SlideShare ist ein Scribd-Unternehmen logo
1 von 35
THE TRUSTS SYSTEM
Tactical Randomizations for Urban Security in
Transit Systems and its Mobile App




                                            Submission 25
THE TRUSTS SYSTEM
Part 1: An Overview of the TRUSTS System




                                           Submission 25
Setting: Proof of Payment Transit Systems
Motivation: Fare Evasion in L.A. Metro
The Stackelberg Games Model
Modeling the Transit Patrolling Problem
The TRUSTS Approach




 Reduced Transit System Transition Graph
TRUSTS-Generated Schedules




       Optimized Patrol Strategy
TRUSTS and The METRO App
The METRO App




Schedule View       Reporting View   Summary View
The METRO App: Schedule View
The METRO App: Reporting View
The METRO App: Summary View
THE TRUSTS SYSTEM
Part 2: Interactive Simulation




                                 Submission 25
Setup




         Simulation Display Monitor




TRUSTS                                The METRO App
Start of the Shift
         • Launch the app into
          the Schedule View to
          see the TRUSTS-
          generated patrol
          schedule
Current Patrol Action: Station Check
Patrol Event Occurrence
            • No violations found!
Patrol Officer Response
            • Prepare for next patrol
             action
Current Patrol Action: Metro Check
Patrol Event Occurrence
            • Four inspected
             passengers have valid
             tickets
Patrol Officer Response
            • Use Reporting View to
             report four passed
             passenger checks in
             this shift segment
Patrol Event Occurrence
            • Fare evader caught!
Patrol Officer Response
            • Use Reporting View to
              report one violation
              issued in this shift
              segment
            • Prepare for next patrol
              action
Current Patrol Action: Station Check
Patrol Event Occurrence
            • An arrest was made!
Patrol Officer Response
            • Use Reporting View to
             report one arrest in this
             shift segment
Patrol Event Occurrence
            • The arrest caused the
             patrol officer to miss
             the next patrol action!
Patrol Event Response
           • Update the location to
            the current station
Patrol Event Response
           • Select the current
            station
Metro App Response
         • Current location is
           updated
         • A new schedule is
           generated from the
           TRUSTS-generated
           strategy
         • The officer can
           continue their shift with
           the new schedule
End of the Shift
        • The officer submits
         their shift data report
THE TRUSTS SYSTEM
Part 3: Real-World System Deployment




                                       Submission 25
Robust Deployment in the
               L.A. Metro System
• Successful in L.A. Metro System simulation and trial
    testing
•   Deter fare evasion and crime
•   Maximize transit system revenue
•   Valuable data collection for analysis by TRUSTS
    research team and L.A. Police Department
•   Efficient violation data reporting for LAPD officers
THE TRUSTS SYSTEM
      Thank you!




                   Submission 25

Weitere ähnliche Inhalte

Ähnlich wie Game-theoretic Patrol Strategies for Transit Systems (Slideshow deck)

Oral report paul lesigues (n8892946)
Oral report   paul lesigues (n8892946)Oral report   paul lesigues (n8892946)
Oral report paul lesigues (n8892946)Paul Lesigues
 
Leak-Detection-Program-Management-RP-1175-Cybernetics-Symposium.pdf
Leak-Detection-Program-Management-RP-1175-Cybernetics-Symposium.pdfLeak-Detection-Program-Management-RP-1175-Cybernetics-Symposium.pdf
Leak-Detection-Program-Management-RP-1175-Cybernetics-Symposium.pdfPrimitivoGonzlez1
 
Game-theoretic Patrol Strategies for Transit Systems: the TRUSTS System and i...
Game-theoretic Patrol Strategies for Transit Systems: the TRUSTS System and i...Game-theoretic Patrol Strategies for Transit Systems: the TRUSTS System and i...
Game-theoretic Patrol Strategies for Transit Systems: the TRUSTS System and i...Samantha Luber
 
K10888 ramratan malav (mechanical measurement & control theory,application)
K10888 ramratan malav (mechanical measurement & control theory,application)K10888 ramratan malav (mechanical measurement & control theory,application)
K10888 ramratan malav (mechanical measurement & control theory,application)9672269693
 
