Abstract—Cities are complex systems of diverse and inter-tangled activities. These activities and their complex interrelationships create diverse urban phenomena. And such urban phenomena have considerable influences on the lives of citizens. This research aimed to develop a method to reveal the causes and effects among diverse urban elements in order to enable better understanding of urban activities and, therefrom, to make better urban planning strategies. Specifically, this study was conducted to solve a data-recommendation problem found on a Korean public data homepage. First, a correlation analysis was conducted to find the correlations among random urban data. Then, based on the results of that correlation analysis, the weighted data network of each urban data was provided to people. It is expected that the weights of urban data thereby obtained will provide us with insights into cities and show us how diverse urban activities influence each other and induce feedback. Keywords—Big data, correlation analysis, data recommendation system, urban data network. I. INTRODUCTION ITIES are made up of many elements including people, buildings, natural environments, infrastructure, and others. Activities in cities have complex relationships and generate a diversity of urban phenomena that influence the lives of citizens positively or negatively. Diverse urban phenomena occur via the clear causal relationships among urban elements [1]; multiple elements influence each other within a complex network. The relations among multiple elements can have hidden relations that people cannot perceive. And it is very difficult to reveal such relations of urban elements intuitively. Therefore it is a significant challenge to find the hidden relations among urban elements. One key to solving this problem is big data. Many urban phenomena occurring in cities are stored as data, which are often offered free to citizens. By analysis of urban data, people can understand the influences and complex relations among urban phenomena. If methods to reveal the complex relationships among diverse urban elements can be derived, urban activities will be better understood, and therefore also, urban planning strategies will become possible. Y.-M. Song is with the Department of Convergence Engineering for Future City, Sungkyunkwan University, Suwon, Republic of Korea (e-mail: hanimyu@skku.edu). S.-A. Kim is with the Department of Architecture, Sungkyunkwan University, Suwon, Republic of Korea (e-mail: sakim@skk.edu). D. Shin is with the BTU, Department of Architectural Engineering, Sungkyunkwan University, Suwon, Republic of Korea (corresponding author, phone: +82 1063745354; e-mail: dongyoun79@gmail.com). II. STATE OF THE ART OF URBAN BIG DATA Many studies have applied big data to cities. Urban data are collected through sensors installed on a person’s devices or in cities. In this way, the embedding of computers in the fabric of urban life has given rise to the notion of the ‘smart city’ wherein municipal functioning is supported by massive datasets [2]. Certainly, there is a role for big data in efforts to improve sustainability and overall living standards in cities. Thus, the current availability of smart devices that generate large heterogeneous datasets and the smart applications that offer seamless connections among various objects and individuals have been researched in efforts to realize the dream of the smart city. To this end too, comprehensive and in-depth analyses of state-of-art technologies have been performed, and suitable big-data structures have been presented [3]. Other research has explored how big data can be useful in urban planning by formalizing the planning process as a general computational problem. They resolved the dilemma between the need for planning and its impossibility in detail by recognizing that cities are foremost self-organizing social networks embedded in space and enabled by infrastructure and services of cities [4]. Another recent paper proposed a combined IoT-based system for smart city development and urban planning based on big-data analytics. The proposed system consists of eight steps that begin with data generation and end in decision making. In that study, the system was tested and evaluated with respect to efficiency measures in terms of throughput and processing time [5]. However, cities are complex spaces with integrated social, cultural, and technical aspects; utilizing of big data in such contexts, therefore, is problematic. One relevant study in this regard compared two countries in discussing issues of big data as they relate to urban research. It looked at the process of change of datasets in urban research and explored opportunities for big data. Then, it discussed the issues and solutions for the two cities [6]. Another study conducted systematic research in an attempt to understand the complex relations among urban data. It then provided, based on the concept of data vitalization, a data-correlation framework within which the correlation characteristics of data can be understood and expressed via a data-correlation diagram [7]. III. RESEARCH QUESTIONS Even though various studies seeking to understand urban complexities by means of urban big data have been undertaken, Forthcoming Big Data on Smart Buildings and Cities: An Experimental Study on Correlations among Urban Data Yu-Mi Song, Sung-Ah Kim, Dongyoun Shin C World Academy of Science, Engineering and Technology International Journal of Urban and Civil Engineering Vol:11, No:4, 2017 501 International Scholarly and Scientific Research & Innovation 11(4) 2017 scholar.waset.org/1307-6892/10007124 International Science Index, Urban and Civil Engineering Vol:11, No:4, 2017 waset.org/Publication/10007124