Many conflicting issues exist between product design and manufacturing department. In the early design stage, designers often do not have enough expertise to successfully address all these issues. This results in a product design with a low level of assemblability and manufacturability. Hence, an intelligent decision support system is needed for early design stages to improve a design. This paper proposed a web-based intelligent decision support system, CBR-DFMA, connecting with a case base, database and knowledge base. Early experimental results indicate that potential design problems can be detected in advance, design expertise can be effectively disseminated and effective training is offered to designer by employing this system.

Robot selection is one of critical decisions in the design of robotic workcells. Over the last ten years, many Case-Based Reasoning (CBR) systems have been developed to solve decision making problems successfully. We propose to develop three sort systems: browsing systems, preference-based selection organizers, and alternative suggestion agents. All four stages of the CBR cycle are designed to assist robotic application designers to go through robot selection and decision-making. A case-based reasoning approach is employed to solve new robot selection decision problems by adapting solutions that were used to solve previous robot selection problems. In this study, CBR has shown that it has several advantages over other techniques. The results of this study will help robot workcell designers to develop a more efficient and effective method to select robots for specific robot applications.

<p>This dissertation consists of three interrelated articles about supporting instructors to develop their facilitation skills both on the instructional and emotional sides during online case-based discussions. In the first study, we examined the influence of instructors with varying levels of experience on student participation and interaction in online case discussions. Findings showed that while both expert and novice instructors utilized facilitation strategies in clusters to facilitate discussions, the novice instructor displayed less flexibility as a facilitator, and these differences impacted student activeness. Our second study explored experts’ teaching practices, such as structuring, facilitating, and assessing online case discussions, and the reasons behind their decisions. We found that the experts clustered strategies during online case discussions while maintaining differences in how they implemented them. There was practical guidance provided for novice instructors that could be adapted to meet their own needs. Using a learning experience design lens, the last paper conceptually discussed opportunities for facilitating students’ emotions during online case discussions and offered suggestions that instructors can incorporate into the planning, implementation, and evaluation phases.</p>

Preconstruction services play a vital role in ensuring timely approval of infrastructure funds and successful execution of construction projects. Most state DOTs use simple methods such as a percentage of estimated construction costs that has proven to be unreliable. Several studies have developed statistical models using historical data to improve current practices. However, such models have performed poorly, and practitioners have not utilized these models. This study develops and evaluates data mining models such as multiple regression and artificial neural networks and concludes that such models do not provide sufficiently accurate estimates of preconstruction service fees and hours. Subsequently, it proposes an alternative approach using a case-based reasoning (CBR) technique that uses similarity scoring to retrieve the most similar projects. The historical preconstruction service fees and hours of similar projects can be used to estimate preconstruction service fees and hours for a new project and make any adjustment necessary. A spreadsheet tool is developed to implement this CBR technique. The tool provides a simple and flexible platform that enables engineers to extract necessary data and help them in making data-driven estimates. Thus, the tool is expected to aid state DOT engineers in negotiating with consultants with higher confidence.

The following report is a description of the design, development, and evaluation of an online statistics performance support system. The target audience for the support system is students of Instructional Psychology and Technology (IP&T), especially those who have taken the IP&T 550 "Empirical Inquiry and Statistics" course. The product is designed to be used as a supplemental reference tool. The main purpose of the online performance support system is to help IP&T students select appropriate statistical procedures for their research and learn how to perform the necessary calculations using a statistics analysis software package called SPSS. This report summarizes the needs analysis, target audience analysis, instructional design process and the formative evaluation of the product. The results of the evaluation indicated that the users found great value in the product, that it was useful and effective in helping them select an appropriate statistical procedure, and that it helped them conduct the procedure in SPSS.

No description available.

Developing a head and neck cancer treatment plan for a candidate of Intensity Modulated Radiation Therapy (IMRT) requires extensive domain knowledge and subjective experience. Therefore, it takes a cancer treatment team at least 2 to 3 days to develop such a plan from scratch. Many times the team may not use a reference plan. Sometimes, to reduce the amount of time taken to generate each treatment plan, these experts recall a patient, whose plan they recently prepared, and who had similar symptoms as the candidate. Using this recalled patient's plan as the starting point, the cancer treatment team modifies it based on the differences in the symptoms of the new candidate and those of the reference patient record. The resultant plan after modification is presented as the new treatment plan for the oncologist to evaluate its suitability for treatment of the candidate. This approach is heavily dependent on the team's choice of the reference patient record. Choosing a starting treatment plan where the patient's symptoms are not the closest to the new candidate implies that more time will be spent modifying the plan than is necessary and the resultant treatment plan may not be the best achievable under the same circumstances given a better starting plan. Therefore, the team's bias in choosing the starting plan may affect the quality of treatment plan that is finally produced for the candidate. This thesis proposes a system that behaves like an un-biased radiotherapy expert - following a similar process and standards as the human experts and which searches the entire IMRT patient database and returns the record (with patient symptoms and treatment plan) for a patient whose symptoms are most similar to the candidate's symptoms. It takes in the new candidate's information (from diagnosis, scans of the tumor and interviews with the candidate), searches the database and prints out a patient record showing another patient's treatment plan as the suggested starting point for generating the new plan. The system uses Case-Based Reasoning (CBR) because it mimics the experts' approach since it makes use of previous successes and shuns reasoning that has failed in the past. This occurs by considering only treatment plans that have been implemented successfully on patients in the hospital archive. For this thesis, CBR is applied using fuzzy IF-THEN rules to search the patient database. Fuzzy logic is used because it can handle imprecise expressions commonly used in natural language to determine the appropriate weight of the patient attributes in the search process. Filtering of patient records based on parameter value ranges is also used to reduce the number of records that have to be compared. The system code developed for this thesis was prepared in Java and C Language Integrated Production System (CLIPS) using the Java Expert System Shell (JESS). This system is part of a bigger expert system that is being prepared by the Intelligent Systems Applications Center (ISAC) for Thomas Jefferson University Hospital, expected to generate a radiotherapy plan for a patient designated for IMRT treatment. Initial results from the developed prototype prove the viability of selecting similar patients using CBR. It is important to note that the overall objective of the project is to build a system that effectively aids decision support by the IMRT team when generating a new treatment plan and not to replace them. The team is expected to use the generated plan as a starting point in determining a new treatment plan. If the generated plan is sufficient, the oncologist and their team will have to check this plan (in their various capacities) against expected standards for quality control before passing it on for implementation. This will save them time in planning and allow them to focus more on the patient's needs hence a higher quality of life for the patient after treatment. / Electrical and Computer Engineering