Praktijkrelevantie TRAIL PhD onderzoek
Praktijkrelevantie TRAIL PhD onderzoekPraktijkrelevantie TRAIL PhD onderzoek
Praktijkrelevantie TRAIL PhD onderzoekSerge Hoogendoorn
 
Automated Fault Analysis - IVPower for Transmission System Operators and Dist...
Automated Fault Analysis - IVPower for Transmission System Operators and Dist...Automated Fault Analysis - IVPower for Transmission System Operators and Dist...
Automated Fault Analysis - IVPower for Transmission System Operators and Dist...AFAS - Automated Fault Analysis NetCeler
 
Traffic volume study
Traffic volume studyTraffic volume study
Traffic volume studyStone Rayhan
 
Crowd dynamics management in IOT system
Crowd dynamics management in IOT systemCrowd dynamics management in IOT system
Crowd dynamics management in IOT systematul sahay
 
Fault diagnosis & fault tolerance in wind turbines
Fault diagnosis & fault tolerance in wind turbinesFault diagnosis & fault tolerance in wind turbines
Fault diagnosis & fault tolerance in wind turbinesNitin Goyal
 
Worldsensing: A Real World Use Case for Flux by Albert Zaragoza, CTO & Head o...
Worldsensing: A Real World Use Case for Flux by Albert Zaragoza, CTO & Head o...Worldsensing: A Real World Use Case for Flux by Albert Zaragoza, CTO & Head o...
Worldsensing: A Real World Use Case for Flux by Albert Zaragoza, CTO & Head o...InfluxData
 
Self-adaptive container monitoring with performance-aware Load-Shedding policies
Self-adaptive container monitoring with performance-aware Load-Shedding policiesSelf-adaptive container monitoring with performance-aware Load-Shedding policies
Self-adaptive container monitoring with performance-aware Load-Shedding policiesNECST Lab @ Politecnico di Milano
 
Introduction to PTV Vistro
Introduction to PTV VistroIntroduction to PTV Vistro
Introduction to PTV VistroJongsun Won, PE
 
Intellegent Transportation System with Case Study
Intellegent Transportation System with Case StudyIntellegent Transportation System with Case Study
Intellegent Transportation System with Case StudySupreethSP4
 

Ähnlich wie Game-theoretic Patrol Strategies for Transit Systems (Slideshow deck) (20)

Oral report paul lesigues (n8892946)
Oral report   paul lesigues (n8892946)Oral report   paul lesigues (n8892946)
Oral report paul lesigues (n8892946)
 
Hoist drop from monorail investigation
Hoist drop from monorail investigationHoist drop from monorail investigation
Hoist drop from monorail investigation
 
Leak-Detection-Program-Management-RP-1175-Cybernetics-Symposium.pdf
Leak-Detection-Program-Management-RP-1175-Cybernetics-Symposium.pdfLeak-Detection-Program-Management-RP-1175-Cybernetics-Symposium.pdf
Leak-Detection-Program-Management-RP-1175-Cybernetics-Symposium.pdf
 
Game-theoretic Patrol Strategies for Transit Systems: the TRUSTS System and i...
Game-theoretic Patrol Strategies for Transit Systems: the TRUSTS System and i...Game-theoretic Patrol Strategies for Transit Systems: the TRUSTS System and i...
Game-theoretic Patrol Strategies for Transit Systems: the TRUSTS System and i...
 
K10888 ramratan malav (mechanical measurement & control theory,application)
K10888 ramratan malav (mechanical measurement & control theory,application)K10888 ramratan malav (mechanical measurement & control theory,application)
K10888 ramratan malav (mechanical measurement & control theory,application)
 
PROJECT PPT.pptx
PROJECT PPT.pptxPROJECT PPT.pptx
PROJECT PPT.pptx
 
Presentation 5.pptx
Presentation 5.pptxPresentation 5.pptx
Presentation 5.pptx
 
Praktijkrelevantie TRAIL PhD onderzoek
Praktijkrelevantie TRAIL PhD onderzoekPraktijkrelevantie TRAIL PhD onderzoek
Praktijkrelevantie TRAIL PhD onderzoek
 
Automated Fault Analysis - IVPower for Transmission System Operators and Dist...
Automated Fault Analysis - IVPower for Transmission System Operators and Dist...Automated Fault Analysis - IVPower for Transmission System Operators and Dist...
Automated Fault Analysis - IVPower for Transmission System Operators and Dist...
 
