Presentation is loading. Please wait.

Presentation is loading. Please wait.

Detecting sensor malfunctions in ecological sensor networks Owen Langman Center for Limnology University of Wisconsin - Madison EIM Conference Sept. 11,

Published byTyler Simon Modified over 8 years ago

Similar presentations

Presentation on theme: "Detecting sensor malfunctions in ecological sensor networks Owen Langman Center for Limnology University of Wisconsin - Madison EIM Conference Sept. 11,"— Presentation transcript:

1 Detecting sensor malfunctions in ecological sensor networks Owen Langman Center for Limnology University of Wisconsin - Madison EIM Conference Sept. 11, 2008 Albuquerque, NM

2 This is what we want to detect! What are we trying to detect? To paraphrase Jim Clark's keynote, “sometimes the data are weird” “Level 0” error “Level 1” error - No data returned - Error value - Sensor itself generates notification of error

3 *Image source: NTL LTER webpage: http://www.limnology.wisc.edu * Well, our data managers and QA/QC people do the detection now, what is wrong with their eyes scanning through data visualizations?

4 Online: model updates immediately as it receives data Generalizable: Algorithm learns its parameters from the data and it can describe a large number of sensor traces State driven: Computationally simple enough to put near the sensor (Math)‏

5 Model A: Gamma PDF, moderate sensitivity Model B: Skew-elliptical (bimodal) PDF, moderate sensitivity Model C: Gamma PDF, very low sensitivity

6

7 Earlier detection?

8 Performance - 2 years of expert classified data - Fairly diverse collection of sensors (DO, temperature profile, PAR, wind, etc)‏

9 The Near Future: Currently implementing this within the data flow in the Wisconsin buoy network

10 Questions! Thanks: Steve Carpenter Paul Hanson Dave Balsiger Luke Winslow Kenneth Chiu Yu Hen Hu Basic R script available, email: Owen Langman*** oclangman@wisc.edu ***Currently unemployed and seeking jobs / PhD positions

Download ppt "Detecting sensor malfunctions in ecological sensor networks Owen Langman Center for Limnology University of Wisconsin - Madison EIM Conference Sept. 11,"

Similar presentations

Diel Oxygen Analysis Tim Kratz, Laurence Choi, Barbara Benson, Yu Hen Hu University of Wisconsin-Madison Center for Limnology.

Diel Oxygen Analysis Tim Kratz, Laurence Choi, Barbara Benson, Yu Hen Hu University of Wisconsin-Madison Center for Limnology.
Paul Hanson, Fang-Pang Lin, Miron Livny, Chin Wu, Chris Solomon, Many colleagues of the GLEON Transforming ecological sensor networks from data collectors.

Paul Hanson, Fang-Pang Lin, Miron Livny, Chin Wu, Chris Solomon, Many colleagues of the GLEON Transforming ecological sensor networks from data collectors.
Event detection in ecological sensor networks Owen Langman Center for Limnology University of Wisconsin - Madison GLEON 7 Sept. 29, 2008 Norrtälje, Sweden.

Event detection in ecological sensor networks Owen Langman Center for Limnology University of Wisconsin - Madison GLEON 7 Sept. 29, 2008 Norrtälje, Sweden.
Active Shape Models Suppose we have a statistical shape model –Trained from sets of examples How do we use it to interpret new images? Use an “Active Shape.

Active Shape Models Suppose we have a statistical shape model –Trained from sets of examples How do we use it to interpret new images? Use an “Active Shape.
Rapid Object Detection using a Boosted Cascade of Simple Features Paul Viola, Michael Jones Conference on Computer Vision and Pattern Recognition 2001.

Rapid Object Detection using a Boosted Cascade of Simple Features Paul Viola, Michael Jones Conference on Computer Vision and Pattern Recognition 2001.
Rapid Object Detection using a Boosted Cascade of Simple Features Paul Viola, Michael Jones Conference on Computer Vision and Pattern Recognition 2001.

