• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.45 no.5
• /
• pp.173-179
• /
• 2008

This paper proposes an efficient 1:N matching scheme for fingerprint identification. Usually, in the minutiae-based matching scheme, fingerprint matching score could be calculated by analyzing geometrical similarity between minutiae from two fingerprints. To calculate the geometrical similarity between them, it is necessary to fingerprint align a fingerprint data with the other one. The final matching score is obtained by bidirectional matching in the common fingerprint matching scheme, because the similarity between two fingerprints varies with the result of alignments. The reliability of matching score by the bidirectional matching is better than by the unidirectional matching, but it takes two times comparing with unidirectional matching. To solve the problem, this paper proposes an efficient 1:N fingerprint matching scheme based on the distribution of bidirectional matching scores for the large fingerprints database. The experimental result shows the usefulness of the proposed scheme.

• Proceedings of the Korea Multimedia Society Conference
• /
• 2002.05c
• /
• pp.449-454
• /
• 2002

네트워크 혼잡으로 인한 패킷 손실은 인터넷 망에서는 필수 불가결이고, 압축된 비디오 비트 스트림을 인터넷 망에 전송할 경우 공-시간적 도메인상에 에러 전파을 야기하므로 화질에 심각한 화질열화를 초래한다. 본 논문에서는 수신측에서 손상된 영상 일부분을 복구하기 위하여 새로운 에러 은닉 알고리즘인 EBMA(Edge detecting for Boundary Matching Algorithm)를 제안한다. 기존 BMA는 부호화된 인접한 블록의 움직임벡터들이 상당히 높은 유사도 혹은 상관도 (correlation)를 갖고 있다는 점과 손실블록과 인접블록 경계에 존재하는 화소간의 유사도를 이용하기 때문에 비교적 신뢰할 수 있지만, 손실블록과 정확히 복원된 인접블록 화소간의 방향성을 고려하지 않는 단점이 있다. 따라서 제안한 알고리즘은 에지영역을 검출하고, 검출된 에지영역에서 방향성을 조사하므로 기존 BMA 방법 보다 성능이 향상되었다. 실험결과는 제안한 알고리즘이 기존 BMA 방법보다 계산 및 화질측면에서 우월하였을 뿐만 아니라, PSNR 값과 주관적인 화질상에서도 좋은 결과를 나타내었다.

• The Journal of the Acoustical Society of Korea
• /
• v.28 no.3
• /
• pp.279-284
• /
• 2009

Speaker verification determines whether the claimed speaker is accepted based on the score of the test utterance. In recent years, methods based on Gaussian mixture models and universal background model have been the dominant approaches for text-independent speaker verification. These speaker verification systems based on these methods provide very good performance under laboratory conditions. However, in real situations, the performance of speaker verification system is degraded dramatically. For overcoming this performance degradation, the feature recombination method was proposed, but this method had a drawback that whole sub-band feature vectors are used to compute the likelihood scores. To deal with this drawback, a modified feature recombination method which can use each sub-band likelihood score independently was proposed in our previous research. In this paper, we propose a sub-band weighting method based on sub-band signal-to-noise ratio which is combined with previously proposed modified feature recombination. This proposed method reduces errors by 28% compared with the conventional feature recombination method.

• Proceedings of the KIEE Conference
• /
• 2003.11b
• /
• pp.343-346
• /
• 2003

본 논문에서는 최신 동영상 압축 표준 규격 H.264에서 화면 간 예측 부호화시 참조 화면 수가 제한되어 있을 때 부호화 효율을 최대화할 수 있는 적웅적 참조 화면 선택 기법을 제안하였다. 참조 화면 선택 시 시간적인 거리를 우선시 하는 현재 방식은 부호화 효율 측면에서 최적의 선택과는 거리가 있다. 따라서 참조 화면 선택에 있어서 실시간 온라인 상황을 가정하고 부가적인 계산을 최소화하는 것을 조건으로 했을 때 대표 화면과의 간접 비교를 통하여 현재 참조 화면들 간 상호 유사성이 가장 큰 화면을 제외하는 방법을 통해 문제를 해결하고자 하였다. 화면 간 예측 부호화 시 참조 화면 간 중복되는 요소를 최대한 줄이는 방향으로 참조 화면을 선택해 나감으로서 참조되는 샘플들을 다양화할 수 있다. 참조 화면 간 상호 유사성 판별은 대표 화면과 각 참조 화면 간 움직임 정보를 고려해 화면 간 부호화시 계산되는 8*8 블록의 R-D 비용함수 값을 사용하였다. 실험 결과 기존의 슬라이딩 윈도우 방식을 이용한 참조 화면 선택 방법에 비해 부가적인 계산이 거의 없이 부호화 효율의 개선이 있었으며 그 개선 정도는 기존의 방식에서 참조 화면을 $1{\sim}2$장 더 사용한 결과와 같았다. 이는 기존의 방법에 의해 참조 화면을 선택할 경우 나타나는 참조 화면 간 중복성을 줄였기 때문이다.

