Digital Assistance Systems to Implement Machine Learning in Manufacturing: A Systematic Review
Implementing machine learning technologies in manufacturing environment relies heavily on human expertise in terms of domain and machine learning knowledge. Yet, the required machine learning knowledge is often not available in manufacturing companies. A possible solution to overcome this competence...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-12-01
|
| Series: | Machine Learning and Knowledge Extraction |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2504-4990/6/4/134 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | Implementing machine learning technologies in manufacturing environment relies heavily on human expertise in terms of domain and machine learning knowledge. Yet, the required machine learning knowledge is often not available in manufacturing companies. A possible solution to overcome this competence gap and let domain experts with limited machine learning programming skills build viable applications are digital assistance systems that support the implementation. At the present, there is no comprehensive overview over corresponding assistance systems. Thus, within this study a systematic literature review based on the PRISMA-P process was conducted. Twenty-nine papers were identified and analyzed in depth regarding machine learning use case, required resources and research outlook. Six key findings as well as requirements for future developments are derived from the investigation. As such, the existing assistance systems basically focus on technical aspects whereas the integration of the users as well as validation in industrial environments lack behind. Future assistance systems should put more emphasis on the users and integrate them both in development and validation. |
|---|---|
| ISSN: | 2504-4990 |