Bus Arrival Time Prediction Using Support Vector Machines



Σχετικά έγγραφα
CorV CVAC. CorV TU317. 1

Research on model of early2warning of enterprise crisis based on entropy

Quick algorithm f or computing core attribute

2016 IEEE/ACM International Conference on Mobile Software Engineering and Systems

A research on the influence of dummy activity on float in an AOA network and its amendments

ER-Tree (Extended R*-Tree)

Study of urban housing development projects: The general planning of Alexandria City

Automatic extraction of bibliography with machine learning

Research on vehicle routing problem with stochastic demand and PSO2DP algorithm with Inver2over operator

Ανάλυση Προτιμήσεων για τη Χρήση Συστήματος Κοινόχρηστων Ποδηλάτων στην Αθήνα

Schedulability Analysis Algorithm for Timing Constraint Workflow Models

Nov Journal of Zhengzhou University Engineering Science Vol. 36 No FCM. A doi /j. issn

Vol. 31,No JOURNAL OF CHINA UNIVERSITY OF SCIENCE AND TECHNOLOGY Feb

Motion analysis and simulation of a stratospheric airship

( ) , ) , ; kg 1) 80 % kg. Vol. 28,No. 1 Jan.,2006 RESOURCES SCIENCE : (2006) ,2 ,,,, ; ;

Research on Economics and Management

Buried Markov Model Pairwise

Study on the Strengthen Method of Masonry Structure by Steel Truss for Collapse Prevention

Intelligent Prediction Method for Small2Batch Producing Quality based on Fuzzy Least Square SVM

No. 7 Modular Machine Tool & Automatic Manufacturing Technique. Jul TH166 TG659 A

High order interpolation function for surface contact problem

EM Baum-Welch. Step by Step the Baum-Welch Algorithm and its Application 2. HMM Baum-Welch. Baum-Welch. Baum-Welch Baum-Welch.

A Method for Describing Coordination Problem Based on Coordination Knowledge Level

A System Dynamics Model on Multiple2Echelon Control

Analysis of energy consumption of telecommunications network and application of energy-saving techniques

CAP A CAP

Gro wth Properties of Typical Water Bloom Algae in Reclaimed Water

ΚΑΤΑΣΚΕΥΑΣΤΙΚΟΣ ΤΟΜΕΑΣ

Web-based supplementary materials for Bayesian Quantile Regression for Ordinal Longitudinal Data

Area Location and Recognition of Video Text Based on Depth Learning Method

SVM. Research on ERPs feature extraction and classification

Yahoo 2. SNS Social Networking Service [3,5,12] Copyright c by ORSJ. Unauthorized reproduction of this article is prohibited.

Stabilization of stock price prediction by cross entropy optimization

Probabilistic Approach to Robust Optimization

Εφαρμογή Υπολογιστικών Τεχνικών στην Γεωργία

3: A convolution-pooling layer in PS-CNN 1: Partially Shared Deep Neural Network 2.2 Partially Shared Convolutional Neural Network 2: A hidden layer o

VSC STEADY2STATE MOD EL AND ITS NONL INEAR CONTROL OF VSC2HVDC SYSTEM VSC (1. , ; 2. , )

Στοιχεία εισηγητή Ημερομηνία: 10/10/2017

Stress Relaxation Test and Constitutive Equation of Saturated Soft Soil

1 (forward modeling) 2 (data-driven modeling) e- Quest EnergyPlus DeST 1.1. {X t } ARMA. S.Sp. Pappas [4]

1530 ( ) 2014,54(12),, E (, 1, X ) [4],,, α, T α, β,, T β, c, P(T β 1 T α,α, β,c) 1 1,,X X F, X E F X E X F X F E X E 1 [1-2] , 2 : X X 1 X 2 ;

A Method for Creating Shortcut Links by Considering Popularity of Contents in Structured P2P Networks

ΔΙΠΛΩΜΑΤΙΚΕΣ ΕΡΓΑΣΙΕΣ

Optimization, PSO) DE [1, 2, 3, 4] PSO [5, 6, 7, 8, 9, 10, 11] (P)

Development of a Seismic Data Analysis System for a Short-term Training for Researchers from Developing Countries

