Report cards for manholes: Eliciting expert feedback for a learning task
We present a manhole profiling tool, developed as part of the Columbia/Con Edison machine learning project on manhole event prediction, and discuss its role in evaluating our machine learning model in three important ways: elimination of outliers, elimination of falsely predictive features, and asse...
| Main Authors: | , , , |
|---|---|
| Other Authors: | |
| Format: | Article |
| Language: | en_US |
| Published: |
Institute of Electrical and Electronics Engineers
2010
|
| Online Access: | http://hdl.handle.net/1721.1/60059 |
| _version_ | 1826190915500244992 |
|---|---|
| author | Radeva, Axinia Rudin, Cynthia Passonneau, Rebecca Isaac, Delfina F. |
| author2 | Sloan School of Management |
| author_facet | Sloan School of Management Radeva, Axinia Rudin, Cynthia Passonneau, Rebecca Isaac, Delfina F. |
| author_sort | Radeva, Axinia |
| collection | MIT |
| description | We present a manhole profiling tool, developed as part of the Columbia/Con Edison machine learning project on manhole event prediction, and discuss its role in evaluating our machine learning model in three important ways: elimination of outliers, elimination of falsely predictive features, and assessment of the quality of the model. The model produces a ranked list of tens of thousands of manholes in Manhattan, where the ranking criterion is vulnerability to serious events such as fires, explosions and smoking manholes. Con Edison set two goals for the model, namely accuracy and intuitiveness, and this tool made it possible for us to address both of these goals. The tool automatically assembles a "report card" or "profile" highlighting data associated with a given manhole. Prior to the processing work that underlies the profiling tool, case studies of a single manhole took several days and resulted in an incomplete study; locating manholes such as those we present in this work would have been extremely difficult. The model is currently assisting Con Edison in determining repair priorities for the secondary electrical grid. |
| first_indexed | 2024-09-23T08:47:34Z |
| format | Article |
| id | mit-1721.1/60059 |
| institution | Massachusetts Institute of Technology |
| language | en_US |
| last_indexed | 2024-09-23T08:47:34Z |
| publishDate | 2010 |
| publisher | Institute of Electrical and Electronics Engineers |
| record_format | dspace |
| spelling | mit-1721.1/600592022-09-30T11:16:02Z Report cards for manholes: Eliciting expert feedback for a learning task Radeva, Axinia Rudin, Cynthia Passonneau, Rebecca Isaac, Delfina F. Sloan School of Management Rudin, Cynthia Rudin, Cynthia We present a manhole profiling tool, developed as part of the Columbia/Con Edison machine learning project on manhole event prediction, and discuss its role in evaluating our machine learning model in three important ways: elimination of outliers, elimination of falsely predictive features, and assessment of the quality of the model. The model produces a ranked list of tens of thousands of manholes in Manhattan, where the ranking criterion is vulnerability to serious events such as fires, explosions and smoking manholes. Con Edison set two goals for the model, namely accuracy and intuitiveness, and this tool made it possible for us to address both of these goals. The tool automatically assembles a "report card" or "profile" highlighting data associated with a given manhole. Prior to the processing work that underlies the profiling tool, case studies of a single manhole took several days and resulted in an incomplete study; locating manholes such as those we present in this work would have been extremely difficult. The model is currently assisting Con Edison in determining repair priorities for the secondary electrical grid. 2010-12-02T18:45:04Z 2010-12-02T18:45:04Z 2010-01 2009-12 Article http://purl.org/eprint/type/ConferencePaper 978-0-7695-3926-3 INSPEC Accession Number: 11084866 http://hdl.handle.net/1721.1/60059 Radeva, A. et al. “Report Cards for Manholes: Eliciting Expert Feedback for a Learning Task.” Machine Learning and Applications, 2009. ICMLA '09. International Conference on. 2009. 719-724. © Copyright 2009 IEEE en_US http://dx.doi.org/10.1109/ICMLA.2009.72 International Conference on Machine Learning and Applications, 2009. ICMLA '09. Article is made available in accordance with the publisher's policy and may be subject to US copyright law. Please refer to the publisher's site for terms of use. application/pdf Institute of Electrical and Electronics Engineers IEEE |
| spellingShingle | Radeva, Axinia Rudin, Cynthia Passonneau, Rebecca Isaac, Delfina F. Report cards for manholes: Eliciting expert feedback for a learning task |
| title | Report cards for manholes: Eliciting expert feedback for a learning task |
| title_full | Report cards for manholes: Eliciting expert feedback for a learning task |
| title_fullStr | Report cards for manholes: Eliciting expert feedback for a learning task |
| title_full_unstemmed | Report cards for manholes: Eliciting expert feedback for a learning task |
| title_short | Report cards for manholes: Eliciting expert feedback for a learning task |
| title_sort | report cards for manholes eliciting expert feedback for a learning task |
| url | http://hdl.handle.net/1721.1/60059 |
| work_keys_str_mv | AT radevaaxinia reportcardsformanholeselicitingexpertfeedbackforalearningtask AT rudincynthia reportcardsformanholeselicitingexpertfeedbackforalearningtask AT passonneaurebecca reportcardsformanholeselicitingexpertfeedbackforalearningtask AT isaacdelfinaf reportcardsformanholeselicitingexpertfeedbackforalearningtask |