Real-Time Trip Information Service for a Large Taxi Fleet

Slides:



Advertisements
Similar presentations
Research Challenges in the CarTel Mobile Sensor System Samuel Madden Associate Professor, MIT.
Advertisements

Presented by: Richard Wood. Goals and strategies Methods Performance evaluation Performance improvements Remaining Challenges.
Driving with Knowledge from the Physical World Jing Yuan, Yu Zheng Microsoft Research Asia.
Urban Computing with Taxicabs
Aggregating local image descriptors into compact codes
Guard4Life Advanced GPS
VTrack: Accurate, Energy-Aware Road Traffic Delay Estimation Using Mobile Phones Arvind Thiagarajan, Lenin Ravindranath, Katrina LaCurts, Sivan Toledo,
SignalGuru: Leveraging Mobile Phones for Collaborative Traffic Signal Schedule Advisory MobiSys 2011 Best paper award.
Critical Analysis Presentation: T-Drive: Driving Directions based on Taxi Trajectories Authors of Paper: Jing Yuan, Yu Zheng, Chengyang Zhang, Weilei Xie,
Tracking Fine-grain Vehicular Speed Variations by Warping Mobile Phone Signal Strengths Presented by Tam Vu Gayathri Chandrasekaran*, Tam Vu*, Alexander.
IBM TJ Watson Research Center © 2010 IBM Corporation – All Rights Reserved AFRL 2010 Anand Ranganathan Role of Stream Processing in Ad-Hoc Networks Where.
T-Drive : Driving Directions Based on Taxi Trajectories Microsoft Research Asia University of North Texas Jing Yuan, Yu Zheng, Chengyang Zhang, Xing Xie,
NTPT: On the End-to-End Traffic Prediction in the On-Chip Networks Yoshi Shih-Chieh Huang 1, June 16, Department of Computer Science, National Tsing.
WindMine: Fast and Effective Mining of Web-click Sequences SDM 2011Y. Sakurai et al.1 Yasushi Sakurai (NTT) Lei Li (Carnegie Mellon Univ.) Yasuko Matsubara.
Scaling Distributed Machine Learning with the BASED ON THE PAPER AND PRESENTATION: SCALING DISTRIBUTED MACHINE LEARNING WITH THE PARAMETER SERVER – GOOGLE,
Chapter Physical Database Design Methodology Software & Hardware Mapping Logical Design to DBMS Physical Implementation Security Implementation Monitoring.
TrafficView: A Scalable Traffic Monitoring System Tamer Nadeem, Sasan Dashtinezhad, Chunyuan Liao, Liviu Iftode* Department of Computer Science University.
1 An Empirical Study on Large-Scale Content-Based Image Retrieval Group Meeting Presented by Wyman
MTA ETA. Product Description A real-time simulation system that estimates the expected time that it will take a certain bus to arrive at an end- user’s.
Crossroads: A Practical Data Sketching Solution for Mining Intersection of Streams Jun Xu, Zhenglin Yu (Georgia Tech) Jia Wang, Zihui Ge, He Yan (AT&T.
TrafficView: A Driver Assistant Device for Traffic Monitoring based on Car-to-Car Communication Sasan Dashtinezhad, Tamer Nadeem Department of CS, University.
Logitrac Advanced GPS THE FUTURE OF GPS TECHNOLOGY.
World Renewable Energy Forum May 15-17, 2012 Dr. James Hall.
Identifying and Incorporating Latencies in Distributed Data Mining Algorithms Michael Sevilla.
Hashed Samples Selectivity Estimators for Set Similarity Selection Queries.
Sensys 2009 Speaker:Lawrence.  Introduction  Overview & Challenges  Algorithm  Travel Time Estimation  Evaluation  Conclusion.
Enabling a national road and street database in population statistics Pasi Piela Q2014 Vienna Conference.
Sidewinder A Predictive Data Forwarding Protocol for Mobile Wireless Sensor Networks Matt Keally 1, Gang Zhou 1, Guoliang Xing 2 1 College of William and.
Using Traffic Models as a Tool When Creating Noise Maps - Methods used in the EU project QCity Pia Sundbergh Div. for Transport and Localisation Analysis.
Report Samples. 2 Stop Report Shows where, when and for how long a vehicle has stopped.
The Future of gps technology