Ερευνητική+Ομάδα+Τεχνολογιών+ Διαδικτύου+

ΖΩΝΟΠΟΙΗΣΗ ΤΗΣ ΚΑΤΟΛΙΣΘΗΤΙΚΗΣ ΕΠΙΚΙΝΔΥΝΟΤΗΤΑΣ ΣΤΟ ΟΡΟΣ ΠΗΛΙΟ ΜΕ ΤΗ ΣΥΜΒΟΛΗ ΔΕΔΟΜΕΝΩΝ ΣΥΜΒΟΛΟΜΕΤΡΙΑΣ ΜΟΝΙΜΩΝ ΣΚΕΔΑΣΤΩΝ

Control Theory & Applications PID (, )

ΕΘΝΙΚΟ ΜΕΤΣΟΒΙΟ ΠΟΛΥΤΕΧΝΕΙΟ ΣΧΟΛΗ ΗΛΕΚΤΡΟΛΟΓΩΝ ΜΗΧΑΝΙΚΩΝ ΚΑΙ ΜΗΧΑΝΙΚΩΝ ΥΠΟΛΟΓΙΣΤΩΝ

Approximation Expressions for the Temperature Integral

ΝΕΟ ΠΡΟΓΡΑΜΜΑ ΣΠΟΥΔΩΝ, ΤΜΗΜΑ ΔΙΟΙΚΗΣΗΣ ΕΠΙΧΕΙΡΗΣΕΩΝ, ΣΧΟΛΗ ΔΙΟΙΚΗΣΗΣ ΚΑΙ ΟΙΚΟΝΟΜΙΑΣ, ΤΕΙ ΙΟΝΙΩΝ ΝΗΣΩΝ ΕΙΣΑΓΩΓΙΚΗ ΚΑΤΕΥΘΥΝΣΗ ΔΙΟΙΚΗΣΗ ΕΠΙΧΕΙΡΗΣΕΩΝ

Optimization Investment of Football Lottery Game Online Combinatorial Optimization

ΑΝΩΤΑΤΗ ΣΧΟΛΗ ΠΑΙΔΑΓΩΓΙΚΗΣ ΚΑΙ ΤΕΧΝΟΛΟΓΙΚΗΣ ΕΚΠΑΙΔΕΥΣΗΣ. Ενίσχυση Ερευνητικών ομάδων στην Α.Σ.ΠΑΙ.Τ.Ε.»

Quantum dot sensitized solar cells with efficiency over 12% based on tetraethyl orthosilicate additive in polysulfide electrolyte

ΕΛΛΗΝΙΚΑ. Πεδίο Έρευνας και Τεχνολογίας. Όνομα Εργαστηρίου Σχολή Ιστορίας. Έρευνα Εργαστηρίου Α/Α

Κεφάλαιο 1 Βιβλιογραφική Επισκόπηση. Κεφάλαιο 2 Η ευχρηστία των Ποιοτικών Μεταφορικών Συστημάτων

J. of Math. (PRC) Banach, , X = N(T ) R(T + ), Y = R(T ) N(T + ). Vol. 37 ( 2017 ) No. 5

Δυνατότητα Εργαστηρίου Εκπαιδευτικής Ρομποτικής στα Σχολεία (*)

Reading Order Detection for Text Layout Excluded by Image

Πτυχιακή Εργασι α «Εκτι μήσή τής ποιο τήτας εικο νων με τήν χρή σή τεχνήτων νευρωνικων δικτυ ων»

: Monte Carlo EM 313, Louis (1982) EM, EM Newton-Raphson, /. EM, 2 Monte Carlo EM Newton-Raphson, Monte Carlo EM, Monte Carlo EM, /. 3, Monte Carlo EM

ΕΘΝΙΚΟ ΜΕΤΣΟΒΙΟ ΠΟΛΥΤΕΧΝΕΙΟ

ΒΙΟΓΡΑΦΙΚΟ ΣΗΜΕΙΩΜΑ ΣΤΥΛΙΑΝΗΣ Κ. ΣΟΦΙΑΝΟΠΟΥΛΟΥ Αναπληρώτρια Καθηγήτρια. Τµήµα Τεχνολογίας & Συστηµάτων Παραγωγής.

