Study of Case-Based Reasoning System

Study of Case-Based Reasoning System Shilpa Dahiya ${ }^{1}$ Mohita Gupta Lecturer ${ }^{2}$
${ }^{2}$ Lecturer
${ }^{1,2}$ Department of Computer Science & Engineering
${ }^{1,2}$ SKIET Kurukshetra University, Kurukshetra, Haryana, India

Abstract

Case-Based Reasoning is a problem solving paradigm that in many respects is fundamentally different from other major AI approaches. Instead of relying solely on general knowledge of a problem domain, or making associations along generalized relationships between problem descriptors and conclusions, CBR is able to utilize the specific knowledge of previously experienced, concrete problem situations (cases). A new problem is solved by finding a similar past case, and reusing it in the new problem situation. A second important difference is that CBR also is an approach to incremental, sustained learning, since a new experience is retained each time a problem has been solved, making it immediately available for future problems. The CBR field has grown rapidly over the last few years, as seen by its increased share of papers at major conferences, available commercial tools, and successful applications in daily use. A CBR tool should support the four main processes of CBR: retrieval, reuse, revision and retention.

Key words: CBR, Retrieve, Reuse, Revision, Retention, Learning

I. INTRODUCTION

Case-based reasoning is a problem solving paradigm that instead of relying solely on general knowledge of a problem domain, or making associations along generalized relationships between problem descriptors and conclusions, CBR is able to utilize the specific knowledge of previously experienced, concrete problem situations (cases). A new problem is solved by finding a similar past case, and reusing it in the new problem situation. A second important difference is that CBR also is an approach to incremental, sustained learning, since a new experience is retained each time a problem has been solved, making it immediately available for future problems. The CBR field has grown rapidly over the last few years, as seen by its increased share of papers at major conferences, available commercial tools, and successful applications in daily use.
The description of CBR principles, methods, and systems is made within a general analytic scheme. To solve a new problem, the CBR remembers previous similar situation and reuses information and knowledge of that situation. Let us illustrate this by looking at some typical problem solving situations:

• A physician - after having examined a particular patient in his office - gets a reminding to a patient that he treated two weeks ago. Assuming that the reminding was caused by a similarity of important symptoms, the physician uses the diagnosis and treatment of the previous patient to determine the disease and treatment for the patient in front of him.
• A drilling engineer, who have experienced two dramatic blow out situations, is quickly reminded of one of these situations (or both) when the combination of critical measurements matches those of a blow out case. In particular, he may get a reminding to a mistake he made during a previous blow-out, and use this to avoid repeating the error once again.

II. CASE-BASED PROBLEM SOLVING

As the above examples indicate, reasoning by re-using past cases is a powerful and frequently applied way to solve problems for humans. This claim is also supported by results from cognitive psychological research. Part of the foundation for the case-based approach, is its psychological plausibility. Several studies have given empirical evidence for the dominating role of specific, previously experienced situations (what we call cases) in human problem solving.

In CBR terminology, a case usually denotes a problem situation. A previously experienced situation, which has been captured and learned in a way that it can be reused in the solving of future problems, is referred to as a past case, previous case, stored case, or retained case. Correspondingly, a new case or unsolved case is the description of a new problem to be solved. Case-based reasoning is - in effect - a cyclic and integrated process of solving a problem, learning from this experience, solving a new problem, etc.

The term problem solving is used here in a wide sense, coherent with common practice within the area of knowledge-based systems in general. This means that problem solving is not necessarily the finding of a concrete solution to an application problem, it may be any problem put forth by the user. For example, to justify or criticize a solution proposed by the user, to interpret a problem situation, to generate a set of possible solutions, or generate expectations in observable data are also problem solving situations.

III. LEARNING IN CASE-BASED REASONING

A very important feature of case-based reasoning is its coupling to learning. The driving force behind case-based methods has to a large extent come from the machine learning community, and case-based reasoning is also regarded a subfield of machine learning. Thus, the notion of case-based reasoning does not only denote a particular reasoning method, irrespective of how the cases are acquired, it also denotes a machine learning paradigm that enables sustained learning by updating the case base after a problem has been solved. Learning in CBR occurs as a natural byproduct of problem solving. When a problem is successfully solved, the experience is retained in order to solve similar problems in the future. When an attempt to solve a problem fails, the reason for the failure is identified

and remembered in order to avoid the same mistake in the future.

