FIND2: A flexible functional diagnosis framework based on machine-learning technique
Research Area:
Research Lines:
Research Lines:
Responsible:
Collaboration with industry
-
Start date: 2014-10-01
Length: 12 months
Project abstract
A gift from the Cisco University Research Program Fund, a corporate advised fund of Silicon Valley Community Foundation, has been awarded to support Cristiana Bolchini's research project "FIND2: A flexible functional diagnosis framework based on machine-learning technique".
The project will develop an incremental engine exploiting different machine learning techniques to use a reduced set of tests for identifying the faulty component(s), with the goal to minimize diagnosis costs and efforts, without compromising accuracy.
Two main usages are envisioned: i) an accuracy-oriented one, where the user is interested in getting the most accurate answer (possibly 100%), and ii) a user-tuned one, where the user can set a maximum cost (e.g., number/cost of components to be replaced, maximum number of tests to be executed).
The project will develop an incremental engine exploiting different machine learning techniques to use a reduced set of tests for identifying the faulty component(s), with the goal to minimize diagnosis costs and efforts, without compromising accuracy.
Two main usages are envisioned: i) an accuracy-oriented one, where the user is interested in getting the most accurate answer (possibly 100%), and ii) a user-tuned one, where the user can set a maximum cost (e.g., number/cost of components to be replaced, maximum number of tests to be executed).