Rapid Object Detection using a Boosted Cascade of Simple Features Paul Viola, Michael Jones Conference on Computer Vision and Pattern Recognition 2001.
On-Demand Lake Circulation Modeling Chin Wu Nobuaki Kimura Environmental Fluid Mechanics Laboratory University of Wisconsin Paul Hanson Tim Kratz Tim Meinke.

On-Demand Lake Circulation Modeling Chin Wu Nobuaki Kimura Environmental Fluid Mechanics Laboratory University of Wisconsin Paul Hanson Tim Kratz Tim Meinke.
June 2010 At A Glance The Room Alert Adapter software in conjunction with AVTECH Room Alert™ devices assists in monitoring computer room environments as.

June 2010 At A Glance The Room Alert Adapter software in conjunction with AVTECH Room Alert™ devices assists in monitoring computer room environments as.
Improvement of CT Slice Image Reconstruction Speed Using SIMD Technology Xingxing Wu Yi Zhang Instructor: Prof. Yu Hen Hu Department of Electrical & Computer.

Improvement of CT Slice Image Reconstruction Speed Using SIMD Technology Xingxing Wu Yi Zhang Instructor: Prof. Yu Hen Hu Department of Electrical & Computer.
Jim Graham, Humboldt State University Instructor: Jim Graham Advanced GIS.

Jim Graham, Humboldt State University Instructor: Jim Graham Advanced GIS.
RBF Neural Networks x2 - + - 1 - + 2 - - - - x1 Examples inside circles 1 and 2 are of class +, examples outside both circles are of class – What NN does.

RBF Neural Networks x x1 Examples inside circles 1 and 2 are of class +, examples outside both circles are of class – What NN does.
UNIVERSITY OF SOUTH CAROLINA Department of Computer Science and Engineering On-line Alert Systems for Production Plants A Conflict Based Approach.

UNIVERSITY OF SOUTH CAROLINA Department of Computer Science and Engineering On-line Alert Systems for Production Plants A Conflict Based Approach.
Integrating Historical and Realtime Monitoring Data into an Internet Based Watershed Information System for the Bear River Basin Jeff Horsburgh David Stevens,

Integrating Historical and Realtime Monitoring Data into an Internet Based Watershed Information System for the Bear River Basin Jeff Horsburgh David Stevens,
1 Adaptive Kalman Filter Based Freeway Travel time Estimation Lianyu Chu CCIT, University of California Berkeley Jun-Seok Oh Western Michigan University.

1 Adaptive Kalman Filter Based Freeway Travel time Estimation Lianyu Chu CCIT, University of California Berkeley Jun-Seok Oh Western Michigan University.
GLEON Data Management Luke Winslow PASEO 3/18/09.

GLEON Data Management Luke Winslow PASEO 3/18/09.
Problem Description: To develop an autonomous network for monitoring aquatic environment Problem Description: To develop an autonomous network for monitoring.

Problem Description: To develop an autonomous network for monitoring aquatic environment Problem Description: To develop an autonomous network for monitoring.
1 System Control & MSGQ. 2 System Control & MSGQ Features Uses QSYSOPR or any application message queue data as input to iSecurity Action module Enables.

1 System Control & MSGQ. 2 System Control & MSGQ Features Uses QSYSOPR or any application message queue data as input to iSecurity Action module Enables.
Environmental Boundary Tracking Using Multiple Autonomous Vehicles Mayra Cisneros & Denise Lewis Mentor: Martin Short July 16, 2008.

Environmental Boundary Tracking Using Multiple Autonomous Vehicles Mayra Cisneros & Denise Lewis Mentor: Martin Short July 16, 2008.
1 Action Automated Security Breach Reporting and Corrections.

1 Action Automated Security Breach Reporting and Corrections.
EARLY DETECTION OF TWITTER TRENDS MILAN STANOJEVIC UNIVERSITY OF BELGRADE SCHOOL OF ELECTRICAL ENGINEERING.

EARLY DETECTION OF TWITTER TRENDS MILAN STANOJEVIC UNIVERSITY OF BELGRADE SCHOOL OF ELECTRICAL ENGINEERING.

Similar presentations

Ads by Google