• 한국정보시스템학회지:정보시스템연구
• /
• 제21권3호
• /
• pp.137-161
• /
• 2012

The increasing interest in big data analysis using various data mining techniques indicates that many commercial data mining tools now need to be equipped with fundamental text analysis modules. The most essential prerequisite for accurate analysis of text documents is an understanding of the exact semantics of each term in a document. The main difficulties in understanding the exact semantics of terms are mainly attributable to homonym and synonym problems, which is a traditional problem in the natural language processing field. Some major text mining tools provide a thesaurus to solve these problems, but a thesaurus cannot be used to resolve complex synonym problems. Furthermore, the use of a thesaurus is irrelevant to the issue of homonym problems and hence cannot solve them. In this paper, we propose a semantic text mining methodology that uses ontologies to improve the quality of text mining results by resolving the semantic ambiguity caused by homonym and synonym problems. We evaluate the practical applicability of the proposed methodology by performing a classification analysis to predict customer churn using real transactional data and Q&A articles from the "S" online shopping mall in Korea. The experiments revealed that the prediction model produced by our proposed semantic text mining method outperformed the model produced by traditional text mining in terms of prediction accuracy such as the response, captured response, and lift.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제16권10호
• /
• pp.3230-3255
• /
• 2022

Causality mining in NLP is a significant area of interest, which benefits in many daily life applications, including decision making, business risk management, question answering, future event prediction, scenario generation, and information retrieval. Mining those causalities was a challenging and open problem for the prior non-statistical and statistical techniques using web sources that required hand-crafted linguistics patterns for feature engineering, which were subject to domain knowledge and required much human effort. Those studies overlooked implicit, ambiguous, and heterogeneous causality and focused on explicit causality mining. In contrast to statistical and non-statistical approaches, we present Bidirectional Encoder Representations from Transformers (BERT) integrated with Multi-level Feature Networks (MFN) for causality recognition, called BERT+MFN for causality recognition in noisy and informal web datasets without human-designed features. In our model, MFN consists of a three-column knowledge-oriented network (TC-KN), bi-LSTM, and Relation Network (RN) that mine causality information at the segment level. BERT captures semantic features at the word level. We perform experiments on Alternative Lexicalization (AltLexes) datasets. The experimental outcomes show that our model outperforms baseline causality and text mining techniques.

• 정보보호학회논문지
• /
• 제23권3호
• /
• pp.383-393
• /
• 2013

데이터 스트림 마이닝 기술은 실시간으로 발생하는 데이터를 분석하여 유용한 정보를 얻는 기술이다. 데이터 스트림 마이닝 기술 중에서 빈발항목 마이닝은 전송되는 데이터들 중에서 어떤 항목이 빈발한지 찾는 기술이며, 찾은 빈발항목들은 다양한 분야에서 패턴분석이나 마케팅의 목적으로 사용된다. 기존에 제안된 데이터 스트림 빈발항목 마이닝은 악의적인 공격자가 전송되는 데이터를 스니핑할 경우 데이터 제공자의 실시간 정보가 노출되는 문제점을 가지고 있다. 이러한 문제는 전송되는 데이터에서 원본 데이터를 구별 못하게 하는 더미 데이터 삽입 기법을 통해 해결가능하다. 본 논문에서는 더미 데이터 삽입 기법을 이용한 프라이버시 보존 데이터 스트림 빈발항목 마이닝 기법을 제안한다. 또한, 제안하는 기법은 암호화 기법이나 다른 수학적 연산이 요구되지 않아 연산량 측면에서 효과적이다.

• 한국경영과학회지
• /
• 제28권3호
• /
• pp.135-148
• /
• 2003

In this paper we introduce the Internet-based purchase support systems using data mining and case-based reasoning (CBR). Internet Business activity that involves the end user is undergoing a significant revolution. The ability to track users browsing behavior has brought the vendor and end customer's closer than ever before. It is now possible for a vendor to personalize his product message for individual customers at massive scale. Most of former researchers, in this research arena, used data mining techniques to pursue the customer's future behavior and to improve the frequency of repurchase. The area of data mining can be defined as efficiently discovering association rules from large collections of data. However, the basic association rule-based data mining technique was not flexible. If there were no inference rules to track the customer's future behavior, association rule-based data mining systems may not present more information. To resolve this problem, we combined association rule-based data mining with CBR mechanism. CBR is used in reasoning for customer's preference searching and training through the cases. Data mining and CBR-based hybrid purchase support mechanism can reflect both association rule-based logical inference and case-based information reuse. A Web-log data gathered in the real-world Internet shopping mall is given to illustrate the quality of the proposed systems.