Case-based reasoning favours learning from experience, since it is usually easier to learn by retaining a concrete problem solving experience than to generalize from it. Still, effective learning in CBR requires a well worked out set of methods in order to extract relevant knowledge from the experience, integrate a case into an existing knowledge structure, and index the case for later matching with similar cases.

IV. CBR CYCLE

At the highest level of generality, a general CBR cycle may be described by the following four Processes:
(1) RETRIEVE the most similar case or cases.
(2) REUSE the information and knowledge in that case to solve the problem.
(3) REVISE the proposed solution.
(4) RETAIN the parts of this experience likely to be useful for future problem solving
A new problem is solved by retrieving one or more previously experienced cases, reusing the case in one way or another, revising the solution based on reusing a previous case, and retaining the new experience by incorporating it into the existing knowledge-base (case-base). The four processes each involve a number of more specific steps, which will be described in the task model. In figure 1 this cycle is illustrated.

Fig. 1: The CBR Cycle
An initial description of a problem (top of figure) defines a new case.

• This new case is used to RETRIEVE a case from the collection of previous cases.
• The retrieved case is combined with the new case through REUSE - into a solved case, i.e. a proposed solution to the initial problem.
• Through the REVISE process this solution is tested for success, e.g. by being applied to the real world environment or evaluated by a teacher, and repaired if failed.
• During RETAIN, useful experience is retained for future reuse, and the case base is updated by a new

learned case, or by modification of some existing cases.
As indicated in the figure, general knowledge usually plays a part in this cycle, by supporting the CBR processes. This support may range from very weak (or none) to very strong, depending on the type of CBR method [5]. By general knowledge we here mean general domaindependent knowledge, as opposed to specific knowledge embodied by cases. For example, in diagnosing a patient by retrieving and reusing the case of a previous patient, a model of anatomy together with causal relationships between pathological states may constitute the general knowledge used by a CBR system. A set of rules may have the same role.

V. ADVANTAGES OF CASE-BASED REASONING

Case-based reasoning is often used where experts find it hard to articulate their thought processes when solving problems. This is because knowledge acquisition for a classical KBS would be extremely difficult in such domains, and is likely to produce incomplete or inaccurate results. When using case-based reasoning, the need for knowledge acquisition can be limited to establishing how to characterise cases.

Case-based reasoning allows the case-base to be developed incrementally, while maintenance of the case library is relatively easy and can be carried out by domain experts. It has following advantages as given below:
(1) Case-based reasoning allows the reasoner to propose solutions to problems quickly, avoiding the time necessary to derive those answers from scratch
(2) Case-based reasoning allows a reasoner to propose solutions in domains that are not completely understood by the reasoner
(3) Case-based reasoning gives a reasoner a means of evaluating solutions when no algorithmic method is available for evaluation
(4) Cases are useful in interpreting open-ended and ill-formed concepts
(5) Remembering previous experiences is particularly useful in warning of the potential for problems that have occurred in the past, alerting a reasoner to take actions to avoid repeating past mistakes
(6) Cases help a reasoner to focus its reasoning on important parts of a problem by pointing out what features of a problem are the important ones.

VI. DISADVANTAGES OF CASE-BASED REASONING

But it has following disadvantages as given below:
(1) A case-based reasoner might be tempted to use old cases blindly, relying on previous experience without validating it in the new situation
(2) A case-based reasoner might allow cases to bias it too much in solving a new problem
Often people, especially novices, are not reminded of the most appropriate sets of cases when they are reasoning.

VII. Related Work

Burke et al. (2006) presented a multiple-retrieval approach that partitioned a large problem into small solvable subproblems by recursively inputting the unsolved part of the graph into the decision tree for retrieval. The adaptation combined the retrieved partial solutions of all the partitioned sub-problems and employed a graph heuristic method to construct the whole solution for the new case. They presented a methodology which was not dependent upon problem specific information and which, as such, represented an approach which underpinned the goal of building more general timetabling systems. They also explored the question of whether this multiple-retrieval CBR could be an effective initialization method for local search methods such as Hill Climbing, Tabu Search and Simulated Annealing. Significant results were obtained from a wide range of experiments. An evaluation of the CBR system was presented and the impact of the approach on timetabling research was discussed. They saw that the approach did indeed represent an effective initialization method for these approaches.

