• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.5 no.3
• /
• pp.560-574
• /
• 2011

In this paper, we propose a hybrid method of Machine Learning (ML) algorithm and a rule-based algorithm to implement a lightweight Named Entity (NE) extraction system for Korean SMS text. NE extraction from Korean SMS text is a challenging theme due to the resource limitation on a mobile phone, corruptions in input text, need for extension to include personal information stored in a mobile phone, and sparsity of training data. The proposed hybrid method retaining the advantages of statistical ML and rule-based algorithms provides fully-automated procedures for the combination of ML approaches and their correction rules using a threshold-based soft decision function. The proposed method is applied to Korean SMS texts to extract person's names as well as location names which are key information in personal appointment management system. Our proposed system achieved 80.53% in F-measure in this domain, superior to those of the conventional ML approaches.

• Journal of the Korean Institute of Telematics and Electronics C
• /
• v.34C no.5
• /
• pp.71-81
• /
• 1997

This paper proposes noun and affix extraction methods using conjunctive information for making an automatic indexing system thorugh morphological analysis and syntactic analysis. The korean language has a peculiar spacing words rule, which is different from other languages, and the conjunctive information, which is extracted from the rule, can reduce the number of multiple parts of speech at a minimum cost. The proposed algorithms also solve the problem that one word is seperated by newline charcter. We show efficiency of the proposed algorithms through the process of morhologica analyzing.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 1998.06a
• /
• pp.725-730
• /
• 1998

Recently we extended the fuzzy model for rule based systems incorporating an importance factor for each rule. The model permits for both unrestricted as well as non-negative importance factors. We use this extended model to design a fuzzy rule based classifier system which uses both the firing strength of the rule and the importance factor to decide the class label. The effectiveness of the scheme is established using several data sets.

• Journal of Intelligence and Information Systems
• /
• v.7 no.2
• /
• pp.83-93
• /
• 2001

Prediction of corporate failure using past financial data is well-documented topic. Early studies of bankruptcy prediction used statistical techniques such as multiple discriminant analysis, logit and probit. Recently, however, numerous studies have demonstrated that artificial intelligence such as neural networks (NNs) can be an alternative methodology for classification problems to which traditional statistical methods have long been applied. Although numerous theoretical and experimental studies reported the usefulness or neural networks in classification studies, there exists a major drawback in building and using the model. That is, the user can not readily comprehend the final rules that the neural network models acquire. We propose a genetic algorithms (GAs) approach in this study and illustrate how GAs can be applied to corporate failure prediction modeling. An advantage of GAs approach offers is that it is capable of extracting rules that are easy to understand for users like expert systems. The preliminary results show that rule extraction approach using GAs for bankruptcy prediction modeling is promising.

• International Journal of Control, Automation, and Systems
• /
• v.4 no.3
• /
• pp.372-381
• /
• 2006

The purpose of this study was to develop a process management system to manage ingot fabrication and improve ingot quality. The ingot is the first manufactured material of wafers. Trace parameters were collected on-line but measurement parameters were measured by sampling inspection. The quality parameters were applied to evaluate the quality. Therefore, preprocessing was necessary to extract useful information from the quality data. First, statistical methods were used for data generation. Then, modeling was performed, using the generated data, to improve the performance of the models. The function of the models is to predict the quality corresponding to control parameters. Secondly, rule extraction was performed to find the relation between the production quality and control conditions. The extracted rules can give important information concerning how to handle the process correctly. The dynamic polynomial neural network (DPNN) and decision tree were applied for data modeling and rule extraction, respectively, from the ingot fabrication data.

• Proceedings of the Korean Society for Agricultural Machinery Conference
• /
• 2000.11c
• /
• pp.715-721
• /
• 2000

In this research, rule and neuro net based boundary extraction algorithm was developed. Extracting boundary of the interest, lean tissue, is essential for the quality evaluation of the beef based on color machine vision. Major quality features of the beef are size, marveling state of the lean tissue, color of the fat, and thickness of back fat. To evaluate the beef quality, extracting of loin parts from the sectional image of beef rib is crucial and the first step. Since its boundary is not clear and very difficult to trace, neural network model was developed to isolate loin parts from the entire image input. At the stage of training network, normalized color image data was used. Model reference of boundary was determined by binary feature extraction algorithm using R(red) channel. And 100 sub-images(selected from maximum extended boundary rectangle 11${\times}$11 masks) were used as training data set. Each mask has information on the curvature of boundary. The basic rule in boundary extraction is the adaptation of the known curvature of the boundary. The structured model reference and neural net based boundary extraction algorithm was developed and implemented to the beef image and results were analyzed.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.11 no.3
• /
• pp.231-240
• /
• 2001

