Learning by Observing: Case-Based Decision Making in Complex Strategy Games

2008 ◽  
pp. 284-291
Author(s):  
Darko Obradovič ◽  
Armin Stahl
Keyword(s):  
Decision Making ◽  
Strategy Games ◽  
Case Based

scholarly journals A top-level model of case-based argumentation for explanation: Formalisation and experiments

2021 ◽  
pp. 1-36
Author(s):  
Henry Prakken ◽  
Rosa Ratsma
Keyword(s):  
Machine Learning ◽  
Decision Making ◽  
Linear Models ◽  
Evaluation Studies ◽  
Data Sets ◽  
Machine Learning Applications ◽  
Level Model ◽  
Similarities And Differences ◽  
Further Development ◽  
Case Based

This paper proposes a formal top-level model of explaining the outputs of machine-learning-based decision-making applications and evaluates it experimentally with three data sets. The model draws on AI & law research on argumentation with cases, which models how lawyers draw analogies to past cases and discuss their relevant similarities and differences in terms of relevant factors and dimensions in the problem domain. A case-based approach is natural since the input data of machine-learning applications can be seen as cases. While the approach is motivated by legal decision making, it also applies to other kinds of decision making, such as commercial decisions about loan applications or employee hiring, as long as the outcome is binary and the input conforms to this paper’s factor- or dimension format. The model is top-level in that it can be extended with more refined accounts of similarities and differences between cases. It is shown to overcome several limitations of similar argumentation-based explanation models, which only have binary features and do not represent the tendency of features towards particular outcomes. The results of the experimental evaluation studies indicate that the model may be feasible in practice, but that further development and experimentation is needed to confirm its usefulness as an explanation model. Main challenges here are selecting from a large number of possible explanations, reducing the number of features in the explanations and adding more meaningful information to them. It also remains to be investigated how suitable our approach is for explaining non-linear models.

Added Value of Ontologies for Modeling an Organizational Memory

2010 ◽  
pp. 127-147 ◽  
Author(s):  
Maria de los Angeles Martin ◽  
Luis Olsina
Keyword(s):  
Decision Making ◽  
Knowledge Management ◽  
Knowledge Exchange ◽  
Automatic Processing ◽  
Organizational Knowledge ◽  
Organizational Memory ◽  
Added Value ◽  
Practical Case ◽  
High Level ◽  
Case Based

With the aim to manage and retrieve the organizational knowledge, in the last years numerous proposals of models and tools for knowledge management and knowledge representation have arisen. However, most of them store knowledge in a non-structured or semi-structured way, hindering the semantic and automatic processing of this knowledge. In this chapter the authors specify a case-based organizational memory ontology, which aims at contributing to the design of an organizational memory based on cases so that it can be used to support better decision-making. One ontology goal is to serve as a base for the organizational knowledge exchange with semantic power, which can facilitate the reuse, interoperability, and automatic processing by agents. In addition, the ontology aims to be at a high level from which other more specific representations can be formulated. In order to illustrate its utility a practical case is shown.

A case-based reasoning system for fault detection and isolation: a case study on complex gearboxes

2019 ◽  
Vol 25 (2) ◽  
pp. 213-235 ◽  
Author(s):  
Soumava Boral ◽  
Sanjay Kumar Chaturvedi ◽  
V.N.A. Naikan
Keyword(s):  
Decision Making ◽  
Fault Detection ◽  
Large Scale ◽  
Fault Detection And Isolation ◽  
Decision Making Process ◽  
Case Based Reasoning ◽  
Content Type ◽  
Complex Decision Making ◽  
Complex Decision ◽  
Case Based

Purpose Usually, the machinery in process plants is exposed to harsh and uncontrolled environmental conditions. Even after taking different types of preventive measures to detect and isolate the faults at the earliest possible opportunity becomes a complex decision-making process that often requires experts’ opinions and judicious decisions. The purpose of this paper is to propose a framework to detect, isolate and to suggest appropriate maintenance tasks for large-scale complex machinery (i.e. gearboxes of steel processing plant) in a simplified and structured manner by utilizing the prior fault histories available with the organization in conjunction with case-based reasoning (CBR) approach. It is also demonstrated that the proposed framework can easily be implemented by using today’s graphical user interface enabled tools such as Microsoft Visual Basic and similar. Design/methodology/approach CBR, an amalgamated domain of artificial intelligence and human cognitive process, has been applied to carry out the task of fault detection and isolation (FDI). Findings The equipment failure history and actions taken along with the pertinent health indicators are sufficient to detect and isolate the existing fault(s) and to suggest proper maintenance actions to minimize associated losses. The complex decision-making process of maintaining such equipment can exploit the principle of CBR and overcome the limitations of the techniques such as artificial neural networks and expert systems. The proposed CBR-based framework is able to provide inference with minimum or even with some missing information to take appropriate actions. This proposed framework would alleviate from the frequent requirement of expert’s interventions and in-depth knowledge of various analysis techniques expected to be known to process engineers. Originality/value The CBR approach has demonstrated its usefulness in many areas of practical applications. The authors perceive its application potentiality to FDI with suggested maintenance actions to alleviate an end-user from the frequent requirement of an expert for diagnosis or inference. The proposed framework can serve as a useful tool/aid to the process engineers to detect and isolate the fault of large-scale complex machinery with suggested actions in a simplified way.

Sign in / Sign up

Export Citation Format

Share Document