2010年台灣將「智慧綠建築」列為重點發展的四大新興智慧型產業之一（其餘為雲端運算、智慧電動車及發明專利產業化），智慧綠建築之推動，即是運用臺灣資通訊高科技產業科技與節能減碳之綠建築結合，提供安全健康、便利舒適及節能永續的生活環境，促進台灣建築科技產業發展。本研究探討台灣推動「智慧綠建築」相關政策（綠建築標章、智慧建築標章及綠建材標章）之推動歷程，分析自1988年～2014年間通過「綠建築標章」、「智慧建築標章」及「綠建材標章」評定案件之消長情形與各階段實施之推動政策關連性，運用二次資料分析歸納台灣推動「智慧綠建築」政策之關鍵成功要素，如下：1. 制定明確規範及基準供智慧綠建築設計及改善有明確遵循之依據；2.優先由公有建築物推動，提供業界試行場域及受保障之市場商機，規範公部門採購綠建材產品；3.分級評估漸進提高標準帶動相關連技術、產業之升級；4.強制性或獎勵性政策工具之運用考量區域特色因地制宜；5.針對「智慧綠建築」產業鏈相關利害關係人分別規劃獎勵政策提供實質誘因；6.「智慧綠建築」政策鏈結關連產業發展以帶動整體建築產業發展；7.強化政策行銷工作主動積極推廣政策。
為了將臺灣「智慧綠建築」政策進行科學量化之分析，提供後續制定建築產業推動政策之決策及評估流程參考，本研究進一步利用Fuzzy Hierarchical Analysis及Fuzzy Transformation Matrix為工具，透過深度訪談萃取資深領域專家之集體智慧，據以評估各項政策工具對達成「智慧綠建築政策目標」貢獻度之權重排序，經過彙整評估1999～2015年間之各年度間綠建築標章、智慧建築標章及綠建材標章政策工具施行，並將評定案件之消長情形、民間自發性參與及評估分級之變化情形等成果進行整合性分析，結果發現：1.本文所提出之政策評估方法其評估結果與「智慧綠建築政策」實際執行成果之趨勢有高度相依性，證明其具有參考價值；2.臺灣之「智慧綠建築政策」針對新建建築在設計規劃階段實施管制之政策工具其成效優於在維運管理階段進行管制者；3.對民間建築提供容積獎勵、對公有建築進行強制性管制及強制「綠建材」納入綠色公共採購等措施，為臺灣推動「智慧綠建築政策」最有效之三大政策工具。
針對臺灣推動智慧綠建築政策具有成效及特色之綠色便利商店推動為對象，分別運用大數據（Big Data mining）、機器學習（Machine learning）分析技術及傳統統計方法（Traditional statistics method），探討臺灣便利商店之能耗特性及建立節能對策，並以開源軟體(open source software，OSS)WEKA及Minitab 18為工具，利用TABC (Taiwan Architecture and Building Center)團隊於2014年間進行調查之1052家台灣連鎖便利超商（分屬於統一、全家、萊爾富超商集團）為對象所獲得之大數據資料，全面性探討便利超商能耗性能與1.建築空間環境及地理條件類影響因素；2.經營型態類影響因素；3.營業用設備類影響因素；4.在地氣候條件類影響因素及5.服務區域社會經濟條件類影響因素之交互關係，並發掘隱含知識，改善傳統分析技術對複雜、不精確、不確定性之便利超商動態耗能系統不易建立模型之缺點，實作證明產出具有參考價值的分析結果。
其分析結果中，透過分析維度降階（Data attributes selection）可發掘影響便利超商能耗之關鍵影響因子及其影響強度排序；運用迴歸分析及分類技術建立耗能之數值預測模型，獲得各項影響因子之最佳化門檻值；應用聚類分析於比對不同分群資料間之差異性，判斷各項對便利超商耗能特性產生影響之因子之相關性，經由以上分析獲得之超商耗能特性隱含知識。統計分析方法利用多元複回歸方程式（Multiple regression model）建立便利商店能耗之預測模式，並經由各影響變數間之關連性（Correlation coefficient）分析，探討各項影響因素對能耗之貢獻度，分析結果可提供以下之利用：1.提供業主精準預測能耗性能，進行建築空間、營業設備及營運管理方式之最佳化配置；2.對於設計規劃人員可由各項關鍵因子之門檻值規劃及預測模式之驗證，獲得投資性/價比(C/P )最佳設計方案；3.對於政府能源及環境部門可提供決策支援，建立節能減碳政策及推估及設定便利商店產業耗能情境。

In 2010, Taiwan launched a plan called “the Four Emerging Intellectual Industries, which covers intelligent green buildings. The aim of promoting intelligent green buildings is to stimulate the architecture technology industry. This has been combined with information and communication technology and the concept of green buildings to provide a safe and healthy living environment while reducing carbon emissions and saving energy. This study investigated intelligent green building policies and their promotion in Taiwan using cases from 1988 to 2014. Key success factors were derived from analyzing and summarizing intelligent green building experiences in Taiwan. This was done through secondary data analyses by: 1) establishing clear norms and standards for intelligent green building design and improvement; 2) carrying out policies in the public sector in order to provide field trials and safeguarded market opportunities for industries; 3) implementing rating-based assessments in order to raise the quality of design; 4) introducing mandatory or incentive policies that depend on local specialties and conditions; 5) respectively planning incentives for relevant interested parties in the industrial chain; 6) linking the Smart Green Building policy chain to industrial development to drive the development of the overall construction industry; and 7) strengthening marketing efforts and proactively promoting policies.
