analytics for intelligent surveillance - infolab · 2016-05-21 · 2 farnoush banaei-kashani, ph.d....
TRANSCRIPT
![Page 1: Analytics for Intelligent Surveillance - InfoLab · 2016-05-21 · 2 Farnoush Banaei-Kashani, Ph.D. Research Associate, Computer Science Department Associate Director, IMSC Viterbi](https://reader033.vdocuments.us/reader033/viewer/2022043016/5f38b6e1a2a9727f61718b2a/html5/thumbnails/1.jpg)
1
![Page 2: Analytics for Intelligent Surveillance - InfoLab · 2016-05-21 · 2 Farnoush Banaei-Kashani, Ph.D. Research Associate, Computer Science Department Associate Director, IMSC Viterbi](https://reader033.vdocuments.us/reader033/viewer/2022043016/5f38b6e1a2a9727f61718b2a/html5/thumbnails/2.jpg)
2
Farnoush Banaei-Kashani, Ph.D.Research Associate, Computer Science Department
Associate Director, IMSCViterbi School of Engineering
University of Southern CaliforniaLos Angeles, CA 90089-0781
iWatch: BIG Data Management and Analytics for Intelligent Surveillance
![Page 3: Analytics for Intelligent Surveillance - InfoLab · 2016-05-21 · 2 Farnoush Banaei-Kashani, Ph.D. Research Associate, Computer Science Department Associate Director, IMSC Viterbi](https://reader033.vdocuments.us/reader033/viewer/2022043016/5f38b6e1a2a9727f61718b2a/html5/thumbnails/3.jpg)
3
Outline
• An Overview of the iWatch Project
• Vertical Cuts: Application-Specific Prototypes– iWatch for Safety and Security (i4S)– iWatch for Health (i4H)– iWatch for Energy (i4E)
![Page 4: Analytics for Intelligent Surveillance - InfoLab · 2016-05-21 · 2 Farnoush Banaei-Kashani, Ph.D. Research Associate, Computer Science Department Associate Director, IMSC Viterbi](https://reader033.vdocuments.us/reader033/viewer/2022043016/5f38b6e1a2a9727f61718b2a/html5/thumbnails/4.jpg)
4
Project Objectives
• A Multi-purpose System for Intelligent Geoimmersive Surveillance
• An End-to-End System!• A Research Showcase• A Technology Showcase
![Page 5: Analytics for Intelligent Surveillance - InfoLab · 2016-05-21 · 2 Farnoush Banaei-Kashani, Ph.D. Research Associate, Computer Science Department Associate Director, IMSC Viterbi](https://reader033.vdocuments.us/reader033/viewer/2022043016/5f38b6e1a2a9727f61718b2a/html5/thumbnails/5.jpg)
5
GeoImmersive Surveillance
• Sense Multi-modal sensing Deep sensing Active sensing
• Detect Events Forensic analysis Real-time monitoring Prediction of potential
expected (and unexpected!) events
• Act Visualization Recommendation Actuation
![Page 6: Analytics for Intelligent Surveillance - InfoLab · 2016-05-21 · 2 Farnoush Banaei-Kashani, Ph.D. Research Associate, Computer Science Department Associate Director, IMSC Viterbi](https://reader033.vdocuments.us/reader033/viewer/2022043016/5f38b6e1a2a9727f61718b2a/html5/thumbnails/6.jpg)
6
iWatch System Architecture
Data Acquisition
Incident Detection
Real-time Event Detection and
Prediction from Incident Stream
Incident Archive
Each Incident is an object with
spatial, temporal, and textual attributes
Incident StreamEfficient Incident
Retrieval
Active Sensing
SenseEvent DetectionEv
ent D
etec
tion
Act
![Page 7: Analytics for Intelligent Surveillance - InfoLab · 2016-05-21 · 2 Farnoush Banaei-Kashani, Ph.D. Research Associate, Computer Science Department Associate Director, IMSC Viterbi](https://reader033.vdocuments.us/reader033/viewer/2022043016/5f38b6e1a2a9727f61718b2a/html5/thumbnails/7.jpg)
