Online Program Home
  My Program

All Times EDT

Abstract Details

Activity Number: 214 - Contributed Poster Presentations: Quality and Productivity Section
Type: Contributed
Date/Time: Tuesday, August 4, 2020 : 10:00 AM to 2:00 PM
Sponsor: Quality and Productivity Section
Abstract #314001
Title: Shmoo Distance Metric with Clustering Application
Author(s): Katherine Freier* and Sarah Hedberg
Companies: Intel and Intel
Keywords: shmoo; clustering; distance metric; cluster; unsupervised; classification
Abstract:

A “shmoo” is a pass/fail heatmap type graph commonly used by electrical engineers to assess the capabilities and limitations of a device over a series of discrete conditions. They can be helpful in evaluating quality and when debugging issues, characteristics seen in shmoo plots can be key in finding both a root-cause and solution. This work describes a metric for measuring the difference between two shmoo plots and how, with that metric, variations on common clustering algorithms can be applied to efficiently group devices with similar shmoo behavior. Shmoo clustering results with example data relating to voltage and frequency of computer chips will be shared.


Authors who are presenting talks have a * after their name.

Back to the full JSM 2020 program