Case indexing in Case-Based Reasoning by applying Situation Operator Model as knowledge representation model

Multi-modal diagnosis combining case-based and model-based reasoning: a formal and experimental analysis

Case-based reasoning (CBR) is an artificial intelligence (AI) technique for solving problems. The very fact that CBR draws on past experiences to solve a new problem makes it intuitively appealing as humans also have the same problem-solving behavior. Another advantage of CBR over other conventional AI techniques is that it can work on a shallow knowledge base to start with. These make CBR an excellent method to solve real-life problems and useful in the field like medical diagnosis, engineering diagnosis, product selection, weather prediction, aerospace applications, etc. Classification plays a vital role in the retrieval of cases, as a correct classification results in a correctly retrieved case, which eventually results in a correct solution given by the CBR system. Typically, case retrieval is similarity-based and uses a k-nearest neighbor (k-NN) algorithm. Retrieval aims to find among the stored cases the best match for a given new case. Typically, CBR systems use the nearest neighbor algorithm as a similarity metric for retrieving cases. In this paper, the researchers use the machine learning workbench WEKA to combine well-known classifiers multilayer perceptron and fuzzy-rough nearest neighbor and compare the performance of k-NN with them. They have used benchmark medical data sets to carry out the evaluation process. The experimental results show that the combination of multilayer perceptron and fuzzy-rough nearest neighbor outperforms k-NN to a significant extent for classification, thus effectively improving the case retrieval efficiency and performance.

Semantic approaches present an efficient, detailed and easily understandable representation of knowledge from documents. Al-Quran contains a vast amount of knowledge that needs appropriate knowledge extraction. A semantic based approach can help in designing an efficient and explainable knowledge representation model for Al-Quran. This research aims to propose a semantic-graph knowledge representation model for verses of Al-Quran based on word dependencies. These features are used in the proposed knowledge representation model allowing the semantic graph matching to improve Al-Quran search applications' accuracy. The proposed knowledge representation model is essentially a formalism for generating a semantic graph representation of Quranic verses, which can be applied for knowledge base construction for other applications such as information retrieval system. A set of rules called Semantic Dependency Triple Rules are defined to be mapped into the semantic graph representing the verse's logic. The rules translate word dependencies and other NLP metadata into a triple form that holds logical information. The proposed model has been tested with English translation of Al-Quran on a document retrieval prototype The basic system has been enhanced with anaphoric pronouns correction, which has shown improvement in retrieval performance. The results have been compared with a closely related system and evaluated on the accuracy of the document retrieval in Precision, Recall and F-score measurements. The proposed model has achieved 65%, 60% and 62.4% for the measurements, respectively. It has also improved the overall accuracy of previous system by 43.8%.

Autonomic systems are the software systems capable to manage themselves. These systems undergo a learning process to achieve this capability. Case-based reasoning (CBR) is one of the promising learning paradigms for autonomic managers. Autonomic managers monitor the pulse of the monitored system on periodic basis and analyze the captured state of the system. In case of a problematic state, autonomic managers use their CBR based decision support system to rectify the problem. One of the critical problems in such systems is recovery from failures. The problem of identifying the factors affecting the performance of CBR system is a key element to build successful and accurate decision support systems. For this purpose, a hybrid CBR based self-healing system supported by attribute selection methods has been proposed. An empirical investigation has been conducted in this paper using different similarity measures, solution adaptation methods and attribute selection techniques. To address the performance problem of CBR in self-healing systems, we have conducted experiments on an emulator of self-healing systems called RUIBiS using different machine learning techniques to determine the significance of weights for these similarity distances.

To improve the performance of electronic commerce recommendation system (ECRS), the system implement frame by case-based reasoning (CBR) and artificial immune system (AIS) is proposed. The inner mechanism of AIS is analyzed, in leaning subsystem of ECRS, the AIS implement cycles such as antigen identifying, initial antibody population generating, affinity calculating, clone selecting, population updating and so on are studied. The key techniques of CBR for reasoning subsystem of ECRS such as case representation, case retrieval, case adaptation and case maintenance are introduced. The ECRS is tested by history record information of some Website, the result demonstrates that both the recommendation accuracy and reasoning response velocity are improved, the ECRS frame based on CBR and AIS is a potent one.