In order to promote Taiwan's Intelligent Green Building Policy, this study engaged scientific quantitative analysis, provided follow-up decision-making for the evaluation process of the construction industry promotion policy, and used Fuzzy Hierarchical Analysis (FHA) and the Fuzzy Transformation Matrix (FTM) as tools to extract the experts’ collective intelligence upon in-depth interviews. The experts collectively assessed the contribution weights of various policy tools that are used to achieve the Intelligent Green Building policy objectives. The green building label, intelligent building label, and green building material label during the years from 1999 to 2015 were assessed. The findings on the implementation of the labeling policy measures, the integrated analysis of the results of the evaluation for the growth and decline of the applications, the spontaneous participation of people, and the change of the evaluation grading were as follows: 1) FHA and FTM could be used to extract the collective expert opinions and establish a policy evaluation method with a reference value; 2) additional bulk incentives for private buildings, mandatory control for public buildings, and mandatory incorporation of green public purchasing into green building materials are the most effective policy measures in Taiwan; and 3) the implementation of control measures during the design and planning stage for new buildings is superior to the use of control measures during the operation and management stage.
This study was aimed at the promotion of green convenience stores, and used Big Data mining, machine learning analysis, and traditional statistical methods to explore the energy consumption characteristics and feasible energy-saving measures of Taiwan's convenience stores. A total of 1,052 surveys were conducted by the TABC (Taiwan Architecture and Building Center) team in 2014 using the open source software (OSS) WEKA and Minitab 18 as tools. This study was focused on obtaining information and comprehensively exploring the convenience stores’ energy performance information, including: 1) the building space environment and geographical condition-related factors; 2) the influence of business type; 3) the influence of business equipment; 4) the influence of local climatic conditions; and 5) the influence of the socio-economic conditions of consumers in service areas.
According to the validation results, the quality of analysis could be upgraded and the convenience stores could be provided with specific and feasible energy saving and carbon reduction improvement proposals. The outcome of this study could provide convenience stores with the following directions: 1) convenience stores could receive accurate predictions of energy consumption performance to optimize the architectural space, business equipment, and operations management mode; 2) design planners could obtain the optimum design and cost/performance ratio by determining the thresholds of various key factors; and 3) decision support could be provided for government energy and environment departments to create energy saving and carbon emission reduction policies for the convenience store industry.