Traffic volume study
Traffic volume studyTraffic volume study
Traffic volume study
 
Crowd dynamics management in IOT system
Crowd dynamics management in IOT systemCrowd dynamics management in IOT system
Crowd dynamics management in IOT system
 
Fault diagnosis & fault tolerance in wind turbines
Fault diagnosis & fault tolerance in wind turbinesFault diagnosis & fault tolerance in wind turbines
Fault diagnosis & fault tolerance in wind turbines
 
Seminar sib final
Seminar sib finalSeminar sib final
Seminar sib final
 
Worldsensing: A Real World Use Case for Flux by Albert Zaragoza, CTO & Head o...
Worldsensing: A Real World Use Case for Flux by Albert Zaragoza, CTO & Head o...Worldsensing: A Real World Use Case for Flux by Albert Zaragoza, CTO & Head o...
Worldsensing: A Real World Use Case for Flux by Albert Zaragoza, CTO & Head o...
 
Self-adaptive container monitoring with performance-aware Load-Shedding policies
Self-adaptive container monitoring with performance-aware Load-Shedding policiesSelf-adaptive container monitoring with performance-aware Load-Shedding policies
Self-adaptive container monitoring with performance-aware Load-Shedding policies
 
demandlocker_TRB_v3
demandlocker_TRB_v3demandlocker_TRB_v3
demandlocker_TRB_v3
 
FINAL PPT ALL.pptx
FINAL PPT ALL.pptxFINAL PPT ALL.pptx
FINAL PPT ALL.pptx
 
Introduction to PTV Vistro
Introduction to PTV VistroIntroduction to PTV Vistro
Introduction to PTV Vistro
 
Intellegent Transportation System with Case Study
Intellegent Transportation System with Case StudyIntellegent Transportation System with Case Study
Intellegent Transportation System with Case Study
 
Adaptive Traffic Control Systems Overview
Adaptive Traffic Control Systems OverviewAdaptive Traffic Control Systems Overview
Adaptive Traffic Control Systems Overview
 

Mehr von Samantha Luber

Media-based Querying and Searching
Media-based Querying and SearchingMedia-based Querying and Searching
Media-based Querying and SearchingSamantha Luber
 
TRUSTS Mobile App Demo Poster (AAMAS 2013)
TRUSTS Mobile App Demo Poster (AAMAS 2013)TRUSTS Mobile App Demo Poster (AAMAS 2013)
TRUSTS Mobile App Demo Poster (AAMAS 2013)Samantha Luber
 
Autonomous Robot Band Presentation
Autonomous Robot Band PresentationAutonomous Robot Band Presentation
Autonomous Robot Band PresentationSamantha Luber
 
Object-retrieving Autonomous Robotic Arm
Object-retrieving Autonomous Robotic ArmObject-retrieving Autonomous Robotic Arm
Object-retrieving Autonomous Robotic ArmSamantha Luber
 
Web-controlled Car Poster
Web-controlled Car PosterWeb-controlled Car Poster
Web-controlled Car PosterSamantha Luber
 
Autonomous Band Project Writeup
Autonomous Band Project WriteupAutonomous Band Project Writeup
Autonomous Band Project WriteupSamantha Luber
 
Electronic Dance Music Presentation
Electronic Dance Music PresentationElectronic Dance Music Presentation
Electronic Dance Music PresentationSamantha Luber
 
Digital Tuner Project Final Report
Digital Tuner Project Final ReportDigital Tuner Project Final Report
Digital Tuner Project Final ReportSamantha Luber
 
Digital Tuner Project Final Presentation
Digital Tuner Project Final PresentationDigital Tuner Project Final Presentation
Digital Tuner Project Final PresentationSamantha Luber
 
