Clustering on Highways Study Clustering of Traffic on

  • Slides: 21
Download presentation
Clustering on Highways: Study “Clustering” of Traffic on Highways By Dr. Mohammad Almalag Dr.

Clustering on Highways: Study “Clustering” of Traffic on Highways By Dr. Mohammad Almalag Dr. Samy El-Tawab Department of Informatics Indiana University Kokomo, IN Department of Integrated Science & Technology James Madison University Harrisonburg, VA ODU-NSF-Drive. Sense 2014 Oct 2014

Outline q q q Introduction Motivation and background Objectives and goals Research Directions Concluding

Outline q q q Introduction Motivation and background Objectives and goals Research Directions Concluding Remarks ODU-NSF-Drive. Sense 2014 Oct 2014 2

Where to start! • • FRIEND and Cluster-Based MAC Protocol Highways vs. Cities Harrisonburg

Where to start! • • FRIEND and Cluster-Based MAC Protocol Highways vs. Cities Harrisonburg I 81 Carmel to Kokomo, US 31 Picture Source: http: //www. thefloridastandard. com/ ODU-NSF-Drive. Sense 2014 Oct 2014 3

ODU-NSF-Drive. Sense 2014 Oct 2014 4

ODU-NSF-Drive. Sense 2014 Oct 2014 4

Introduction • Clustering: – Many people built their research on the idea that vehicles

Introduction • Clustering: – Many people built their research on the idea that vehicles drive in clusters on highway. – The focus in the research was more toward the cluster head or center, size of the cluster, use of cluster…etc – To study clustering we need to return back to traffic patterns. http: //media. nowpublic. net ODU-NSF-Drive. Sense 2014 Oct 2014 5

ODU-NSF-Drive. Sense 2014 Oct 2014 6

ODU-NSF-Drive. Sense 2014 Oct 2014 6

Motivation • There are several Pattern Flow(s) on Highways • In a congested highways:

Motivation • There are several Pattern Flow(s) on Highways • In a congested highways: clusters are very stable and can stay together for long period of time. • In a normal traffic on a highway: patterns can vary • In a very sparse traffic on a highway: very few patterns exists ODU-NSF-Drive. Sense 2014 Oct 2014 7

Patterns on Highways - Congested Highways • It is clear that many vehicles will

Patterns on Highways - Congested Highways • It is clear that many vehicles will stay together for a long period of time. ** http: //media. nowpublic. net 8

Patterns on Highways - Normal Traffic • A vehicle X can speed up and

Patterns on Highways - Normal Traffic • A vehicle X can speed up and pass another vehicle Y • For some vehicle(s) Y can re-accelerate after a certain time and pass X again • This is the pattern we wish to identify **http: //media. nowpublic. net 9

Anyone studied Clustering on highways before? – in brief – not all • 2013

Anyone studied Clustering on highways before? – in brief – not all • 2013 [Selvan and Mary]: A cluster-based Highway Vehicle Communication in VANET. • 2012 [Lakshmi Devi and Maria]: A Cluster Based Authentic Vehicular Environment for Simple Highway Communication • 2011 [ Li and Chen]: Highway Road Accident Analysis Based on Clustering Ensemble • 2005 [Weijermars and Berkum]: Analyzing highway flow patterns using cluster analysis ODU-NSF-Drive. Sense 2014 Oct 2014 10

Anyone studied Clustering on highways before? – 2013 [Selvan and Mary] • 2013 [Selvan

Anyone studied Clustering on highways before? – 2013 [Selvan and Mary] • 2013 [Selvan and Mary]: A cluster-based Highway Vehicle Communication in VANET. • Focus: – Cluster formation – Cluster head ODU-NSF-Drive. Sense 2014 Oct 2014 11

Any studied Clustering on highways before? – 2012 [Lakshmi Devi and Maria] • 2012

Any studied Clustering on highways before? – 2012 [Lakshmi Devi and Maria] • 2012 [Lakshmi Devi and Maria]: A Cluster Based Authentic Vehicular Environment for Simple Highway Communication: • Focus: performance with /without Clusters! ODU-NSF-Drive. Sense 2014 Oct 2014 12

Anyone studied Clustering on highways before? – 2011 [ Li and Chen] • 2011

Anyone studied Clustering on highways before? – 2011 [ Li and Chen] • 2011 [ Li and Chen]: Highway Road Accident Analysis Based on Clustering Ensemble • Focus: – Using of clusters to avoid accidents ODU-NSF-Drive. Sense 2014 Oct 2014 13

Anyone studied Clustering on highways before? – 2005 [Weijermars and Berkum] • 2005 [Weijermars

Anyone studied Clustering on highways before? – 2005 [Weijermars and Berkum] • 2005 [Weijermars and Berkum]: Analyzing highway flow patterns using cluster analysis • Cluster formation on a base of 15 mins traffic flow ODU-NSF-Drive. Sense 2014 Oct 2014 14

