---
title: "Techniques for Sensor-Based Diagnosis"
authors:
  - "Mark S. Fox"
  - "Simon Lowenfeld"
  - "Pamela Kleinosky"
doi: ""
url: "https://ijcai.org/proceedings/1983/36"
pdf: "https://ijcai.org/proceedings/1983/0036.pdf"
venue: "Proceedings of the Eighth International Joint Conference on Artificial Intelligence"
year: 1983
pages: "158-162"
track: "Expert Systems"
keywords:
---

# Techniques for Sensor-Based Diagnosis

Mark S. Fox, Simon Lowenfeld, Pamela Kleinosky

*Proceedings of the Eighth International Joint Conference on Artificial Intelligence*, pages 158-162.

## Abstract

This paper describes a system called PDS , a forward chaining, rule-ba se d architecture designed for the online, realtime diagnosis of .nachine processes. Two issues arise in the application of expert systems to the analysis of sensor-based data: spurious readings and se nsor degradation . PDS implemen ts techniques called retrospective analysis and meta-diagnosis as solutions to these problems. These techniques and our experiences in knowledge ac quisition in a large organization, and the implementation of PDS as a portable diagnostic tool are described.