Case-Based Reasoning (CBR) is a system for taking care of issues based on the experience. The principles of CBR are constructed intimately with respect to how individuals normally approach the undertaking of issues. CBR includes acquiring an issue depiction, estimating the similarities of the present issue to the past issues stores in a case-based or memory with their known arrangements, retrieving at least one similar cases, and attempting to reuse the arrangement of one of the recovered cases, possibly after adapting it to represent contrasts in problem descriptions (Ramon Lopez de Mantaras, David Mcsherry, Derek Bridge, David Leake, Barry Smith, Susan Craw, Boi Faltings, Mary Lou Haper, Michael T. Cox, Kenneth Forbus, Mark Keane, Agnar Aamodt, and Ian Watson, 2005). There have been numerous endeavors to create critical thinking frameworks outfitted with thinking motors in light of this methodological point of view. It has seen pragmatic use in fields, for example, designing critical thinking, therapeutic finding, legitimate thinking, and learning administration. Notwithstanding, case-based reasoning faces the feedback that despite the fact that it is an approach that utilizations prove based thinking unless that confirmation is contained information that can confront measurable examination, it is just a judgment in light of episodic proof.
Case-based reasoning is widely used in the recent years, its diagnosis were relied on the historical experience and the diagnostic efficiency is relatively high, but knowledge acquisition is the bottleneck. Based on the paper of Teng Zhe, Chen Jian and Xia Huicheng (2015), an observation on which solving based in CBR, namely that similar problems have similar solutions, has been shown to hold in expectation for simple scenarios, and is empirically validated in many real-world domains. The CBR field has grown rapidly over the last two decades, as seen by its increased share of papers at major conferences, available commercial tools, and successful applications in daily use.
According to Ha Manh Tran and Jürgen Schönwälder (2015), case-based reasoning seeks a solution to the problem. A case basically comprises a depiction of a speciﬁc issue and the relating arrangement. At the point when another issue shows up, the thinking procedure ﬁrst utilizes a closeness capacity to recover cases coordinating the present issue and afterward it adjusts the recovered cases to the conditions of the present issue so as to get a conceivable arrangement.
The following are the steps that will be done on CBR process, divided into 4 steps:
Retrieval is a key stage in the case-based reasoning (CBR) since it establishes the framework for the general adequacy of CBR frameworks. Its point is to recover helpful cases that can be utilized to tackle the objective issue. To play out the recovery procedure. According to Mobyin Uddin Ahmed, Shahina Begum, and Peter Funk (2012) Case-Based Reasoning (CBR) is a promising Artificial Intelligence (AI) strategy that is connected to a problem-solving task. Based on the study of Stefania Montani and Lakhmi C. Jain (2010), retrieve is the case base with a respect to the current input situation and contained case repository. Retrieval starts when the new problem is readily available and completes.
According to Malik Jahan Khan (2013), various solution algorithms will used on this purpose like weighted average, arithmetic average and majority voting. And based on Stefania Montani and Lakhmi C. Jain (2010), reuse are more precisely the solutions in order to solve the new problem. According to M.M. Richer, R.O Weber (2013), when the new problem is identical to the first phase the reuse is quite simple.
In this step, the solution was suggested and it will be verified for its correctness (Ning Xiong, Peter Funk, and Tomas Olsson`). Stefania Montani and Lakhmi C. Jain (2010), state that revise is the proposed new solution.
According to Malik Jahan Khan (2013), retain is the final step or the final suggested solution along with the corresponding problem description in the case-base to remember this new experience for future usage. Also retain is the case for possible future problem solving. Although CBR claims to reduce the effort required for developing knowledge-based systems substantially compared with more traditional Artificial Intelligence approaches, the implementation of a CBR application from scratch is still a time-consuming task.