Retrieval of Seismic Data Recorded on Open-reel-type Magnetic Tapes (MT) by Using Existing Devices

HMY 795: Αναγνώριση Προτύπων

Research on real-time inverse kinematics algorithms for 6R robots

GPGPU. Grover. On Large Scale Simulation of Grover s Algorithm by Using GPGPU


ΠΑΝΕΠΙΣΤΗΜΙΟ ΠΑΤΡΩΝ ΤΜΗΜΑ ΗΛΕΚΤΡΟΛΟΓΩΝ ΜΗΧΑΝΙΚΩΝ ΚΑΙ ΤΕΧΝΟΛΟΓΙΑΣ ΥΠΟΛΟΓΙΣΤΩΝ ΤΟΜΕΑΣ ΣΥΣΤΗΜΑΤΩΝ ΗΛΕΚΤΡΙΚΗΣ ΕΝΕΡΓΕΙΑΣ

AΡΙΣΤΟΤΕΛΕΙΟ ΠΑΝΕΠΙΣΤΗΜΙΟ ΘΕΣΣΑΛΟΝΙΚΗΣ ΠΟΛΥΤΕΧΝΙΚΗ ΣΧΟΛΗ ΤΜΗΜΑ ΠΟΛΙΤΙΚΩΝ ΜΗΧΑΝΙΚΩΝ

Models for Asset Liability Management and Its Application of the Pension Funds Problem in Liaoning Province

Προσαρμογή περιοχικών υδρολογικών σχέσεων στις Ελληνικές λεκάνες

{takasu, Conditional Random Field

Zigbee. Zigbee. Zigbee Zigbee ZigBee. ZigBee. ZigBee

«Σενάρια ήπιας κινητικότητας για μια βιώσιμη πόλη»

«Χρήσεις γης, αξίες γης και κυκλοφοριακές ρυθμίσεις στο Δήμο Χαλκιδέων. Η μεταξύ τους σχέση και εξέλιξη.»

HIV HIV HIV HIV AIDS 3 :.1 /-,**1 +332

Homomorphism in Intuitionistic Fuzzy Automata

ΔΘΝΙΚΗ ΥΟΛΗ ΓΗΜΟΙΑ ΓΙΟΙΚΗΗ ΙΗ ΔΚΠΑΙΓΔΤΣΙΚΗ ΔΙΡΑ

ΕΛΕΓΧΟΣ ΤΩΝ ΠΑΡΑΜΟΡΦΩΣΕΩΝ ΧΑΛΥΒ ΙΝΩΝ ΦΟΡΕΩΝ ΜΕΓΑΛΟΥ ΑΝΟΙΓΜΑΤΟΣ ΤΥΠΟΥ MBSN ΜΕ ΤΗ ΧΡΗΣΗ ΚΑΛΩ ΙΩΝ: ΠΡΟΤΑΣΗ ΕΦΑΡΜΟΓΗΣ ΣΕ ΑΝΟΙΚΤΟ ΣΤΕΓΑΣΤΡΟ

Δυσκολίες που συναντούν οι μαθητές της Στ Δημοτικού στην κατανόηση της λειτουργίας του Συγκεντρωτικού Φακού

þÿ Ç»¹º ³µÃ ± : Ãż²» Ä Â

Supporting Information

2. Βιβλιογραφική ανασκόπηση

«Ευφυή Συστήματα Μεταφορών & εξελίξεις στην Ελλάδα»

ΚΛΙΜΑΤΟΛΟΓΙΑ CLIMATOLOGY

Η Διδακτική Ενότητα «Γνωρίζω τον Υπολογιστή», στα πλαίσια των Προγραμμάτων Σπουδών της Πληροφορικής: μια Μελέτη Περίπτωσης.

