CoChat
Sign Up
Cited by 11Explainable Artificial Intelligence (XAI)Ethics and Social Impacts of AISafety Systems Engineering in Autonomy

Toward Accountable and Explainable Artificial Intelligence Part Two: The Framework Implementation

Open access
Vice, Jordan, Khan, Masood Mehmood·2022·IEEE Access
DOI 10.1109/access.2022.3163523
Open this paper in CoChat — free accountOpen PDF

Abstract

This paper builds upon the theoretical foundations of the Accountable eXplainable Artificial Intelligence (AXAI) capability framework presented in part one of this paper. We demonstrate incorporation of the AXAI capability in the real time Affective State Assessment Module (ASAM) of a robotic system. We show that adhering to the eXtreme Programming (XP) practices would help in understanding user behavior and systematic incorporation of the AXAI capability in Machine Learning (ML) systems. We further show that a collaborative software design and development process (SDDP) would facilitate identification of ethical, technical, functional, and domain-specific system requirements. Meeting these requirements would increase user confidence in ML and AI systems. Our results show that the ASAM can synthesize discrete and continuous models of affective state expressions for classifying them in real-time. The ASAM continuously shares important inputs, processed data and the output information with users via a graphical user interface (GUI). Thus, the GUI presents reasons behind system decisions and disseminates information about local reasoning, data handling and decision-making. Through this demonstrated work, we expect to move toward enhancing AI systems’ acceptability, utility and establishing a chain of responsibility if a system fails. We hope this work will initiate further investigations on developing the AXAI capability and use of a suitable SDDP for incorporating them in AI systems.

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1109/access.2022.3163523

Cites

58 of 58 references verified0 citation errors · 0 not checkable

Statistics

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

  • The development of reliability will strengthen the engineering behind autonomous vehicles' openness and accountability.

    “The development of reliability will strengthen the engineering behind autonomous vehicles' openness and accountability [27], [89].”

    From A Review of Trustworthy and Explainable Artificial Intelligence (XAI) (2023) · cites this paper as [27]

    The Background describes an AI framework that makes predictive accuracy and accountability visible to users, and the Introduction links its design to transparency. The paper demonstrates the framework in a robotic affective-state module, not an autonomous vehicle; these passages do not establish that developing reliability strengthens vehicle engineering or its openness and accountability. (LLM, conf=0.84)

    Experimental — accuracy not yet measured

  • The populace's adoption of autonomous vehicle technology would expand if the intended consumers' involvement, ideas, and expectations are sought out during the conception and creation of autonomous vehicles.

    “The populace's adoption of the aforementioned technology would expand if the intended consumers' involvement, ideas, and expectations are sought out during the conception and creation of autonomous vehicles [27], [89].”

    From A Review of Trustworthy and Explainable Artificial Intelligence (XAI) (2023) · cites this paper as [27]

    Sections III and VII (page not available) support involving users, gathering their feedback and expectations, and engaging them during AI-system design. The paper discusses an affective-state assessment module, not autonomous vehicles, and does not establish that such involvement would increase public adoption of them. (LLM, conf=0.86)

    Experimental — accuracy not yet measured

  • In tightly controlled domains such as IoT systems, avionics, finance, banking, autonomous systems, and medical services, integrating AI and its interoperability with legacy applications is much more onerous.

    “However, in tightly controlled domains like IoT systems, avionics, finance, banking, autonomous systems, and medical services, integrating AI and its interoperability with legacy applications is much more onerous [27], [47].”

    From A Review of Trustworthy and Explainable Artificial Intelligence (XAI) (2023) · cites this paper as [27]

    The Introduction discusses difficulty incorporating explainability into AI systems, while Section V describes making an affective-state module work with existing robotic infrastructure. Neither addresses whether AI integration and interoperability with legacy applications are more onerous in the listed tightly controlled domains. Searches for those domains and for legacy-application interoperability found no passage making that comparison; page numbers were unavailable in our copy. (LLM, conf=0.76)

    Experimental — accuracy not yet measured

  • Israelson and Ahmed have demonstrated that there exists a fundamental requirement for computational guarantee to foster interactions between human-autonomous systems.

    “Israelson and Ahmed have demonstrated that there exists a fundamental requirement for computational guarantee to foster interactions between human-autonomous systems.”

    From A Review of Trustworthy and Explainable Artificial Intelligence (XAI) (2023) · cites this paper as [27]

    The Abstract and Section VI (page unavailable) discuss explainability, quantifiable information, and user confidence in a robotic system, but do not state that computational guarantees are a fundamental requirement for human–autonomous-system interaction. Searches for “Israelson,” “computational guarantee,” and the claimed relationship found no supporting passage in our copy. (LLM, conf=0.75)

    Experimental — accuracy not yet measured

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Cites

Flagged first, then by citations

Research works printed but not linked: 5

  1. D. Michie, ''Machine learning in the next five years,'' in Proc. 3rd Eur. Conf. Eur. Work. Session Learn., Glasgow, U.K., 1988, pp. 107-122.
  2. R. Steyer, P. Schwenkmezger, P. Notz, and M. Eid, ''Testtheoretische anal- ysen des mehrdimensionalen befindlichkeitsfragebogen (MDBF),'' Diag- nostica, vol. 40, no. 4, pp. 320-328, 1997.
  3. A. M. Ruef and R. W. Levenson, ''Continuous measurement of emotion,'' in Handbook of Emotion Elicitation and Assessment, J. A. Coan and J. J. Allen, Eds. Oxford, U.K.: Oxford Univ. Press, 2007, pp. 286-297.
  4. Mach. Intell. (CogMI), Los Angeles, CA, USA, Dec. 2019, pp. 87-92.
  5. MASOOD MEHMOOD KHAN (Member, IEEE) received the B.E. (mechanical), M.S. (mechan- ical), and Ph.D. (computational engineering) degrees. He had taught at the National Uni- versity of Computer and Emerging Sciences, Jefri Bolkiah College of Engineering, and the American University of Sharjah, before joining the Faculty of Science and Engineering, Curtin University, WA. He has published more than 50 peer-reviewed articles in top quality journals and conference proceedings. His research interests include machine learn- ing, affective computing, machine vision, human-computer interaction, and robotics. He is a fellow of the Higher Education Academy.

Cited by

Sorted by citations

Related

Authors
Vice, J., & Khan, M. M.
Affiliations
Curtin University (AU)
ORCID
Venue
IEEE Access
Publisher
Institute of Electrical and Electronics Engineers (IEEE)
Published
2022
Volume
10
Pages
36091-36105
ISSN
2169-3536 (ISSN-L)
DOI
10.1109/access.2022.3163523
OpenAlex
W4226093670
Cited by
11
References
58
Citations by year
2026: 3 · 2024: 3 · 2023: 4 · 2022: 1
FWCI
0.66
Type
journal article
Language
en
Open access
Licence
Locations
  • IEEE Access (publishedVersion, cc-by)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion)
  • eSpace (Curtin University) (submittedVersion, cc-by)
Funders
Curtin University of Technology
Topics
  • Physical Sciences › Computer Science › Artificial Intelligence › Explainable Artificial Intelligence (XAI)
  • Social Sciences › Safety Research › Ethics and Social Impacts of AI
  • Physical Sciences › Engineering › Safety, Risk, Reliability and Quality › Safety Systems Engineering in Autonomy
Keywords
affective computing, robots, Extreme Programming, system requirements, explainable machine learning, graphical user interface, user trust in AI, chain of responsibility

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review