內湖科學園區在早期規劃為輕工業區，區內之道路設計對於乘載大量就業人口上有限制，近十年來，隨著就業人口移入內湖科學園區帶來了大量的通勤人口。然而內湖地區的軌道交通系統，缺乏有效的運輸量能載運通勤者，內湖科學園區大多位於捷運可及性低之區域，公車成為軌道運輸外的重要運具選擇。
相關研究表明，長時間的通勤和較長的公車行駛路線，對於通勤者和駕駛帶有負面影響，藉由公車著手改善、調整運輸服務水準，將比起軌道交通系統更為彈性、合適。
隨著GPS、ITS研究和無線通訊技術的發展，以及政府對數據開放的積極態度，研究者以及相關單位得以取得大量的交通資料數據，其中之一項為電子票證資料（SCD）。過往通勤相關研究中，電子票證資料是分析通勤模式的合適素材。為分析內湖地區的通勤模式，本研究採用了兩種方法。首先，利用集群分析法對電子票證資料將通勤群體進行分類；其次，利用關聯式法則，找出各個搭乘群體其頻繁搭乘站牌。透過此兩種方法，分析內湖科技園區的公車通勤模式。
透過本研究暸解內湖科學園區通勤至其他地區之旅運需求，以一小時尺度之電子票證資料，得以分析出內湖科學園區通勤乘客族群；後續透過關聯式法則的兩項指標，進一步探索往返內湖科學園區間，具有搭乘規律之站牌。研究結果可提供公部門，針對現行內科通勤專車及其他公車路線、時刻表的服務水準的調整；也提供私部門之業主，作為調整彈性上下班之參考依據。

Neihu Technology Park was planned as a light industrial zone in the early days. The road design in the area had restrictions on carrying a large number of employed people. In the past decade, as the employed population moved into Neihu Technology Park, it brought a large number of commuters. However, the rail transit system in the Neihu area lacks effective transportation capacity to carry commuters. Most of the Neihu Technology Park are located in areas with low MRT accessibility. Buses have become an important transportation option besides rail transportation.
Relevant studies have shown that long commutes and long bus routes have a negative impact on commuters and drivers. Improving and adjusting transportation service levels through buses will be more flexible and appropriate than rail transit systems.
With the development of GPS, ITS research, and wireless communication technologies, as well as the government's proactive approach to data openness, researchers and interested parties have access to a large amount of transportation data, one of which is smart card data (SCD). SCD is a suitable material for analyzing commuting patterns in previous commuting-related studies. In order to analyze the commuting patterns in the Neihu Technology Park, two methods were used in this study. First, cluster analysis was used to categorize commuter groups using SCD, and second, the association rule was used to identify the frequent stops of each group. By using these two methods, the bus commuting patterns in Neihu Technology Park were analyzed.
Through this research, we understand the travel demand for commuting from Neihu Technology Park to other areas. Using smart card data on an hourly basis, we can analyze the commuter passenger group of Neihu Technology Park. Subsequently, through the two indicators of the Association Rule, to further explore the stop signs with regular boarding rules between Neihu Technology Park and back. The research results can provide the public sector with adjustments to the service levels of current Neihu Technology Park commuter buses and other bus routes and timetables; it can also provide private sector owners with a reference basis for adjusting flexible commuting.