7
Research Showcase
Data Acquisition
Incident Detection
Real-time Event Detection and
Prediction from Incident Stream
Incident Archive
Each Incident is an object with
spatial, temporal, and textual attributes
Incident StreamEfficient Incident
Retrieval
Active Sensing
SenseEvent DetectionEv
ent D
etec
tion
Act 1. Active Sensing
2. Inferred Archival3. Dynamic Integration
4. Scale-up
![Page 8: Analytics for Intelligent Surveillance - InfoLab · 2016-05-21 · 2 Farnoush Banaei-Kashani, Ph.D. Research Associate, Computer Science Department Associate Director, IMSC Viterbi](https://reader033.vdocuments.us/reader033/viewer/2022043016/5f38b6e1a2a9727f61718b2a/html5/thumbnails/8.jpg)
8
Technology Showcase
Data Acquisition
Incident Detection
Real-time Event Detection and
Prediction from Incident Stream
Incident Archive
Each Incident is an object with
spatial, temporal, and textual attributes
Incident StreamEfficient Incident
Retrieval
Active Sensing
SenseEvent DetectionEv
ent D
etec
tion
Act
• VideoIQ (through DPS): Smart PTZ Cameras• Qualcomm/HTC: Evo 3D Smartphones• USC: KNOWME Network (BAN)• OSIsoft (through Chevron): SCADA/PI• Verizon (through AIL)?• Intel?
• Microsoft: StreamInsight CEP Engine• IBM: IBM InfoSphere Streams• Oracle: DBMS 11g• Lockheed Martin/Rocket Software: AeorText (?)• NEC?• HP?
• Qualcomm/HTC: Evo 3D Smartphones• Verizon (through AIL)? • Samsung?• ESRI?
![Page 9: Analytics for Intelligent Surveillance - InfoLab · 2016-05-21 · 2 Farnoush Banaei-Kashani, Ph.D. Research Associate, Computer Science Department Associate Director, IMSC Viterbi](https://reader033.vdocuments.us/reader033/viewer/2022043016/5f38b6e1a2a9727f61718b2a/html5/thumbnails/9.jpg)
9
Project TimelineJanuary 2011
Applications Sponsors Technologies Funding Team
Safety and Security IMSC Oracle 11g ~20K IMSC Researchers (4)IMSC Students (2)
![Page 10: Analytics for Intelligent Surveillance - InfoLab · 2016-05-21 · 2 Farnoush Banaei-Kashani, Ph.D. Research Associate, Computer Science Department Associate Director, IMSC Viterbi](https://reader033.vdocuments.us/reader033/viewer/2022043016/5f38b6e1a2a9727f61718b2a/html5/thumbnails/10.jpg)
10
Project Timeline (cont’d)
Applications Sponsors Technologies Funding Team
Safety and Security Public Health Energy
IMSCNIJNGCCREATE (DHS)USC (DPS)CIA?NGA?CTSI?NIH?LA County?Oracle?CiSoft (Chevron)
Oracle 11gIBMMicrosoftQualcomm
1.2M+ USC Public SafetyUSC Doctors (3)CHLA Doctors (1)Reservoir EngineersSponsors’ PMsIMSC Researchers (4)IMSC Postdocs (4)IMSC Students (15)Industry PartnersUSC AMI
January 2012
![Page 11: Analytics for Intelligent Surveillance - InfoLab · 2016-05-21 · 2 Farnoush Banaei-Kashani, Ph.D. Research Associate, Computer Science Department Associate Director, IMSC Viterbi](https://reader033.vdocuments.us/reader033/viewer/2022043016/5f38b6e1a2a9727f61718b2a/html5/thumbnails/11.jpg)
11
Outline
• An Overview of the iWatch Project
• Vertical Cuts: Application-Specific Prototypes– iWatch for Safety and Security (i4S)– iWatch for Health (i4H)– iWatch for Energy (i4E)
![Page 12: Analytics for Intelligent Surveillance - InfoLab · 2016-05-21 · 2 Farnoush Banaei-Kashani, Ph.D. Research Associate, Computer Science Department Associate Director, IMSC Viterbi](https://reader033.vdocuments.us/reader033/viewer/2022043016/5f38b6e1a2a9727f61718b2a/html5/thumbnails/12.jpg)