Identification of skin disease has become a challenging task with the origination of various skin diseases. This paper presents a case-based reasoning (CBR) decision support system to enhance dermatological diagnosis for rural and remote communities. In this proposed work, an automated way is introduced to deal with the inconsistency problem in CBRs. This new hybrid architecture is to support the diagnosis in multiple skin diseases. The architecture used case-based reasoning terminology facilitates the medical diagnosis. Case based reasoning system retrieves the data which contains symptoms and treatment plan of the disease from the data repository by the way of matching visual contents of the image, such as shape, texture, and color descriptors. The extracted feature vector is fed into a framework to retrieve the data. The results proved using ROC curve that the proposed architecture yields high contribution to the computer-aided diagnosis of skin lesions. In experimental analysis, the system yields a specificity of 95.25% and a sensitivity of 86.77%. Our empirical evaluation has a superior retrieval and diagnosis performance when compared to the performance of other works.

This paper presents a decision support system for radiotherapy treatment planning for head, neck and brain cancer. The aim of a treatment plan is to apply radiation to kill tumor cells, while minimizing the damage to healthy tissue and critical organs. Since treatment planning is a complex decision making process that relies heavily on the subjective experience of clinicians, we propose the use of case-based reasoning (CBR), in which problems are solved based on the solutions of similar past problems. This paper focuses on the case retrieval process of a CBR system. The attributes, which describe the cases, are selected by assessing their effect on the performance of the CBR system. We have developed a context sensitive local weighting scheme that assigns weights to attributes based on their value and the values of other attributes in the target case. A novel two phase retrieval mechanism is developed, in which each phase is optimized to retrieve a particular part of the solution. We also present an original use of fuzzy logic in order to represent nonlinearity in the similarity measure. Experiments, which evaluate the similarity measure using real brain cancer patient cases, show promising results.

One of the major tasks when developing diagnostic decision support systems is to find the best fitting inference method and knowledge representation model for the domain at hand. There are many existing approaches for decision support in different fields such as technology, economies and medicine, each using different knowledge representations and inference methods. Inference methods mainly have been designed for certain domains or at least been adapted to the domain, so that often the application of methods or representation models in other fields is not working well. Especially in fields where the knowledge is characterized by uncertainty, imprecision and vagueness, standard approaches fail. In this article a new approach (ICARUS) is presented integrating rule-based and case based reasoning in a hybrid system and using fuzzy sets and fuzzy relations for the representation and application of uncertain or imprecise knowledge. The main idea of the integration is that rule-based reasoning applies knowledge on a higher level of abstraction and is used to represent the normal case while case-based reasoning does so on a lower level of abstraction and is there for an ideal method to manage special cases. This approach was designed for a diagnostic decision support system in the field of acute abdominal pain (AAP).

The process of manually annotating ancient manuscripts may rise a problem of verifying each user annotations. Thus, it is important to use a supporting system to correct certain annotations; this may be done on the basis of the experience of other users in similar cases. In this chapter, we present how we used case-based reasoning (CBR) in a digital archive to make a recommender system, which will accelerate the annotation process and correct user errors. In fact, our system tracks important user actions and saves those actions as traces. The CBR is applied to users’ traces that are considered as users’ experiences. Traces are structured in reusable sections called episodes (cases); each episode represents the work done on one document unit. Episode actions comprise both problems and solutions. The recommender system compares the current episode of the annotator trace with the traces database to find similar episodes, and recommends the most appropriate actions representing the solution to the user. At that point, the user takes the responsibility of accepting or refusing the recommendations. A prototype of this application has been developed to test the performance of using the CBR system in a digital archive. The experimental results confirmed the efficiency of using case-based reasoning in this domain.

Optimized artificial intelligence models for predicting project award price

In this decade with increasing technology development and wide usage of mobile devices, using applications in teaching patients specially the ones with particular restrictions such as Spinal Cord Injury (SCI) patients who are not able to move that easily, could be beneficial. On the other hand, due to their various body capabilities, the teaching material could not be the same for all the patients. Thus personalizing support systems seems to have a significant role on increasing user satisfaction, improving treatment trend and increasing the patient's ability to do daily activities. Taking the above point into account, in this paper we are going to describe the personalization process of "Spinal Cord Injury Mobility and Transfer Support Application" which is based on Case-Based Reasoning (CBR). The support application will provide personalized educational contents such as videos teaching mobility and transfer, text and audio guides, according to the patients' characteristics. In order to optimize the personalization process, performance of the support system was evaluated in two situations, changing the number of clusters and changing the similarity threshold. At the end, the results concluded that CBR can be used as an effective method in personalizing medical support systems.

