Recursive approach to combine expert knowledge and data-driven RSW weldability certification decision making process
نویسندگان
چکیده
• Recursive and collaborative approach where knowledge gained from machine learning models is integrated with ontological knowledge. Ontology-based semantic framework supports recursive communication experts for data-driven RST weldability certification. Extracted RSW concepts the decision trees formalized by ontology converted rules into SWRL rules. Transformed datasets helped to develop improved that work as a new source of prediction. Data-driven techniques have shown promising results in analysis understanding complex welding processes. Data analytics play significant role turn data valuable insights assist certification decision-making Resistance Spot Welding (RSW) well. However, successfully perform associated analytics, domain essential construct more ‘sense-making’ models, often cannot properly capture nuances do not indicate relationship among parameters. Thus, developed rough experimental provide meaningful sensible expert. In this article, we employ between so can be process. An ontology-based while helping instil confidence models. The implemented study helps tap their form expert opinions using are then used learn about transform incorporating features were included earlier transformed help us which knowledge, discovered through our pilot implementation.
منابع مشابه
Making Decision Process Knowledge Explicit Using the Decision Data Model
In this paper we present an approach for mining decisions. We show that through the use of a Decision Data Model (DDM) we can make explicit the knowledge employed in decision making. We use the DDM to provide insights into the data view of a business decision process. To support our claim we introduce our complete, functional decision mining approach. First, a ‘decisionaware system’ introduces ...
متن کاملMaking Ontology-Based Knowledge and Decision Trees Interact: An Approach to Enrich Knowledge and Increase Expert Confidence in Data-Driven Models
When using data-driven models to make simulations and predictions in experimental sciences, it is essential for the domain expert to be confident about the predicted values. Increasing this confidence can be done by using interpretable models, so that the expert can follow the model reasoning pattern, and by integrating expert knowledge to the model itself. New pieces of useful formalised knowl...
متن کاملImproving Data-Driven Decision Making through Human-centered Knowledge Sharing
This research focuses on human-centered knowledge sharing within data-driven decision making processes enabled by advanced analytics. The paper describes an exploratory study of an innovative approach to ongoing improvement of complex data-driven decision making processes found in a large retail distribution company by considering a complex interplay of business intelligence (BI) /business anal...
متن کاملExpert knowledge and decision-making in controversy contexts
There was a time when the mobilization of experts was a taken-for-prated. unproblematic aspect of decision-making processes. That confidence has vanished. Ascertaining the significance of expertise now requires a reconsideration of the dynamics of controversies. The current view still assimilates conlroversy to the medieval exercise of the disputatio in which two parties argue one against the o...
متن کاملAggregating and Weighting Expert Knowledge in Group Decision Making
In this paper, we proposed a methodology based on group decision making for aggregating and weighting expert knowledge or opinions and identifying the final agreement for a group of experts. We use a case study on causes of Alzheimer’s Disease (AD) for an illustration of the procedural steps in the proposed methodology. We begin by mapping nine most commonly discussed possible causes or risk fa...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Robotics and Computer-integrated Manufacturing
سال: 2023
ISSN: ['1879-2537', '0736-5845']
DOI: https://doi.org/10.1016/j.rcim.2022.102428