GM與ANFIS機車跟車模式之比較

Motorcycle-Following Models of General Motors (GM) and Adaptive Neuro-Fuzzy Inference System (ANFIS)

10.6402/TPJ.200409.0511

藍武王(Lawrence W . Lan)；張瓊文(Chiung-Wen Chang)

機車跟車行為 ； 通用汽車GM跟車模式 ； 適應性類神經模糊推論系統ANFIS跟車模式 ； Motorcycle-following behaviors ； General Motors GM model ； Adaptive neuro-fuzzy inference system ANFIS model

運輸計劃季刊

33卷3期（2004 / 09 / 30）

511 - 536

繁體中文

本文旨在探討具有跟車現象之機車行為特性，界定影響機車跟車行為之顯著因素，據以構建機車跟車模式。經實地錄影觀察發現，機車具有跟車現象的比率僅占所有觀察機車樣本之13.8%。由機車與旁車間互動所呈現之相關資料分析與檢定結果發現，相對速率差、與前車間距、前車加速率係影響後（機）車跟車加速率之顯著因素。依據實地觀察資料，本文首先構建通用汽車(GM)機車跟車模式，發現情況1（僅正前方有車）之迴歸判定係數(R^2)僅為0.20~0.29間，均方誤差根(RMSE)值為0.73~0.81；情況2（正前方及斜前方含左或右或左右同時有車）之值亦僅為0.06~0.14間，RMSE值更達0.89~0.97，均顯示GM跟車模式配適度相當低，難以有效描述機車之跟車行為。因此本文另構建適應性類神經模糊推論系統(ANFIS)機車跟車模式，發現情況1及情況2之RMSE值分別僅為0.16及0.34，其配適度比GM跟車模式優越甚多；進一步以Q-Q相關係數檢定發現，情況1通過預測值與觀察值完全正相關之檢定，情況2雖未通過完全正相關檢定，惟其統計量相當接近臨界值，顯示情況2預測值與觀察值亦近乎完全正相關，說明ANFIS跟車模式確能描述實際之機車跟車行為。

The main purposes of this paper are to investigate the characteristics of motorcycle flow in a mixed traffic, to identify significant factors affecting the motorcycle-following behaviors, and to construct models that can properly describe the relationship between motorcycle acceleration rates and these factors. A field observation is conducted and outcomes shows that only 13.8% of the overall samples reveal a motorcycle-following phenomenon. Statistical tests show that the significant factors affecting motorcycle-following behaviors include relative speed, space headway between a motorcycle and its leading vehicle, and acceleration rate of leading vehicle. General Motors (GM) five-generation models are firstly attempted to explain the motorcycle's following behaviors in two cases: (1) only one leading vehicle in front; (2) two or more leading vehicles in front and neighboring-front (including either left-front, right-front, or both). The rather low values of the coefficient of multiple regression determination (R^2=0.20~0.29 and 0.06~0.14 for both cases) and relative large root-mean-square-error values (RMSE=0.73~0.81 and 0.89~0.97 for both cases) imply that all of the GM models have poorly described the motorcycle-following behaviors. Therefore, we further propose a motorcycle-following model by incorporating the adaptive neuro-fuzzy inference system (ANFIS) with those significant factors that affect the motorcycle-following behaviors. Compared with the GM models, the ANFIS model outperforms with much smaller RMSE values (0.16 and 0.34 for both cases). Moreover the Q-Q plot correlation coefficient tests also reveal that the predicted acceleration rates have a highly strong positive correlation with the observed acceleration rates in case (1) and a strong positive correlation in case (2). It suggests that our proposed ANFIS model can satisfactorily capture the nature of motorcycle-following behaviors in a mixed traffic.