HERO: Online Real-time Vehicle Tracking in Shanghai Xuejia Lu 11/17/2008.
LOGO Ensemble Learning Lecturer: Dr. Bo Yuan
© 2010 IBM Corporation IBM Research - Ireland © 2014 IBM Corporation xStream Data Fusion for Transport Smarter Cities Technology Centre IBM Research.
Presenter: Mathias Jahnke Authors: M. Zhang, M. Mustafa, F. Schimandl*, and L. Meng Department of Cartography, TU München *Chair of Traffic Engineering.
RELATING SPEED TO DISTANCE AND TIME Chapter TYPES OF SPEED 1) AVERAGE SPEED  Is the total distance divided by the total time for an entire trip.
Dynamic Origin-Destination Trip Table Estimation for Transportation Planning Ramachandran Balakrishna Caliper Corporation 11 th TRB National Transportation.
Chapter Four: Motion  4.1 Position, Speed and Velocity  4.2 Graphs of Motion  4.3 Acceleration.
Presented to Time of Day Subcommittee May 9, 2011 Time of Day Modeling in FSUTMS.
1-1 CMPE 259 Sensor Networks Katia Obraczka Winter 2005 Storage and Querying.
Project Lachesis: Parsing and Modeling Location Histories Daniel Keeney CS 4440.
Learning to Navigate Through Crowded Environments Peter Henry 1, Christian Vollmer 2, Brian Ferris 1, Dieter Fox 1 Tuesday, May 4, University of.
Methodological Considerations for Integrating Dynamic Traffic Assignment with Activity-Based Models Ramachandran Balakrishna Daniel Morgan Srinivasan Sundaram.
BlinkDB: Queries with Bounded Errors and Bounded Response Times on Very Large Data ACM EuroSys 2013 (Best Paper Award)
A User Experience-based Cloud Service Redeployment Mechanism KANG Yu Yu Kang, Yangfan Zhou, Zibin Zheng, and Michael R. Lyu {ykang,yfzhou,
A Study of Comfort Measuring System Using Taxi Trajectories Li-Ping Tung 1, Tsung-Hsun Chien 2,3, Ting-An Wang 3, Cheng-Yu Lin 3, Shyh-Kang Jeng 2, and.
Analytical Queries on Road Networks: An Experimental Evaluation of Two System Architectures Shangfu PengHanan Samet Department.
Discount Tracking Solutions THE FUTURE OF GPS TRACKING IS HERE!
LODManager A framework for rendering multiresolution models in real-time applications J. Gumbau O. Ripollés M. Chover.
Preparation of the Body. Quick Question O Describe, in detail, a complex skill or technique from an activity of your choice. O (4 marks) O
Efficient Gigabit Ethernet Switch Models for Large-Scale Simulation Dong (Kevin) Jin David Nicol Matthew Caesar University of Illinois.
DOiT Dynamic Optimization in Transportation Ragnhild Wahl, SINTEF (Per J. Lillestøl SINTEF)
ParkNet: Drive-by Sensing of Road-Side Parking Statistics Irfan Ullah Department of Information and Communication Engineering Myongji university, Yongin,
Computational Challenges in BIG DATA 28/Apr/2012 China-Korea-Japan Workshop Takeaki Uno National Institute of Informatics & Graduated School for Advanced.
PHYSICS AND MOTION. If you want to understand how an object (like a car, ball, person, or rocket) moves, you have to understand three things about what.
Presented by: Shahab Helmi Spring 2016
Lessons learned from Metro Vancouver
Reza Yazdani Albert Segura José-María Arnau Antonio González
T-Share: A Large-Scale Dynamic Taxi Ridesharing Service
1st November, 2016 Transport Modelling – Developing a better understanding of Short Lived Events Marcel Pooke – Operational Modelling & Visualisation Manager.
Network Assignment and Equilibrium for Disaggregate Models
CFA: A Practical Prediction System for Video Quality Optimization
Crowd Density Estimation for Public Transport Vehicles
What is OCACCESS Online?
Understanding and Exploiting Amazon EC2 Spot Instances
Overview of CV2X Requirements
Predicting Traffic Dmitriy Bespalov.
STAT 689 Class Project STAT 689 Class Project
MUST HAVE PASSENGER AND DRIVER TAXI APP FEATURES.
Speed Notes.
Presentation transcript:

