Advertisement

Designing the AI Developing System Through Ecological Interface Design

  • Daehee ParkEmail author
  • Heesung Park
  • Scott Song
Conference paper
  • 27 Downloads
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 1217)

Abstract

In recent years, several kinds of machine learning tools have developed, each involving complex functions and tasks, which means usage knowledge varies between tools. Integrating the environment for effective AI machine learning can be regarded as a complicated task and may even consist of several separate tasks, such as building a test environment, data acquisition, data cleansing, machine learning training, and model management. In terms of the cognitive engineering approach, most tasks not only require knowledge-based cognitive control over skill-based or rule-based behaviours higher cognitive loads and workloads as well. Since complex knowledge and higher cognitive loads are required, the use of AI machine learning is limited and leads to ineffective work procedures. Thus, this research analysed the AI development process via various methods of cognitive task analysis in order to identify which tasks induce cognitive workload. Then, a new integrated AI development system was created, which was expected to reduce the number of ineffective tasks and workload. Experiments were conducted twice to validate the system’s effectiveness, and the results indicate that there were significant differences between the several different AI development tasks.

Keywords

Cognitive engineering Task analysis EID AI development system 

References

  1. 1.
    Vicente, K.J., Rasmussen, J.: A theoretical framework for ecological interface design (1988)Google Scholar
  2. 2.
    Rasmussen, J., Mark Pejtersen, A., Goodstein, L.P.: Cognitive Systems Engineering. Wiley, New York (1994)Google Scholar
  3. 3.
    Rasmussen, J.: Skills, rules, and knowledge; signals, signs, and symbols, and other distinctions in human performance models. IEEE Trans. Syst. Man Cybern. 3, 257–266 (1983)CrossRefGoogle Scholar
  4. 4.
    Reason, J.: Framework models of human performance and error: a consumer guide. In: Tasks, Errors, and Mental Models, pp. 35–49. Taylor & Francis, Inc., March 1988Google Scholar
  5. 5.
    Hart, S.G.: NASA-task load index (NASA-TLX); 20 years later. In: Proceedings of the Human Factors and Ergonomics Society Annual Meeting, vol. 50, no. 9, pp. 904–908. Sage Publications, Los Angeles, October 2006Google Scholar
  6. 6.
    Lintern, G.: Tutorial: work domain analysis (2011)Google Scholar
  7. 7.
    Vicente, K.J.: Cognitive Work Analysis: Toward Safe, Productive, and Healthy Computer-Based Work. CRC Press (1999)Google Scholar
  8. 8.
    Drivalou, S.: Supporting critical operational conditions in an electricity distribution control room through ecological interfaces. In: Proceedings of the 2005 Annual Conference on European Association of Cognitive Ergonomics, pp. 263–270 (2005)Google Scholar
  9. 9.
    Rasmussen, J.: Outlines of a hybrid model of the process plant operator. In: Monitoring Behavior and Supervisory Control, pp. 371–383. Springer, Boston (1976)Google Scholar
  10. 10.
    Rasmussen, J.: Models of mental strategies in process plant diagnosis. In: Human Detection and Diagnosis of System Failures, pp. 241–258. Springer, Boston (1981)Google Scholar
  11. 11.
    Mcllroy, R.C., Stanton, N.A.: Eco-Driving: From Strategies to Interfaces. CRC Press (2017)Google Scholar
  12. 12.
    Grier, R.A.: How high is high? A meta-analysis of NASA-TLX global workload scores. In: Proceedings of the Human Factors and Ergonomics Society Annual Meeting, vol. 59, no. 1, pp. 1727–1731. SAGE Publications, Los Angeles, September 2015Google Scholar

Copyright information

© The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Switzerland AG 2020

Authors and Affiliations

  1. 1.Samsung ElectronicsSeoulRepublic of Korea

Personalised recommendations