantic annotation of places in location-based social networks , 2011, KDD.

[2]  Thomas Blaschke,et al.  Land cover change assessment using decision trees, support vector machines and maximum likelihood classification algorithms , 2010, Int. J. Appl. Earth Obs. Geoinformation.

[3]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[4]  Alessandro Laio,et al.  Clustering by fast search and find of density peaks , 2014, Science.

[5]  Qi Li,et al.  User-level psychological stress detection from social media using deep neural network , 2014, ACM Multimedia.

[6]  Gustavo Camps-Valls,et al.  Classification of Satellite Images with Regularized AdaBoosting of RBF Neural Networks , 2008, Speech, Audio, Image and Biomedical Signal Processing using Neural Networks.

[7]  ChengXiang Zhai,et al.  Instance Weighting for Domain Adaptation in NLP , 2007, ACL.

[8]  Wolfram Burgard,et al.  Supervised Learning of Places from Range Data using AdaBoost , 2005, Proceedings of the 2005 IEEE International Conference on Robotics and Automation.

[9]  Qiang Yang,et al.  Boosting for transfer learning , 2007, ICML '07.

[10]  Trevor Hastie,et al.  Multi-class AdaBoost ∗ , 2009 .

[11]  Sean Hughes,et al.  Clustering by Fast Search and Find of Density Peaks , 2016 .

[12]  Pawel Forczmanski,et al.  Applying Image Features and AdaBoost Classification for Vehicle Detection in the 'SM4Public' System , 2015, IP&C.

[13]  Yu Zheng,et al.  U-Air: when urban air quality inference meets big data , 2013, KDD.

[14]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.

[15]  Carlo Gatta,et al.  Unsupervised Deep Feature Extraction for Remote Sensing Image Classification , 2015, IEEE Transactions on Geoscience and Remote Sensing.

[16]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[17]  Trevor Darrell,et al.  Caffe: Convolutional Architecture for Fast Feature Embedding , 2014, ACM Multimedia.

[18]  Qiang Yang,et al.  Transfer Knowledge between Cities , 2016, KDD.

[19]  Qiang Yang,et al.  A Survey on Transfer Learning , 2010, IEEE Transactions on Knowledge and Data Engineering.

[20]  Lawrence Carin,et al.  Logistic regression with an auxiliary data source , 2005, ICML.

[21]  Ann Q. Gates,et al.  TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING , 2005 .

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

[23]  Dengxin Dai,et al.  Satellite Image Classification via Two-Layer Sparse Coding With Biased Image Representation , 2011, IEEE Geoscience and Remote Sensing Letters.

[24]  Nitish Srivastava,et al.  Multimodal learning with deep Boltzmann machines , 2012, J. Mach. Learn. Res..

[25]  John Krumm,et al.  Placer: semantic place labels from diary data , 2013, UbiComp.

[26]  Stefano Ermon,et al.  Transfer Learning from Deep Features for Remote Sensing and Poverty Mapping , 2015, AAAI.

[27]  Michael I. Jordan,et al.  Advances in Neural Information Processing Systems 30 , 1995 .