• Proceedings of the KIEE Conference
• /
• 2007.10a
• /
• pp.182-183
• /
• 2007

본 논문에서는 전형적인 비선형 회귀문제를 다루기 위해 슈뢰딩거 방정식에 의해 표현되는 Hilbert공간에서 수행되는 Quantum 클러스터링과 Mountain 함수를 이용하여, 수치적인 입출력데이터로부터 TSK 형태의 자동적인 퍼지 if-then 규칙의 생성방법을 제안한다. 여기서 슈뢰딩거 방정식은 분석적으로 확률함수로부터 유도되어질 수 있는 포텐셜 함수를 포함한다. 이 포텐셜의 최소점들은 데이터의 특성을 포함하는 클러스터 중심들과 관련되어진다. 그러나 이들 클러스터 중심들은 데이터의 수와 같으므로 퍼지 규칙을 생성하기 어려울 뿐만 아니라 수렴속도가 느린 문제점을 가지고 있다. 이러한 문제점들을 해결하기 위해서, 본 논문에서는 밀도 척도에 기초한 클러스터 중심의 근사적인 추정에 대해 간단하면서 효과적인 Mountain 함수를 이용하여 효과적인 클러스터 중심을 얻음과 동시에 적응 뉴로-퍼지 네트워크의 자동적인 퍼지 규칙을 생성하도록 한다. 자동차 MPG 예측문제에 대한 시뮬레이션 결과는 제안된 방법이 기존 문헌에서 제시한 예측성능보다 더 좋은 특성을 보임을 알 수 있었다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2019.10a
• /
• pp.809-812
• /
• 2019

소프트웨어 크래시 분류를 개선하기 위해 호출 스택 정보를 기반한 많은 연구들이 있다. 본 연구에서는 크래시 직전 이미지를 수집하여, 기존 호출 스택 기반의 분류에서 발생하는 문제를 개선하고자 한다. 또한 이미지 자체의 직관성으로 개발자뿐만 아니라 개발 지식이 없는 실무자도 크래시 정보를 활용할 수 있고, 문제 해결을 위한 재현 루트 파악, 위변조 여부와 같은 추가 정보를 확인할 수 있을 것으로 기대한다. 비지도 학습 기반인 딥러닝 클러스터링 N2D 알고리즘을 통하여 이미지를 자동 분류하고 순위화하는 시스템을 구축하여, 특정 소프트웨어에 특화되지 않고 다양한 소프트웨어의 크래시 이미지 자동 분류에 기여할 수 있을 것으로 기대한다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2009.11a
• /
• pp.935-936
• /
• 2009

본 논문에서는 과학기술문서에 존재하는 기술용어와 이들 간의 연관관계를 설명하는 디스크립터를 찾아서 [subject predicate object] 형태의 트리플을 생성하는 애플리케이션을 개발할 때 발생하는 단어 의미 애매성 해소 문제를 다룬다. 기술용어가 가지고 있는 연관관계를 결정하기 위해서 워드넷의 신셋 정보를 사용하는데 이 방법은 동사를 워드넷에 매핑할 때와 상위어 관계로 전이할 때 여러 개의 의미에 매핑되는 문제점이 발생한다. 이것을 해결하기 위해서 상위어 시퀀스 클러스터링을 이용한 단어의 의미 애매성 해결 방안을 제시한다. 이 방법을 사용함으로써 워드넷 매핑과 상위어 전이 시에 발생하는 다중 매핑 문제를 동시에 해결할 수 있다.

• Journal of KIISE:Software and Applications
• /
• v.36 no.9
• /
• pp.683-690
• /
• 2009

One of the major problems that prevent us from building a good recognition system for large-scale on-line Chinese character recognition using HMMs is increasing recognition time. In this paper, we propose a clustering method to solve recognition speed problem and an efficient distance measure between HMMs. From the experiments, we got about twice the recognition speed and 95.37% 10-candidate recognition accuracy, which is only 0.9% decrease, for 20,902 Chinese characters defined in Unicode CJK unified ideographs.