12
iWatch for Safety and Security (i4S)• Purpose: Forensic and Real-time Criminal Activity Detection from
Multi-Source Multi-Modal Data• Sponsors: NIJ, NGC, CREATE, DPS
• Team:– Law Enforcement and Security/Intelligence Experts: Mark
Greene (NIJ), Ed Tse (NGC), Carol Hayes (DPS)– Risk Analysis: Isaac Maya (CREATE)– Incident Detection from Video: Ram Nevatia (Tracking),
Gerard Medioni (Face detection)– Geo-keyword Incident Indexing: Cyrus Shahabi– Spatiotemporal Event Detection: Farnoush Banaei-Kashani– Mobile Video Search: Seon Ho Kim
![Page 13: Analytics for Intelligent Surveillance - InfoLab · 2016-05-21 · 2 Farnoush Banaei-Kashani, Ph.D. Research Associate, Computer Science Department Associate Director, IMSC Viterbi](https://reader033.vdocuments.us/reader033/viewer/2022043016/5f38b6e1a2a9727f61718b2a/html5/thumbnails/13.jpg)
13
Approach• Motivation:
Multi-modal integration enables more effective surveillance systems for criminal activity detection
• Challenge: Data overload in detecting events in large environments over long time intervals
• Proposed Approach: Utilize state-of-the-art content analysis techniques to extract incidentsfrom input data streams, while integrating the incidents in the spatiotemporal domain (rather than content domain) to detect events
![Page 14: Analytics for Intelligent Surveillance - InfoLab · 2016-05-21 · 2 Farnoush Banaei-Kashani, Ph.D. Research Associate, Computer Science Department Associate Director, IMSC Viterbi](https://reader033.vdocuments.us/reader033/viewer/2022043016/5f38b6e1a2a9727f61718b2a/html5/thumbnails/14.jpg)
14
Approach (cont’d)
CC
Sensors
Content Analysis Modules
Incidents
Events
Spatiotemporal Cross-Referencing
• Advantage: Allows for event detection in large spatial and temporal scales
![Page 15: Analytics for Intelligent Surveillance - InfoLab · 2016-05-21 · 2 Farnoush Banaei-Kashani, Ph.D. Research Associate, Computer Science Department Associate Director, IMSC Viterbi](https://reader033.vdocuments.us/reader033/viewer/2022043016/5f38b6e1a2a9727f61718b2a/html5/thumbnails/15.jpg)
15
Last Year’s Demonstration• Mode: Forensic Analysis• Input: Video feed from 25 PTZ cameras
![Page 16: Analytics for Intelligent Surveillance - InfoLab · 2016-05-21 · 2 Farnoush Banaei-Kashani, Ph.D. Research Associate, Computer Science Department Associate Director, IMSC Viterbi](https://reader033.vdocuments.us/reader033/viewer/2022043016/5f38b6e1a2a9727f61718b2a/html5/thumbnails/16.jpg)
16
i4S Prototype: System Architecture
Data Acquisition
Incident Detection from Video, Text, Sensor
Real-time Event Detection from Incident Stream
Incident Archive
Incident StreamEfficient Incident
Retrieval
Active Sensing for Face Capture
SenseEvent DetectionEv
ent D
etec
tion
Act
72 PTZ Cameras, CrowdsourcedMobile Video
(TB/day)45 LPRs
(KB/day)
Police Reports, Tweets
(GB/day)1100 ACR(KB/day)
![Page 17: Analytics for Intelligent Surveillance - InfoLab · 2016-05-21 · 2 Farnoush Banaei-Kashani, Ph.D. Research Associate, Computer Science Department Associate Director, IMSC Viterbi](https://reader033.vdocuments.us/reader033/viewer/2022043016/5f38b6e1a2a9727f61718b2a/html5/thumbnails/17.jpg)
17
i4S Prototype: Research Showcase
Data Acquisition
Incident Detection from Video, Text, Sensor
