• 한국IT서비스학회지
• /
• 제14권1호
• /
• pp.237-249
• /
• 2015

The volume of unstructured text data generated by various social media has been increasing rapidly; therefore, use of text mining to support decision making has also been increasing. Especially, issue Clustering-determining a new relation with various issues through clustering-has gained attention from many researchers. However, traditional issue clustering methods can only be performed based on the co-occurrence frequency of issue keywords in many documents. Therefore, an association between issues that have a low co-occurrence frequency cannot be discovered using traditional issue clustering methods, even if those issues are strongly related in other perspectives. Therefore, issue clustering that fits each of criteria needs to be performed by the perspective of analysis and the purpose of use. In this study, a multi-dimensional issue clustering is proposed to overcome the limitation of traditional issue clustering. We assert, specifically in this study, that issue clustering should be performed for a particular purpose. We analyze the results of applying our methodology to two specific perspectives on issue clustering, (i) consumers' interests, and (ii) related R&D terms.

• 지능정보연구
• /
• 제20권2호
• /
• pp.93-107
• /
• 2014

대부분의 인터넷 쇼핑몰은 자사 고객의 관심 분야를 파악하고 이를 상품 추천에 효과적으로 활용하기 위해 많은 노력을 기울이고 있다. 하지만 고객이 회원 가입 시 직접 입력한 개인 정보는 신뢰하기가 어렵고, 고객의 구매 패턴을 통해 파악한 관심 분야 정보는 자사 사이트 내에 진입한 이후에만 보인 한정된 패턴이라는 측면에서 해당 고객의 다양한 관심분야를 제대로 나타낸다고 보기 어렵다. 이러한 한계를 극복하기 위해 본 연구에서는 고객의 평소 인터넷 사용 기록을 통해 최근 방문 사이트들의 주제를 분석함으로써, 고객의 실제 관심 분야를 파악할 수 있는 방안을 제시하였다. 또한 토픽 분석을 통해 각 사이트의 주제를 도출하고 도출된 주제를 다시 동시 방문자 관점에서 군집화 함으로써, 고객 관점에서 의미가 있는 상위 수준의 새로운 테마를 발굴하기 위한 방법론을 제안하였다. 연구의 특징은 유사주제 중심의 군집화라는 기존 연구와는 달리 사용자 관점의 관심주제 중심 군집화라 할 수 있다. 향후 사용자 중심의 카테고리 설계를 비롯한 새로운 관점의 고객군 정의 등 보다 높은 차원의 마케팅 전략 수립에 활용이 가능할 것으로 기대된다. 사용자 관점의 이슈 군집화 과정은 크롤링, 토픽 분석, 액세스 패턴 분석, 네트워크 병합, 네트워크 변환 및 군집화와 같은 여섯 가지 주요단계로 구성되어있다. 이를 위해 텍스트 마이닝과 소셜 네트워크 분석 기법을 활용한 비정형 텍스트를 기반으로한 빅데이터의 활용 방법을 모색하였다. 제안 방법론의 실무 적용 가능성을 평가하기 위해, 국내 최대 포털 뉴스 사이트의 방문자 2,177명의 1년간 방문 기록과 뉴스기사 대한 분석을 수행하고 그 결과를 요약하여 제시하였다.

• Journal of Information Technology Applications and Management
• /
• 제22권3호
• /
• pp.83-103
• /
• 2015

