• Proceedings of the Korean Information Science Society Conference
• /
• 2006.06b
• /
• pp.244-246
• /
• 2006

웹 기반 교육 시스템에서 문제 집합 구성은 주로 고정 출제 방식, 무작위 출제 방식, 난이도에 따른 출제 방식으로 이루어진다. 문제 집합의 구성 시 문제 은행에서 문제 난이도에 대한 객관성을 유지하는 것이 무엇보다 중요하다. 따라서 본 논문에서는 난이도를 재조정하는데 학습자들의 문제 풀이 결과를 반영하는 새로운 난이도 재조정 알고리즘을 제시한다. 본 논문에서 제안하는 학습자 피드백 기반 문제 수준 조절 방법은 개인 시험 결과, 그룹 시험 결과 그리고 개인의 특정 섹션 시험 결과를 함께 고려하여 난이도를 조절한다. 기존 알고리즘과 비교 분석한 결과 문제 난이도의 변화율 측면에서 보다 현실적인 문제 난이도 변화를 확인할 수 있었다.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.11 no.3
• /
• pp.619-626
• /
• 2007

Constructive induction is a technique to draw useful attributes from given primitive attributes to classify given examples more efficiently. Useful attributes are obtained from given primitive attributes by applying appropriate operators to them. The paper proposes a constructive induction approach for a GA-based inductive learning environment that learns classification rules that ate similar to rules used in PROSPECTOR from given examples. The paper explains our constructive induction approach in details, centering on operators to combine primitive attributes and methods to evaluate the usefulness of derived attributes, and presents the results of various experiments performed to evaluate the effect of our constructive induction approach on the GA-based learning environment.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.24 no.6
• /
• pp.1065-1078
• /
• 2014

Considering the safety of the data and performance, it can be said that the performance of the AES algorithm in a symmetric key-based encryption is the best in the IPSec-based VPN. When using the AES algorithm in IPSec-based VPN even with the expensive hardware encryption card such as OCTEON Card series of Cavium Networks, the Performance of VPN works less than half of the firewall using the same hardware. In 2008, Intel announced a set of 7 AES-NI instructions in order to improve the performance of the AES algorithm on the Intel CPU. In this paper, we verify how much the performance IPSec-based VPN can be improved when using seven sets of AES-NI instruction of the Intel CPU.

• KIISE Transactions on Computing Practices
• /
• v.21 no.7
• /
• pp.494-499
• /
• 2015

As the size of data increases, it becomes important to identify properties by analyzing big data. In this paper, we propose a k-Means based efficient clustering technique, called MCSKMeans (Multi centroid set k-Means), using distributed parallel processing framework MapReduce. A problem with the k-Means algorithm is that the accuracy of clustering depends on initial centroids created randomly. To alleviate this problem, the MCSK-Means algorithm reduces the dependency of initial centroids using sets consisting of k centroids. In addition, we apply the agglomerative hierarchical clustering technique for creating k centroids from centroids in m centroid sets which are the results of the clustering phase. In this paper, we implemented our MCSK-Means based on the MapReduce framework for processing big data efficiently.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.35 no.2A
• /
• pp.112-120
• /
• 2010

In this paper, we propose semi-ML adaptive parallel QRDM (APQRDM) and iterative QRDM (AIQRDM) algorithms based on set grouping. Using the set grouping, the tree-search stage of QRDM algorithm is divided into partial detection phases (PDP). Therefore, when the treesearch stage of QRDM is divided into 4 PDPs, the APQRDM latency is one fourth of that of the QRDM, and the hardware requirements of AIQRDM is approximately one fourth of that of QRDM. Moreover, simulation results show that in $4{\times}4$ system and at Eb/N0 of 12 dB, APQRDM decreases the average computational complexity to approximately 43% of that of the conventional QRDM. Also, at Eb/N0 of 0dB, AIQRDM reduces the computational complexity to about 54% and the average number of metric comparisons to approximately 10% of those required by the conventional QRDM and AQRDM.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2004.10a
• /
• pp.463-466
• /
• 2004