Real-time Event Detection from Incident Stream
Incident Archive
Incident StreamEfficient Incident
Retrieval
Active Sensing for Face Capture
SenseEvent DetectionEv
ent D
etec
tion
Act
72 PTZ Cameras, CrowdsourcedMobile Video
(TB/day)45 LPRs
(KB/day)
Police Reports, Tweets
(GB/day)1100 ACR(KB/day)
Active Face Tracking (NIJ: Medioni)
Online Tracking (NIJ: Nevatia)
Dynamic Event Detection (NIJ: Banaei-Kashani)
Efficient Incident Search (NIJ & NGC: Shahabi, Kim, Banaei-Kashani)
Event Detection Supporting Data Uncertainty (NGC: Medioni, Shahabi, Banaei-Kashani)
Dynamic Risk Analysis (CREATE: Maya)
![Page 18: Analytics for Intelligent Surveillance - InfoLab · 2016-05-21 · 2 Farnoush Banaei-Kashani, Ph.D. Research Associate, Computer Science Department Associate Director, IMSC Viterbi](https://reader033.vdocuments.us/reader033/viewer/2022043016/5f38b6e1a2a9727f61718b2a/html5/thumbnails/18.jpg)
18
i4S Prototype: Technology Showcase
Data Acquisition
Incident Detection from Video, Text, Sensor
Real-time Event Detection from Incident Stream
Incident Archive
Incident Stream
Efficient Incident Retrieval
Active Sensing for Face Capture
SenseEvent DetectionEv
ent D
etec
tion
Act
72 PTZ Cameras, CrowdsourcedMobile Video
(TB/day)45 LPRs
(KB/day)
Police Reports, Tweets
(GB/day)1100 ACR(KB/day)
VideoIQ PTZ Cameras
• VideoIQ PTZ Cameras• IBM Streams (Text
Analytics Toolkit, Video Analytics Toolkit (iMARS, OpenCV 2.0)
• AeorText
IBM Streams
Oracle 11g
Qualcomm/HTC Smartphones
![Page 19: Analytics for Intelligent Surveillance - InfoLab · 2016-05-21 · 2 Farnoush Banaei-Kashani, Ph.D. Research Associate, Computer Science Department Associate Director, IMSC Viterbi](https://reader033.vdocuments.us/reader033/viewer/2022043016/5f38b6e1a2a9727f61718b2a/html5/thumbnails/19.jpg)
19
Create
Update
Monitor
Mobile ClientServer-side User Interface
Sample Demonstration
Search for “Geofence Demo” on Youtube
![Page 20: Analytics for Intelligent Surveillance - InfoLab · 2016-05-21 · 2 Farnoush Banaei-Kashani, Ph.D. Research Associate, Computer Science Department Associate Director, IMSC Viterbi](https://reader033.vdocuments.us/reader033/viewer/2022043016/5f38b6e1a2a9727f61718b2a/html5/thumbnails/20.jpg)
20
Outline
• An Overview of the iWatch Project
• Vertical Cuts: Application-Specific Prototypes– iWatch for Safety and Security (i4S)– iWatch for Health (i4H)– iWatch for Energy (i4E)
![Page 21: Analytics for Intelligent Surveillance - InfoLab · 2016-05-21 · 2 Farnoush Banaei-Kashani, Ph.D. Research Associate, Computer Science Department Associate Director, IMSC Viterbi](https://reader033.vdocuments.us/reader033/viewer/2022043016/5f38b6e1a2a9727f61718b2a/html5/thumbnails/21.jpg)
21
iWatch for Health (i4H)
• Special-Purpose Prototypes– Prototype I: Contact Investigation– Prototype II: Understanding Geography of Diabetes– Prototype III: Point-of-Care Mobility Monitoring
![Page 22: Analytics for Intelligent Surveillance - InfoLab · 2016-05-21 · 2 Farnoush Banaei-Kashani, Ph.D. Research Associate, Computer Science Department Associate Director, IMSC Viterbi](https://reader033.vdocuments.us/reader033/viewer/2022043016/5f38b6e1a2a9727f61718b2a/html5/thumbnails/22.jpg)
22
i4H-Prototype I: Contact Investigation
• Purpose: Retrospective and Real-time Contact Investigation
• Sponsor: NIH?