Εικονικά Περιβάλλοντα Μάθησης για Παιδιά με Αυτισμό: Επισκόπηση Πεδίου και Προτάσεις Σχεδιασμού

Β Ι Ο Γ Ρ Α Φ Ι Κ Ο Σ Η Μ Ε Ι Ω Μ Α ΕΛΕΝΗ ΣΦΑΚΙΑΝΑΚΗ

Μεθοδολογία Αξιολόγησης Υφιστάμενων Ποδηλατοδρόμων και Εφαρμογή σε Μεσαίου Μεγέθους Ελληνική Πόλη

Autonomous navigation control for mobile robots based on emotion and environment cognition

J. of Math. (PRC) 6 n (nt ) + n V = 0, (1.1) n t + div. div(n T ) = n τ (T L(x) T ), (1.2) n)xx (nt ) x + nv x = J 0, (1.4) n. 6 n

Δθαξκνζκέλα καζεκαηηθά δίθηπα: ε πεξίπησζε ηνπ ζπζηεκηθνύ θηλδύλνπ ζε κηθξνεπίπεδν.

τεχνική περιγραφή e-situ

ΠΟΛΥΤΕΧΝΕΙΟ ΚΡΗΤΗΣ ΣΧΟΛΗ ΜΗΧΑΝΙΚΩΝ ΠΕΡΙΒΑΛΛΟΝΤΟΣ

TAMIL NADU PUBLIC SERVICE COMMISSION REVISED SCHEMES

Q L -BFGS. Method of Q through full waveform inversion based on L -BFGS algorithm. SUN Hui-qiu HAN Li-guo XU Yang-yang GAO Han ZHOU Yan ZHANG Pan

The Simulation Experiment on Verifying the Convergence of Combination Evaluation

ΜΕΘΟΔΟΙ ΥΠΟΛΟΓΙΣΜΟΥ ΤΗΣ ΖΕΝΙΘΕΙΑΣ ΤΡΟΠΟΣΦΑΙΡΙΚΗΣ ΥΣΤΕΡΗΣΗΣ ΣΕ ΜΟΝΙΜΟΥΣ ΣΤΑΘΜΟΥΣ GNSS

IPSJ SIG Technical Report Vol.2014-CE-127 No /12/6 CS Activity 1,a) CS Computer Science Activity Activity Actvity Activity Dining Eight-He

Transcript:

2007 4 4 :100026788 (2007) 0420160205 1, 1, 2 (11, 116026 ;21, 116024) : 2 (SVM),, SVM. 5., 4,. : ; ;SVM : U121 : A Bus Arrival Time Prediction Using Support Vector Machines YU Bin 1, YANG Zhong2zhen 1, LIN Jian2yi 2 (11Transportation College, Dalian Maritime University, Dalian 116026, China ;21Civil Engineering Dept, Dalian University of Technology, Dalian 116024, China) Abstract: Effective prediction of bus arrival time is central to many advanced traveler information system. This paper presents support vector machines ( SVM), a new neural network algorithm, to predict bus arrival time. The objective of this paper is to examine the feasibility and applicability of SVM in vehicle travel time forecasting area. Time2of2day, weather, segment, the travel time of current segment and the latest travel time of next segment are taken as five input features. Bus arrival time predicted by the SVM is assessed with the data of transit route number 4 in Dalian economic and technological development zone in China and some conclusions are drawn. Key words : prediction ;bus arrival time ;support vector machine 1 APTS ATIS,.,,, ( [1 ],, ), ;,, (, ),. (, ),,,, : Kalman. [2,3 ],, [4 ].. Kalman, [2,5 7 ]. Kalman ( ) ( Kalman ),,,, [8 ]. 2,, :2005212212 : (20050151007) : (1977 - ),,,,,E2mail :minlfish @yahoo. com. cn ; (1964 - ),,,,,,E2mail :yangzhongzhen @263. net.

4 161.,., [9 11 ].,, [12 15 ]., 2 (SVM) [16 18 ], ( ),,. SVM,,,SVM.,,., SVM,,,,,.,.,., GPS,, 24 2,.,. 2,,,, SVM ( ) (, ). SVM,.,SVM,,. 211 l ( x 1, y 1 ), ( x 2, y 2 ),, ( x l, y l ) ( x i X Α R n, y i Y Α R),SVM, x H,,., : f ( x) = <( x) + b. (1), : 1 2 2 + C 1 l l 1 L ( y i,f ( x i ) ), (2) (2),, ;,, C > 0. 2 ( 1) L ( y i,f ( x i ) ) = max( y i - f ( x i ) -,0). (3) L ( y i,f ( x i ) ), f ( x i ) y i, 0 ;,, i, 3 i min 1 2 2 + C 1 l l, (2) : ( i + 3 i ), (4) s. t. y i - <( x i ) - b + i, (5) <( x i ) + b - y i + 3 i,,, l, (6)