1. Aycin, M. F.,Benekohal, R. F.(1999).Comparison of Car-Following Models for Simulation.Transportation Research Record,1678,116-127.
2. Bierley, R. L.(1963).Investigation of an Inter-Vehicle Spacing Display.Highway Research Record,25,58-75.
3. Brackstone, M.,McDonald, M.(1999).Transportation Research.
4. Chakroborty, P.,Kikuchi, S.(1999).Evaluation of the General Motors Based Car-Following Models and a Proposed Fuzzy Inference Model.Transportation Research,7,209-235.
5. Dijker, T.,Bovy, P. H. L.,Vermijs, R. G. M. M.(1998).Car-Following under Congested Conditions Empirical Findings.Transportation Research Record,1644,20-28.
6. Evans, L.,Rothery, R.(1973).Experimental Measurement of Perceptual Thresholds in Car Following.Highway Research Record,64,13-29.
7. Evans, L.,Rothery, R.(1977).Perceptual Thresholds in Car Following-Recent Comparison.Transportation Science,11(1),60-72.
8. Gipps, P. G.(1981).A Behavioral Car Following Model for Computer Simulation.Transportation Research,15,105-111.
9. Herman, R.,Montroll, E. W.,Potts, R. B.,Rothery, R. W.(1959).Traffic Dynamics: Analysis of Stability in Car Following.Operations Research,7(1),86-106.
10. Jang, J. S. R.(1993).ANFIS: Adaptive-Network-Based Fuzzy Inference System.IEEE Transactions on Systems, Man, and Cybernetics,23(3),665-685.
11. Jang, J. S. R.,Sun, C. T.,Mizutani, E.(1997).Neuro-Fuzzy and Soft Computing.Prentice Hall, International Editions.
12. Johnson, R. A.,Wichern, D. W.(1998).Applied Multivariate Statistical Analysis.Fourth Edition, Prentice-Hall, Inc.
13. Kometani, E.,Sasaki, T.(1959).A Safety Index for Traffic with a Linear Spacing.Operations Research,7(6),707-720.
14. May, A. D.(1990).Traffic Flow Fundamentals, Prentice-Hall, Inc.
15. Michaels, R. M.,Cozan, L. W.(1963).Perceptual and Field Factors Causing Lateral Displacement.Highway Research Record,25,1-13.
16. Pipes, L. A.(1967).Transportation Research Record.
17. Pipes, L. A.(1953).An Operational Analysis of Traffic Dynamics.Application Physical,24(3),274-281.
18. Powell, M.(2000).A Model to Represent Motorcycle Behavior at Signalized Intersection Incorporating an Amended First Order Macroscopic Approach.Transportation Research,34,497-514.
19. Rockwell, T. H.,Treiterer, J.(1968).NCHRP Report.HRB, Washington, D.C:
20. Tsoukalas, L. H.,Uhrig, R. E.(1997).Fuzzy and Neural Approaches in Engineering.John Wiley & Sons, Inc.
21. 交通部運輸研究所(2001)。2001年臺灣地區路容量手冊。
22. 交通部運輸研究所(1999)。機車車道寬度與路口疏解型態之研究。
23. 朱建全(1999)。機車駕駛者面臨交通衝突之行為反應研究。交通大學運輸工程與管理學系。
24. 周義華、許鉅秉(1992)。運輸計劃季刊。
25. 林大煜(1979)。臺北市天津街機車專用道之交通量及特性分析。運輸計劃季刊，8(2)，231-244。
26. 林育瑞(2001)。成功大學交通管理學系。
27. 邱宏華(1995)。交通大學交通運輸研究所。
28. 邱裕鈞、藍武王(2001)。中華民國運輸學會第十六屆學術論文研討會論文集。
29. 許添本、許敦淵、王義川(2001)。中華民國第三屆機車交通安全研討會學術論文集。
30. 許添本、游政霖、彭玉妤(1995)。機車行駛空間車道化構想與車流特性初步研究。運輸，28，19-36。
31. 許添本、蔣靜宜(2001)。中華民國第十七屆學術論文研討會論文集。
32. 許添本、鄭雅文(1999)。巷道汽機車車流特性比較研究。運輸學刊，11(4)，1-18。
33. 陳世泉(1993)。混合車流中機車駕駛行為之分析。臺灣大學土木工程研究所。
34. 湯儒彥(2001)。中華民國第三屆機車交通安全研討會學術論文集。
35. 湯儒彥(1998)。中華民國第二屆機車交通安全研討會學術論文集。
36. 黃泰林、何志宏(1994)。中華民國第九屆學術論文研討會論文集。
37. 藍武王、王日昌、江勁毅(1994)。運輸。
38. 藍武王、葉信宏(2001)。不同冒險度駕駛人之跟車行為：適應性類神經模糊推論系統。中國土木水利工程學刊，13(2)，427-434。
39. 魏健宏、林鄉鎮(1999)。應用類神經網路與遺傳演算法建構小汽車跟車模式之研究。運輸計劃季刊，28(3)，353-378。

1. 曾平毅、陳志明、張瓊文(2007)。機車專用道實際使用疏解寬度及容量估計之研究。運輸計劃，36(3)，371-392。
2. 柳永青、何晉亨(2008)。應用模糊理論與類神經網路建構煞車行爲模式。危機管理學刊，5(2)，39-48。