CEVM: Constrained Evidential Vocabulary Maintenance Policy for CBR Systems

Adaptive semi-supervised dimensionality reduction with sparse representation using pairwise constraints

Medical case-based reasoning (CBR) systems require the handling of vague or imprecise data. The fuzzy set theory is particularly suitable for this purpose. This paper proposes a case-base preparation framework for CBR systems, which converts the electronic health record medical data into fuzzy CBR knowledge. It generates fuzzy case-base knowledge by suggesting a standard crisp entity–relationship data model for CBR case-base. The resulting data model is fuzzified using a proposed relational data model fuzzification methodology. The performances of this methodology and its resulting fuzzy case-base structure are evaluated. Diabetes diagnosis is used as a case study. A set of 60 real diabetic cases is used in the study. A fuzzy CBR system is implemented to check the diagnoses accuracy. It combines the resulting fuzzy case-base with a proposed fuzzy similarity measure. Experimental results indicate that the proposed fuzzy CBR method is superior to traditional CBR and other machine-learning methods. Our fuzzy CBR achieves an accuracy of 95%, a precision of 96%, a recall 97.96%, an f-measure of 96.97%, a specificity of 81.82%, and good robustness for dealing with vagueness. The resulting fuzzy case-base relational database enhances the representation of case-base knowledge, the performance of retrieval algorithms, and the querying capabilities of CBR systems.

By design, Case-Based Reasoning (CBR) systems do not need deep general knowledge. In contrast to (rule-based) expert systems, CBR systems can already be used with just some initial knowledge. Further knowledge can then be added manually or learned over time. CBR systems are not addressing a special group of users. Expert systems, on the other hand, are intended to solve problems similar to human experts. Because of the complexity and difficulty of building and using expert systems, research in this area addressed generating explanations right from the beginning. But for knowledge-intensive CBR applications, the demand for explanations is also growing. This paper is a first pass on examining issues concerning explanations produced by CBR systems from the knowledge containers perspective. It discusses what naturally can be explained by each of the four knowledge containers (vocabulary, similarity measures, adaptation knowledge, and case base) in relation to scientific, conceptual, and cognitive explanations.

The retrieval-only Case-Based Reasoning (CBR) systems do not provide acceptable accuracy in critical domains such as medical. Besides, the case adaptation process in CBR is often a challenging issue as it has been traditionally carried out manually by domain experts. In this paper, a new case-based approach using transformational adaptation rules called "range adaptation rules" is proposed to improve the accuracy of a retrieval-only CBR system. The rangeadaptation rules are automatically generated from the case-base. In this approach, after solving each new problem, the case-base is expanded and the range adaptation rules are updated automatically. To evaluate the proposed approach, a prototype is implemented and experimented in agriculture domain to classify the IRIS plant types. The experimental results show that the proposed approach increases the classification accuracy comparing with the retrieval-only CBR system.KeywordsCase-based reasoning (CBR)Case adaptationIRIS plant classificationRange adaptation rules

Several artificial intelligence approaches, particularly case-based reasoning (CBR), which is analogous to the context of human reasoning for problem resolution, have demonstrated their efficiency and reliability in the medical field. In recent years, deep learning represents the latest iteration of an advance in artificial intelligence technologies in medicine to aid in data classification, diagnosis of new diseases, and complex decision-making. Although these two independent approaches have good results in the medical field, the latter is still a complex field. This chapter reviews the available literature on CBR systems, deep learning systems, and CBR deep learning systems in medicine. The methods used and results obtained are discussed, and key findings are highlighted. Further, in the light of this review, some directions for future research are given. This chapter presents the proposed approach, which helps to make the retrieval phase of the CBR cycle more reliable and robust.

