Towards Automated Case Knowledge Discovery in the M 2 Case-Based Reasoning System

In this paper we present the M ² Case-Based Reasoning (CBR) system. The M ² system addresses a number of issues that present methodologies for CBR systems have shied away from. We discuss techniques for removing the knowledge acquisition bottleneck when acquiring case knowledge. Here, case knowledge refers to the complementary knowledge structures, cases (more specific in nature) and adaptation rules (more general). We address the use of negative cases for updating the case knowledge as well as for refining the similarity measures. In particular we discuss in detail, showing experimental results, the use of Data Mining within the M ² system to build the case base from a database containing operational data, and discover adaptation rules. A methodology to monitor the competence of the CBR system and to utilize negative cases for updating the CBR system to enhance its competence is also discussed. The M ² CBR system also employs Rough Set and Fuzzy Set theories to further enhance its capabilities within real-world applications as well as providing a richer and truer model of human reasoning.     

Extended object model for product configuration design

This paper presents an extended object model for case-based reasoning (CBR) in product configuration design. In the extended object model, a few methods of knowledge expression are adopted, such as constraints, rules, objects, etc. On the basis of extended object model, case representation model for CBR is applied to product configuration design system. The product configuration knowledge can be represented by the extended object. The model can support all the processes of CBR in product configuration design, such as case representation, indexing, retrieving, and case revising. The presented model is an extension of the traditional object-oriented model by including the relationship class used to express the relation between the cases, constraints class used in the product configuration knowledge representation, index class used in case retrieving, and solution class used in case revising. Therefore, the product configuration knowledge used in the product configuration design can be represented by using this model. In the end, a metering pump product configuration design system is developed on the basis of the proposed product configuration model to support customized products.     

Impact of momentum bias on forecasting through knowledge discovery techniques in the foreign exchange market

To an increasing extent since the late 1980s, software learning methods including neural networks (NN) and case based reasoning (CBR) have been used for prediction in financial markets and other areas. In the past, the prediction of foreign exchange rates has focused on isolated techniques, as exemplified by the use of time series models including regression models or smoothing methods to identify cycles and trends. At best, however, the use of isolated methods can only represent fragmented models of the causative agents, which underlie business cycles. Experience with artificial intelligence applications since the early 1980s points toward a multistrategy approach to discovery and prediction.This paper investigates the impact of momentum bias on forecasting financial markets through knowledge discovery techniques. Different modes of bias are used as input into learning systems using implicit knowledge representation (NNs) and CBR. The concepts are examined in the context of predicting movements in the Japanese yen.     

ASHSD-II: A computational model for litigation support

Abstract: In this paper a hybrid knowledge-based system which exploits both rule-based reasoning (RBR) and case-based reasoning (CBR) is presented. The issues of RBR and CBR in general in the context of legal knowledge-based systems and legislation in rule form and previously-decided cases in an interconnected graph form are discussed. It is possible for the user to select either reasoning method (RBR or CBR), or indicate no preference. The rule base of this system consists of two types of rule. The first type of rule determines which options are legally applicable. The second type indicates how the courts are likely to act within the range of options available, which is determined by the first type of rule. When CBR is selected, the system uses the features of previously-decided cases to select the most similar cases to the situation that is described in the input and displays their details of decisions. In case of the selection of no preference option, the system applies RBR and CBR method separately, and then presents results based on an automated relative rating of the qualities of the RBR (based on the second type of rules) and CBR advice. These ideas have been implemented in a prototype system, known as A dvisory S upport for H ome S ettlement in D ivorce (ASHSD-II).     

Estimate-based goodness-of-fit test for large sparse multinomial distributions

The Pearson’s chi-squared statistic (X²) does not in general follow a chi-square distribution when it is used for goodness-of-fit testing for a multinomial distribution based on sparse contingency table data. We explore properties of [Zelterman, D., 1987. Goodness-of-fit tests for large sparse multinomial distributions. J. Amer. Statist. Assoc. 82 (398), 624-629] D² statistic and compare them with those of X² and compare the power of goodness-of-fit test among the tests using D², X², and the statistic (L_r) which is proposed by [Maydeu-Olivares, A., Joe, H., 2005. Limited- and full-information estimation and goodness-of-fit testing in 2ⁿ contingency tables: A unified framework. J. Amer. Statist. Assoc. 100 (471), 1009-1020] when the given contingency table is very sparse. We show that the variance of D² is not larger than the variance of X² under null hypotheses where all the cell probabilities are positive, that the distribution of D² becomes more skewed as the multinomial distribution becomes more asymmetric and sparse, and that, as for the L_r statistic, the power of the goodness-of-fit testing depends on the models which are selected for the testing. A simulation experiment strongly recommends to use both D² and L_r for goodness-of-fit testing with large sparse contingency table data.     