Jiang et al. (2006) presented a novel methodology to apply fuzzy similarity-based Rough Set algorithm in feature weighting and reduction for CBR system. The algorithm was used in tool selection for die and mold NC machining. The proposed method did not need to discretize continuous or real-valued features included in cases, from which can effectively reduce information loss. The weight of feature ai is computed based on the difference of its dependency defined as $p$, which also represented the significance of the corresponding feature. If the difference is equal to 0 , the feature was considered to be redundant and should be removed. Finally, a case study is also implemented to prove the proposed method.

Gu et al. (2006) reviewed the current component retrieval methods and proposed our conversational component retrieval model (CCRM). In CCRM, components were represented as cases, a knowledgeintensive case-based reasoning (CBR) method was adopted to explore context-based semantic similarities between users" query and stored components, and a conversational case-based reasoning (CCBR) technology was selected to acquire users" requirements interactively and incrementally.

Pan et al. (2007) presented a novel algorithm for automatically mining a high-quality case base from a raw case set that could preserve and sometimes even improve the competence of case-based reasoning. In this paper, they analyzed two major problems in previous case-mining algorithms. The first problem was caused by noisy cases such that the nearest neighbor cases of a problem may not provide correct solutions. The second problem was caused by uneven case distribution, such that similar problems may have dissimilar solutions. To solve these problems, they developed a theoretical framework for the error bound in case-based reasoning, and proposed a novel case-base mining algorithm guided by the theoretical results that returned a high-quality case base from raw data efficiently. They supported their theory and algorithm with extensive empirical evaluation using different benchmark data sets.

Wang et al. (2007) presented a new cost estimation concept based on the case-based reasoning (CBR) approach
instead of a traditionally intuitive estimation method. In CBR model, two retrieval techniques, ‘Inductive Indexing’ and ‘Nearest Neighbor’, were then applied to retrieve relevant cases from the knowledge-based database. Two of the most common types of Taiwan historical buildings were tested to explore the restoration cost implications. The result revealed that the CBR solution could effectively predict the actual restoration cost, solve order change problems, and reduce the budget review time. These applications were also useful for many other countries, especially for those seismic belt regions, that were facing similar problems regarding historical building restoration.

Li et al. (2009) proposed new retrieval model of case-based reasoning (CBR) by integrating the classical mechanism of case retrieval, grey relational degree, and decision support system. Basic working flow of the new case retrieval model in CBR was firstly analyzed. On the precondition of multiple levels of management case structure, stratification retrieval strategy and delaminating structure of cases were then set up. On their basis, multilevel case retrieval and selection model in decision support system was finally constructed. In the retrieval model, layer similarity was employed to calculate the integrated similarity between a pair of cases. Grey relational degree was employed in the approach to improve performance of case retrieval. At last, multi-level case similarity of decision group could be reckoned. Empirical experiment results indicated that the new retrieval model achieved a little better performance than traditional models based on Manhattan distance and Euclidean distance.

Srisura et al. (2009) proposed how Case-Based Reasoning (CBR) - an approach solved new problem from recalling experiences, could be effectively applied to support the use case diagram reuse. In this research, the diagram retrieval method was designed to match the use case diagram by considering two dimensions: use case and actor dimension and relationship dimension. However, in order to present the significant accuracy and practicality of the proposed method, a tool and five comparative setsincluding four various dimensional weights and one commercial tool were carefully set up to test in an experiment.

Wang et al. (2010) focused on heuristics retrieval in human problem solving by combining computational cognitive modeling and neuroimaging. An event-related fMRI (functional Magnetic Resonance Imaging) experiment was conducted on a simplified Sudoku puzzle problem solving and an ACT-R (Adaptive Control of ThoughtRational) cognitive model was developed to simulate the information processing processes of heuristics retrieval to solve the problems. They assumed that when participants retrieve heuristics, they might conform to a principle of maximizing the information effectiveness and minimizing the cognitive cost. Based on the assumption, the model was built to predict both behavioral performance and neurophysiologic activities. Compared ACT-R predictions with fMRI results, the difference on response time was 0.287 and the average correlation of BOLD (Blood Oxygenation Level-Dependent) response between them was about 0.95 . The high fitness supported their assumption. This study showed that heuristics retrieving in human problem solving is an optimizing process in which

appropriate information is selected actively through visual selective attention based on goal-oriented to minimize the cost of time and energy. It might shed light on developing a new heuristic search model based on cognition for Web intelligence.