Strategic Trading in Credit Networks
Strategic Trading in Credit NetworksStrategic Trading in Credit Networks
Strategic Trading in Credit NetworksSamantha Luber
 
Phi Sigma Rho Engineering Sorority
Phi Sigma Rho Engineering SororityPhi Sigma Rho Engineering Sorority
Phi Sigma Rho Engineering SororitySamantha Luber
 
Efficient Belief Propagation in Depth Finding
Efficient Belief Propagation in Depth FindingEfficient Belief Propagation in Depth Finding
Efficient Belief Propagation in Depth FindingSamantha Luber
 
Gangs and Violence in Brazil
Gangs and Violence in BrazilGangs and Violence in Brazil
Gangs and Violence in BrazilSamantha Luber
 
MSAIL Mass Meeting Winer 2011
MSAIL Mass Meeting Winer 2011MSAIL Mass Meeting Winer 2011
MSAIL Mass Meeting Winer 2011Samantha Luber
 
Cognitive Science Artificial Intelligence
Cognitive Science Artificial IntelligenceCognitive Science Artificial Intelligence
Cognitive Science Artificial IntelligenceSamantha Luber
 
The AbioCor System: Overview
The AbioCor System: OverviewThe AbioCor System: Overview
The AbioCor System: OverviewSamantha Luber
 

Mehr von Samantha Luber (19)

Media-based Querying and Searching
Media-based Querying and SearchingMedia-based Querying and Searching
Media-based Querying and Searching
 
TRUSTS Mobile App Demo Poster (AAMAS 2013)
TRUSTS Mobile App Demo Poster (AAMAS 2013)TRUSTS Mobile App Demo Poster (AAMAS 2013)
TRUSTS Mobile App Demo Poster (AAMAS 2013)
 
Autonomous Robot Band Presentation
Autonomous Robot Band PresentationAutonomous Robot Band Presentation
Autonomous Robot Band Presentation
 
Object-retrieving Autonomous Robotic Arm
Object-retrieving Autonomous Robotic ArmObject-retrieving Autonomous Robotic Arm
Object-retrieving Autonomous Robotic Arm
 
Web-controlled Car Poster
Web-controlled Car PosterWeb-controlled Car Poster
Web-controlled Car Poster
 
Autonomous Band Project Writeup
Autonomous Band Project WriteupAutonomous Band Project Writeup
Autonomous Band Project Writeup
 
Electronic Dance Music Presentation
Electronic Dance Music PresentationElectronic Dance Music Presentation
Electronic Dance Music Presentation
 
Digital Tuner Project Final Report
Digital Tuner Project Final ReportDigital Tuner Project Final Report
Digital Tuner Project Final Report
 
Digital Tuner Project Final Presentation
Digital Tuner Project Final PresentationDigital Tuner Project Final Presentation
Digital Tuner Project Final Presentation
 
Strategic Trading in Credit Networks
Strategic Trading in Credit NetworksStrategic Trading in Credit Networks
Strategic Trading in Credit Networks
 
Phi Sigma Rho Engineering Sorority
Phi Sigma Rho Engineering SororityPhi Sigma Rho Engineering Sorority
Phi Sigma Rho Engineering Sorority
 
Efficient Belief Propagation in Depth Finding
Efficient Belief Propagation in Depth FindingEfficient Belief Propagation in Depth Finding
Efficient Belief Propagation in Depth Finding
 
Gangs and Violence in Brazil
Gangs and Violence in BrazilGangs and Violence in Brazil
Gangs and Violence in Brazil
 
MSAIL Mass Meeting Winer 2011
MSAIL Mass Meeting Winer 2011MSAIL Mass Meeting Winer 2011
MSAIL Mass Meeting Winer 2011
 
Cognitive Science Artificial Intelligence
Cognitive Science Artificial IntelligenceCognitive Science Artificial Intelligence
Cognitive Science Artificial Intelligence
 
AbioCor Heart System
AbioCor Heart SystemAbioCor Heart System
AbioCor Heart System
 