162 2007 4 3 i 0. (7) (4),, :, - l ( a i - a 3 i ) x i = 0, (8) l f ( x) = ( a i - a 3 i ) <( x i ) <( x) + b. (9) K( x i, x j ) (9) : l f ( x) = ( a i - a 3 i ) K( x i, x) + b, (10) K( x i, x j ) x i x j <( x i ) <( x j ), K( x i, x j ) = <( x i ) <( x j ),. SVM, SVM. [19 21 ]. 212 SVM SVM 2. 5 : ( x 1 ), ( x 2 ), ( x 3 k k + 1, k k + 1 ), ( x 4 k k + 1, k k + 1 ) ( x 5 k - 1 k, k - 1 k ). SVM 5 k k + 1 y k k + 1, x 5 k - 1 k k + 1 t k + 1. x 1 x 2, ; x 3 k k + 1 x 4 k k + 1 x 5 k - 1 k,,., x 4 k k + 1 x 5 k - 1 k,,,. SVM,, ( SVM ) ; SVM.,,., x 1 x 2 x 3 k k + 1 SVM.,. m k 2, ( x 1 x 2 x 3 k k + 1 x 4 k k + 1 x 5 k - 1 k ) m k + 1, k - 1 k, : x 4 k - 1 k = x 5 k - 1 k.,,. 3, 4. 4, 1311, 17, 42. 10,, 10. 3. :1) ;2) C,.,, Sigmoid,,. ( C,, ),. ( C, ),

4 163 3 4,,, NP2 hard., [19,22 ],, ( ), ( C), MS E i ;,, ( C), ( ), MS E i + 1,.,, : (2-2,2-5,012)., ( ) ( ) : (SP ) (SO ) (RP ) (RO ). 10, 2005 9. (6 :3027 :30) (10 :00211 :00), 270 (270, 10 ),, (SP ) 160, (SO ) 70 (RP ) 22 (RO ) 18. SVM,,, 2,430., 238 SVM (146 SP 60 SO 18 RP 14 RO ),.,. SVM, SVM, SVM23, SVM SVM25.,, 4. 4,,,SVM25 SVM23,.,,, ( ), SVM23,,,,. SVM25,.,,. 4. SVM,, SVM,,

164 2007 4 4 SVM25 SVM23 SVM. 2 ( ) 3 ( ), 5., SVM.,,. : [ 1 ] Ben2Akiva M, Lerman S R. Discrete Choice Analysis : Theory and Application to Travel Demand[M]. MIT Press, Cambridge, Mass, 1985. [ 2 ] Stephanedes YJ, Kwon E, Michalopoulos P. On2Line Diversion Prediction for Dynamic Control and Vehicle Guidance in Freeway Corridors[M]. Transp Res Rec, 1990,1287, 11-19. [ 3 ] DeLurgio S A. Forecasting principles and applications, McGraw2Hill, New York,1998. [ 4 ] Smith B L, Demetsky MJ. Short2Term Traffic Flow Prediction :Neural Network Approach[M]. Transp Res Rec, 1995,1453, 98-104. [ 5 ] Okutani I, Stephanedes YJ. Dynamic prediction of traffic volume through kalman filtering theory[j ]. Transp Res, 1984,18B(1) : 1-11. [ 6 ] Dailey D, Maclean S, Cathey F,et al. Transit vehicle arrival prediction : Algorithm and large2scale implementation[j ]. Journal of the Transportation Research Board, 2001,1771, 46-51. [ 7 ] Shalaby A,Farhan A. Bus Travel Time Prediction Model for Dynamic Operations Control and Passenger Information Systems, CD2 ROM, The 82nd Annual Meeting of the Transportation Research Board, Washington, DC. 2003. [ 8 ] Park D,Rilett L R. Forecasting freeway link travel times with a multilayer feedforward neural network[j ]. Computer2Aided Civil and Infrastructure Engineering, 1999,14(5) :357-367. [ 9 ] Ding Y, Chien S. The Prediction of Bus Arrival Times with Link2Based Artificial Neural Networks [ C ]ΠΠProceedings of the International Conference on Computational Intelligence & Neurosciences (CI&N) 2Intelligent Transportation Systems, Atlantic City, New Jersey, 2000,730-3. [10 ] Chien I2Jy, Ding Y,Wei C. Dynamic bus arrival time prediction with artificial neural networks [J ]. Journal of Transportation Engineering, ASCE, 2002,128(5) : 429-38. [11 ] Chen M, Liu X B, Xia J X,et al. A dynamic bus2arrival time prediction model based on APC data[j ]. Computer2Aided Civil and Infrastructure Engineering, 2004,19 :364-376. ( 176 )