In the analysis results, through the analysis of the data attributes, the key factors affecting the energy consumption of the convenience stores and their intensity ranking were discovered. Regression analysis and classification techniques were used to establish a numerical prediction model of energy consumption. Cluster analysis was applied to compare the differences between different clusters of data. The correlation between factors affecting the energy consumption characteristics of the convenience stores was judged, and the energy consumption obtained through the above analysis was obtained. The statistical analysis method used a multiple regression model to establish a prediction model for the convenience stores’ energy consumption and discuss the contribution of various influencing factors through the correlation coefficient analysis of each influencing variable. The results could provide the following benefits: 1) owners could be provided with an accurate prediction of energy consumption performance that could help them optimize the construction space, business equipment, and operation management methods; 2) design planners could obtain the best design for the investment/price ratio based on threshold value planning and the forecasting of various key factors in the model; and 3) decision support could be provided for government energy and environment departments for the establishment of energy conservation and carbon reduction policies as well as to estimate and set up energy consumption standards for the convenience store industry.

參考文獻
[1] 內政部(2003)。綠建築推動方案。臺北：行政院。
[2] 內政部(2008)。生態城市綠建築推動方案。臺北：行政院。
[3] 林子平、莊惠雯、林奉怡、吳佩儒(2016)。臺灣綠建築評估系統應用於國外案例適用性之問題收集與歸納。臺北：內政部建築研究所。
[4] 呂文弘(2016)。因應氣候變遷調適的智慧綠建築發展課題探討研究。臺北：內政部建築研究所。
[5] 內政部(2011)。智慧綠建築推動方案。臺北：行政院。
[6] 陳慶利、林杰宏(2014)。智慧綠建築發展現況與重要推動政策。電機技師雙月刊，28，34-45。
[7] 李彥頤、江哲銘、廖妍婷、陳柏瑎(2011)。生態城市綠建築推動方案執行成效評估研究。臺北：社團法人臺灣綠建築發展協會。
[8] 內政部(2016)。永續智慧城市-智慧綠建築與社區推動方案。臺北：行政院。
[9] 練福星、林杰宏(2014)。智慧綠建築產業驅動要素與推動政策之分析-Analysis of Intelligent Green Building Industry Promotion and Driven Policy。1(2)，1-8。
[10] 鄭宜平、林杰宏(2016)。邁向健康建築－帶動居住空間的永續綠色風潮。健康與建築雜誌，3(2)，8-12。
[11] Stern, N., Peters, S., Bakhshi, V., & Bowen, A. (2006). Stern Review: The Economics of Climate Change. UK: Cambridge University Press.
[12] Stern, N. H., & Great Britain. Treasury. (2007). The economics of climate change : the Stern review. Cambridge, UK: Cambridge University Press.
[13] OECD, A. (2003). Environmentally Sustainable Buildings, Challenges and Policies. Paris, France: OECD publications Service.
[14] Yang, L., & Li, Y. (2013). Low-carbon City in China. Sust. Cities Soc., 9, 62-66.
[15] Légales, C.-M. (2016). United Nations conference on climate change(COP 21/CPM 11) Retrieved from http://www.cop21.gouv.fr/en/page-daccueil-v2/
[16] Robie, D., & Chand, S. (2017). Bearing witness 2016: A fiji climate change journalism case study. Pacific Journalism Review, 23(1), 186-206.
[17] Hourcade, J.-C., & Shukla, P. R. (2015). Cancun’s paradigm shift and COP 21: to go beyond rhetoric. Int. Environ. Agreem.-Polit. Law Econom., 15(4), 343-351.
[18] Ghezloun, A., Saidane, A., & Merabet, H. (2017). The COP 22 New commitments in support of the Paris Agreement. Energy Procedia, 119, 10-16.
[19] UNFCCC. (2017). COP23.HOME.Retrieved from https://cop23.com.fj/
[20] Interational Energy Agency, (IEA). (2015). KeyWorld Energy Statistics 2015.
[21] Huang, W. M., & Lee, G. W. M. (2009). Feasibility analysis of GHG reduction target: Lessons from Taiwan's energy policy. Renew. Sust. Energ. Rev, 13(9), 2621-2628.
[22] Germanwatch, & CAN, (Climate Action Network Europe). (2015). The Climate Change Performance Index Results 2016. Retrieved from Bonn, Germany.
[23] 臺灣環保署(2015)。臺灣自主減碳承諾。臺北：臺灣環保署。
[24] Interational Energy Agency, (IEA). (2011). Energy Efficiency Policy Recommend- ations. Retrieved from Paris, France.