（一）中文文獻
王晉元（2015）。公車動態資訊系統巨量資料（big data）蒐集與視覺化分析研究。國立交通大學運輸研究中心。
王昶閔（2004）。考量旅次起迄需求量下車輛偵測器佈設策略之研究。﹝碩士論文。淡江大學運輸管理學系碩士論文。
呂政達（2006）。身體與勞動 ─工作、身體意識的世代差異研究。國立臺灣大學國家發展研究所碩士論文。
李炫逸（2008）。臺北市內湖科技園區發展對都市結構變遷之影響。中國文化大學地學研究所碩士論文。
交通部資中心（2020）公共運輸票證資料-旅運分析用標準(V2.01)，1-2。
周依潔（2008）。高齡者日常活動步道系統規劃。國立交通大學交通運輸研究所碩士論文，51。
林祥生、邱詩淳、劉益豪（2005）「應用悠遊卡資料挖据公車乘客之需求特性」，中華民國運輸學會第20屆學術文研討論文集，367-387。
林美君（2011）。多層多類分區密度之空間人口重分布模式。博士論文，國立臺灣大學生物環境系統工程學研究所博士論文，6。
林育瑄（2013）。模化旅運者運具選擇行為之動態性與異質性。國立交通大學運輸與物流管理學系碩士論文。
林浩瑋（2016）。悠遊卡大數據應用於大眾運輸乘客旅運型態之研究。淡江大學運輸管理學系碩士論文。
林珈羽（2019）。臺北都會區公車路線治理機制的轉變：跳蛙公車。國立臺灣大學建築與城鄉研究所碩士論文。
邱詩淳（2006）。運用悠遊卡及資料探勘求解公車營運改善方案。中華大學運輸科技與物流管理學系碩士論文。
柴彥威、王恩宙（1997）。時間地理學的基本概念與表示方法。經濟地理，17(3)，55-61。
張鈞閔（2017）。港口國管制缺失項目之關聯性分析。國立臺灣海洋大學運輸科學系碩士論文。
郭靜燕、吳炯義、詹金淦、詹前隆（2020）。應用資料探勘之群集分析法於小兒氣喘表現型態。北市醫學雜誌，17(4)，425-434。https://doi.org/10.6200/TCMJ.202012_17(4).0007
陳彥嘉（2012）。以區域性鄰集為基礎之相似度轉換方法應用於分群演算法。國立交通大學資訊科學與工程研究所碩士論文。
陳鑫智（2021）。以智慧卡資料探討臺南市公車使用者時空行為。中國文化大學地學研究所地理組碩士論文。
黃宇翔、王品鈞、方志強（2017）。混合型資料集的K-means分群演算法，電子商務學報19卷1期，Pp. 1-28。
葉奕新（2017）。臺北捷運系統之人潮移動分析。中國統計學報，55(2)，69-95。
廖章鈞（2015）。以智慧卡資料探討公共運輸使用者轉乘行為之空間變異。國立臺灣大學地理環境資源學系碩士論文，1-144。
臺北市政府產業發展局（2021）臺北市都市計書 - 修訂「變更臺北市『臺北內湖科技園區』(原內湖輕工業區)計畫案」。
謝萬興（2015）。運用悠遊卡巨量資料分析公車乘客行為。國立臺灣大學土木工程學研究所學位論文，1-125。
（二）外文文獻
Ankerst, M., Breunig, M. M., Kriegel, H. P., and Sander, J. (1999). OPTICS: Ordering Points To Identify the Clustering Structure. ACM Sigmod record, 28(2), 49-60.
Caio Pieroni, Mariana Giannotti, Bianca B. Alves, Renato Arbex. (2021). Big data for big issues: Revealing travel patterns of low-income population based on smart card data mining in a global south unequal city. Journal of Transport Geography, Volume 96.
Congming Shi1, Bingtao Wei, Shoulin Wei, Wen Wang, Hai Liu, Jialei Liu1(2021). A quantitative discriminant method of elbow point for the optimal number of clusters in clustering algorithm. J Wireless Com Network 2021, 31.
Ester, M., Kriegel, H.-P., Sander, J., and Xu, X. (1996). A density-based algorithm for discovering clusters in large spatial databases with noise. Paper presented at the Kdd.
Guo, X., Wang, D. Z., Wu, J., Sun, H., & Zhou, L. (2020). Mining commuting behavior of urban rail transit network by using association rules. Physica A: Statistical Mechanics and its Applications, 559, 125094.
Hägerstrand, T. (1970).What about people in Regional Science?. Papers of the Regional Science Association 24, 6–21.
Han, J., Lee, J. G., and Kamber, M. (2009). An overview of clustering methods in geographic data analysis. Geographic data mining and knowledge discovery, 2, 149-170.
Han, J., Pei, J., and Kamber, M. (2011). Data mining: concepts and techniques: Elsevier.