• Journal of KIISE:Information Networking
• /
• v.31 no.1
• /
• pp.101-111
• /
• 2004

As different from wired internet, wireless internet has limitations due to the following characteristics; low bandwidth, frequent disconnection, low computing power, small screen in user terminal, and user mobility. Also, wireless internet server should be scalable to handle a large scale traffic due to rapidly growing users. Wireless proxy servers are used for the wireless internet because their caching and transcoding functions are helpful to overcome the above limitation. TranSend was proposed as a clustering based wireless proxy server but its scalability is difficult to achieve because there is no systematic way to do it. In this Paper. we proposed a clustering based wireless internet proxy server which can be scalable in a systematic way. We performed experiments using 16 PCs and experimental results show 32.17% performance improvement of the proposed system compared to TranSend system.

• Journal of KIISE:Information Networking
• /
• v.36 no.2
• /
• pp.98-107
• /
• 2009

In this paper, we propose a novel centralized energy-efficient clustering algorithm, called "MCCA : Max k-Cut based Clustering Algorithm for Wireless Sensor Networks." The algorithm does not use location information and constructs clusters via a distributive Max k-Cut based cluster-head election method, where only relative and approximate distance information with neighbor nodes is used and nodes, not having enough energy, are excluded for cluster-heads for a specific period. We show that the energy efficiency performance of MCCA is better than that of LEACH, EECS and similar to BCDCP's by simulation studies.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.38 no.6
• /
• pp.712-720
• /
• 2001

In this paper, we propose an efficient method to detect abrupt shot changes in a video sequence using an unsupervised clustering. Conventional clustering-based shot change detection algorithms use multiple features in order to overcome the shortcomings of a single feature. In such methods it is very important to determine the appropriate initial cluster centers well. In this paper we propose a modified k-means clustering algorithm which estimates the initial cluster center adaptively. Experimental results show that the proposed algorithm works well.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.12 no.5
• /
• pp.451-461
• /
• 2002

Differential evolution(DE) has been preyed to be an efficient method for optimizing real-valued multi-modal objective functions. DE's main assets are its conceptual simplicity and ease of use. However, the convergence properties are deeply dependent on the control parameters of DE. This paper proposes an adaptive differential evolution(ADE) method which combines with a variant of DE and an adaptive mechanism of the control parameters. ADE contributes to the robustness and the easy use of the DE without deteriorating the convergence. 12 optimization problems is considered to test ADE. As an application of ADE the paper presents a supervised clustering method for predicting events, what is called, an evolutionary event clustering(EEC). EEC is tested for 4 cases used widely for the validation of data modeling.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.13 no.5
• /
• pp.512-519
• /
• 2003

In this paper, we propose a neuro-fuzzy modeling to improve the performance using the hierarchical clustering and Gaussian Mixture Model(GMM). The hierarchical clustering algorithm has a property of producing unique parameters for the given data because it does not use the object function to perform the clustering. After optimizing the obtained parameters using the GMM, we apply them as initial parameters for Adaptive Network-based Fuzzy Inference System. Here, the number of fuzzy rules becomes to the cluster numbers. From this, we can improve the performance index and reduce the number of rules simultaneously. The proposed method is verified by applying to a neuro-fuzzy modeling for Box-Jenkins s gas furnace data and Sugeno's nonlinear system, which yields better results than previous oiles.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.14 no.1
• /
• pp.378-384
• /
• 2013

In this paper, we propose the fuzzy neural networks based on fuzzy c-means clustering algorithm. Typically, the generation of fuzzy rules have the problem that the number of fuzzy rules exponentially increases when the dimension increases. To solve this problem, the fuzzy rules of the proposed networks are generated by partitioning the input space in the scatter form using FCM clustering algorithm. The premise parameters of the fuzzy rules are determined by membership matrix by means of FCM clustering algorithm. The consequence part of the rules is expressed in the form of polynomial functions and the learning of fuzzy neural networks is realized by adjusting connections of the neurons, and it follows a back-propagation algorithm. The proposed networks are evaluated through the application to nonlinear process.