176 2007 4 [2 ]. [M]. :,2002. Gu Junsi. Computer Supported Cooperative Work[M]. Beijing :Tsinghua University Publish, 2002. [3 ],. [J ].,2000,20(5) :24-29. Yang Canjun, Chen Ying. Study on humachined cooperation decision2making[j ]. Systems Engineering - Theory & Practice,2000, 20 (5) :24-29. [4 ] Corkill D D. Cooperative Distributed Problem Solving[M]. AI handbook IV,1990. [5 ] H.. 2 [M]. :,1988. H. Haken. Synergetics - the Arcanum of Natural Structure[M]. Shanghai :Shanghai Science Popularization Publish, 1988. [6 ],. [J ].,2000. 9 :460-469. Bai Hua, Han Wenxiu. General theories about complex systems and their coordination [ J ]. System Science and Engineering Research, 2000,9 :460-469. [7 ],,. [J ].,2006,32(20) :235-239. Meng Xiuli1, Cao Jie, Han Xiangdong. Research on collaborative design support environment for machine tool [ J ]. Computer Engineering,2006,32(20 :235-239. [8 ],,,. [J ].,2004,5(5) :1-7. Lei Sheping, Xie Jiancang, Huang Mingcong,et al. Coordination degree analysis of regional industry water use system[j ]. Shuili Xuebao,2004,5(5) :1-7. [9 ],,,. Web [J ]. ( ),2000,19 (5) :16-19. Li Minbo, Tang Dong, Cheng Ye,et al. Web2based co2decision2making approach and application for manufacturing process[j ]. Journal of Tsinghua University,2000,19(5) :16-19. ( 164 ) [12 ] Lawrence S, Giles C L, Tsoi A 2C. Lessons in Neural Network Training : Overfitting May Be Harder Than Expected [ C ]ΠΠ Proceedings of the Fourteenth National Conference on Artificial Intelligence, Mento Park, CA : AAAl Press. 1997,AAAl297, 540-545. [13 ] Moody J E. The effective number of parameters : An analysis of generalization and regularization in nonlinear learning systems[j ]. NIPS, 1992,4 :847-854. [14 ] Sarle W S. Stopped Training and Other Remedies for Overfitting[ C]ΠΠProceedings of the Twenty2seventh Symposium on the Interface of Computing Science and Statistics,1995,352-360. [15 ] Weigend A. On Overfitting and the Effective Number of Hidden Units[ C]ΠΠProceedings of the 1993 Connectionist Models Summer School,1994,335-342. [16 ] Vapnik V N. The Nature of Statistical Learning Theory[M]. Springer,1995. [17 ] Vapnik V N. An overview of statistical learning theory[j ]. IEEE Transactions on Neural Networks,1999,10(5) :988-999. [18 ] Vapnik V N. The Nature of Statistical Learning Theory[M]. Springer, New York. (2000). [19 ] Dong B, Cao C, Lee S E. Applying support vector machines to predict building energy consumption in tropical region[j ]. Energy and Buildings, 2005,37 :545-553. [20 ] Cao L J, Francis E H. Support vector machine with adaptive parameters in financial time series forecasting[j ]. IEEE Transactions on Neural Networks, 2003,14(6). [21 ],,,. [J ].,2003,18(1) :89-91. Wang D C, Fang T J, Gao L F,et al. Support vector machines regressing on2line modeling and its application[j ]. Control and Decision, 2003,18(1) :89-91. [22 ] Hsu C W, Chang C C, Lin C J. A Practical Guide to Support Vector Classification[ R ]. Department of Computer Science and Information Engineering, National Taiwan University,2003.