Measuring the Performance and Intelligence of Systems: Proceedings of the 2001 PerMIS Workshop

Abstract

Testing of performance pertains to evaluation of the potential and actual capabilities of a system to satisfy the expectations of the designer and the users via exploration of its functioning. This includes determining how well the system performs its declared "job," how efficiently and effectively it does so, how robust it is, and so forth. The "job" and expected performance must therefore be defined at the outset. Efficiency is defined as how well the system does things right, effectiveness is defined as how well the system does the right thing, and robustness is defined as "the degree to which a system can function correctly in the presence of invalid inputs or stressful environmental conditions." [Finklestein, 00] Furthermore, the tests under consideration are not meant to be broad-based general evaluations of the system's knowledge or the full spectrum of its capabilities. In particular, we are not striving to ascertain whether a system has common-sense generic knowledge applicable to general-purpose problem solving. The system being evaluated has a given sphere of responsibility and known abilities and tasks that it is able to undertake under its specifications. Comments regarding the testing of intelligent versus non-intelligent systems are not meant to underestimate the difficulty of testing non-intelligent systems. Testing robustness, efficiency, and even functionality of non-intelligent software systems is difficult enough, e.g., see [Mukherjee 97]. Since the software execution can follow a myriad of combinations of paths through the code, it is impossible, in typical practice to exhaustively test all the possible combinations. In non-deterministic real-time systems, the problem is compounded by the uncertainty in the execution times of various processes, the sequence of events, asynchronous interrupts, etc [Butler, 93]. In general, the evaluation of intelligent systems (IS's) is broader than testing of non-intelligent systems (NIS).

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Sep 04, 2001
Accession Number
ADA515942

Entities

People

  • A. M. Meystel
  • E. R. Messina

Organizations

  • National Institute of Standards and Technology

Tags

Communities of Interest

  • Autonomy
  • C4I
  • Ground and Sea Platforms
  • Human Systems
  • Sensors
  • Weapons Technologies

DTIC Thesaurus Topics

  • Application Software
  • Artificial Intelligence
  • Automata Theory
  • Cognitive Science
  • Cognitive Workload
  • Computational Science
  • Computer Languages
  • Computer Programming
  • Computer Programs
  • Control Systems
  • Information Processing
  • Information Science
  • Information Systems
  • Machine Learning
  • Ontologies
  • Psychology
  • Two Dimensional

Fields of Study

  • Computer science

Readers

  • Parallel and Distributed Computing.
  • Systems Analysis and Design
  • Theoretical Analysis.