Toward Accountable and Explainable Artificial Intelligence Part Two: The Framework Implementation
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....
| Main Authors: | , |
|---|---|
| Format: | Journal Article |
| Published: |
IEEE
2022
|
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/xpl/RecentIssue.jsp?punumber=6287639 http://hdl.handle.net/20.500.11937/88248 |
| _version_ | 1848764992417955840 |
|---|---|
| author | Vice, Jordan Khan, Masood |
| author_facet | Vice, Jordan Khan, Masood |
| author_sort | Vice, Jordan |
| building | Curtin Institutional Repository |
| collection | Online Access |
| description | 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 AI 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 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 provides 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. |
| first_indexed | 2025-11-14T11:28:10Z |
| format | Journal Article |
| id | curtin-20.500.11937-88248 |
| institution | Curtin University Malaysia |
| institution_category | Local University |
| last_indexed | 2025-11-14T11:28:10Z |
| publishDate | 2022 |
| publisher | IEEE |
| recordtype | eprints |
| repository_type | Digital Repository |
| spelling | curtin-20.500.11937-882482022-05-02T06:40:19Z Toward Accountable and Explainable Artificial Intelligence Part Two: The Framework Implementation Vice, Jordan Khan, Masood 0801 - Artificial Intelligence and Image Processing 4602 - Artificial intelligence 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 AI 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 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 provides 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. 2022 Journal Article http://hdl.handle.net/20.500.11937/88248 10.1109/ACCESS.2022.3163523 https://ieeexplore.ieee.org/xpl/RecentIssue.jsp?punumber=6287639 http://creativecommons.org/licenses/by/4.0/ IEEE fulltext |
| spellingShingle | 0801 - Artificial Intelligence and Image Processing 4602 - Artificial intelligence Vice, Jordan Khan, Masood Toward Accountable and Explainable Artificial Intelligence Part Two: The Framework Implementation |
| title | Toward Accountable and Explainable Artificial Intelligence Part Two: The Framework Implementation |
| title_full | Toward Accountable and Explainable Artificial Intelligence Part Two: The Framework Implementation |
| title_fullStr | Toward Accountable and Explainable Artificial Intelligence Part Two: The Framework Implementation |
| title_full_unstemmed | Toward Accountable and Explainable Artificial Intelligence Part Two: The Framework Implementation |
| title_short | Toward Accountable and Explainable Artificial Intelligence Part Two: The Framework Implementation |
| title_sort | toward accountable and explainable artificial intelligence part two: the framework implementation |
| topic | 0801 - Artificial Intelligence and Image Processing 4602 - Artificial intelligence |
| url | https://ieeexplore.ieee.org/xpl/RecentIssue.jsp?punumber=6287639 http://hdl.handle.net/20.500.11937/88248 |