• Team:– Contact Investigation: Dr. Brenda Jones (TB), Dr. Pia
Pannaraj (Flu)– Tracking and Face Detection: Gerard Medioni– Spatiotemporal Contact Analysis: Farnoush Banaei-
Kashani, Cyrus Shahabi
![Page 23: Analytics for Intelligent Surveillance - InfoLab · 2016-05-21 · 2 Farnoush Banaei-Kashani, Ph.D. Research Associate, Computer Science Department Associate Director, IMSC Viterbi](https://reader033.vdocuments.us/reader033/viewer/2022043016/5f38b6e1a2a9727f61718b2a/html5/thumbnails/23.jpg)
23
Step I: Data Collection
![Page 24: Analytics for Intelligent Surveillance - InfoLab · 2016-05-21 · 2 Farnoush Banaei-Kashani, Ph.D. Research Associate, Computer Science Department Associate Director, IMSC Viterbi](https://reader033.vdocuments.us/reader033/viewer/2022043016/5f38b6e1a2a9727f61718b2a/html5/thumbnails/24.jpg)
24
Step II: Reachability Analysis
Within a time interval [a,b], find:• Whether u is reachable from v?• The individuals reachable from v?• The individuals that can reach v?
Input
Queries
A graph G which is:• Large scale (Huge number of edges and vertices)• Temporal (Edges are added and deleted over time)• Geospatial (Nodes are moving in space)
![Page 25: Analytics for Intelligent Surveillance - InfoLab · 2016-05-21 · 2 Farnoush Banaei-Kashani, Ph.D. Research Associate, Computer Science Department Associate Director, IMSC Viterbi](https://reader033.vdocuments.us/reader033/viewer/2022043016/5f38b6e1a2a9727f61718b2a/html5/thumbnails/25.jpg)
25
i4H-Prototype I: System Architecture
Data Acquisition
Incident Detection from Video
Incident Archive
Incident StreamEfficient Incident
Retrieval
Active Sensing for Face Capture
SenseEvent DetectionEv
ent D
etec
tion
Act
![Page 26: Analytics for Intelligent Surveillance - InfoLab · 2016-05-21 · 2 Farnoush Banaei-Kashani, Ph.D. Research Associate, Computer Science Department Associate Director, IMSC Viterbi](https://reader033.vdocuments.us/reader033/viewer/2022043016/5f38b6e1a2a9727f61718b2a/html5/thumbnails/26.jpg)
26
Data Acquisition
Incident Detection from Video
Incident Archive
Incident StreamEfficient Incident
Retrieval
Active Sensing for Face Capture
SenseEvent DetectionEv
ent D
etec
tion
Act
Active Face Tracking (Medioni)
Online Tracking (Medioni)
Efficient Reachability Analysis (Banaei-Kashani, Shahabi)
i4H-Prototype I: Research Showcase
![Page 27: Analytics for Intelligent Surveillance - InfoLab · 2016-05-21 · 2 Farnoush Banaei-Kashani, Ph.D. Research Associate, Computer Science Department Associate Director, IMSC Viterbi](https://reader033.vdocuments.us/reader033/viewer/2022043016/5f38b6e1a2a9727f61718b2a/html5/thumbnails/27.jpg)
27
Data Acquisition
Incident Detection from Video
Incident Archive
Incident StreamEfficient Incident
Retrieval
Active Sensing for Face Capture
SenseEvent DetectionEv
ent D
etec
tion
Act
PTZ Cameras
Oracle 11g
i4H-Prototype I: Technology Showcase
![Page 28: Analytics for Intelligent Surveillance - InfoLab · 2016-05-21 · 2 Farnoush Banaei-Kashani, Ph.D. Research Associate, Computer Science Department Associate Director, IMSC Viterbi](https://reader033.vdocuments.us/reader033/viewer/2022043016/5f38b6e1a2a9727f61718b2a/html5/thumbnails/28.jpg)
28
• Purpose: Spatial Analysis and Mining of Diabetes Patient Data to Understand Spatial Causative pathways, Processes, and Patterns
• Sponsor: Verizon?, Oracle?