The knowledge stored in a case base is central to the problem solving of a case‐based reasoning (CBR) system. Therefore, case‐base maintenance is a key component of maintaining a CBR system. However, other knowledge sources, such as indexing and similarity knowledge for improved case retrieval, also play an important role in CBR problem solving. For many CBR applications, the refinement of this retrieval knowledge is a necessary component of CBR maintenance. This article focuses on optimization of the parameters and feature selections/weights for the indexing and nearest‐neighbor algorithms used by CBR retrieval. Optimization is applied after case‐base maintenance and refines the CBR retrieval to reflect changes that have occurred to cases in the case base. The optimization process is generic and automatic, using knowledge contained in the cases. In this article we demonstrate its effectiveness on a real tablet formulation application in two maintenance scenarios. One scenario, a growing case base, is provided by two snapshots of a formulation database. A change in the company's formulation policy results in a second, more fundamental requirement for CBR maintenance. We show that after case‐base maintenance, the CBR system did indeed benefit from also refining the retrieval knowledge. We believe that existing CBR shells would benefit from including an option to automatically optimize the retrieval process.

This paper shows how humans and machines can better collaborate to acquire adaptation knowledge (AK) in the framework of a case-based reasoning (CBR) system whose knowledge is encoded in a semantic wiki. Automatic processes like the CBR reasoning process itself, or specific tools for acquiring AK are integrated as wiki extensions. These tools and processes are combined on purpose to collect AK. Users are at the center of our approach, as they are in a classical wiki, but they will now benefit from automatic tools for helping them to feed the wiki. In particular, the CBR system, which is currently only a consumer for the knowledge encoded in the semantic wiki, will also be used for producing knowledge for the wiki. A use case in the domain of cooking is given to exemplify the man-machine collaboration.

In this paper, we propose a hybrid case-based reasoning (CBR) system for predicting the construction cost of high-rise buildings at the preliminary design stage. First, the extracted cost factors (CFs) of a high-rise building were shown to significantly improve the cost estimation system’s performance. For developing a CBR system, a hybrid approach that combines CBR with genetic algorithms (GAs) for cost estimation was adopted. Genetic algorithms were used for optimized weight generation and applied to real project cases. Additionally, this paper proposes the identification of an alternative similarity score measurement formula. The proposed formula evaluates the contrast between the alternative case matching approach and the classical formula in a scenario involving the use of cost factors describing a case. The results indicate that the proposed GA-based CBR system can consistently reduce errors and potentially be useful to owners and contractors in the early financial planning stage. Accordingly, it is expected that the developed CBR system would provide decision-makers with accurate cost information to assess and compare multiple alternatives for obtaining the optimal solution and controlling the cost.

Case revising is a crucial but difficult step in case-based reasoning (CBR) system. In this paper, the case revising rule, gained by applying intelligent retrieving method, is to help decision maker revise the casepsilas scheme. Generally it consists of secondary revising rules and primary revising rules. Firstly the rough set theory is applied to get the Secondary Revising Rules. Secondly, with the case revising transactions set obtained from decision makers as reference, the association rules mining method is employed to get the Primary Case Revising Rules. Lastly, by combining the two types of rules, the author expounds the detailed case Revising procedure.

Academic advising is a repetitive, time-consuming, and tedious job. In providing academic recommendations, an academic advisor applies three forms of knowledge i.e. formal knowledge, and Formal knowledge is the knowledge about the curriculum as given in the university and department catalogs. The expert knowledge is gained by training and experience. The case-based knowledge is obtained from the accumulated academic cases in the department. The best choice to eliminate the disadvantages of manual academic advising is to automate it. The key to automation lies in the effective application of the computer science field called artificial intelligence (AI).It was therefore considered by the Mechanical Engineering Department at the University of Queensland that a new framework for an Academic Advisory System (AAS) should be developed as the topic of this PhD. This thesis also develops and demonstrates a prototype based on the new framework. The AAS is an integrated system consisting of an Academic Database Management System (ADBMS), an Expert System (ES) based on decision tables, and a Case Based Reasoning System (CBRS). The ES deals with adviser's formal knowledge and expert knowledge, while the CBRS deals with adviser's case-based knowledge. The ADBMS is used to manage large and diverse academic data such as schedules, time tables, and hundreds of students' records and also to prepare input data for the ES and the CBRS.A new framework of the development of a Case Based Reasoning System (CBRS) using the relational model and extending the case based reasoning techniques by combining CBR with GT coding system, fuzzy sets, and rule base has been developed. GT coding system plays the main role as the foundation of the knowledge representation. Fuzzy sets contribute by making the case retrieval more flexible; and rules provide an easy strategy for case adaptation.To test the approach, prototypes of the AAS and the CBRS have been developed. They are PC based and run under Microsoft Windows and were developed using the relational database packages Paradox for Windows and Microsoft Access. The prototypes demonstrates the general techniques needed for academic advising and has been tested to the specific application of advice within the Department of Mechanical Engineering, at The University of Queensland, Australia and the Department of Mechanical Engineering, at The University of Brawijaya, Indonesia.

