![trajectories andprovide the end user with a smart route, whichincorporatesthe physical feature of a route, the
time-dependent trafficflow as well as the users’ driving behaviors (of both the fleetdrivers and of the end user
for whom the route is beingcomputed). We build a real system with real-world GPStrajectories generated by
over 33,000 taxis in a period ofthree months, then evaluate the system with extensiveexperiments and in-the-
field evaluations. The results showthat our method significantly outperforms the competingmethods in the
aspects of effectiveness and efficiency infinding the practically fastest routes. Overall, more than60 percent of
our routes are faster than that of the existingonline map services, and 50 percent of these routes are atleast 20
percent faster than the latter. On average, ourmethod can save about 16 percent of time for a trip, i.e.,5 minutes
per 30-minutes driving.
REFERENCE
[1] J. Yuan, Y. Zheng, C. Zhang, W. Xie, G. Sun, H. Yan, and X. Xie,“T-Drive: Driving Directions Based on
Taxi Trajectories,” Proc.18th SIGSPATIAL Int’l Conf. Advances in Geographic InformationSystems (GIS),
2010.
[2] T. Hunter, R. Herring, P. Abbeel, and A. Bayen, “Path and TravelTime Inference from GPS Probe Vehicle
Data,” Proc. NeuralInformation Processing Systems (NIPS), 2009.
[3] Y. Lou, C. Zhang, Y. Zheng, X. Xie, W. Wang, and Y. Huang“Map-Matching for Low-Sampling-Rate GPS
Trajectories,” Proc.Int’l Conf. Advances in Geographic Information Systems (GIS),2009.
[4] J. Yuan, Y. Zheng, C. Zhang, and X. Xie, “An Interactive-VotingBased Map Matching Algorithm,” Proc.
Int’l Conf. Mobile DataManagement (MDM), 2010.
[5] E. Kanoulas, Y. Du, T. Xia, and D. Zhang, “Finding Fastest Pathson a Road Network with Speed Patterns,”
Proc. Int’l Conf. DataEng. (ICDE), 2006.
[6] A. Orda and R. Rom, “Shortest-Path and Minimum-DelayAlgorithms in Networks with Time-Dependent
Edge-Length,”J. ACM, vol. 37, no. 3, pp. 607-625, 1990.
[7] N. Leibowitz, B. Baum, G. Enden, and A. Karniel, “TheExponential Learning Equation as a Function of
Successful TrialsResults in Sigmoid Performance,” J. Math. Psychology, vol. 54,
no. 3, pp. 338-340, 2010.
[8] B.C. Dean, “Continuous-Time Dynamic Shortest Path Algorithms,”master’s thesis, MIT, 1999.](https://image.slidesharecdn.com/t-driveenhancingdrivingdirectionswithtaxidriversintelligence-131008055149-phpapp01/85/JAVA-2013-IEEE-DATAMINING-PROJECT-T-drive-enhancing-driving-directions-with-taxi-drivers-intelligence-6-320.jpg)
JAVA 2013 IEEE DATAMINING PROJECT T drive enhancing driving directions with taxi drivers’ intelligence
- 1. T-Drive: Enhancing Driving Directions with Taxi Drivers’ Intelligence Abstract This paper presents a smart driving direction system leveraging the intelligence of experienced drivers. In this system,GPS-equipped taxis are employed as mobile sensors probing the traffic rhythm of a city and taxi drivers’ intelligence in choosing drivingdirections in the physical world. We propose a time-dependent landmark graph to model the dynamic traffic pattern as well as theintelligence of experienced drivers so as to provide a user with the practically fastest route to a given destination at a given departuretime. Then, a Variance-Entropy-Based Clustering approach is devised to estimate the distribution of travel time between twolandmarks in different time slots. Based on this graph, we design a two-stage routing algorithm to compute the practically fastest andcustomized route for end users. We build our system based on a real-world trajectory data set generated by over 33,000 taxis in aperiod of three months, and evaluate the system by conducting both synthetic experiments and in-the-field evaluations. As a result, 60-70 percent of the routes suggested by our method are faster than the competing methods, and 20 percent of the routes share the sameresults. On average, 50 percent of our routes are at least 20 percent faster than the competing approaches. GLOBALSOFT TECHNOLOGIES IEEE PROJECTS & SOFTWARE DEVELOPMENTS IEEE FINAL YEAR PROJECTS|IEEE ENGINEERING PROJECTS|IEEE STUDENTS PROJECTS|IEEE BULK PROJECTS|BE/BTECH/ME/MTECH/MS/MCA PROJECTS|CSE/IT/ECE/EEE PROJECTS CELL: +91 98495 39085, +91 99662 35788, +91 98495 57908, +91 97014 40401 Visit: www.finalyearprojects.org Mail to:ieeefinalsemprojects@gmail.com