Real-Time Trip Information Service for a Large Taxi Fleet Rajesh Krishna Balan, Nguyen Xuan Khoa, and Lingxiao Jiang MobiSys 2011

Introduction Real-time trip information system that provides passengers with the expected fare and trip duration of the taxi ride they are planning to take. 15000 taxi, 21 month, 250 million data in Singapore Large scale implementation and evaluations

Motivation Unscrupulous driver who take longer routes Passenger can estimate trip time and fares by themselves. Failed solution : Google Maps Latency Trip fare Not accurate 35% time error

Taxi Network Taxi are cheap Taxi are common and found everywhere Most pickups are street pickups Used for all activities

Taxi locations in one day

challenge Large amount data Real time query requirement Various time-related factors How much data is sufficient? How to filter the data?

Service requirements Accuracy Real time capability Fares Real time capability Low computational requirements Easy to deploy operationally

Method design Partition Time location Prediction Hash table KNN

Time partition Hour Days of week(DoW) Hourly DoW Peak period 24*7=168Hr Peak period Week day 7am~10am, 5pm~8pm +35% Week day 6am-7am, 10am~5pm non-peak Weekend 6am~0am non-peak night 0am~6am +50%

location partition Static zone Dynamic zone 25km x 50km 50x50m~500x500m to divide zones Dynamic zone Adjust zone size for each trip

Prediction Input : start time, start GPS, end GPS Static Dynamic Similar historical data and average ( fare, duration, distance Index and hash table Dynamic KNN Data set (start time, S_long, S_latt, E_long, E_latt)

Evaluation Set1: 20 subsets for training 2010/8 2010/7+8 ….. 2009/1~2010/8 Set2 : 1 subset for testing(query) 2010/9

Evaluation LOC: start and end location PEAK: peak hour DoW: days of week HR: 24 hour DoW x HR: 168hr

Fare and duration in Static zone Fare error : 0.87$~2.53$ Duration error: 2min ~4min

Hit rate in static zone Hit rate: % of test trips having a non-empty entry in prediction table Hit rate in static zone is 17%~58%

Fare and duration in dynamic Fare error : 1.05$~1.25$ Duration error: <3min K=25 is the optimal choice

PEAK predictor w/ various K Save the fare 15 cents at most Save the time 15 sec at mosy

Radius of dynamic zone Mean: 375m Std.dev. :741m

Speed and memory Static is efficient than dynamic Dynamic costs lots of memory space static zones dynamic zones

Accuracy analysis Still not very accurate using three basic features Why? Indirect routing Traffic conditions

Accuracy analysis PEAK predictor with 200m zones Same start time, start point ,end point Distance error 6km max Duration error 1000 sec max

Filter design Filter 1: Filter 2: Trip distance > 2 straight distance of Start and End Filter 2: Average speed <20 km/h or >100km/h

Apply filter result Save fare 25 cents Save time 30 sec

Traffic conditions Rainfall is severe Save fare 10 cents Save time 60 sec

Future work Different zone size for various location Zone size determined by radius of dynamic

Conclusion reducing the data size through aggregation and smart filtering is essential. real world data needs to be cleaned before use deploying a research prototype into a real production environment requires far more work than we naively expected

contribution Detailed description of the steps to build such real time taxi system Method of identifying real-time patterns, applicable for other transportation network Principled approach to balance the tradeoffs between accuracy, real time performance KNN method to produce accurate predictor Insight into challenge from prototype to operational environment