Machine Learning and Optimization For Traffic and Emergency Resource Management. Milos Hauskrecht Department of Computer Science University of Pittsburgh.

Slides:



Advertisements
Similar presentations
Bayesian Belief Propagation
Advertisements

CS188: Computational Models of Human Behavior
Scaling Up Graphical Model Inference
Autonomic Scaling of Cloud Computing Resources
COS 461 Fall 1997 Routing COS 461 Fall 1997 Typical Structure.
Dynamic Bayesian Networks (DBNs)
Yu Stephanie Sun 1, Lei Xie 1, Qi Alfred Chen 2, Sanglu Lu 1, Daoxu Chen 1 1 State Key Laboratory for Novel Software Technology, Nanjing University, China.
Hidden Markov Models Reading: Russell and Norvig, Chapter 15, Sections
Introduction to Belief Propagation and its Generalizations. Max Welling Donald Bren School of Information and Computer and Science University of California.
Introduction of Probabilistic Reasoning and Bayesian Networks
Introduction to Sampling based inference and MCMC Ata Kaban School of Computer Science The University of Birmingham.
Planning under Uncertainty
Bayesian Networks Chapter 2 (Duda et al.) – Section 2.11
1 © 1998 HRL Laboratories, LLC. All Rights Reserved Construction of Bayesian Networks for Diagnostics K. Wojtek Przytula: HRL Laboratories & Don Thompson:
1 Simulation Modeling and Analysis Session 13 Simulation Optimization.
Regulatory Network (Part II) 11/05/07. Methods Linear –PCA (Raychaudhuri et al. 2000) –NIR (Gardner et al. 2003) Nonlinear –Bayesian network (Friedman.
Mobility Improves Coverage of Sensor Networks Benyuan Liu*, Peter Brass, Olivier Dousse, Philippe Nain, Don Towsley * Department of Computer Science University.
Math443/543 Mathematical Modeling and Optimization
Towards a Learning Incident Detection System ICML 06 Workshop on Machine Learning for Surveillance and Event Detection June 29, 2006 Tomas Singliar Joint.
Ants-based Routing Marc Heissenbüttel University of Berne
5/25/2005EE562 EE562 ARTIFICIAL INTELLIGENCE FOR ENGINEERS Lecture 16, 6/1/2005 University of Washington, Department of Electrical Engineering Spring 2005.
1 MACHINE LEARNING TECHNIQUES IN IMAGE PROCESSING By Kaan Tariman M.S. in Computer Science CSCI 8810 Course Project.
Probabilistic Analysis of a Large-Scale Urban Traffic Sensor Data Set Jon Hutchins, Alexander Ihler, and Padhraic Smyth Department of Computer Science.
Collaborative Reinforcement Learning Presented by Dr. Ying Lu.
Adaptive Traffic Light Control with Wireless Sensor Networks Presented by Khaled Mohammed Ali Hassan.
Radial Basis Function Networks
ADITI BHAUMICK ab3585. To use reinforcement learning algorithm with function approximation. Feature-based state representations using a broad characterization.
Optimal Placement and Selection of Camera Network Nodes for Target Localization A. O. Ercan, D. B. Yang, A. El Gamal and L. J. Guibas Stanford University.
Applied Transportation Analysis ITS Application SCATS.
Extracting Places and Activities from GPS Traces Using Hierarchical Conditional Random Fields Yong-Joong Kim Dept. of Computer Science Yonsei.
Chapter 8 Prediction Algorithms for Smart Environments
A model for combination of set covering and network connectivity in facility location Rana Afzali and Shaghayegh Parhizi.
Anomaly detection with Bayesian networks Website: John Sandiford.
Machine Learning1 Machine Learning: Summary Greg Grudic CSCI-4830.
Stochastic Algorithms Some of the fastest known algorithms for certain tasks rely on chance Stochastic/Randomized Algorithms Two common variations – Monte.
Stochastic Routing Routing Area Meeting IETF 82 (Taipei) Nov.15, 2011.
Bayesian networks Classification, segmentation, time series prediction and more. Website: Twitter:
Prediction of Traffic Density for Congestion Analysis under Indian Traffic Conditions Proceedings of the 12th International IEEE Conference on Intelligent.
Various topics Petter Mostad Overview Epidemiology Study types / data types Econometrics Time series data More about sampling –Estimation.
Copyright © 2012, SAS Institute Inc. All rights reserved. ANALYTICS IN BIG DATA ERA ANALYTICS TECHNOLOGY AND ARCHITECTURE TO MANAGE VELOCITY AND VARIETY,
Research Interest overview and future directions Mina Guirguis Computer Science Department Texas State University – San Marcos CS5300 9/16/2011.
Ch 8. Graphical Models Pattern Recognition and Machine Learning, C. M. Bishop, Revised by M.-O. Heo Summarized by J.W. Nam Biointelligence Laboratory,
A Passive Approach to Sensor Network Localization Rahul Biswas and Sebastian Thrun International Conference on Intelligent Robots and Systems 2004 Presented.
1 CONTEXT DEPENDENT CLASSIFICATION  Remember: Bayes rule  Here: The class to which a feature vector belongs depends on:  Its own value  The values.
Analyzing wireless sensor network data under suppression and failure in transmission Alan E. Gelfand Institute of Statistics and Decision Sciences Duke.
Distributed Models for Decision Support Jose Cuena & Sascha Ossowski Pesented by: Gal Moshitch & Rica Gonen.
Lecture 2: Statistical learning primer for biologists
CSE4334/5334 DATA MINING CSE4334/5334 Data Mining, Fall 2014 Department of Computer Science and Engineering, University of Texas at Arlington Chengkai.
Unsupervised Mining of Statistical Temporal Structures in Video Liu ze yuan May 15,2011.
Expectation-Maximization (EM) Algorithm & Monte Carlo Sampling for Inference and Approximation.
Monte-Carlo based Expertise A powerful Tool for System Evaluation & Optimization  Introduction  Features  System Performance.
Artificial Intelligence: Research and Collaborative Possibilities a presentation by: Dr. Ernest L. McDuffie, Assistant Professor Department of Computer.
Smart Sleeping Policies for Wireless Sensor Networks Venu Veeravalli ECE Department & Coordinated Science Lab University of Illinois at Urbana-Champaign.
DEPARTMENT/SEMESTER ME VII Sem COURSE NAME Operation Research Manav Rachna College of Engg.
Global Illumination (3) Path Tracing. Overview Light Transport Notation Path Tracing Photon Mapping.
Bayesian Networks Chapter 2 (Duda et al.) – Section 2.11 CS479/679 Pattern Recognition Dr. George Bebis.
CSE543T: Algorithms for Nonlinear Optimization Yixin Chen, PhD Professor Department of Computer Science & Engineering Washington University in St Louis.
Analytics and OR DP- summary.
Machine Learning Basics
CSCI1600: Embedded and Real Time Software
Harm van Seijen Bram Bakker Leon Kester TNO / UvA UvA
L12. Network optimization
Stochastic Optimization Maximization for Latent Variable Models
CONTEXT DEPENDENT CLASSIFICATION
CS 188: Artificial Intelligence
MACHINE LEARNING TECHNIQUES IN IMAGE PROCESSING
MACHINE LEARNING TECHNIQUES IN IMAGE PROCESSING
Network Architecture By Dr. Shadi Masadeh 1.
CSCI1600: Embedded and Real Time Software
What is Artificial Intelligence?
Presentation transcript:

Machine Learning and Optimization For Traffic and Emergency Resource Management. Milos Hauskrecht Department of Computer Science University of Pittsburgh Students: Branislav Kveton, Tomas Singliar UPitt collaborators: Louise Comfort, JS Lin External: Eli Upfal (Brown), Carlos Guestrin (CMU)

S-CITI related projects Modeling multivariate distributions of traffic variables Optimization of (emergency) resources over unreliable transportation network Traffic monitoring and traffic incident detection Optimization of distributed systems with discrete and continuous variables: Traffic light control

S-CITI related projects Modeling multivariate distributions of traffic variables Optimization of (emergency) resources over unreliable transportation network Traffic monitoring and traffic incident detection Optimization of control of distributed systems with discrete and continuous variables: Traffic light control

Traffic network PITTSBURGH Traffic network systems are  stochastic (things happen at random)  distributed (at many places concurrently) Modeling and computational challenges  Very complex structure  Involved interactions  High dimensionality

Challenges Modeling the behavior of a large stochastic system  Represent relations between traffic variables Inference (Answer queries about model)  Estimate congestion in unobserved area using limited information  Useful for a variety of optimization tasks Learning (Discovering the model automatically)  Interaction patterns not known  Expert knowledge difficult to elicit  Use Data Our solutions: probabilistic graphical models, statistical Machine learning methods

Road traffic data We use PennDOT sensor network 155 sensors for volume and speed every 5 minutes

Models of traffic data Local interactions Markov random field Effects are circular Solution: Break the cycles

The all-independent assumption Unrealistic!