The AbioCor System: Overview
The AbioCor System: OverviewThe AbioCor System: Overview
The AbioCor System: Overview
 
Spinal Disc Implants
Spinal Disc ImplantsSpinal Disc Implants
Spinal Disc Implants
 
SCAI Presentation
SCAI PresentationSCAI Presentation
SCAI Presentation
 

Kürzlich hochgeladen

Data Cloud, More than a CDP by Matt Robison
Data Cloud, More than a CDP by Matt RobisonData Cloud, More than a CDP by Matt Robison
Data Cloud, More than a CDP by Matt RobisonAnna Loughnan Colquhoun
 
ICT role in 21st century education and its challenges
ICT role in 21st century education and its challengesICT role in 21st century education and its challenges
ICT role in 21st century education and its challengesrafiqahmad00786416
 
Apidays Singapore 2024 - Modernizing Securities Finance by Madhu Subbu
Apidays Singapore 2024 - Modernizing Securities Finance by Madhu SubbuApidays Singapore 2024 - Modernizing Securities Finance by Madhu Subbu
Apidays Singapore 2024 - Modernizing Securities Finance by Madhu Subbuapidays
 
Ransomware_Q4_2023. The report. [EN].pdf
Ransomware_Q4_2023. The report. [EN].pdfRansomware_Q4_2023. The report. [EN].pdf
Ransomware_Q4_2023. The report. [EN].pdfOverkill Security
 
TrustArc Webinar - Stay Ahead of US State Data Privacy Law Developments
TrustArc Webinar - Stay Ahead of US State Data Privacy Law DevelopmentsTrustArc Webinar - Stay Ahead of US State Data Privacy Law Developments
TrustArc Webinar - Stay Ahead of US State Data Privacy Law DevelopmentsTrustArc
 
2024: Domino Containers - The Next Step. News from the Domino Container commu...
2024: Domino Containers - The Next Step. News from the Domino Container commu...2024: Domino Containers - The Next Step. News from the Domino Container commu...
2024: Domino Containers - The Next Step. News from the Domino Container commu...Martijn de Jong
 
MS Copilot expands with MS Graph connectors
MS Copilot expands with MS Graph connectorsMS Copilot expands with MS Graph connectors
MS Copilot expands with MS Graph connectorsNanddeep Nachan
 
FWD Group - Insurer Innovation Award 2024
FWD Group - Insurer Innovation Award 2024FWD Group - Insurer Innovation Award 2024
FWD Group - Insurer Innovation Award 2024The Digital Insurer
 
presentation ICT roal in 21st century education
presentation ICT roal in 21st century educationpresentation ICT roal in 21st century education
presentation ICT roal in 21st century educationjfdjdjcjdnsjd
 
Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...
Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...
Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...Miguel Araújo
 
A Year of the Servo Reboot: Where Are We Now?
A Year of the Servo Reboot: Where Are We Now?A Year of the Servo Reboot: Where Are We Now?
A Year of the Servo Reboot: Where Are We Now?Igalia
 
MINDCTI Revenue Release Quarter One 2024
MINDCTI Revenue Release Quarter One 2024MINDCTI Revenue Release Quarter One 2024
MINDCTI Revenue Release Quarter One 2024MIND CTI
 
Real Time Object Detection Using Open CV
Real Time Object Detection Using Open CVReal Time Object Detection Using Open CV
Real Time Object Detection Using Open CVKhem
 
DBX First Quarter 2024 Investor Presentation
DBX First Quarter 2024 Investor PresentationDBX First Quarter 2024 Investor Presentation
DBX First Quarter 2024 Investor PresentationDropbox
 
Emergent Methods: Multi-lingual narrative tracking in the news - real-time ex...
Emergent Methods: Multi-lingual narrative tracking in the news - real-time ex...Emergent Methods: Multi-lingual narrative tracking in the news - real-time ex...
Emergent Methods: Multi-lingual narrative tracking in the news - real-time ex...Zilliz
 