Bergmann et al. (2011) described a new model for representing semantic work-ows as semantically labeled graphs, together with a related model for knowledge intensive similarity measures. The application of this model to scientific and business work flows was discussed. Experimental evaluations showed that similarity measures could be modeled that were well aligned with manual similarity assessments. Further, new algorithms for workflow similarity computation based on $\mathrm{A}^{*}$ search are described. A new retrieval algorithm was introduced that goes beyond traditional sequential retrieval for graphs, interweaving similarity computation with case selection. Significant reductions on the overall retrieval time were demonstrated without sacrificing the correctness of the computed similarity

Yahia et al. (2011) combined fuzzy logic with case-based reasoning to identify useful cases that can support the DM. At the beginning, a fuzzy CBR based on both problems and actors’ similarities was advanced to measure usefulness of past cases. For efficiency, they needed an optimal design of membership functions of fuzzy sets. Then, they relied on a meta-heuristic optimization technique i.e. Particle Swarm Optimization to adjust the parameters of the inputs and output fuzzy membership functions.

Kim et al. (2013) proposed 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 combined 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 proposed the identification of an alternative similarity score measurement formula. The proposed formula evaluated 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 indicated that the proposed GA-based CBR system could consistently reduce errors and potentially be useful to owners and contractors in the early financial planning stage. Accordingly, it was 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.

VIII. CONCLUSION

It is still the theoretical and practical centre of case-based reasoning and CBR continues to be put forward as a model for human memory and reasoning. Although there is currently limited practical evidence, there is anecdotal evidence from knowledge engineers building CBR systems who state that experts and users seem comfortable with CBR. Originally, it was an area of research in AI that was exclusively the focus of academic research and was little
known by commercial AI developers. However, CBR emerged from the research labs as the new hot topic both for industry and academe with the development of commercial products addressing this area of reasoning.

REFERENCES

[1] J. Walston, Case-Based Reasoning in Agent-Based Decision Support System, ActaPolytechnicaHungarica, 4(1), pp. 127-138, 2007.
[2] Wang, C. A Conceptual Case Based Model Supporting ASME’S Strategic Supply Chain Decision. Proceeding of IET International Conference on Agile Manufacturing, ICAM 2007, pp. 189 - 196, 2007.
[3] Bozarth, C. C. & Handfi eld, R. B. (2008). Introduction to Operations and Supply Chain Management, (2nd ed.). U.S.A.: Pearson Education Inc.
[4] Hui Li and Jie Sun, “The Multi-Level Case Retrieval Model by Integrating Case-Based Reasoning, Grey Relational Degree and Decision Support System”, Tamkang Journal of Science and Engineering, Vol. 12, No. 2, pp. 135-142, 2009.
[5] B. Srisura, Dr. J. Daengdej, “Retrieving use case diagram with case-based Reasoning approach”, Journal of Theoretical and Applied Information Technology, Vol. 3, Issue 1, 2009, pp. 68-79.
[6] A. Lawanna and J. Daengdej, —Methods for Case Maintenance in Case-Based Reasoning!, International Journal of Computer and Information Engineering Vol. 4 Issue 1, pp. 10-18, 2010.
[7] Ralph Bergmann and Yolanda Gil," Retrieval of Semantic Workflows with Knowledge Intensive Similarity Measures", Proceedings 19th International Conference on Case-Based Reasoning, ICCBR 2011, London, UK, September 12-15, 2011.
[8] Jin Qi, Jie Hu, -A new adaptation method based on adaptability under k-nearest neighbors for case adaptation in case-based design!, Expert Systems with Applications Volume 39, Issue 7, 1 June 2012, Pages 6485-6502.
[9] Nesrine ben yahia, Narjès bellamine and Henda ben ghezala, “Integrating fuzzy case-based reasoning and particle swarm optimization to support decision making” International Journal of Computer Science Issues, Vol. 9, Issue 3, No 3, May 2012, pp. 117-125.
[10] Sangyong Kim, Jae Heon Shim, “Combining casebased reasoning with genetic algorithm optimization for preliminary cost estimation in construction industry”, Canadian Journal of Civil Engineering, 2014, 41(1): 65-73