The rapid development of internet technologies and social media over the last few years has generated a huge amount of unstructured text data, which contains a great deal of valuable information and issues. Therefore, text mining-extracting meaningful information from unstructured text data-has gained attention from many researchers in various fields. Topic analysis is a text mining application that is used to determine the main issues in a large volume of text documents. However, it is difficult to identify related issues or meaningful insights as the number of issues derived through topic analysis is too large. Furthermore, traditional issue-clustering methods can only be performed based on the co-occurrence frequency of issue keywords in many documents. Therefore, an association between issues that have a low co-occurrence frequency cannot be recognized using traditional issue-clustering methods, even if those issues are strongly related in other perspectives. Therefore, in this research, a methodology to reorganize social issues from a research and development (R&D) perspective using social network analysis is proposed. Using an R&D perspective lexicon, issues that consistently share the same R&D keywords can be further identified through social network analysis. In this study, the R&D keywords that are associated with a particular issue imply the key technology elements that are needed to solve a particular issue. Issue clustering can then be performed based on the analysis results. Furthermore, the relationship between issues that share the same R&D keywords can be reorganized more systematically, by grouping them into clusters according to the R&D perspective lexicon. We expect that our methodology will contribute to establishing efficient R&D investment policies at the national level by enhancing the reusability of R&D knowledge, based on issue clustering using the R&D perspective lexicon. In addition, business companies could also utilize the results by aligning the R&D with their business strategy plans, to help companies develop innovative products and new technologies that sustain innovative business models.

• 한국콘텐츠학회논문지
• /
• 제20권6호
• /
• pp.556-578
• /
• 2020

실시간으로 발생하는 뉴스 기사로부터 이슈를 분석하기 위한 다양한 연구가 진행되어 왔다. 하지만 범주에 따라 계층적으로 이슈를 분석하는 연구는 많이 진행되지 않았고, 계층적 이슈 분석을 위한 기존의 연구에서 제안하는 방식 또한 뉴스 기사 증가에 따라 군집화 속도가 느려지는 문제점이 있다. 따라서 본 논문에서는 준 실시간으로 뉴스 기사의 이슈를 분석하는 계층적·점증적 군집화 방식을 제안한다. 제안하는 군집화 방식은 샴 신경망을 이용한 가중 코사인 유사도 측정 모델 기반의 k-평균 알고리즘을 이용한 단어 군집 기반 문서 표현 방식을 통해 뉴스 기사를 문서 벡터로 표현한다. 그리고 문서 벡터로부터 초기 이슈 군집 트리를 생성하고, 새로 발생한 뉴스 기사를 해당 이슈 군집 트리에 추가하는 점증적 군집화 방식을 제안함으로써 뉴스 기사의 계층적 이슈를 준 실시간으로 분석한다. 마지막으로, 본 논문에서 제안하는 방식과 기존 방식들과의 성능평가를 통해 제안하는 군집화 방식이 정확도 측면에서 기존 방식 대비 NMI 지표 기준 0.26 정도 성능이 향상되었고, 속도 측면에서 약 10배 이상의 성능이 향상됨을 입증하였다.

• 대한산업공학회지
• /
• 제27권2호
• /
• pp.214-225
• /
• 2001

This research deals with an off-line learning method targeted for systematically constructing negotiation strategies in automated electronic commerce. Single-issue negotiation is assumed. Variants of competitive learning and hierarchical clustering method are devised and applied to extracting negotiation strategies, given historical negotiation data set and tactics. Our research is motivated by the following fact: evidence from both theoretical analysis and observations of human interaction shows that if decision makers have prior knowledge on the behaviors of opponents from negotiation, the overall payoff would increase. Simulation-based experiments convinced us that the proposed method is more effective than human negotiation in terms of the ratio of negotiation settlement and resulting payoff.

• Journal of Information Processing Systems
• /
• 제7권1호
• /
• pp.29-42
• /
• 2011

Wireless sensor networks are composed of a large number of sensor nodes with limited energy resources. One critical issue in wireless sensor networks is how to gather sensed information in an energy efficient way, since their energy is limited. The clustering algorithm is a technique used to reduce energy consumption. It can improve the scalability and lifetime of wireless sensor networks. In this paper, we introduce a clustering protocol with mode selection (CPMS) for wireless sensor networks. Our scheme improves the performance of BCDCP (Base Station Controlled Dynamic Clustering Protocol) and BIDRP (Base Station Initiated Dynamic Routing Protocol) routing protocol. In CPMS, the base station constructs clusters and makes the head node with the highest residual energy send data to the base station. Furthermore, we can save the energy of head nodes by using the modes selection method. The simulation results show that CPMS achieves longer lifetime and more data message transmissions than current important clustering protocols in wireless sensor networks.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제13권3호
• /
• pp.1238-1259
• /
• 2019