"I see eyes in my soup": How Delivery Hero implemented the safety system for ...
"I see eyes in my soup": How Delivery Hero implemented the safety system for ..."I see eyes in my soup": How Delivery Hero implemented the safety system for ...
"I see eyes in my soup": How Delivery Hero implemented the safety system for ...Zilliz
 
AXA XL - Insurer Innovation Award Americas 2024
AXA XL - Insurer Innovation Award Americas 2024AXA XL - Insurer Innovation Award Americas 2024
AXA XL - Insurer Innovation Award Americas 2024The Digital Insurer
 
Web Form Automation for Bonterra Impact Management (fka Social Solutions Apri...
Web Form Automation for Bonterra Impact Management (fka Social Solutions Apri...Web Form Automation for Bonterra Impact Management (fka Social Solutions Apri...
Web Form Automation for Bonterra Impact Management (fka Social Solutions Apri...Jeffrey Haguewood
 
Apidays Singapore 2024 - Scalable LLM APIs for AI and Generative AI Applicati...
Apidays Singapore 2024 - Scalable LLM APIs for AI and Generative AI Applicati...Apidays Singapore 2024 - Scalable LLM APIs for AI and Generative AI Applicati...
Apidays Singapore 2024 - Scalable LLM APIs for AI and Generative AI Applicati...apidays
 
TrustArc Webinar - Unlock the Power of AI-Driven Data Discovery
TrustArc Webinar - Unlock the Power of AI-Driven Data DiscoveryTrustArc Webinar - Unlock the Power of AI-Driven Data Discovery
TrustArc Webinar - Unlock the Power of AI-Driven Data DiscoveryTrustArc
 

Kürzlich hochgeladen (20)

Data Cloud, More than a CDP by Matt Robison
Data Cloud, More than a CDP by Matt RobisonData Cloud, More than a CDP by Matt Robison
Data Cloud, More than a CDP by Matt Robison
 
ICT role in 21st century education and its challenges
ICT role in 21st century education and its challengesICT role in 21st century education and its challenges
ICT role in 21st century education and its challenges
 
Apidays Singapore 2024 - Modernizing Securities Finance by Madhu Subbu
Apidays Singapore 2024 - Modernizing Securities Finance by Madhu SubbuApidays Singapore 2024 - Modernizing Securities Finance by Madhu Subbu
Apidays Singapore 2024 - Modernizing Securities Finance by Madhu Subbu
 
Ransomware_Q4_2023. The report. [EN].pdf
Ransomware_Q4_2023. The report. [EN].pdfRansomware_Q4_2023. The report. [EN].pdf
Ransomware_Q4_2023. The report. [EN].pdf
 
TrustArc Webinar - Stay Ahead of US State Data Privacy Law Developments
TrustArc Webinar - Stay Ahead of US State Data Privacy Law DevelopmentsTrustArc Webinar - Stay Ahead of US State Data Privacy Law Developments
TrustArc Webinar - Stay Ahead of US State Data Privacy Law Developments
 
2024: Domino Containers - The Next Step. News from the Domino Container commu...
2024: Domino Containers - The Next Step. News from the Domino Container commu...2024: Domino Containers - The Next Step. News from the Domino Container commu...
2024: Domino Containers - The Next Step. News from the Domino Container commu...
 
MS Copilot expands with MS Graph connectors
MS Copilot expands with MS Graph connectorsMS Copilot expands with MS Graph connectors
MS Copilot expands with MS Graph connectors
 
FWD Group - Insurer Innovation Award 2024
FWD Group - Insurer Innovation Award 2024FWD Group - Insurer Innovation Award 2024
FWD Group - Insurer Innovation Award 2024
 
presentation ICT roal in 21st century education
presentation ICT roal in 21st century educationpresentation ICT roal in 21st century education
presentation ICT roal in 21st century education
 
Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...
Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...
Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...
 
A Year of the Servo Reboot: Where Are We Now?
A Year of the Servo Reboot: Where Are We Now?A Year of the Servo Reboot: Where Are We Now?
A Year of the Servo Reboot: Where Are We Now?
 