[25] 經濟部能源局(2016)。2016年能源統計手冊Energy statistics handbook。臺北: 經濟部能源局，28-41。
[26] 行政院主計總處(2014)。國情統計通報。臺北：行政院綜合統計處，1-3.
[27] 行政院主計總處(2015)。產業關連表編制報告。臺北。
[28] Hong, T. (2009). A close look at the China Design Standard for Energy Efficiency of Public Buildings. Energy Build., 41(4), 426-435.
[29] Huang, Z., Yuan, H., & Shen, L. (2012). Contribution of promoting the green residence assessment scheme to energy saving. Energy Policy, 51, 374-381.
[30] 吳舜文(2011)。我國綠建築政策評估之研究。新北市：國立臺北大學。
[31] Julie, A., Aduda, K. O., Chen, J. L., & Chiu, C. Y. (2011). Green buildings and the law (J. Adshead Ed.). London: Spon Press.
[32] 經濟部統計處(2017)。產業經濟統計簡訊。臺北：經濟部。
[33] 經濟部商業司(2017)。連鎖式便利商店業之現況與未來趨勢。臺北：財團法人商業發展研究院。
[34] 傅任淇(2015)。便利商店用電解析與評估之研究。臺中市：朝陽科技大學。
[35] 經濟部能源局(2001)。便利商店節能技術手冊。臺北：經濟部能源局。
[36] 郭柏巖、傅任淇、卓鎮穎(2013)。綠色便利商店能源分級認證之研究。建築學報，84，17-39。
[37] 卓鎮顥(2013)。便利商店耗能及使用特性分析。臺中市：朝陽科技大學。
[38] 陳慶利、楊冠雄(2011)。100年度綠色便利商店分級認證及節能改造計畫成果報告。臺北：財團法人臺灣建築中心。
[39] 練福星、林杰宏、侯雅壹(2014)。低碳社區評估指標及排碳量推估。健康與建築雜誌，1(3)，1-9。
[40] 楊欽富、許銘文、林杰宏、陳文洲(2016)。智慧化居住空間展示推廣計畫。臺北：財團法人臺灣建築中心。
[41] 練福星、林杰宏(2014)。智慧綠建築產業驅動要素與推動政策之分析。健康與建築雜誌，1(2)，1-8。
[42] 內政部(2008)。生態城市綠建築推動方案。臺北：行政院。
[43] 林憲德(2003)。2003年版綠建築解說與評估手冊。臺北：內政部建築研究所。
[44] 林憲德(2006)。2006年版綠建築解說與評估手冊。臺北：內政部建築研究所。
[45] 林憲德(2012)。2012年版綠建築解說與評估手冊。臺北：內政部建築研究所。
[46] 林憲德(2015)。2015年版綠建築解說與評估手冊。臺北：內政部建築研究所。
[47] 財團法人臺灣建築中心(2018)。綠建築節能效益揭露。臺北：財團法人臺灣建築中心。
[48] Ying, H. C., Lin, C. R., & Chin, H. M. (2008). Report on the state of sustainable building in Taiwan. Taipei,Taiwan: World sustainable building conference.
[49] Bay, J.-H., & Ong, B. L. (2006). Tropical sustainable architecture: social and environmental dimensions (1st ed.). UK: Architectural Press.
[50] 林素琴(2017)。2017我國綠建築產業三大趨勢。臺灣：IEK產業情報網。
[51] 林素琴(2015)。我國綠建築產業環境掃描。工業技術研究院 (ITRI) 產業技術情報網 (IEK)，2-7。
[52] Eichholtz, P., & Quigley, J. M. (2012). Green building finance and investments: Practice, policy and research. Europ. Econ. Rev., 56(5), 903-904.
[53] Construction, M. H. (2013). World Green Building Trends SmartMarket Report 2013. New York, USA:, McGraw-Hill.
[54] 江哲銘(2007)。綠建材解說與評估手冊2007年版。臺北：內政部建築研究所 。
[55] 江哲銘(2011)。綠建材解說與評估手冊2011年版。臺北：內政部建築研究所。
[56] Cheng, Y. H., Lin, C. C., & Hsu, S. C. (2015). Comparison of conventional and green building materials in respect of VOC emissions and ozone impact on secondary carbonyl emissions. Build. Environ., 87, 274-282.