A Priori knowledge based secure payload estimation

Many contemporary steganographic schemes aim to embed fixed-length secret message in the cover while minimizing the stego distortion. However, in some cases, the secret message sender requires to embed a variable-length secret payload within his expected stego security. This kind of problem is named as secure payload estimation (SPE). In this paper, we propose a practical SPE approach for individual cover. The stego security metric we adopt here is the detection error rate of steganalyzer (P _E ). Our method is based on a priori knowledge functions, which are two kinds of functions to be determined before the estimation. The first function is the relation function of detection error rate and stego distortion (P _E ? D function). The second function reflects the relationship between stego distortion and payload rate (D ? α) of the chosen cover. The P _E ? D is the general knowledge, which is calculated from image library. On the other hand, D ? α is for specific cover, which is needed to be determined on site. The estimating procedure is as follows: firstly, the sender solves the distortion D under his expected P _E via P _E ? D, and then calculates the corresponding secure payload α via D ? α of the cover. For on-site operations, the most time-consuming part is calculating D ? α function for cover image, which costs 1 time of STC coding. Besides this, the rest on-site operations are solving single-variable formulas, which can be easily tackled. Our approach is an efficient and practical solution for SPE problem.     

Transferring Case Knowledge To Adaptation Knowledge: An Approach for Case-Base Maintenance

In this article we propose a case-base maintenance methodology based on the idea of transferring knowledge between knowledge containers in a case-based reasoning (CBR) system. A machine-learning technique, fuzzy decision-tree induction, is used to transform the case knowledge to adaptation knowledge. By learning the more sophisticated fuzzy adaptation knowledge, many of the redundant cases can be removed. This approach is particularly useful when the case base consists of a large number of redundant cases and the retrieval efficiency becomes a real concern of the user. The method of maintaining a case base from scratch, as proposed in this article, consists of four steps. First, an approach to learning feature weights automatically is used to evaluate the importance of different features in a given case base. Second, clustering of cases is carried out to identify different concepts in the case base using the acquired feature-weights knowledge. Third, adaptation rules are mined for each concept using fuzzy decision trees. Fourth, a selection strategy based on the concepts of case coverage and reachability is used to select representative cases. In order to demonstrate the effectiveness of this approach as well as to examine the relationship between compactness and performance of a CBR system, experimental testing is carried out using the Traveling and the Rice Taste data sets. The results show that the testing case bases can be reduced by 36 and 39 percent, respectively, if we complement the remaining cases by the adaptation rules discovered using our approach. The overall accuracies of the two smaller case bases are 94 and 90 percent, respectively, of the originals.     

A study on the cognitive of complexity and difficulty of chinese characters when reading and recognizing

The Index of cognitive Information Complexity (C_info) and the Index of cognitive Information Difficulty (D_info) are measured at the psychological level for the application of learning and design when people are reading and recognizing the characters; thus, how to effectively monitor the information complexity and difficulty for the purpose of educational learning and design becomes an essential issue. This study combines information theory and Fitts’ Law to propose the concept of Information Mass (M_info) and through the test of the C_info and D_info toward the M_info of Chinese characters, the subjects are surveyed for measuring the complexity and difficulty of 218 selected Chinese characters. The results indicate that there is no significant discrepancy in the C_info of genders. The result of regression analysis indicates that the correlation coefficient of logarithm value of M_info and C_info is 0.684 and RSQ equals to 0.468. On the other hand, the Paired-Samples T-test shows the discrepancy of the D_info on Chinese characters between and among different groups. Overall, the M_info threshold value to recognize the D_info on Chinese characters between male and female subjects reaches to 0.017; among it, the M_info threshold value for male and female high school students is 0.06; for male and female university students is 0.01. The average value of D_info between genders found in regression analysis indicates the correlation coefficient of M_info and D_info is 0.861 and RSQ is 0.741. From results of this study, subjects are shown to have closer relations between M_info and D_info than that of M_info and C_info. In the other words, the concept to apply M_info gives reasonable explanation to the difficulty of Chinese characters and the model of linear regression serves the function for the reference of educational learning and design.     

Determinacy and query rewriting for conjunctive queries and views

Answering queries using views is the problem which examines how to derive the answers to a query when we only have the answers to a set of views. Constructing rewritings is a widely studied technique to derive those answers. In this paper we consider the problem of the existence of rewritings in the case where the answers to the views uniquely determine the answers to the query. Specifically, we say that a view set Vdetermines a query Q if for any two databases D₁,D₂ it holds: V(D₁)=V(D₂) implies Q(D₁)=Q(D₂). We consider the case where query and views are defined by conjunctive queries and investigate the question: If a view set V determines a query Q, is there an equivalent rewriting of Q using V? We present here interesting cases where there are such rewritings in the language of conjunctive queries. Interestingly, we identify a class of conjunctive queries, CQ_path, for which a view set can produce equivalent rewritings for “almost all” queries which are determined by this view set. We introduce a problem which relates determinacy to query equivalence. We show that there are cases where restricted results can carry over to broader classes of queries.     

Weighted aggregation operators based on minimization

Minimization based aggregation operators A_g,D are discussed. Special attention is paid to weighting function g based cases related to some fixed dissimilarity function D. When D₂(x,y)=(x-y)², we recognize mixture operators and we recall some sufficient conditions for g ensuring the monotonicity of A_g,D. For D₁(x,y)=|x-y| and non-decreasing (non-increasing) g, A_g,D is shown to be the upper (lower) median whenever A_g,D is an aggregation operator.     