This article addresses the task of mining for cases from biomedical literature to automatically build an initial case base for a case-based reasoning (CBR) system. This research takes place within the Memoire project, which has for goal to provide a framework to facilitate building CBR systems in biology and medicine. By analyzing medical literature, the ProCaseMiner system mines for medical concepts such as diseases, signs and symptoms, laboratory tests, and treatment plans in relationship with one another, and connects them together in a given medical domain. It then organizes these concepts in a higher-level structure called a case. This case mining component provides a definite help to bootstrap the creation of a biomedical CBR system case base, composed of both concrete cases and prototypical cases. Currently, most cases learnt correspond to prototypical cases, given the level of abstraction of their features. This article validates the approach by presenting a comparison between the prototypical cases learnt from stem-cell transplantation domain with those created by a team of experts in the domain.

While in standard clustering no side information is used, users might be interested in providing additional information to influence the clustering. In case of document clustering, additional information can take the form of pairwise constraints where a user provides additional information about pairs of documents as must-link and cannot-link constraints (indicating respectively whether the documents in the pair are coming from the same cluster or not). In this paper, we propose a novel deep document clustering framework which can employ pairwise constraints while learning document representations to obtain better tailored results. Indeed, in our proposed framework, data representations (obtained through an autoencoder) and cluster representatives are learned through back propagation in a joint way. Devising a fully differentiable deep clustering framework with the ability of using pairwise constraints is the main contribution of this paper. Experiments conducted on 5 public datasets show the gain in clustering performance which the resulting approach can yield.

Case-based reasoning (CBR) infers a solution to a new problem by searching a collection of previously solved problems for cases which are similar to the new problem. The collection of previous problems and their associated solutions represents the CBR system's realm of expertise. A CBR system helps to exploit data so that smarter decisions can be made in less time and/or at lower cost. A key issue is that can we always trust the solutions suggested by a case-based reasoning system? This paper studies the reliability of CBR systems based on previous study results, factors affecting the reliability of a CBR system are also discussed in this paper, especially the property that whether inter-feature of case exists redundancy. After that, the reliability of an individual suggested solution is studied. To illustrate these ideas, some experiments and their results are discussed in this paper. The results of experiments show a new route concerning on how to improve the reliability of a CBR system at an overall level.

A key benefit of case-based reasoning (CBR) and recommender systems is the use of past experience to guide the synthesis or selection of the best solution for a specific context or user. Typically, the solution presented to the user is based on a value system that privileges the closest match in a query and the solution that performs best when evaluated according to predefined requirements. In domains in which creativity is desirable or the user is engaged in a learning activity, there is a benefit to moving beyond the expected or “best match” and include results based on computational models of novelty and surprise. In this paper, models of novelty and surprise are integrated with both CBR and Recommender Systems to encourage user curiosity.

A hybrid control system with Case Based Reasoning (CBR) procedure is considered. It is intended for complex industrial plants in abnormal and fault situations where the conventional control systems cannot work autonomously. CBR systems allow capture and use a specific experience by Case Base (CB) creation, similarity assessment, case adaptation and learning new cases. Some new results are incorporated into the traditional CBR cycle, relevant to control tasks - uncertainty, presence of multivariant solutions from different operators, rational distribution of knowledge among autonomous agents, ontologies and CBR-system. Simulation results are represented for an industrial plant with a non-square matrix.