CCLS Internship Presentation

44 %
56 %
Information about CCLS Internship Presentation
Technology

Published on February 12, 2009

Author: cnaut

Source: slideshare.net

Description

A presentation about the work me and my fellow intern did during our summer at Columbia University Center for Computational Learning Systems.

Data Mining and Feeder Attribute Analysis Interns Charles Naut Lawrence Ng Columbia University’s Center for Computational Learning Systems

Transformer Attribute Time Series 7 years worth of data from Con Edison databases Attributes for transformers: temperature, phase voltage, and phase load B phase load for one week - 168 data points (one point per hour) 41.9 61 40.9 60 … … … … 18.9 1 19.2 128 19.3 127 18.6 2 Load Hour

7 years worth of data from Con Edison databases

Attributes for transformers: temperature, phase voltage, and phase load

B phase load for one week - 168 data points (one point per hour)

Piecewise Aggregate Approximation (PAA ) Symbolic Aggregate Approximation (SAX) PAA 1 Time series is divided into equally sized frames Value of a frame is the average of data falling in that frame Reduces dimensionality of time series Lower bounding of Euclidean Distance SAX 2 Discretizes time series data PAA values are given symbols based on calculated breakpoints Retains reduced dimensionality of PAA Allows for lower bounding of Euclidean Distance 1- E. Keogh, J. Lin & A. Fu (2005). HOT SAX: Efficiently Finding the Most Unusual Time Series Subsequence. In Proc. of the 5th IEEE International Conference on Data Mining (ICDM 2005), pp. 226 - 233., Houston, Texas, Nov 27-30, 2005.  2- B. Yi, & C. Faloutsos. Fast time sequence indexing for arbitrary lp norms. In Proc. of the 26th Int'l Conf. on Very Large Databases. pp 385-394, 2000.

PAA 1

Time series is divided into equally sized frames

Value of a frame is the average of data falling in that frame

Reduces dimensionality of time series

Lower bounding of Euclidean Distance

SAX 2

Discretizes time series data

PAA values are given symbols based on calculated breakpoints

Retains reduced dimensionality of PAA

Allows for lower bounding of Euclidean Distance

SAX Conversion Process Steps: Attain raw time series Normalize time series Convert to PAA format Convert to a SAX string Result: cbbbddaa

Steps:

Attain raw time series

Normalize time series

Convert to PAA format

Convert to a SAX string

Result: cbbbddaa

SAX Goals Detect abnormalities among time series data from transformers by comparing differences in SAX strings of baseline data to SAX strings of live data Predict when a transformer will fail by using dynamic (time series) data to indicate how stressed it is B phase loads for two feeders Top: caaadddb - Normal Bottom: cbbbddaa - Failure

Detect abnormalities among time series data from transformers by comparing differences in SAX strings of baseline data to SAX strings of live data

Predict when a transformer will fail by using dynamic (time series) data to indicate how stressed it is

B phase loads for two feeders

Top: caaadddb - Normal

Bottom: cbbbddaa - Failure

Tarzan and Hot SAX Methods for finding time series discords Tarzan 3 Detects novel time series patterns Novelty based on expected pattern frequency Hot SAX 4 Finds patterns most unlike others Aids in clustering and discovery of motifs 3- S.Lonardi, J. Lin, E. Keogh & B. Chiu (2007). Efficient Discovery of Unusual Patterns in Time Series. Special Issue of New Generation Computing Journal. To Appear. 4- E. Keogh, J. Lin and A. Fu (2005). HOT SAX: Efficiently Finding the Most Unusual Time Series Subsequence. In Proc. of the 5th IEEE International Conference on Data Mining (ICDM 2005), pp. 226 - 233., Houston, Texas, Nov 27-30, 2005. 