• Team:– Diabetes: Dr. Andy Lee– Use-case and Market Analysis: Nathalie Gosset (AMI)– Body Area Sensor Network: Murali Annavaram– Spatial Data Analysis and Mining: Farnoush Banaei-
Kashani, Cyrus Shahabi
i4H-Prototype II: Understanding Geography of Diabetes
![Page 29: Analytics for Intelligent Surveillance - InfoLab · 2016-05-21 · 2 Farnoush Banaei-Kashani, Ph.D. Research Associate, Computer Science Department Associate Director, IMSC Viterbi](https://reader033.vdocuments.us/reader033/viewer/2022043016/5f38b6e1a2a9727f61718b2a/html5/thumbnails/29.jpg)
29
Patie
nt A
naly
tics
(PA)
Expe
rt A
naly
tics
(EA)
AnalyticsCare-Providers Patient
Vision
![Page 30: Analytics for Intelligent Surveillance - InfoLab · 2016-05-21 · 2 Farnoush Banaei-Kashani, Ph.D. Research Associate, Computer Science Department Associate Director, IMSC Viterbi](https://reader033.vdocuments.us/reader033/viewer/2022043016/5f38b6e1a2a9727f61718b2a/html5/thumbnails/30.jpg)
30
• Categories:– Patient Analytics vs. Expert Analytics– Trajectory Analytics vs. Spatial Analytics– Individual Analytics vs. Collective Analytics
• Exemplary Analytics:– Spatial outlier detection to distinguish “good signatures”– Spatial co-location rules to identify causative processes
Analytics
![Page 31: Analytics for Intelligent Surveillance - InfoLab · 2016-05-21 · 2 Farnoush Banaei-Kashani, Ph.D. Research Associate, Computer Science Department Associate Director, IMSC Viterbi](https://reader033.vdocuments.us/reader033/viewer/2022043016/5f38b6e1a2a9727f61718b2a/html5/thumbnails/31.jpg)
31
i4H-Prototype II: System Architecture
Data Acquisition
Incident Detection from BAN Data
Incident Archive
Incident StreamEfficient Incident
Retrieval
Active Sensing for Energy Efficient Data Collection
SenseEvent DetectionEv
ent D
etec
tion
Act
Real-time Event Detection from Incident Stream
![Page 32: Analytics for Intelligent Surveillance - InfoLab · 2016-05-21 · 2 Farnoush Banaei-Kashani, Ph.D. Research Associate, Computer Science Department Associate Director, IMSC Viterbi](https://reader033.vdocuments.us/reader033/viewer/2022043016/5f38b6e1a2a9727f61718b2a/html5/thumbnails/32.jpg)
32
i4H-Prototype II: Research Showcase
Data Acquisition
Incident Detection from BAN Data
Incident Archive
Incident StreamEfficient Incident
Retrieval
Active Sensing for Energy Efficient Data Collection
SenseEvent DetectionEv
ent D
etec
tion
Act
Real-time Event Detection from Incident Stream
Energy Efficient BAN Data Collection (Murali)
Spatial BAN Data Analytics (Banaei-Kashani, Shahabi)
![Page 33: Analytics for Intelligent Surveillance - InfoLab · 2016-05-21 · 2 Farnoush Banaei-Kashani, Ph.D. Research Associate, Computer Science Department Associate Director, IMSC Viterbi](https://reader033.vdocuments.us/reader033/viewer/2022043016/5f38b6e1a2a9727f61718b2a/html5/thumbnails/33.jpg)
33
i4H-Prototype II: Technology Showcase
Data Acquisition
Incident Detection from BAN Data
Incident Archive
Incident StreamEfficient Incident
Retrieval
Active Sensing for Energy Efficient Data Collection
SenseEvent DetectionEv
ent D
etec
tion
Act
Real-time Event Detection from Incident Stream
Oracle?
