Mining Place Design Knowledge from Multi-source Data in an Informed Design Platform

Along with the prevailing development of Smart Cities (SC), a novel knowledge management system is required to comprehensively manage data derived from ubiquitous physical and virtual objects for sophisticated and innovative analysis services. Particularly, in urban design, an "Informed Design" concept can be enabled by such system to harness big and heterogeneous geo-referenced data for a knowledge-based and responsive place design. As a solution to address emerging issues in collecting, storing, cleansing, analyzing, integrating, mining and visualizing multi-source data, an Informed Design Platform (IDP) is designed and being implemented. In this paper, an activity related multi-source data processing flow implemented in IDP is discussed to exemplify 1) how multi-source data can be efficiently and effectively processed based on concurrent data cleansing, analyzing and integrating cascades, 2) how indirectly related contents can be fully utilized to support a synergetic multisource data integration based on an outperforming ensemble-based social activity detection mechanism, and 3) how activity related place design knowledge can be easily mined based on a multi-dimension and multi-measure query (MMQ) to reveal place design context of the project testbed Jurong East, Singapore.

[1]  Bige Tunçer,et al.  Exploring the utilization of places through a scalable “Activities in Places” analysis mechanism , 2016, 2016 IEEE International Conference on Big Data (Big Data).

[2]  Michael R. Lyu,et al.  A Unified Point-of-Interest Recommendation Framework in Location-Based Social Networks , 2016, ACM Trans. Intell. Syst. Technol..

[3]  Prem Prakash Jayaraman,et al.  OpenIoT: Open Source Internet-of-Things in the Cloud , 2014, OpenIoT@SoftCOM.

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

[5]  Bige Tunçer,et al.  Informed Design Platform: Interpreting “Big Data” to Adaptive Place Designs , 2016, 2016 IEEE 16th International Conference on Data Mining Workshops (ICDMW).

[6]  Jeremy Ellman,et al.  Simple Approaches of Sentiment Analysis via Ensemble Learning , 2015 .

[7]  Preslav Nakov,et al.  SemEval-2015 Task 10: Sentiment Analysis in Twitter , 2015, *SEMEVAL.

[8]  Christos Doulkeridis,et al.  DsUniPi: An SVM-based Approach for Sentiment Analysis of Figurative Language on Twitter , 2015, SemEval@NAACL-HLT.

[9]  Ralf Tönjes,et al.  CityPulse: Large Scale Data Analytics Framework for Smart Cities , 2016, IEEE Access.

[10]  Bige Tunçer,et al.  SAPAM: A Scalable "Activities in Places" Analysis Mechanism for Informed Place Design , 2016, 2016 IEEE/ACM 3rd International Conference on Big Data Computing Applications and Technologies (BDCAT).

[11]  Bige Tunçer,et al.  Exploring public sentiments for livable places based on a crowd-calibrated sentiment analysis mechanism , 2016, 2016 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM).

[12]  Alessandro Moschitti,et al.  Twitter Sentiment Analysis with Deep Convolutional Neural Networks , 2015, SIGIR.

[13]  Joaquim Melendez,et al.  Identifying services for short-term load forecasting using data driven models in a Smart City platform , 2017 .

[14]  Bin Cheng,et al.  Building a Big Data Platform for Smart Cities: Experience and Lessons from Santander , 2015, 2015 IEEE International Congress on Big Data.

[15]  Tianyi Ma,et al.  CITY FEED , 2016, ACM Trans. Intell. Syst. Technol..

[16]  Pearl Pu,et al.  Dystemo: Distant Supervision Method for Multi-Category Emotion Recognition in Tweets , 2016, ACM Trans. Intell. Syst. Technol..

[17]  Yue Gao,et al.  Event Classification in Microblogs via Social Tracking , 2017, ACM Trans. Intell. Syst. Technol..

[18]  Tomas Mikolov,et al.  Enriching Word Vectors with Subword Information , 2016, TACL.