In this paper we propose to combine three AI techniques to speed up a Reinforcement Learning algorithm in a Transfer Learning problem: Case-based Reasoning, Heuristically Accelerated Reinforcement Learning and Neural Networks. To do so, we propose a new algorithm, called L3, which works in 3 stages: in the first stage, it uses Reinforcement Learning to learn how to perform one task, and stores the optimal policy for this problem as a case-base; in the second stage, it uses a Neural Network to map actions from one domain to actions in the other domain and; in the third stage, it uses the case-base learned in the first stage as heuristics to speed up the learning performance in a related, but different, task. The RL algorithm used in the first phase is the Q-learning and in the third phase is the recently proposed Case-based Heuristically Accelerated Q-learning. A set of empirical evaluations were conducted in transferring the learning between two domains, the Acrobot and the Robocup 3D: the policy learned during the solution of the Acrobot Problem is transferred and used to speed up the learning of stability policies for a humanoid robot in the Robocup 3D simulator. The results show that the use of this algorithm can lead to a significant improvement in the performance of the agent.

Case‐Based Reasoning for Real‐Time Traffic Flow Management

With the exponentially growing amount of information available on the Internet, an effective technique for users to discern the useful information from the unnecessary information is urgently required. Cleaning web pages for web data extraction becomes critical for improving performance of information retrieval and information extraction. So, we investigate to remove various noise patterns in Web pages instead of extracting relevant content from Web pages to get main content information. In this paper, we propose an approach that detect multiple noise patterns and remove these noise patterns from Web pages of any Web sites. The method first build DOM tree for any Web page. Our approach is based on the basic idea of Case-Based Reasoning (CBR) to find noise pattern in current Web page by matching similar noise pattern kept in Case-Based. We also apply a back propagation neural network algorithm to classify the stored various noise patterns by matching similar noise data in current Web page. We have implemented our method on several commercial Web sites and News Web sites to evaluate the performance and improvement of our approach. Experiments show that results leads to a more accurate and effectiveness of the approach.

최근 IT 서비스 발달과 함께 고장제어, 고장의 원인분석 등의 복잡한 문제에 대하여 적합한 해결책을 제시할 수 있는 효과적인 진단시스템의 필요성이 커지고 있다. 따라서 본 논문에서는 지능형 진단 시스템분야에서의 시스템의 성능을 향상시키고, 최적의 진단을 수행하고자 사례기반추론과 인공신경망을 혼합한 지능형 진단 시스템을 제안 한다. 사례기반추론은 과거의 사례(경험)를 통해 현재의 제시된 문제를 해결하는 추론방식으로, 지식 획득이 덜 복잡하고, 정형화되기 어려운 규칙이나 문제영역이 불분명한 분야를 효율적으로 추론할 수 있다. 하지만 사례기반추론만을 이용해 추론된 사례는 증상에 대해 다수의 원인을 추론하게 된다. 이때 추론된 증상에 따른 다수의 원인은 동일한 가중치를 가져 불필요한 원인까지 진단해야 하는 문제점이 있다. 이러한 문제를 해결하고자 인공신경망의 오류역전파 학습 알고리즘을 이용하여 증상에 대한 원인들의 쌍을 학습 시킨 후 각각의 증상에 대한 원인의 가중치를 구해 제시된 증상에 대해 가장 발생 가능성이 높은 원인을 찾아내어, 보다 명확하고 신뢰성 있는 진단을 하는 데 그 목적이 있다. As the recent development of the IT services, there is a urgent need of effective diagnosis system to present appropriate solution for the complicated problems of breakdown control, a cause analysis of breakdown and others. So we propose an intelligent diagnosis system that integrates the case-based reasoning and the artificial neural network to improve the system performance and to achieve optimal diagnosis. The case-based reasoning is a reasoning method that resolves the problems presented in current time through the past cases (experience). And it enables to make efficient reasoning by means of less complicated knowledge acquisition process, especially in the domain where it is difficult to extract formal rules. However, reasoning by using the case-based reasoning alone in diagnosis problem domain causes a problem of suggesting multiple causes on a given symptom. Since the suggested multiple causes of given symptom has the same weight, the unnecessary causes are also examined as well. In order to resolve such problems, the back-propagation learning algorithm of the artificial neural network is used to train the pairs of the causes and associated symptoms and find out the cause with the highest weight for occurrence to make more clarified and reliable diagnosis.