Data mining on commuting distance mode of urban residents based on the analysis of decision tree
Received date: 2009-04-07
Revised date: 2009-08-26
Online published: 2009-11-25
Supported by
国家自然科学基金资助项目(40601030)
With the development of suburbanization, urban residents now have more choices in jobs and housing locations. Nowadays, scholars increasingly pay attention to the studies on citizens' commuting mode. The analysis of commuting space characteristics belongs to the study of geography. Based on questionnaire survey, this paper first makes a descriptive analysis of people's commuting variables, distances, and directions. Then it discusses the commuters of Beijing by decision tree analysis and data mining. Conclusions are obtained as follows: First, under the fixed pruning severity, people's commuting distance is related to their traveling vehicles, resident locations, jobs, youngest child's education conditions, living space, family incomes, usage of cars, and employment rate on local areas. Factors such as gender, educational level, marital status, housing property are not involved in the mode. Second, our study of the relations between the eight variables and commuting distance is different from some foreign studies. Some of these variables are decisive to long-distance commuters while others are decisive to short-distance commuters. Since the housing property has various types such as commercial housing, affordable housing, leasing of public housing and so on, the housing space does not have obvious effect on long-distance or short-distance commuters. Among all the reasons, migrating is not the main cause of shortening the commuting distance. Those who do not migrate have longer commuting distance because they work in suburban areas. The family life cycle with children in kindergartens or primary schools is not a key factor in shortening the commuting distance as the situation in western countries, because there are boarding nursery kindergartens, welfare on giving birth and nursing, which is different from China. Also, wage earners and specialists are not the key factors effecting commuting distance, because of the passive suburbanization in Beijing.
Key words： commuting distance; decision tree; decision rules; Beijing
WANG Mao-jun, SONG Guo-qing, XU Jie . Data mining on commuting distance mode of urban residents based on the analysis of decision tree[J]. GEOGRAPHICAL RESEARCH, 2009 , 28(6) : 1516 -1527 . DOI: 10.11821/yj2009060008
[1] 柴彦威,刘志林,李峥嵘,等. 中国城市的时空间结构.北京:北京大学出版社,2002,69~72,162~196.
[2] 周素红,杨利军.广州城市居民通勤空间特征研究.城市交通,2005,3(1):62~67.
[3] 孟庆艳,陈静.城市居民通勤活动行为的时空特征研究—以上海浦东新区为例.交通规划,2006,(1):6~9.
[4] 薛领,王冰松,杨开忠.我国大都市居民通勤、就业与居住变迁的时空间特征研究——以北京市为例.学习与实践,2007,(12):32~39.
[5] 李雪铭,杜晶玉.基于居民通勤行为的私家车对居住空间影响研究——以大连为例.地理研究,2007,26(5):1033~1042.
[6] 胡华颖.城市空间社会:广州城市内部空间分析.广州:中山大学出版社,1993.
[7] 柴彦威,城市空间.北京:科学出版社,2000,129.
[8] 李峥嵘,柴彦威.大连市民通勤特征研究.人文地理,2000,15(6):67~59.
[9] 陈淑美,张金鹗.家庭就业结构与通勤选择之变迁分析——论1990年和2000年间台北市的变化.城市与计划, 2004,31(4): 295~312.
[10] 孟繁瑜,房文斌.城市居住与就业的空间配合研究——以北京市为例.城市发展研究,2007,14(6):87~94。
[11] 李强,李晓林.北京近郊大型居住区居民上班出行特征分析.城市问题,2007,(7):55~59.
[12] 周素红,阎小培.基于居民通勤行为分析的城市空间解读——以广州市典型街区为案例.地理学报,2006,61(2):179~189.
[13] Han J W, Kamber M. Data Mining: Concepts and Techniques, San Francisco: Morgan Kaufmann, 2001.
[14] 古田和久.教育費の動機構造の解明に向けて——教育意識の決定木分析.教育社会学研究,2007,80:207~225.
[15] 河野康成、山下利之.決定木とQM法による職業意思決定過程分析. 応用社会学研究,2004,46: 95~101.
[16] 吉田哲.戸建住宅団地に居住する高齢者を中心とした世帯の犯罪不安感の決定木分析,日本建築学会計画系論文集.2008,73(623):1~7.
[17] Chelghoum N, Zeitouni K, Boulmakoul A. A decision tree for multi-layered spatial data, Symposium on Geospatial Theory, Processing and Applications, Ottawa, 2002.
[18] Pal M, Mather P M. An assessment of the effectiveness of decision tree methods for land cover classification, Remote Sensing of Environment, 2003,86: 554~565.
[19] Moran C J, Bui E N. Spatial data mining for enhanced soil map modeling, International Journal of Geographical Information Science, 2002, 16(6): 533~549.
[20] Pal M, Mather P M.An assessment of the effectiveness of decision tree methods for land cover classification, Remote Sensing of Environment,2003, 86: 554~565.
[21] 豊田秀樹.金鉱を掘り当てる統計学＿データマイニング入門、講談社プルーバックス,2001.
[22] 戴维·奥尔森,石勇,商业数据挖掘导论.北京:机械工业出版社,2007,113~130.
[23] Manuel Artís, Javier Romaní , Jordi Suri?ach .Determinants of Individual Commuting in Catalonia, 1986-91: Theory and Empirical Evidence. Urban Studies, 2000, Vol.37, No 8, 1431~1450.
[24] 郑思齐,张文忠.住房成本与通勤成本的空间互动关系——来自北京市场的微观证据及其宏观含义.地理科学进展,2007,26(2):35~41.
[25] 宋金平,王恩儒,张文新,等.北京住宅郊区化与就业空间错位.地理学报,2007,62(4):387~396.
[26] 曹广忠,刘涛.北京市制造业就业分布重心变动研究——基于基本单位普查数据的分析.城市发展研究,2007,14(6):8~14.
[27] Kelly DeRango.Can commutes be used to test the spatial mismatch hypothesis, Urban Studies,2001,38(9):1521~1529.
[28] Paul Ong Evelyn Blumenberg. Job access, commute and travel burden among welfare recipients, Urban Studies, 1998, 35(1): 77~93.
[29] 荒井良雄,岡本耕平,田原裕子,柴彦威,中国都市生活空间——社会構造·ジェンター·高齢者.ナカニシャ、2008,24~31.
/
| 〈 |
|
〉 |