Conference Paper/Proceeding/Abstract 461 views 84 downloads
Towards an Ontological Framework for Integrating Domain Expert Knowledge with Random Forest Classification
Sadeer Beden,
Arnold Beckmann 
2023 IEEE 17th International Conference on Semantic Computing (ICSC)
Swansea University Authors:
Sadeer Beden, Arnold Beckmann
-
PDF | Accepted Manuscript
Download (398.14KB)
DOI (Published version): 10.1109/icsc56153.2023.00043
Abstract
This paper proposes an ontological framework that combines semantic-based methodologies and data-driven random forests (RF) to enable the integration of domain expert knowledge with machine-learning models. To achieve this, the RF classification process is firstly deconstructed and converted into se...
| Published in: | 2023 IEEE 17th International Conference on Semantic Computing (ICSC) |
|---|---|
| Published: |
IEEE
2023
|
| Online Access: |
http://dx.doi.org/10.1109/icsc56153.2023.00043 |
| URI: | https://cronfa.swan.ac.uk/Record/cronfa63104 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Abstract: |
This paper proposes an ontological framework that combines semantic-based methodologies and data-driven random forests (RF) to enable the integration of domain expert knowledge with machine-learning models. To achieve this, the RF classification process is firstly deconstructed and converted into semantic-based rules, which are combined with external rules constructed from the knowledge of domain experts. The combined rule set is applied to an ontological reasoner for inference, producing two classifications: (1) from simulating the selected RF voting strategy, (2) from the knowledge-driven rules, where the latter is prioritised. A case study in the steel manufacturing domain is presented that uses the proposed framework for real-world predictive maintenance purposes. Results are validated and compared to typical machine-learning approaches. |
|---|---|
| College: |
Faculty of Science and Engineering |