MINDCTI Revenue Release Quarter One 2024
MINDCTI Revenue Release Quarter One 2024MINDCTI Revenue Release Quarter One 2024
MINDCTI Revenue Release Quarter One 2024
 
Real Time Object Detection Using Open CV
Real Time Object Detection Using Open CVReal Time Object Detection Using Open CV
Real Time Object Detection Using Open CV
 
DBX First Quarter 2024 Investor Presentation
DBX First Quarter 2024 Investor PresentationDBX First Quarter 2024 Investor Presentation
DBX First Quarter 2024 Investor Presentation
 
Emergent Methods: Multi-lingual narrative tracking in the news - real-time ex...
Emergent Methods: Multi-lingual narrative tracking in the news - real-time ex...Emergent Methods: Multi-lingual narrative tracking in the news - real-time ex...
Emergent Methods: Multi-lingual narrative tracking in the news - real-time ex...
 
"I see eyes in my soup": How Delivery Hero implemented the safety system for ...
"I see eyes in my soup": How Delivery Hero implemented the safety system for ..."I see eyes in my soup": How Delivery Hero implemented the safety system for ...
"I see eyes in my soup": How Delivery Hero implemented the safety system for ...
 
AXA XL - Insurer Innovation Award Americas 2024
AXA XL - Insurer Innovation Award Americas 2024AXA XL - Insurer Innovation Award Americas 2024
AXA XL - Insurer Innovation Award Americas 2024
 
Web Form Automation for Bonterra Impact Management (fka Social Solutions Apri...
Web Form Automation for Bonterra Impact Management (fka Social Solutions Apri...Web Form Automation for Bonterra Impact Management (fka Social Solutions Apri...
Web Form Automation for Bonterra Impact Management (fka Social Solutions Apri...
 
Apidays Singapore 2024 - Scalable LLM APIs for AI and Generative AI Applicati...
Apidays Singapore 2024 - Scalable LLM APIs for AI and Generative AI Applicati...Apidays Singapore 2024 - Scalable LLM APIs for AI and Generative AI Applicati...
Apidays Singapore 2024 - Scalable LLM APIs for AI and Generative AI Applicati...
 
TrustArc Webinar - Unlock the Power of AI-Driven Data Discovery
TrustArc Webinar - Unlock the Power of AI-Driven Data DiscoveryTrustArc Webinar - Unlock the Power of AI-Driven Data Discovery
TrustArc Webinar - Unlock the Power of AI-Driven Data Discovery
 

Game-theoretic Patrol Strategies for Transit Systems (Slideshow deck)