Methods for finding time series discords

Tarzan 3

Detects novel time series patterns

Novelty based on expected pattern frequency

Hot SAX 4

Finds patterns most unlike others

Aids in clustering and discovery of motifs

Feeder Attribute Analysis Determine the similarity of feeders and create a dendrogram displaying the information Paired feeders allow to better study “treatments”, such as Hipots, statistically Build on SQL queries previously written

Determine the similarity of feeders and create a dendrogram displaying the information

Paired feeders allow to better study “treatments”, such as Hipots, statistically

Build on SQL queries previously written

Dendrogram of Distances Between Feeders Based on Feeder Attributes

Pairing of Feeders List of feeders and companions based on increasing coverage area.

Accomplishments ABF dynamic attribute on feeder outages SAX strings based on time series from transformer RMS data Matlab implementation of Hot SAX algorithm Introduction of a new method for machine learning on feeders and their components. Dendrogram with information of the distance between feeders based on feeder attributes SQL queries creating feeder pairs

ABF dynamic attribute on feeder outages

SAX strings based on time series from transformer RMS data

Matlab implementation of Hot SAX algorithm

Introduction of a new method for machine learning on feeders and their components.

Dendrogram with information of the distance between feeders based on feeder attributes

SQL queries creating feeder pairs

Growth Gained experience with: Matlab, SQL, Python, R, Unix, and Microsoft Office Acquired new knowledge of SAX, machine learning, data mining, pattern recognition, databases, suffix trees, and time series Learned about the Con Edison Distribution System and its relevance to our work Developed good work habits and communication skills

Gained experience with: Matlab, SQL, Python, R, Unix, and Microsoft Office

Acquired new knowledge of SAX, machine learning, data mining, pattern recognition, databases, suffix trees, and time series

Learned about the Con Edison Distribution System and its relevance to our work

Developed good work habits and communication skills

Special Thanks Albert Boulanger Ansaf Salleb-Aouissi Phillip Gross Roger Anderson Leon Bukhman Eugene Klitenik

Albert Boulanger

Ansaf Salleb-Aouissi

Phillip Gross

Roger Anderson

Leon Bukhman

Eugene Klitenik

Add a comment

Related presentations

Related pages

Internship Presentation CCHMC by Katrina Hall on Prezi

Internship Presentation CCHMC. ... Internship Project: Prep ... will be available for all CCLS on eCHIRP after photos received and approved by editing ...
Read more

How to Land a Child Life Internship Caroline Greene, CCLS ...

How to Land a Child Life Internship Caroline Greene, CCLS Sydney Lewis, CCLS. Upload Log in. My presentations; Profile; Feedback; ... Presentation is loading.
Read more

International Bar Association - Student Membership ...

CCLS Seminars - New Voices in ... International Bar Association - Student Membership Presentation 7 February 2012 ... The IBA internship programme; Contact.
Read more

Korie Leigh, MA, CCLS, CT | LinkedIn

Korie Leigh, MA, CCLS, CT. Professor & Internship Supervisor at Mills College. Location San Francisco Bay Area Industry Mental Health Care
Read more

⚡Presentation "Prof. D. Petkovic, Director, CCLS; Chair ...

Prof. D. Petkovic, Director, CCLS; Chair, CS Department SFSU 1 SFSU Center for Computing for Life Sciences – CCLS Advisory Board Meeting April 08 Summary.
Read more

Child Life: The Journey Begins Here by Andrea Zuniga on Prezi

People invited to a presentation do not need a Prezi account; ... Transcript of Child Life: The Journey Begins Here. What is Child Life?
Read more

Child Life Council

Child Life Council 26th Annual Conference on Professional Issues 39. The Ins and Outs of Three Distinctly Different Internship Programs – A Panel
Read more

Child Life Council

Child Life Council ... At the completion of this presentation, the participant will: ... Increase understanding of internship program organization and ...
Read more

Internships - Children's Medical Center Dallas

You can gain practical experience working with children and enhance your career opportunities by taking part in Children’s Child Life Internship Program.
Read more