Saving energy is a big challenge for Wireless Sensor Networks (WSNs), which becomes even more critical in large-scale WSNs. Most energy waste is communication related, such as collision, overhearing and idle listening, so the schedule-based access which can avoid these wastes is preferred for WSNs. On the other hand, clustering technique is considered as the most promising solution for topology management in WSNs. Hence, providing interference-free clustering is vital for WSNs, especially for large-scale WSNs. However, schedule management in cluster-based networks is never a trivial work, since it requires inter-cluster cooperation. In this paper, we propose a clustering method, called Interference-Free Clustering Protocol (IFCP), to partition a WSN into interference-free clusters, making timeslot management much easier to achieve. Moreover, we model the clustering problem as a multi-objective optimization issue and use non-dominated sorting genetic algorithm II to solve it. Our proposal is finally compared with two adaptive clustering methods, HEED-CSMA and HEED-BMA, demonstrating that it achieves the good performance in terms of delay, packet delivery ratio, and energy consumption.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제14권4호
• /
• pp.1419-1436
• /
• 2020

For an energy harvesting sensor network, when the network lifetime is not the only primary goal, maximizing the network performance under environmental energy harvesting becomes a more critical issue. However, clustering protocols that aim at providing maximum information throughput have not been thoroughly explored in Energy Harvesting Wireless Sensor Networks (EH-WSNs). In this paper, clustering protocols are studied for maximizing the data transmission in the whole network. Based on a long short-term memory (LSTM) energy predictor and node energy consumption and supplement models, an uneven clustering protocol is proposed where the cluster head selection and cluster size control are thoroughly designed for this purpose. Simulations and results verify that the proposed scheme can outperform some classic schemes by having more data packets received by the cluster heads (CHs) and the base station (BS) under these energy constraints. The outcomes of this paper also provide some insights for choosing clustering routing protocols in EH-WSNs, by exploiting the factors such as uneven clustering size, number of clusters, multiple CHs, multihop routing strategy, and energy supplementing period.

• 대한음성학회:학술대회논문집
• /
• 대한음성학회 2005년도 춘계 학술대회 발표논문집
• /
• pp.87-90
• /
• 2005

Today's state-of the-art speech recognition systems typically use continuous distribution hidden Markov models with the mixtures of Gaussian distributions. To obtain higher recognition accuracy, the hidden Markov models typically require huge number of Gaussian distributions. Such speech recognition systems have problems that they require too much memory to run, and are too slow for large applications. Many approaches are proposed for the design of compact acoustic models. One of those models is subspace distribution clustering hidden Markov model. Subspace distribution clustering hidden Markov model can represent original full-space distributions as some combinations of a small number of subspace distribution codebooks. Therefore, how to make the codebook is an important issue in this approach. In this paper, we report some experimental results on various quantization methods to make more accurate models.

• 대한산업공학회지
• /
• 제34권4호
• /
• pp.460-469
• /
• 2008

Process mining aims at mining valuable information from process execution results (called "event logs"). Even though process mining techniques have proven to be a valuable tool, the mining results from real process logs are usually too complex to interpret. The main cause that leads to complex models is the diversity of process logs. To address this issue, this paper proposes a trace clustering approach that splits a process log into homogeneous subsets and applies existing process mining techniques to each subset. Based on log profiles from a process log, the approach uses existing clustering techniques to derive clusters. Our approach are implemented in ProM framework. To illustrate this, a real-life case study is also presented.