[57] Hsieh, T. T., Chiang, C. M., Ho, M. C., & Lai, K. P. (2012). The research of Taiwan green building materials (GBM) system and GBM eco-efficiency model on climate change. Paper presented at the World Academy of Science, Engineering and Technology International Journal of Environmental and Ecological Engineering, 6(7), 391-395.
[58] Liang, H. H., Chen, C. P., Hwang, R. L., Shih, W. M., Lo, S. C., & Liao, H. Y. (2014). Satisfaction of occupants toward indoor environment quality of certified green office buildings in Taiwan. Build. Environ., 72, 232-242.
[59] Kuo, P., Fu, J. C., & Jhuo, C. H. (2014). Analysis on the usage characteristics of electrical equipment of Taiwan's convenience stores. Paper presented at the 2013 International Conference on Information Technology and Computer Application Engineering, ITCAE 2013, Hong Kong.
[60] 卓鎮顥(2013)。便利商店耗能及使用特性分析。朝陽科技大學建築系建築及都市設計碩士論文，臺中市。
[61] Shen, H. (2014). A Study on energy performance of convenience stores:Benchmarking and investion of factors on store energy use. (Master of Science), The Pennsylvania State University.
[62] Chou, D.-C., Chang, C.-S., & Hsu, Y.-Z. (2016). Investigation and analysis of power consumption in convenience stores in Taiwan. Energy Build., 133, 670-687.
[63] Chen, H.-H., Wang, P.-F., Sung, C.-T., Yeh, Y.-R., Lee, Y.-J., & Ieee. (2013). Energy Disaggregation via Clustered Regression Models: A Case Study in the Convenience Store. Paper presented at the 2013 Conference on Technologies and Applications of Artificial Intelligence, 37-42, Taipei, Taiwan.
[64] Wang, A.-P., & Hsu, P.-L. (2008). The network-based energy management system for convenience stores. Energy Build., 40(8), 1437-1445.
[65] Philip Chen, C. L., & Zhang, C.-Y. (2014). Data-intensive applications, challenges, techniques and technologies: A survey on Big Data. Inf. Sci., 275, 314-347.
[66] Meeker, W. Q., & Hong, Y. (2013). Reliability Meets Big Data: Opportunities and Challenges. Qual. Eng., 26(1), 102-116.
[67] Hashem, I. A. T., Chang, V., Anuar, N. B., Adewole, K., Yaqoob, I., Gani, A., Ahmed, E. & Chiroma H. (2016). The role of big data in smart city. Int. J. Inf. Manage., 36(5), 748-758.
[68] Yaqoob, I., Hashem, I. A. T., Gani, A., Mokhtar, S., Ahmed, E., Anuar, N. B., & Vasilakos, A. V. (2016). Big data: From beginning to future. Int. J. Inf. Manage., 36(6), 1231-1247.
[69] Kuo, C.-F. J., Lin, C.-H., & Lee, M.-H. (2018). Analyze the energy consumption characteristics and affecting factors of Taiwan's convenience stores-using the big data mining approach. Energy Build., 168, 120-136.
[70] Jung, J. J. (2017). Computational Collective Intelligence with Big Data: Challenges and Opportunities. Future Generation Computer Systems, 66, 87-88.
[71] Yu, Z., Fung, B. C. M., & Haghighat, F. (2013). Extracting knowledge from building-related data - A data mining framework. Build. Simul., 6(2), 207-222.
[72] Witten, I. H., Frank, E., Hall, M. A., & Pal, C. J. (2016). Data mining: Practical machine learning tools and techniques (Fourth ed.). Burlington, Massachusetts: Morgan Kaufmann.
[73] Dean, J. (2014). Big data, data mining, and machine learning: value creation for business leaders and practitioners. Hoboken, New Jersey: Wiley.
[74] Smith, T. C., & Frank, E. (2016). Introducing machine learning concepts with WEKA. In E. Mathé & S. Davis (Eds.), statistical genomics: methods and protocols. New York: Springer.