본 논문에서는 각 입력 변수에 대하여 퍼지 공간을 분할한 퍼지 집합 기반 퍼지 추론 시스템을 제안한다. 퍼지 모델은 주로 경험적 방법에 의해 추출되기 때문에 보다 구체적이고 체계적인 방법에 의한 동정 및 최적화 쥘 필요성이 요구된다. 정보 granules는 근접성, 유사성 또는 기능성 등의 기준에 의해 서로 결합된 물체(특히, 데이터 점)의 연결된 모임으로 간주된다. 정보 데이터의 특성을 살리기 위해 HCM 클러스터링 방법에 의한 중심71을 이용하여 각 입력 변수에 대한 퍼지 집합 기반 전반부/후반부 구조 및 파라미터를 동정한다. 퍼지 추론 방법은 간략 및 선형 퍼지 추론을 수행하며 삼각형 멤버쉽 함수를 사용한다. 구축된 퍼지 모델은 유전자 알고리즘을 이용하여 전반부 파라미터를 최적으로 동정하며, 학습 및 테스트 데이터의 성능 결과의 상호균형을 얻기 위한 하중값을 가진 성능지수를 사용하여 근사화와 예측성능의 향상을 꾀한다. 또한, 제안된 퍼지 모델은 수치적인 예를 통하여 성능을 평가한다.

• Journal of KIISE:Databases
• /
• v.41 no.4
• /
• pp.256-261
• /
• 2014

The problem of top-${\kappa}$ set similarity joins finds the top-${\kappa}$ pairs of records ranked by their similarities between two sets of input records. We propose an efficient algorithm to return top-${\kappa}$ similarity join pairs using a sampling technique. From a sample of the input records, we construct a histogram of set similarity joins, and then compute an estimated similarity threshold in the histogram for top-${\kappa}$ join pairs within the error bound of 95% confidence level based on statistical inference. Finally, the estimated threshold is applied to the traditional similarity join algorithm which uses the min-heap structure to get top-${\kappa}$ similarity joins. The experimental results show the good performance of the proposed algorithm on large real datasets.

• The Transactions of the Korea Information Processing Society
• /
• v.13 no.2
• /
• pp.13-17
• /
• 2024

In this paper, union-based rule antecedent neuro-fuzzy controller, which can guarantee a parsimonious knowledge base with reduced number of rules, is proposed. The proposed neuro-fuzzy controller allows union operation of input fuzzy sets in the antecedents to cover bigger input domain compared with the complete structure rule which consists of AND combination of all input variables in its premise. To construct the proposed neuro-fuzzy controller, we consider the multiple-term unified logic processor (MULP) which consists of OR and AND fuzzy neurons. The fuzzy neurons exhibit learning abilities as they come with a collection of adjustable connection weights. In the development stage, the genetic algorithm (GA) constructs a Boolean skeleton of the proposed neuro-fuzzy controller, while the stochastic reinforcement learning refines the binary connections of the GA-optimized controller for further improvement of the performance index. An inverted pendulum system is considered to verify the effectiveness of the proposed method by simulation and experiment.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2002.11c
• /
• pp.1709-1712
• /
• 2002

지식 탐사 연구의 핵심이 되어온 데이터 마이닝은 축적 데이터로부터 쉽게 추출되지 않는 데이터 상호관계나 일정 패턴과 같은 유용한 내재 정보 추출을 주된 목적으로 수행된다. 그러나, 데이터 마이닝은 대용량의 데이터 처리로 인해 빈번한 메모리 공간 제약과 처리 속도 저하 등의 한계성을 드러낸다. 이를 극복하기 위해 많은 마이닝 알고리즘 개발과 기존 알고리즘 개선 방법이 제시되어 왔으나 여전히 궁극적인 해결방안은 대두되지 않고 있다. 따라서, 만약 데이터 전처리 과정을 통해 마이닝 목적에 적합한 부분 데이터집합 추출 및 가공이 선행된다면 보다 효율적인 데이터 마이닝 작업을 유도할 수 있을 것이다. 본 논문은 효과적 데이터 전처리를 위한 필수 기본 연산 기능들을 주어진 데이터집합의 트랜잭션 및 데이터 특성에 기초하여 관계형 대수 형태로 의미를 정립하고, 적용 사례에 의한 상세 설명 및 실제 구현된 온라인 데이터 전처리 시스템을 제안한다.

• Journal of KIISE:Software and Applications
• /
• v.33 no.2
• /
• pp.252-266
• /
• 2006

Many problems in computer vision are mainly based on mathematical models. Their optimal solutions can be found by estimating the parameters of each model. However, provided an input data set is involved outliers which are relative]V larger than normal noises, they lead to incorrect results. RANSAC is a representative robust algorithm which is used to resolve the problem. One major problem with RANSAC is that it needs priori knowledge(i.e. a percentage of outliers) of the distribution of data. To solve this problem, we propose a FRANSAC algorithm which improves the rejection rate of outliers and the accuracy of solutions. This is peformed by categorizing all data into good sample set, bad sample set and vague sample set using a fuzzy classification at each iteration and sampling in only good sample set. In the experimental results, we show that the performance of the proposed algorithm when it is applied to the linear regression and the calculation of a homography.