PROTOTYPICAL CASES FOR RETRIEVAL, REUSE, AND KNOWLEDGE MAINTENANCE IN BIOMEDICAL CASE-BASED REASONING

Representing biomedical knowledge is an essential task in biomedical informatics intelligent systems. Case-based reasoning (CBR) holds the promise to represent contextual knowledge in a way that was not possible before with traditional knowledge-based methods. One main issue in biomedical CBR is dealing with the rate of generation of new knowledge in biomedical fields, which often makes the content of a case base partially obsolete. This article proposes to make use of the concept of prototypical case to ensure that a CBR system would keep update with current research advances in the biomedical field. Prototypical cases have served various purposes in biomedical CBR systems, among which to organize and structure the memory, to guide the retrieval as well as the reuse of cases, and to serve as bootstrapping a CBR system memory when real cases are not available in sufficient quantity and/or quality. This paper emphasizes the different roles prototypical cases can play in CBR systems, and presents knowledge maintenance as a very important novel role for these prototypical cases.     

Empirical distribution of k-word matches in biological sequences

This study focuses on an alignment-free sequence comparison method: the number of words of length k shared between two sequences, also known as the D₂ statistic. The advantages of the use of this statistic over alignment-based methods are firstly that it does not assume that homologous segments are contiguous, and secondly that the algorithm is computationally extremely fast, the runtime being proportional to the size of the sequence under scrutiny. Existing applications of the D₂ statistic include the clustering of related sequences in large EST databases such as the STACK database. Such applications have typically relied on heuristics without any statistical basis. Rigorous statistical characterisations of the distribution of D₂ have subsequently been undertaken, but have focussed on the distribution's asymptotic behaviour, leaving the distribution of D₂ uncharacterised for most practical cases. The work presented here bridges these two worlds to give usable approximations of the distribution of D₂ for ranges of parameters most frequently encountered in the study of biological sequences.     

Case learning for CBR-based collision avoidance systems

With the rapid development of case-based reasoning (CBR) techniques, CBR has been widely applied to real-world applications such as collision avoidance systems. A successful CBR-based system relies on a high-quality case base, and a case creation technique for generating such a case base is highly required. In this paper, we propose an automated case learning method for CBR-based collision avoidance systems. Building on techniques from CBR and natural language processing, we developed a methodology for learning cases from maritime affair records. After giving an overview on the developed systems, we present the methodology and the experiments conducted in case creation and case evaluation. The experimental results demonstrated the usefulness and applicability of the case learning approach for generating cases from the historic maritime affair records.     

Maintaining Retrieval Knowledge in a Case-Based Reasoning System

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.     

New CBR adaptation method combining with problem–solution relational analysis for mechanical design

Case based reasoning (CBR) methodology is proved to be a promising methodology on determining the parameter values of new mechanical product by adapting previously successful solutions to current problems. Compared with the sophisticated case retrieval technique, the case adaptation under K-nearest neighbour is still a bottleneck problem in CBR researches, which needs to be resolved urgently. According to the characteristics of parametric machinery design (PMD), i.e., less data and many parameters, this paper employs weighted mean (WM) as a basic model, and presents a new CBR adaptation method for PMD by integrating with problem–solution (PS) relational information. In our proposed adaptation method, prior to adapting the similar cases, the grey relational analysis (GRA) is utilized to investigate the PS relational information hidden in K retrieved cases, and the proposed method is called as GRA-WM. Different from classical WM method, the weighting factor of retrieved case for each solution element adaptation is calculated by multiplying similarity matrix (SM) and relational matrix (RM), and the adapted solution values of new mechanical product are subsequently obtained by calculating the weighted average of solution values of K similar cases. A case study on the power transformer design is given to prove the industrial applicability of GRA-WM. Moreover, the empirical comparisons between GRA-WM and other adaptation methods are carried out to validate its superiority. The empirical results indicate that GRA-WM can offer an acceptable adaptation proposal in application of CBR for mechanical design.     

Learning expert systems by being corrected

This paper describes a new method of knowledge acquisition for expert systems. A program, KABCO, interacts with a domain expert and learns how to make examples of a concept. This is done by displaying examples based upon KABCO's partial knowledge of the domain and accepting corrections from the expert. When the expert judges that KABCO has learnt the domain completely a large number of examples are generated and given to a standard machine learning program that learns the actual expert system rules. KABCO vastly eases the task of constructing an expert system using machine learning programs because it allows expert system rule bases to be learnt from a mixture of general (rules) and specific (examples) information. At present KABCO can only be used for classification domains but work is proceedings to extend it to be useful for other domains. KABCO learns disjunctive concepts (represented by frames) by modifying an internal knowledge base to remain consistent with all the corrections that have been entered by the expert. KABCO's incremental learning uses the deductive processes of modification, exclusion, subsumption and generalization. The present implementation is primitive, especially the user interface, but work is proceeding to make KABCO a much more advanced knowledge engineering tool.