Conventional expert systems has been criticized due to its lack of capability to adapt to the changing decision-making environments. In literature, many methods have been proposed to make expert systems more environment-adaptive by incorporating fuzzy logic and neural networks. The objective of this paper is to propose a new approach to building a self-evolving expert system inference mechanism by integrating fuzzy neural network and fuzzy rule extraction technique. The main recipe of our proposed approach is to fuzzify the training data, train them by a fuzzy neural network, extract a set of fuzzy rules from the trained network, organize a knowledge base, and refine the fuzzy rules by applying a pruning algorithm when the decision-making environments are detected to be changed significantly. To prove the validity, we tested our proposed self-evolving expert systems inference mechanism by using the bankruptcy data, and compared its results with the conventional neural network. Non-parametric statistical analysis of the experimental results showed that our proposed approach is valid significantly.

• Journal of the Korean Geographical Society
• /
• v.39 no.4
• /
• pp.633-642
• /
• 2004

This study tries to generalize the stream network by constructing rule-based modelling. A study on the map generalization tends to be concentrated on development of algorithms for modification of linear features and evaluations to the limited cartographic elements. Rule-based modelling can help to improve previous algorithms by application of generalization process with the results that analyzing mapping principles and spatial distribution patterns of geographical phenomena. Rule-based modelling can be applied to generalize various cartographic elements, and make an effective on multi-scaling mapping in the digital environments. In this research, nile-based modelling for stream network is composed of generalization rule, algorithm for centerline extraction and linear features. Before generalization, drainage pattern was analyzed by the connectivity with lake to minimize logical errors. As a result, 17 streams with centerline are extracted from 108 double-lined streams. Total length of stream networks is reduced as 17% in 1:25,000 scale, and as 29% in 1:50,000. Simoo algorithm, which is developed to generalize linear features, is compared to Douglas-Peucker(D-P) algorithm. D-P made linear features rough due to the increase of data point distance and widening of external angle. But in Simoo, linear features are smoothed with the decrease of scale.

• Proceedings of the Korea Inteligent Information System Society Conference
• /
• 2001.01a
• /
• pp.431-434
• /
• 2001

Knowledge discovery in databases(KDD) is the process for extracting valid, novel, potentially useful and understandable knowledge form real data. There are many academic and industrial activities with new technologies and application areas. Particularly, data mining is the core step in the KDD process, consisting of many algorithms to perform clustering, pattern recognition and rule induction functions. The main goal of these algorithms is prediction and description. Prediction means the assessment of unknown variables. Description is concerned with providing understandable results in a compatible format to human users. We introduce an efficient data mining algorithm considering predictive and descriptive capability. Reasonable pattern is derived from real world data by a revised neural network model and a proposed fuzzy rule extraction technique is applied to obtain understandable knowledge. The proposed neural network model is a hierarchical self-organizing system. The rule base is compatible to decision makers perception because the generated fuzzy rule set reflects the human information process. Results from real world application are analyzed to evaluate the system\`s performance.

• KIPS Transactions on Software and Data Engineering
• /
• v.2 no.5
• /
• pp.341-346
• /
• 2013

In this paper, we propose a rule extraction method using a modified Fuzzy Min-Max (FMM) neural network. The suggested method supplements the hyperbox definition with a frequency factor of feature values in the learning data set. We have defined a relevance factor between features and pattern classes. The proposed model can solve the ambiguity problem without using the overlapping test process and the contraction process. The hyperbox membership function based on the fuzzy partitions is defined for each dimension of a pattern class. The weight values are trained by the feature range and the frequency of feature values. The excitatory features and the inhibitory features can be classified by the proposed method and they can be used for the rule generation process. From the experiments of sign language recognition, the proposed method is evaluated empirically.