Hinweis der Redaktion

  1. In this AAMAS(ahh-mus) 2013 demonstration video, we present the TRUSTS system, an interactive agent-based software system that generates randomized patrol strategies for transit systems.
  2. Part 1 of the demonstration provides background context for the TRUSTS system and an overview of its two main components: TRUSTS and its mobile app. This demonstration focuses on the mobile app for user interaction.
  3. First, we’ll introduce the problem our system addresses. In proof of payment transit systems, passengers are legally required to purchase a ticket before boarding a metro train or bus. However, resource limitations prevent patrol officers from actually verifying that every passenger has done so. Instead, patrol officers inspect a subset of passengers based on some patrol strategy. Violations and fines are issued to any fare evaders they catch.
  4. Successful fare evaders, on the other hand, cost the transit system their ticket fare in revenue loss, accumulating to potentially significant amounts over time. In 2007 alone, the Los Angeles Metro system, where our demonstration simulation takes place, lost an estimated $5.6 million in revenue due to fare evasion [2].In order to address this costly issue, there is a need for effective patrol strategies that are unpredictable by passengers and that maximize transit system revenue revenue. Due to the complexity of this patrolling problem, human schedulers cannot manually generate these optimized patrol strategies.
  5. Based on an approach successfully deployed in other security applications, such the police patrolling at LAX, TRUSTS uses Stackelberg games to model the L.A. metro system. In this model, the patrol officer, represented by the leader, commits to a patrol strategy and the potential fare evaders, represented by the followers, observe this patrol strategy and select a counter strategy accordingly [4].
  6. Unique from the other applications, transit systems impose both temporal and spatial constraints on the domain model (shown here in the LA Metro Gold Line timetable and route map), making the model too complicated to be efficiently solved in this form.
  7. The TRUSTS approach addresses this problem by reducing the constraints into a single transition graph, representing all possible patrol office action movements in the transit system as flows from each station node in the graph. In addition, TRUSTS introduces duplicate history station nodes into this graph to represent a state for the past action, allowing the current patrol schedule to be recovered if the patrol officer unexpectedly misses a patrol action.
  8. Finally, TRUSTS extracts the maximum patrol strategy, or optimal flow through the transition graph shown here, using the Decomposed Optimal Bayesian Stackelberg Solver (DOBSS). This solution describes the optimized patrol action from each state node in the graph [4].
  9. For robust deployment of TRUSTS in real-world transit systems, we have developed the METRO app, an innovation in transit system patrol scheduling. The METRO app is a software agent carried by each patrol officer that provides an interface for interaction between the user and TRUSTS. Shown in the this figure, The METRO app provides three principal features: a TRUSTS-generated patrol schedule for the current shift, a tracking system for reporting passenger violations, and a shift statistics summary report.The TRUSTS component runs on a server machine and uses the specified transit system parameters, including route schedules, shift start times, and number of patrol officers, to compute patrol strategies f or each patrol officer’s shift. These patrol strategies are stored in the TRUSTS database for retrieval by the METRO app. At the beginning of an officer’s shift, the METRO app queries the TRUSTS database for the user’s patrol strategy for the current shift. At the end of the shift, the officer submits the patrol and violations data captured throughout their shift. This information is stored in the same TRUSTS database, associated with its generated patrol strategy.
  10. These are the three main views of the METRO app: Schedule View, Reporting View, and Summary View.
  11. Schedule View allows the patrol officer to see their current patrol action as well as upcoming patrol actions. When the end time of the current action is reached, the current action is completed and the view is updated for the next action. As previously discussed, TRUSTS supports schedule interruption recovery. If an unexpected event causes the patrol officer to miss an action, the METRO app allows users to update their current location, triggering a reschedule for the corresponding station node in the TRUSTS-generated patrol strategy and a new schedule to be shown.
  12. Reporting View allows the officer to enter violation data for the current patrol action. This violation data is shown below in the view and included in the information sent back to TRUSTS at the end of the officer’s shift.
  13. Summary View shows a generated statistics report for the officer’s shift. This view also allows patrol officers to view and edit the violation data of past actions. Finally, at the end of their shift, patrol officers use the submit report button to submit their shift patrol data to the TRUSTS database.
  14. The interactive simulation, the focus of the demonstration, showcases the TRUSTS system running over the course of a shortened shift of a patrol officer in the L.A. Metro System. The participants experience the real-world deployment of the TRUSTS system first-hand from the perspective of the patrol officer using the METRO app.
  15. For the demonstration setup, we have a laptop functioning as the TRUSTS server that is connected to a monitor, displaying what the TRUSTS system is doing at the present state in the shift simulation. Throughout the shift simulation, the monitor prompts the user with various event occurrences and instructions on how to use the METRO app in response to these real-world scenarios.The laptop runs TRUSTS on an L.A. Metro Gold Line-based dataset, modified to support a two-minute patrol officer shift for the demonstration, to generate a patrol strategy for the simulated shift. The METRO app, deployed on the mobile phone shown here, has also been modified for the demonstration to continuously communicate the METRO app’s reporting data to the TRUSTS server for display on the monitor.
  16. To conclude our demonstration, we now briefly touch on our expectations from deploying this system in the LA Metro.
  17. The TRUSTS approach has already shown to be successful in increasing fare deterrence in LA Mero simulation and trial testing.By working with the LAPD to deploy our robust system in the real world, we expect to address their fare evasion problem with this novel application. In addition, through analysis on the METRO app-collected patrol data, we expect to gain valuable insight on the L.A. Metro System patrolling domain, such as follower behavior patterns, and be able to evaluate the effectiveness of TRUSTS system deployment in the transit system. This patrol data is also useful for transit systems that manually record violations data or perform their own analysis on this information.