[75] Hall, M., Frank, E., Holmes, G., Pfahringer, B., Reutemann, P., & Witten, I. H. (2009). The WEKA data mining software: an update. SIGKDD Explorations, 11(1), 10-18.
[76] Bilal, M., Oyedele, L. O., Qadir, J., Munir, K., Ajayi, S. O., Akinade.(2016). Big data in the construction industry: A review of present status, opportunities, and future trends. Adv. Eng. Inform., 30(3), 500-521.
[77] Witten, I. H., Frank, E., Hall, M. A., & ebrary Inc. (2011). Data mining practical machine learning tools and techniques (pp. xxxiii, 629 p. ill.). Retrieved from http://site.ebrary.com/lib/calbaptist/Doc?id=10525052
[78] Babu, S. C., Gajanan, S. N., & Sanyal, P. (2014). Effects of commercialization of agriculture (shift from traditional crop to cash crop) on food consumption and nutrition-application of chi-square statistic. In food security, poverty and nutrition policy analysis (2 ed). San Diego: Academic Press.
[79] Lin, J. J., Chang, C. H., & Pal, N. (2015). A revisit to contingency table and tests of independence: Bootstrap is preferred to chi-square approximations as well as Fisher's exact test. J. Biopharm. Stat., 25(3), 438-458.
[80] Taneichi, N., & Sekiya, Y. (2007). Improved transformed statistics for the test of independence in contingency tables. J. Multivariate Anal., 98(8), 1630-1657.
[81] Shi, Q., Lai, X., Xie, X., & Zuo, J. (2014). Assessment of green building policies – A fuzzy impact matrix approach. Renew. Sust. Energ. Rev., 36, 203-211.
[82] Nachmias D(1979). Public policy evaluation: approaches and methods. New York: St. Martin's Press.
[83] Dunn, W. N. (2012). Public policy analysis (5th ed., International ed. ed.). Boston: Pearson.
[84] Ngo, C., Demchenko, Y., & de Laat, C. (2015). Decision diagrams for XACML policy evaluation and management. Comput. Secur., 49, 1-16.
[85] 洪晨淯(2013)。臺灣便利商店設備耗能推估之研究。臺中市：朝陽科技大學。
[86] Zhou, K., Fu, C., & Yang, S. (2016). Big data driven smart energy management: From big data to big insights. Renew. Sust. Energ. Rev, 56, 215-225.
[87] Yu, Z. (2012). Mining Hidden Knowledge from Measured Data for Improving Building Energy Performance. (Ph. D. Thesis (PhD)), Concordia University.
[88] SIGKDD(The association for computing Machinery's special interest on knowledge discovery and data mining) (2017). 2005 SIGKDD Service award: The WEKA team. Retrieved from http://www.kdd.org/awards/view/2005-sigkdd-service-award-the-weka- team
[89] Matsunaga, F. T., Brancher, J. D., & Busto, R.M. Data mining applications and techniques: a systematic review. Londrina State University.
[90] Nikolic, D., Muresan, R. C., Feng, W., & Singer, W. (2012). Scaled correlation analysis: a better way to compute a cross-correlogram. Eur. J. Neurosci., 35(5), 742-762.
[91] Chang, C.-W. (2012). Develop a ranking algorithm for the green building project. Qual. Quant., 48(2), 911-921.
[92] Bakhshi, H., Edwards, J. S., Roper, S., Scully, J., Shaw, D., Morley, L., & Rathbone, N. (2015). Assessing an experimental approach to industrial policy evaluation: Applying RCT+ to the case of Creative Credits. Res. Pol, 44(8), 1462-1472.
[93] Buckley, J. J., Feuring, T., & Hayashi, Y. (2001). Fuzzy hierarchical analysis revisited. Eur. J. Oper. Res, 129(1), 48-64.
[94] Gupta, P., Anand, S., & Gupta, H. (2017). Developing a roadmap to overcome barriers to energy efficiency in buildings using best worst method. Sust. Cities Soc., 31, 244-259.
[95] Mon, D.-L., Cheng, C.-S., & Lin J.-C. (1994). Evaluating weapon system using fuzzy analytic hierarchy process based on entropy weight. Fuzzy Sets Syst., 62(2), 127-134.