Problem definition We noticed that on a highway vehicles can join a group of

Problem definition We noticed that on a highway vehicles can join a group of vehicles forming what called Clusters and disconnect then reconnect and so on. . we call this for now: Regrouping or Family Reunion What is the challenge!? • If I know that we will meet again and again on the highway: I don’t need to keep you in the cluster for a long time! You are coming back!! Regrouping or Family Reunion!! • What Benefits: many jobs (tasks) can be done in a discrete fashion: – You can share some media files ODU-NSF-Drive. Sense 2014 Oct 2014 15

ODU-NSF-Drive. Sense 2014 Oct 2014 16

ODU-NSF-Drive. Sense 2014 Oct 2014 16

Our Idea If a vehicle driving on a highway such as NY/NJ Turnpike and

Our Idea If a vehicle driving on a highway such as NY/NJ Turnpike and stayed in touch ( in range of communication) with another vehicle for a certain time Tv-v: the chances that they have a Family Reunion ( they will meet again and again) is very high! ODU-NSF-Drive. Sense 2014 Oct 2014 17

Simulation? • Aorta Traffic Simulator • Map: I-95 (part of highway) • Map generated

Simulation? • Aorta Traffic Simulator • Map: I-95 (part of highway) • Map generated by: http: //www. openstreetmap. org/ • Analyze the location of vehicles with randomly acceleration/deacceleration ODU-NSF-Drive. Sense 2014 Oct 2014 18

Research Challenge in it? • How will you calculate the % of success Regrouping

Research Challenge in it? • How will you calculate the % of success Regrouping / Family Reunion: – Location at several times – Map it to a node map – Identify the re-union cases ODU-NSF-Drive. Sense 2014 Oct 2014 19

Concluding remarks • We are trying to make use of intelligent transportation in a

Concluding remarks • We are trying to make use of intelligent transportation in a way that allow us to assign tasks (jobs) to several cars on highway. • Our claim that vehicles that tend to stay together in groups will re-union again every couple of mins on a long highway. ODU-NSF-Drive. Sense 2014 Oct 2014 20

Thank You - Questions

Thank You - Questions

Traffic Engineering Traffic Control Devices Traffic Control TrafficTraffic Engineering Traffic Control Devices Traffic Control Traffic
Highways Interface National Highways Interface Team Network RailHighways Interface National Highways Interface Team Network Rail
Highways Contracts Serving the people of Cumbria HighwaysHighways Contracts Serving the people of Cumbria Highways
Highways Transportation 1 November 2018 Head of HighwaysHighways Transportation 1 November 2018 Head of Highways
CURRENTS HIGHWAYS OF THE SEA Highways of theCURRENTS HIGHWAYS OF THE SEA Highways of the
TRAFFIC POLICE DIRECTORATE Traffic Security Section TRAFFIC METODOLOGYTRAFFIC POLICE DIRECTORATE Traffic Security Section TRAFFIC METODOLOGY
TS 4273 Traffic Engineering Traffic Stream Characteristics TrafficTS 4273 Traffic Engineering Traffic Stream Characteristics Traffic
Safety on Traffic Stops Traffic Contacts A trafficSafety on Traffic Stops Traffic Contacts A traffic
AIR TRAFFIC ONTROL Air Traffic Control Air trafficAIR TRAFFIC ONTROL Air Traffic Control Air traffic
AIR TRAFFIC CONTROL Air Traffic Control Air trafficAIR TRAFFIC CONTROL Air Traffic Control Air traffic
Traffic Assignment Definition of Traffic Assignment Traffic AssignmentTraffic Assignment Definition of Traffic Assignment Traffic Assignment
Lecture 12 Clustering What is Clustering Clustering isLecture 12 Clustering What is Clustering Clustering is
ENSEMBLE CLUSTERING ENSEMBLE CLUSTERING clustering algorithm 1 partitionENSEMBLE CLUSTERING ENSEMBLE CLUSTERING clustering algorithm 1 partition
FLAT CLUSTERING HIERARCHICAL CLUSTERING What is clustering GroupingFLAT CLUSTERING HIERARCHICAL CLUSTERING What is clustering Grouping
DATA MINING CLUSTERING Clustering 4 Clustering unsupervised classificationDATA MINING CLUSTERING Clustering 4 Clustering unsupervised classification
Clustering Kmeans Clustering 2 means Clustering Curve ShowsClustering Kmeans Clustering 2 means Clustering Curve Shows
Kmeans Clustering Kmeans Clustering What is clustering WhyKmeans Clustering Kmeans Clustering What is clustering Why
C 0 clustering Liang Zheng Clustering Clustering alongC 0 clustering Liang Zheng Clustering Clustering along
Variable Clustering 1 Variable Clustering Variable clustering findsVariable Clustering 1 Variable Clustering Variable clustering finds
CLUSTERING Overview Definition of Clustering Existing clustering methodsCLUSTERING Overview Definition of Clustering Existing clustering methods