- 2. Existing System The efficient driving directions has become a dailyactivity and been implemented as a key feature in manymap services like Google and Bing Maps. A fast drivingroute saves not only the time of a driver but also energyconsumption (as most gas is wasted in traffic jams). Therefore,this service is important for both end users andgovernments aiming to ease traffic problems and protectenvironment.Essentially, the time that a driver traverses a routedepends on the following three aspects: 1) the physicalfeature of a route, such as distance, capacity (lanes), and thenumber of traffic lights as well as direction turns; 2) thetime-dependent traffic flow on the route; and 3) a user’sdriving behavior. Given the same route, cautious driverswill likely drive relatively slower than those preferringdriving very fast and aggressively. Also, users’ drivingbehaviors usually vary in their progressing driving experiences.For example, traveling on an unfamiliar route, a userhas to pay attention to the road signs, hence drive relativelyslowly. Thus, a good routing service should consider thesethree aspects (routes, traffic, and drivers), which are farbeyond the scope of the shortest/fastest path computing.Usually, big cities have a large number of taxicabstraversing in urban areas. Disadvantages That is, we cannot answeruser queries by directly mining trajectory patterns from thedata. Therefore, how to model taxi drivers’ intelligence thatcan answer a variety of queries is a challenge We cannot guarantee there aresufficient taxis traversing on each road segment even if wehave a large number of taxis. That is, we cannot accuratelyestimate the speed pattern of each road segment Proposed System The preprocessed taxi trajectories, we detect thetop-k frequently traversed road segments, which are termedas landmarks. The reason why we use “landmark” to modelthe taxi drivers’ intelligence is that: first, the sparseness andlow-sampling rate of the taxi trajectories do not support usto directly calculate the travel time for each road segmentwhile we can estimate the traveling time between twolandmarks (which have been frequently traversed by taxis).Second, the notion of landmarks follows the naturalthinking pattern of people.The threshold _ is used to eliminate the edges seldomtraversed by taxis, as the fewer taxis that pass two landmarks,the lower accuracy of the estimated travel time(between the two landmarks) could be. Additionally, we setthe tmax value to remove the landmark edges having a verylong travel time. Due to the low-sampling rate problem,sometimes, a taxi may consecutively
- 3. traverse three landmarkswhile no point is recorded when passing the middle(second) one. This will result in that the travel time betweenthe first and third landmark is very long. Such kinds of edgeswould not only increase the space complexity of a landmarkgraph but also bring inaccuracy to the travel time estimation. Advantages The almost sharesimilar traffic patterns while the weekdays and weekendshave different patterns. Therefore, we build two differentlandmark graphs for weekdays and weekends, respectively. The travel times of transitions pertaining to alandmark edge clearly gather around some values (like a setof clusters) rather than a single value or a typical Gaussiandistribution, as many people expected. This aims to handle the situationthat a taxi was stuck in a traffic jam or waiting at a trafficlight where multiple points may be recorded on the sameroad segment Module 1. Intelligence modeling 2. Low Sampling Rate Problem 3. The Landmark Graph 4. Route Generation 5. Path logging 6. Route Computing Module Description Intelligence modeling A user can select any place as asource or destination, there would be no taxi trajectoryexactly passing the query points. That is, we cannot answeruser queries by directly mining trajectory patterns from thedata. Therefore, how to model taxi drivers’ intelligence thatcan answer a variety of queries is a challenge. Low Sampling Rate Problem To save energy and communicationloads, taxis usually report on their locations in a very lowfrequency, like 2-5 minutes per point. This increases theuncertainty of the routes traversed by a taxi. As shown inthere could exist four possible routes.