Hamed Faroqi, Mahmoud Mesbah, Jiwon Kim, Ahmad Tavassoli.(2018).A model for measuring activity similarity between public transit passengers using smart card data,Travel Behaviour and Society,Volume 13,Pages 11-25.
Holt, J. B. et al. (2004). Dasymetric Estimation of Population Density and Areal Interpolation of Census Data. Cartography and Geographic Information Science, 31, 103-121.
Jain, A. K. (2010). Data clustering: 50 years beyond K-means. Pattern Recognition Letters, 31(8), 651-666. doi:10.1016/j.patrec.2009.09.011
Juan Yong, Linjiang Zheng, Xiaowen Mao, Xi Tang, Ang Gao, Weining Liu(2021)Mining metro commuting mobility patterns using massive smart card data.Physica A: Statistical Mechanics and its Applications,Volume 584,126351.https://doi.org/10.1016/j.physa.2021.126351.
Gregory, I., & Ell, P. S. (2005). Breaking the boundaries: Integrating 200 years of the Census using GIS. Journal of the Royal Statistical Society: Series A Statistics in Society, 168(2), 419-437.
Kieu, L. M., Bhaskar, A., & Chung, E. (2013). Mining temporal and spatial travel regularity for transit planning. In Australasian Transport Research Forum 2013 Proceedings (pp. 1-12). Australasian Transport Research Forum.
Klapka,P.,Ellegård,K. & Frantál,B.(2020).What about Time-Geography in the post-Covid-19 era?. Moravian Geographical Reports,28(4) 238-247.
Kwan, M. P. (2004). GIS methods in time‐geographic research: Geocomputation and geovisualization of human activity patterns. Geografiska Annaler: Series B, Human Geography, 86(4), 267-280.
Lenntorp B. (1976). Paths in space-time environments : a timegeographic study of movement possibilities of individuals. Royal University of Lund Dept. of Geography.
Nina Siu-Ngan Lam.(1983).Spatial Interpolation Methods: A Review.The American Cartographer, 10:2, 129-150.
Maimon, O., & Last, M. (2001). Knowledge discovery and data mining. Info-Fuzzy Netw.(IFN) Methodol, 2, 23-44.
MacQueen, J. (1967). Some methods for classification and analysis of multivariate observations. Paper presented at the Proceedings of the fifth Berkeley symposium on mathematical statistics and probability.
Mannila, H. (1996). Data mining: machine learning, statistics, and databases. Paper presented at the ssdbm.
Mennis, J., and Guo, D. (2009). Spatial data mining and geographic knowledge discovery—An introduction. Computers, Environment and Urban Systems, 33(6), 403-408.
Miller, H. J. (2016). Time geography and space–time prism. International Encyclopedia of Geography: People, the Earth, Environment and Technology, 1-19.
Ming, T. Y. (2020). An Unsupervised Machine Learning Approach for Multi-Dimensional Network Data Mining [master's thesis].National Taiwan Normal University]. https://doi.org/10.6345/NTNU202000822
Pelletier, M., Trépanier, M., & Morency, C. (2011). Smart card data use in public transit: A literature review. Transportation Research Part C: Emerging Technologies, 19(4), 557-568.
Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., Grisel, O., ... & Duchesnay, É. (2011). Scikit-learn: Machine learning in Python. the Journal of machine Learning research, 12, 2825-2830.
Peters, S. E., Grogan, H., Henderson, G. M., López Gómez, M. A., Martínez Maldonado, M., Silva Sanhueza, I., & Dennerlein, J. T. (2021). Working Conditions Influencing Drivers' Safety and Well-Being in the Transportation Industry: "On Board" Program. International journal of environmental research and public health, 18(19), 10173.
Pereira, R.H.M., Andrade, P.R. & Vieira, J.P.B.(2023).Exploring the time geography of public transport networks with the gtfs2gps package. J Geogr Syst 25, 453–466.
R. Agrawal and R. Srikant(1995).Mining sequential patterns. Proceedings of the Eleventh International Conference on Data Engineering, Taipei, Taiwan, pp. 3-14.
Shasha Liu, Toshiyuki Yamamoto, Enjian Yao, Toshiyuki Nakamura(2021).Examining public transport usage by older adults with smart card data: A longitudinal study in Japan. Journal of Transport Geography,Volume 93,103046.