Yes / Case-based reasoning (CBR) is a nature inspired paradigm of machine learning capable to continuously learn from the past experience. Each newly solved problem and its corresponding solution is retained in its central knowledge repository called case-base. Withρ the regular use of the CBR system, the case-base cardinality keeps on growing. It results into performance bottleneck as the number of comparisons of each new problem with the existing problems also increases with the case-base growth. To address this performance bottleneck, different case-base maintenance (CBM) strategies are used so that the growth of the case-base is controlled without compromising on the utility of knowledge maintained in the case-base. This research work presents a hybrid case-base maintenance approach which equally utilizes the benefits of case addition as well as case deletion strategies to maintain the case-base in online and offline modes respectively. The proposed maintenance method has been evaluated using a simulated model of autonomic forest fire application and its performance has been compared with the existing approaches on a large case-base of the simulated case study. / Authors acknowledge the internal funding support received from Namal College Mianwali to complete the research work.

No / Case-Based Reasoning systems retrieve and reuse solutions for previously solved problems that have been encountered and remembered as cases. In some domains, particularly where the problem solving is a classification task, the retrieved solution can be reused directly. But for design tasks it is common for the retrieved solution to be regarded as an initial solution that should be refined to reflect the differences between the new and retrieved problems. The acquisition of adaptation knowledge to achieve this refinement can be demanding, despite the fact that the knowledge source of stored cases captures a substantial part of the problem-solving expertise. This paper describes an introspective learning approach where the case knowledge itself provides a source from which training data for the adaptation task can be assembled. Different learning algorithms are explored and the effect of the learned adaptations is demonstrated for a demanding component-based pharmaceutical design task, tablet formulation. The evaluation highlights the incremental nature of adaptation as a further reasoning step after nearest-neighbour retrieval. A new property-based classification to adapt symbolic values is proposed, and an ensemble of these property-based adaptation classifiers has been particularly successful for the most difficult of the symbolic adaptation tasks in tablet formulation.

Face à l’évolution technologique rapide des produits, l’innovation incrémentale des nouveaux produits, et la mobilité du personnel le plus expérimenté, les entreprises cherchent à formaliser et à capitaliser leurs expériences et les savoir-faire des acteurs d’entreprise en vue d’une réutilisation ultérieure. Afin de répondre à cette problématique, l’approche du raisonnement à partir de cas conversationnel (RàPCC) est une réponse potentielle à la question de la capitalisation et de la réutilisation des connaissances. Notre recherche s’intéresse aux méthodes permettant de piloter le retour d’expérience (RETEX) appliqué à la résolution de problèmes techniques. Notre méthodologie pour créer un système d’aide au diagnostic des pannes est divisée en quatre phases : la description d’événements, l’élaboration de l’ensemble des solutions apportées aux pannes, la mise en place d’une aide au diagnostic grâce aux arbres de défaillances et la mise en place d’un système informatique. Afin d’extraire les connaissances tacites et les formaliser, nous avons créé des protocoles de décision dans le but d’aider l’expert à résoudre un problème industriel. Nous avons donc proposé une formulation et l’élaboration de cas conversationnels dans le domaine du diagnostic. Ces cas doivent être stockés dans une base de cas. Afin de valider notre proposition méthodologique, nous avons réalisé la phase expérimentale dans une entreprise industrielle de l’Est de la France. Nous proposons finalement une maquette informatique conçue pour l’entreprise. Cette maquette permet de réaliser un diagnostic des pannes en créant des cas dans une base de cas pour une réutilisation ultérieure / Faced with the fast technological development of products, incremental innovation of new products, and the mobility of their most experienced staff, companies are seeking to formalize and capitalize on the experiences and know-how of their personnel in order to reuse them later. To deal with these problems, the conversational case based reasoning (CCBR) approach is a potential answer to the question of capitalization and reuse of knowledge. Our research focuses on methods to manage experience feedback (EF). We are placed in the field of experience feedback applied to technical problem solving. Our methodology for creating aided failure diagnosis systems is divided into four phases: the events description, the development of all solutions to failures, the arrangement of a diagnostic aid through fault trees and setting up a computer system. We based our work on the fault tree approach in order to extract tacit knowledge and its formalization. Our objective was to create decision protocols in order to assist the expert in solving an industrial problem. Therefore, we have proposed a formulation and development of conversational cases in diagnosis. These cases must be memorised in a database of cases. To validate our proposal methodology, we have carried out the experimental phase in an industrial company in eastern France. This experiment allowed us to validate our work and highlight its advantages and limitations. Finally, we propose a computer model designed for the company. This model enables failure diagnosis by creating the case in a case base for later utilization