Real-Time Diagnostic Technique for AI-Enabled System
The last few decades have witnessed a dramatic evolution of Artificial Intelligence (AI) algorithms, represented by Deep Neural Networks (DNNs), resulting in AI-enabled systems being significantly dominant in various fields, including robotics, healthcare, and mobility. AI-enabled systems are curren...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2024-01-01
|
| Series: | IEEE Open Journal of Intelligent Transportation Systems |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10614714/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832590344327266304 |
|---|---|
| author | Hiroaki Itsuji Takumi Uezono Tadanobu Toba Subrata Kumar Kundu |
| author_facet | Hiroaki Itsuji Takumi Uezono Tadanobu Toba Subrata Kumar Kundu |
| author_sort | Hiroaki Itsuji |
| collection | DOAJ |
| description | The last few decades have witnessed a dramatic evolution of Artificial Intelligence (AI) algorithms, represented by Deep Neural Networks (DNNs), resulting in AI-enabled systems being significantly dominant in various fields, including robotics, healthcare, and mobility. AI-enabled systems are currently used even for safety-critical applications, including automated driving, where they encounter reliability challenges from both hardware (HW) and software (SW) perspectives. However, there is no effective technique available that can diagnose HW and SW of AI-enabled systems in real-time during operation. Therefore, this paper proposes an intelligent real-time diagnostic technique for detecting HW and SW anomalies of AI-enabled systems and continuously improving the SW quality during operation. The proposed technique can detect HW anomalies to avoid unexpected changes in AI parameters and subsequent AI performance degradation using single context data with a detection accuracy of more than 92%. The proposed technique can also detect SW anomalies and identify edge cases in real-time, which could result in performance degradation by more than 50% compared to normal conditions. The identified edge cases can be used to continuously enhance the SW quality. Experimental results show the effectiveness of the technique for practical applications and thus can contribute to realize reliable and improved AI-enabled systems. |
| format | Article |
| id | doaj-art-94c713fb0e214a79bc92518f38196f3c |
| institution | Kabale University |
| issn | 2687-7813 |
| language | English |
| publishDate | 2024-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Open Journal of Intelligent Transportation Systems |
| spelling | doaj-art-94c713fb0e214a79bc92518f38196f3c2025-01-24T00:02:50ZengIEEEIEEE Open Journal of Intelligent Transportation Systems2687-78132024-01-01548349410.1109/OJITS.2024.343571210614714Real-Time Diagnostic Technique for AI-Enabled SystemHiroaki Itsuji0https://orcid.org/0000-0002-1910-4526Takumi Uezono1https://orcid.org/0000-0002-1804-2714Tadanobu Toba2Subrata Kumar Kundu3https://orcid.org/0009-0002-2249-5115Production Engineering and MONOZUKURI Innovation Center, Center for Sustainability, Research and Development Group, Hitachi, Ltd., Yokohama, JapanAdvanced Technology Development Department, Hitachi Astemo Americas, Inc., Farmington Hills, MI, USAProduction Engineering and MONOZUKURI Innovation Center, Center for Sustainability, Research and Development Group, Hitachi, Ltd., Yokohama, JapanProduction Engineering and MONOZUKURI Innovation Center, Center for Sustainability, Research and Development Group, Hitachi, Ltd., Yokohama, JapanThe last few decades have witnessed a dramatic evolution of Artificial Intelligence (AI) algorithms, represented by Deep Neural Networks (DNNs), resulting in AI-enabled systems being significantly dominant in various fields, including robotics, healthcare, and mobility. AI-enabled systems are currently used even for safety-critical applications, including automated driving, where they encounter reliability challenges from both hardware (HW) and software (SW) perspectives. However, there is no effective technique available that can diagnose HW and SW of AI-enabled systems in real-time during operation. Therefore, this paper proposes an intelligent real-time diagnostic technique for detecting HW and SW anomalies of AI-enabled systems and continuously improving the SW quality during operation. The proposed technique can detect HW anomalies to avoid unexpected changes in AI parameters and subsequent AI performance degradation using single context data with a detection accuracy of more than 92%. The proposed technique can also detect SW anomalies and identify edge cases in real-time, which could result in performance degradation by more than 50% compared to normal conditions. The identified edge cases can be used to continuously enhance the SW quality. Experimental results show the effectiveness of the technique for practical applications and thus can contribute to realize reliable and improved AI-enabled systems.https://ieeexplore.ieee.org/document/10614714/Artificial intelligence (AI)AI-enabled systemreal-time monitoringdiagnostic technologysystem reliability |
| spellingShingle | Hiroaki Itsuji Takumi Uezono Tadanobu Toba Subrata Kumar Kundu Real-Time Diagnostic Technique for AI-Enabled System IEEE Open Journal of Intelligent Transportation Systems Artificial intelligence (AI) AI-enabled system real-time monitoring diagnostic technology system reliability |
| title | Real-Time Diagnostic Technique for AI-Enabled System |
| title_full | Real-Time Diagnostic Technique for AI-Enabled System |
| title_fullStr | Real-Time Diagnostic Technique for AI-Enabled System |
| title_full_unstemmed | Real-Time Diagnostic Technique for AI-Enabled System |
| title_short | Real-Time Diagnostic Technique for AI-Enabled System |
| title_sort | real time diagnostic technique for ai enabled system |
| topic | Artificial intelligence (AI) AI-enabled system real-time monitoring diagnostic technology system reliability |
| url | https://ieeexplore.ieee.org/document/10614714/ |
| work_keys_str_mv | AT hiroakiitsuji realtimediagnostictechniqueforaienabledsystem AT takumiuezono realtimediagnostictechniqueforaienabledsystem AT tadanobutoba realtimediagnostictechniqueforaienabledsystem AT subratakumarkundu realtimediagnostictechniqueforaienabledsystem |