Tan, P.-N., Steinbach, M., and Kumar, V. (2006). Introduction to data mining: Boston : Pearson Addison Wesley, c2006.
Xiaolei Ma, Yao-Jan Wu, Yinhai Wang, Feng Chen, Jianfeng Liu.(2013).Mining smart card data for transit riders’travel patterns. Transportation Research Part C: Emerging Technologies,Volume 36, Pages 1-12.
Xiaolei Ma, Congcong Liu, Huimin Wen, Yunpeng Wang, Yao-Jan Wu.(2017). Understanding commuting patterns using transit smart card data. Journal of Transport Geography, Volume 58, Pages 135-145.
Ying Long, Jean-Claude Thill.(2015).Combining smart card data and household travel survey to analyze jobs–housing relationships in Beijing,Computers, Environment and Urban Systems,Volume 53,Pages 19-35.
Yue Deng, Jiaxin Wang, Chao Gao, Xianghua Li, Zhen Wang, Xuelong Li(2021).Assessing temporal–spatial characteristics of urban travel behaviors from multiday smart-card data.Physica A: Statistical Mechanics and its Applications,Volume 576,126058.
Zhuangbin Shi ,1Yang Liu ,1Mingwei He ,1and Qiyang Liu(2022). How Does Built Environment Affect Metro Trip Time of Elderly? Evidence from Smart Card Data in Nanjing. Journal of Advanced Transportation, Volume 2022.
（三）專書
交通部（2015）。交通技術標準規範公路類公路工程部交通工程規範，16-17。
王穆衡、邱裕鈞、馮正民、周榮昌、溫傑華、黃彥斐、閻姿慧、張贊育、翁美娟、曾幸敏（2013）公共運輸發展政策推動效益之評估與回饋:運具選擇行為變動之分析及決策支援系統建置。臺北市:交通部運研所。
林秀澧、高名孝（2015）。計劃城事──戰後臺北都市發展歷程。臺北:田園城市文化。
蕭世倫、方志祥、陳碧宇、尹凌、陳潔、楊喜平（2017）。城市人群活動時空GIS分析（初版）。科學出版社
蘇昭銘, 邱裕鈞, 王晉元, 張靖, 張志鴻, 林靜芬, 沈美慧, 游思遠, 王穆衡, 張贊育（2018）。先進公共運輸系統整合資料庫加值應用與示範計畫。臺北市:交通部運研所。
蘇昭銘、邱裕鈞、王晉元、林至康、游坤明、周幼珍、郭奕宏、張志鴻、沈美慧、張朝能、蔡欽同（2018）。電子票證資料加值應用分析之研究及示範計（初版）。 臺北市:交通部運研所。
Miller, H. J. (2018). Chapter 5 Time geography. In Handbook of Behavioral and Cognitive Geography. Cheltenham, UK: Edward Elgar Publishing.
Oded Maimon, Mark Last(2001). Knowledge Discovery and Data Mining: The Info-Fuzzy Network (IFN) Methodology. Springer.
（四）網路資源
大臺北公共運輸旅次資訊網。2022年11月5日取，取自https://taipeibusod.gov.taipei/TwinTaipei2/
內政部社會經濟資料服務平台。2023年12月27日取，取自
https://segis.moi.gov.tw/STAT/Web/Portal/STAT_PortalHome.aspx
（五）新聞媒體
臺北大眾捷運股份有限公司（2022年6月28日）。配合「HappyCash有錢卡」終止 7/1起北捷停止相關服務。 https://www.metro.taipei/News_Content.aspx?n=30CCEFD2A45592BF&sms=72544237BBE4C5F6&s=7948400D225DAD99
蘇文彬（2021年1月6日）。交通部運輸資料流通平臺TDX再進化，和11家業者聯手打造資料市集，要整合公私部門數據創造更大價值。iThome。https://www.ithome.com.tw/news/142077
邱秉瑜（2021年5月12日 ）。快速緩解台北內湖塞車問題的提案——城東BRT。聯合新聞網鳴人堂。https://opinion.udn.com/opinion/story/7885/5451149