- 4. The Landmark Graph To save energy and communication loads, taxis usually report on their locations in a very low frequency, like2-5 minutes per point. This increases the uncertainty of theroutes traversed by a taxi. Meanwhile, we cannotguarantee there are sufficient taxis traversing on each roadsegment anytime even if we have a large number of taxis.That is, we cannot directly estimate the speed pattern of eachroad segment based on taxi trajectories. Route Generation The traffic condition of a road, the travel time of aroute also depends on drivers. Sometimes, different driverstake different amounts of time to traverse the same route atthe same time slot. The reasons lie in a driver’s drivinghabit, skills and familiarity of routes. For example, peoplefamiliar with a route can usually pass the route faster than anewcomer. Also, even on the same path, cautious peoplewill likely drive relatively slower than those preferring todrive very fast and aggressively. Path logging The cloud sends the computed drivingroutes along with the travel time distributions of theLandmark edges contained in the driving route to thephone. Later, the mobile phone logs the user’s drivingpath with a GPS trajectory, which will be used forrecalculate the user’s custom factor. The more a driveruses this system, the deeper this system understandsthe driver; hence, a better driving direction servicescan be provided. Route computing According to the departure time,start and destination point, the cloud chooses a properlandmark graph considering the weather informationand whether it’s a holiday or a workday. Based on thelandmark graph, a two-stage routing algorithm isperformed to obtain a time-dependent fastest route
- 5. Flow chart Conclusion This paper describes a system to find out the practicallyfastest route for a particular user at a given departure time.Specifically, the system mines the intelligence of experienceddrivers from a large number of taxi
- 6. trajectories andprovide the end user with a smart route, whichincorporatesthe physical feature of a route, the time-dependent trafficflow as well as the users’ driving behaviors (of both the fleetdrivers and of the end user for whom the route is beingcomputed). We build a real system with real-world GPStrajectories generated by over 33,000 taxis in a period ofthree months, then evaluate the system with extensiveexperiments and in-the- field evaluations. The results showthat our method significantly outperforms the competingmethods in the aspects of effectiveness and efficiency infinding the practically fastest routes. Overall, more than60 percent of our routes are faster than that of the existingonline map services, and 50 percent of these routes are atleast 20 percent faster than the latter. On average, ourmethod can save about 16 percent of time for a trip, i.e.,5 minutes per 30-minutes driving. REFERENCE [1] J. Yuan, Y. Zheng, C. Zhang, W. Xie, G. Sun, H. Yan, and X. Xie,“T-Drive: Driving Directions Based on Taxi Trajectories,” Proc.18th SIGSPATIAL Int’l Conf. Advances in Geographic InformationSystems (GIS), 2010. [2] T. Hunter, R. Herring, P. Abbeel, and A. Bayen, “Path and TravelTime Inference from GPS Probe Vehicle Data,” Proc. NeuralInformation Processing Systems (NIPS), 2009. [3] Y. Lou, C. Zhang, Y. Zheng, X. Xie, W. Wang, and Y. Huang“Map-Matching for Low-Sampling-Rate GPS Trajectories,” Proc.Int’l Conf. Advances in Geographic Information Systems (GIS),2009. [4] J. Yuan, Y. Zheng, C. Zhang, and X. Xie, “An Interactive-VotingBased Map Matching Algorithm,” Proc. Int’l Conf. Mobile DataManagement (MDM), 2010. [5] E. Kanoulas, Y. Du, T. Xia, and D. Zhang, “Finding Fastest Pathson a Road Network with Speed Patterns,” Proc. Int’l Conf. DataEng. (ICDE), 2006. [6] A. Orda and R. Rom, “Shortest-Path and Minimum-DelayAlgorithms in Networks with Time-Dependent Edge-Length,”J. ACM, vol. 37, no. 3, pp. 607-625, 1990. [7] N. Leibowitz, B. Baum, G. Enden, and A. Karniel, “TheExponential Learning Equation as a Function of Successful TrialsResults in Sigmoid Performance,” J. Math. Psychology, vol. 54, no. 3, pp. 338-340, 2010. [8] B.C. Dean, “Continuous-Time Dynamic Shortest Path Algorithms,”master’s thesis, MIT, 1999.