• Journal of Korea Society of Industrial Information Systems
• /
• v.29 no.2
• /
• pp.55-68
• /
• 2024

Plant engineering companies create or refer to requirements documents for each related field, such as plant process/equipment/piping/instrumentation, in different engineering departments. The process-related requirements document includes not only a description of the process but also the requirements of the equipment or related facilities that will operate it. Since the authors and reviewers of the requirements documents are different, there is a possibility that inconsistencies may occur between equipment or parts design specifications described in different requirement documents. Ensuring consistency in these matters can increase the reliability of the overall plant design information. However, the amount of documents and the scattered nature of requirements for a same equipment and parts across different documents make it challenging for engineers to trace and manage requirements. This paper proposes a method to analyze requirement sentences and calculate the similarity of requirement sentences in order to identify semantically identical sentences. To calculate the similarity of requirement sentences, we propose a named entity recognition method to identify compound words for the parts and properties that are semantically central to the requirements. A method to calculate the similarity of the identified compound words for parts and properties is also proposed. The proposed method is explained using sentences in practical documents, and experimental results are described.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2005.05a
• /
• pp.423-426
• /
• 2005

기억기반학습의 일종인 최근접 이웃(k nearest neighbor) 알고리즘은 과거의 데이터들 중에서 새로운 개체와 유사한 데이터들을 이용해서 새로운 개체의 목적 값을 예측하는 것이다. 이 경우 속성의 가중치를 계산하는 방식은 kNN의 성능을 결정하는 중요한 요소가 된다. 본 논문에서는 기존의 다른 이론들과 달리 정보이론에서 사용되는 엔트로피 개념을 이용해서 속성의 가중치를 이론적이고, 효과적으로 계산하는 새로운 방법을 제시하고자한다. 제안된 방법은 각 속성이 목적속성에 제공하는 정보의 양에 따라 가중치를 자동으로 계산하여 kNN의 성능을 향상시킨다. 마지막으로 이러한 방식의 성능을 다수의 실험을 통해 비교하였다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2010.04a
• /
• pp.443-446
• /
• 2010

질의 분류에서 어휘의 다양한 표현으로 인한 어휘 불일치문제는 성능저하의 주요 원인이다. 본 논문에서는 야후!앤써 질의응답 아카이브를 이용해서 같은 카테고리의 질의-질의쌍들에 대해 어휘-어휘 번역확률을 계산하는 방법을 제안한다. 정보검색에서 우수한 성능을 보인 어휘 사이의 번역확률을 반영하는 번역기반 언어모델이 질의 분류에서 유효함을 확인하였고 언어모델과의 비교실험을 통해 성능향상을 보였다. 어휘관계를 측정하는 방법에서 번역확률 계산방법에 따른 성능측정에서 전체 질의-대답쌍들에 대해 번역확률을 계산하는 것보다 같은 카테고리에 속하는 질의-질의쌍들에 대해 번역확률을 계산하는 것이 분류를 위해 더 좋은 번역확률임을 확인하였다.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.21 no.2
• /
• pp.224-229
• /
• 2011

Collaborative filtering is used the most for recommendation systems because it can recommend potential items. However, when there are not many items to be evaluated, collaborative filtering can be subject to the influence of similarity or preference depending on the situation or the whim of the evaluator. In addition, by recommending items only on the basis of similarity with items that have been evaluated previously without relation to the present situation of the user, the recommendations become less accurate. In this paper, in order to solve the above problems, before starting the collaborative filtering procedure, we calculated similarity not by comparing all the values evaluated by users but rather by comparing only those users who were above the average in order to improve the accuracy of the recommendations. In addition, in the ceaselessly changing ubiquitous computing environment, it is not proper to recommend service information based only on the items evaluated by users. Therefore, we used methods of calculating similarity wherein the users' real time context information was used and a high weight was assigned to similar users. Such methods improved the recommendation accuracy by 16.2% on average.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.19 no.2
• /
• pp.236-241
• /
• 2009

Information integration for distributed and heterogeneous data sources is still an open challenging, and schema matching is critical in this process. This paper presents and approach to automatic elements matching between XML application schemas using similarity measure and relaxation labeling. The semantic modeling of XML application schema has also been presented. The similarity measure method considers element categories and their properties. In an effort to achieve an optimal matching, contextual constraints are used in the relaxation labeling method. Based on the semantic modeling of XML application schemas, the compatible constraint coefficients are devised in terms of the structures and semantic relationships as defined in the semantic model. To examine the effectiveness of the proposed methods, an algorithm for XML schema matching has been developed, and corresponding computational experiments show changes of calculated values.

• Journal of the Korea Society of Computer and Information
• /
• v.11 no.4 s.42
• /
• pp.137-145
• /
• 2006

A user remembers a melody as not the combination of pitch and duration which is written in score but the contour which is composed of the relative pitch and duration. Because of the way of remembering a melody the previous Music Information Retrieval Systems which uses keyboard Playing or score as the main input melody are not easily acceptable in Query By Humming Systems. In this paper, we mention about the considerable checkpoints for Query By Humming System and previous researches. And we propose the feature extraction which is similar with the way of remembering a melody and similarity computation algorithms between melody in humming and melody in music. The proposed similarity computation algorithms solves the problem which can be happened when only uses the relative pitches by using relative durations.