[96] Agami, N., Saleh, M., & El-Shishiny, H. (2010). A Fuzzy logic based trend impact analysis method. Technol. Forecast. Soc. Chang., 77(7), 1051-1060.
[97] Saaty, T. L. (2002). Decision making with the Analytic Hierarchy Process. Sci. Iran, 9(3), 215-229.
[98] Saaty, T. L. (2007). Multi-decisions decision-making: In addition to wheeling and dealing, our national political bodies need a formal approach for prioritization. Math. Comput. Model, 46(7-8), 1001-1016.
[99] BOE Taiwan, (Bureau of energy ministry of economic affair, Taiwan, ROC). (2001). Convenience Store Energy Saving Technical Handbook.
[100] Chu, S.-Y., & Chen, Y.-C. (2012). An analysis of energy efficiency in Taiwan's department stores, discount stores, and composite-style shopping malls. J. Glob. Bus. Manag., 8(2), 211-217.
[101] Tan Rich, S., & Rashad, Y. (2015). The review of physical store factors that influence impulsive buying behavior. Int. J. Manag. Account. Econ., 2(9), 1048-1054.
[102] Antonios, G. Z., & Prontzas, E. (2014). Consumer behaviour toward convenience store chains in Greece. EuroMed J. Bus., 9(2), 175-197.
[103] CWB Taiwan, (central weather brueau, Taiwan, ROC). (2017). Automatic weather station - Historical meteorological observation data. Retrieved from http://opendata.cwb. gov. tw/statisticlist
[104] NDC Taiwan, (Taiwan national development council). (2018). Governmental data open plateform. Retrieved from https://data.gov.tw/dataset/32086
[105] NDC Taiwan, (Taiwan national development council). (2017). Governmental data open plateform. Retrieved from http://data.gov.tw/about
[106] DHR MOI Taiwan, (Dept. of Household Registration, Ministry of the Interior, Taiwan, ROC). (2017). The resident population and the population density are statistics according to the township. Retrieved from http://data.moi.gov.tw/MoiOD/System/Download File.aspx? DATA=5B23A53B-C25A-4288-B24C-C8E65F76FDBB
[107] FIA MOF Taiwan, (fiscal information agency, ministry of finance, Taiwan, ROC). Comprehensive income statistics according to the township. 2017.
[108] Koprinska, I., Rana, M., & Agelidis, V. G. (2015). Correlation and instance based feature selection for electricity load forecasting. Knowledge-Based Syst., 82, 29-40.
[109] Kira, K., & Rendell, L. A. (1992). Feature selection problem: traditional methods and a new algorithm. Paper presented at the Proceedings Tenth National Conference on Artificial Intelligence - AAAI-92, Menlo Park, CA, United States
[110] Ghotra, B., McIntosh, S., & Hassan, A. E. (2017). A large-scale study of the impact of feature selection techniques on defect classification models. Paper presented at the 14th IEEE/ACM International Conference on Mining Software Repositories, Buenos Aires, Argentina.
[111] García-Nieto, J., Alba, E., Jourdan, L., & Talbi, E. (2009). Sensitivity and specificity based multiobjective approach for feature selection: Application to cancer diagnosis. Inf. Process. Lett, 109(16), 887-896.
[112] Siu, M. F., Ekyalimpa, R., Lu, M., & Abourizk, S. (2013). Applying regression analysis to predict and classify construction cycle time. Paper presented at the Computing in Civil Engineering - Proceedings of the 2013 ASCE International Workshop on Computing in Civil Engineering, Los Angeles, California.
[113] Schlomer, B. J., & Copp, H. L. (2014). Secondary Data Analysis of Large Data Sets in Urology: Successes and Errors to Avoid. J. Urol, 191(3), 587-596.
[114] Bogner, A., Littig, B., & Menz, W. (2009). Interviewing experts. Basingstoke: Palgrave Macmillan : ECPR.
[115] Bogner, A., Littig, B., & Menz, W. (2014). Interviews mit Experten: eine praxisori- entierte Einführung. Wiesbaden: Springer VS.