• 대한안전경영과학회지
• /
• 제24권4호
• /
• pp.149-156
• /
• 2022

Manufacturing process mining performs various data analyzes of performance on event logs that record production. That is, it analyzes the event log data accumulated in the information system and extracts useful information necessary for business execution. Process data analysis by process mining analyzes actual data extracted from manufacturing execution systems (MES) to enable accurate manufacturing process analysis. In order to continuously manage and improve manufacturing and manufacturing processes, there is a need to structure, monitor and analyze the processes, but there is a lack of suitable technology to use. The purpose of this research is to propose a manufacturing process analysis method using process mining and to establish a manufacturing process mining system by analyzing empirical data. In this research, the manufacturing process was analyzed by process mining technology using transaction data extracted from MES. A relationship model of the manufacturing process and equipment was derived, and various performance analyzes were performed on the derived process model from the viewpoint of work, equipment, and time. The results of this analysis are highly effective in shortening process lead times (bottleneck analysis, time analysis), improving productivity (throughput analysis), and reducing costs (equipment analysis).

• Journal of the Korean Data and Information Science Society
• /
• 제16권4호
• /
• pp.823-833
• /
• 2005

This paper deals the TFT-LCD process and quality, process control problems of the process. For improvement of the process quality and yield, we apply a data mining technique to the LCD industry. And some unique quality features of the LCD process are also described. We describe some preceding researches first and relate to the TFT-LCD process and the problems of data mining in the process. Also we tried to observe the problems which need to solve first and the features from description below hazard must be considered a quality mining in LCD industry.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제13권5호
• /
• pp.2529-2543
• /
• 2019

Scanning electron microscopy (SEM) image can link with the microscopic world through reflecting interaction between electrons and materials. The SEM images are easily subject to blurring distortions during the imaging process. Inspired by the fact that dark channel prior captures the changes to blurred SEM images caused by the blur process, we propose a method to evaluate the SEM images sharpness based on the dark channel prior. A SEM image database is first established with mean opinion score collected as ground truth. For the quality assessment of the SEM image, the dark channel map is generated. Since blurring is typically characterized by the spread of edge, edge of dark channel map is extracted. Then noise is removed by an edge-preserving filter. Finally, the maximum gradient and the average gradient of image are combined to generate the final sharpness score. The experimental results on the SEM blurred image database show that the proposed algorithm outperforms both the existing state-of-the-art image sharpness metrics and the general-purpose no-reference quality metrics.

• Journal of Communications and Networks
• /
• 제17권6호
• /
• pp.568-581
• /
• 2015

Predicting locations of users with portable devices such as IP phones, smart-phones, iPads and iPods in public wireless local area networks (WLANs) plays a crucial role in location management and network resource allocation. Many techniques in machine learning and data mining, such as sequential pattern mining and clustering, have been widely used. However, these approaches have two deficiencies. First, because they are based on profiles of individual mobility behaviors, a sequential pattern technique may fail to predict new users or users with movement on novel paths. Second, using similar mobility behaviors in a cluster for predicting the movement of users may cause significant degradation in accuracy owing to indistinguishable regular movement and random movement. In this paper, we propose a novel fusion technique that utilizes mobility rules discovered from multiple similar users by combining clustering and sequential pattern mining. The proposed technique with two algorithms, named the clustering-based-sequential-pattern-mining (CSPM) and sequential-pattern-mining-based-clustering (SPMC), can deal with the lack of information in a personal profile and avoid some noise due to random movements by users. Experimental results show that our approach outperforms existing approaches in terms of efficiency and prediction accuracy.

• Journal of the Korean Data and Information Science Society
• /
• 제16권1호
• /
• pp.59-69
• /
• 2005

Data mining is the method to find useful information for large amounts of data in database It is used to find hidden knowledge by massive data, unexpectedly pattern, relation to new rule. The methods of data mining are decision tree, association rules, clustering, neural network and so on. We analyze Gyeongnam social indicator survey data by 2001 using association rule technique for environment information. Association rule mining searches for interesting relationships among items in a given large data set. Association rules are frequently used by retail stores to assist in marketing, advertising, floor placement, and inventory control. There are three primary quality measures for association rule, support and confidence and lift. We can use to environmental preservation and environmental improvement by association rule outputs

• Journal of Information Processing Systems
• /
• 제6권1호
• /
• pp.79-90
• /
• 2010

A data stream is a massive unbounded sequence of data elements continuously generated at a rapid rate. The continuous characteristic of streaming data necessitates the use of algorithms that require only one scan over the stream for knowledge discovery. Data mining over data streams should support the flexible trade-off between processing time and mining accuracy. In many application areas, mining frequent itemsets has been suggested to find important frequent itemsets by considering the weight of itemsets. In this paper, we present an efficient algorithm WSFI (Weighted Support Frequent Itemsets)-Mine with normalized weight over data streams. Moreover, we propose a novel tree structure, called the Weighted Support FP-Tree (WSFP-Tree), that stores compressed crucial information about frequent itemsets. Empirical results show that our algorithm outperforms comparative algorithms under the windowed streaming model.