Qualcomm/HTC Smartphones
KNOWME Network
Qualcomm/HTC Smartphones
![Page 34: Analytics for Intelligent Surveillance - InfoLab · 2016-05-21 · 2 Farnoush Banaei-Kashani, Ph.D. Research Associate, Computer Science Department Associate Director, IMSC Viterbi](https://reader033.vdocuments.us/reader033/viewer/2022043016/5f38b6e1a2a9727f61718b2a/html5/thumbnails/34.jpg)
34
• Purpose: Real-time Mobility Monitoring for 1) Rehabilitation of Stroke-induced Mobility Limitations, and 2) Optimization of Pharmacologic Interventions for Parkinson’s Disease
• Sponsor: CTSI?, Oracle?
• Team:– Rehabilitation: Dr. Carolee Winstein et al.– Use-case and Market Analysis: Cesar Blanco (AMI)– Video Data Analysis: Gerard Medioni– Sensor Data Analytics: Farnoush Banaei-Kashani,
Cyrus Shahabi
i4H-Prototype III: Point-of-Care Mobility Monitoring
![Page 35: Analytics for Intelligent Surveillance - InfoLab · 2016-05-21 · 2 Farnoush Banaei-Kashani, Ph.D. Research Associate, Computer Science Department Associate Director, IMSC Viterbi](https://reader033.vdocuments.us/reader033/viewer/2022043016/5f38b6e1a2a9727f61718b2a/html5/thumbnails/35.jpg)
35
Vision
Data Acquisition Module
Data Management andAnalysis Module
RecommendationModule
PoCM-MS
Data
Recommendations
12
3Data Interpretation
Physician Recommendation
![Page 36: Analytics for Intelligent Surveillance - InfoLab · 2016-05-21 · 2 Farnoush Banaei-Kashani, Ph.D. Research Associate, Computer Science Department Associate Director, IMSC Viterbi](https://reader033.vdocuments.us/reader033/viewer/2022043016/5f38b6e1a2a9727f61718b2a/html5/thumbnails/36.jpg)
36
Outline
• An Overview of the iWatch Project
• Vertical Cuts: Application-Specific Prototypes– iWatch for Safety and Security (i4S)– iWatch for Health (i4H)– iWatch for Energy (i4E)
![Page 37: Analytics for Intelligent Surveillance - InfoLab · 2016-05-21 · 2 Farnoush Banaei-Kashani, Ph.D. Research Associate, Computer Science Department Associate Director, IMSC Viterbi](https://reader033.vdocuments.us/reader033/viewer/2022043016/5f38b6e1a2a9727f61718b2a/html5/thumbnails/37.jpg)
37
• Purpose: On-the-Fly Decision-Making based on Real-Time Stream Data to Enahnced Oil Recovery
• Sponsor: Chevron/CiSoft?
• Team:– Stream Data Analytics: Farnoush Banaei-Kashani,
Cyrus Shahabi
iWatch for Energy (i4E)
![Page 38: Analytics for Intelligent Surveillance - InfoLab · 2016-05-21 · 2 Farnoush Banaei-Kashani, Ph.D. Research Associate, Computer Science Department Associate Director, IMSC Viterbi](https://reader033.vdocuments.us/reader033/viewer/2022043016/5f38b6e1a2a9727f61718b2a/html5/thumbnails/38.jpg)
38
Vision1. With GPS data from all moving objects in the field (vehicles, field
workers, and perhaps robots that are monitoring and operating the field, etc.)• A Safety Application: Fire Announcement• Work order optimization application• A Security application: GeoFence
2. With sensor data from all wells in the field (e.g., production/injection rate detectors, bottom hole pressure and temperature readers, smoke and hazard detectors, vibration detectors) • Waterflood monitoring and optimization (WMO) application• A Safety and incident detection application: Fire Detection
3. With sensor data from the equipment in the field (RFID readers, vibration detectors, status sensors) • Inventory application• A Facility management application as well as safety application: Failure
Detection
![Page 39: Analytics for Intelligent Surveillance - InfoLab · 2016-05-21 · 2 Farnoush Banaei-Kashani, Ph.D. Research Associate, Computer Science Department Associate Director, IMSC Viterbi](https://reader033.vdocuments.us/reader033/viewer/2022043016/5f38b6e1a2a9727f61718b2a/html5/thumbnails/39.jpg)
39
Q & A