Mixture of trees A tree structure retains many dependencies but still loses some Have many trees to represent interactions

Latent variable model A combination of latent factors represent interactions

Four projects Modeling multivariate distributions of traffic variables Optimization of (emergency) resources over unreliable transportation network Traffic monitoring and traffic incident detection Optimization of distributed systems with discrete and continuous variables: Traffic light control

Optimizations in unreliable transportation networks Unreliable network – connections (or nodes) may fail  E.g. traffic congestion, power line failure

Optimizations in unreliable transportation networks Unreliable network – connections (nodes) may fail  more than one connection may go down to

Optimizations in unreliable transportation networks Unreliable network – connections (nodes) may fail  many connections may go down together

Optimizations in unreliable transportation networks Unreliable network – connections (nodes) may fail  parts of the network may become disconnected

Optimizations of resources in unreliable transportation networks Example: emergency system. Emergency vehicles use the network system to get from one location to the other

Optimizations of resources in unreliable transportation networks One failure here won’t prevent us from reaching the target, though the path taken can be longer

Optimizations of resources in unreliable transportation networks Two failures can get the two nodes disconnected

Optimizations of resources in unreliable transportation networks Emergencies can occur at different locations and they can come with different priorities

Optimizations of resources in unreliable transportation networks … considering all possible emergencies, it may be better to change the initial location of the vehicle to get a better coverage

Optimizations of resources in unreliable transportation networks … If emergencies are concurrent and/or some connections are very unreliable it may be better to use two vehicles …

Optimizations of resources in unreliable transportation networks where to place the vehicles and how many of them to achieve the coverage with the best expected cost-benefit tradeoff ? ? ? ? ? ? ? ? ? ?

Solving the problem A two stage stochastic program with recourse Problem stages: 1.Find optimal allocations of resources (em. vehicles) 2.Match (repeatedly) emergency demands with allocated vehicles after failures occur Curse of dimensionality: many possible failure configurations in the second stage Our solution: Stochastic (MC) approximations (UAI-2001, UAI-2003) Current: adapt to continuous random quantities (congestion rates,traffic flows and their relations)

Four projects Modeling multivariate distributions of traffic variables Optimization of (emergency) resources over unreliable transportation network Traffic monitoring and traffic incident detection Optimization of distributed systems with discrete and continuous variables: Traffic light control

Incident detection on dynamic data incident no incident

Incident detection algorithms Incidents detected indirectly through caused congestion State of the art: California 2 algorithm  If OCC(up) – OCC(down) > T1, next step  If [OCC(up) – OCC(down)]/ OCC(up) > T2, next step  If [OCC(up) – OCC(down)]/ OCC(down) > T3, possible accident  If previous condition persists for another time step, sound alarm Hand-calibrated for the specific section of the road Occupancy spikesOccupancy falls

Incident detection algorithms Machine Learning approach (ICML 2006) Use a set of simple feature detectors and learn the classifier from the data Improved performance California 2 SVM based model

Four projects Modeling multivariate distributions of traffic variables Optimization of (emergency) resources over unreliable transportation network Traffic monitoring and traffic incident detection Optimization of control of distributed systems with discrete and continuous variables: Traffic light control

Dynamic traffic management A set of intersections A set of connection (roads) in between intersections Traffic lights regulating the traffic flow on roads Traffic lights are controlled independently Objective: coordinate traffic lights to minimize congestions and maximize the throughput

Solutions Problems:  how to model the dynamic behavior of the system  how to optimize the plans Our solutions (NIPS 03,ICAPS 04, UAI 04, IJCAI 05, ICAPS 06, AAAI 06)  Model: Factored hybrid Markov decision processes continuous and discrete variables  Optimization: Hybrid Approximate Linear Programming optimizations over 30 dimensional continuous state spaces and 25 dimensional action spaces Goals: hundreds of state and action variables

Thank you Questions