• 한국지능시스템학회논문지
• /
• 제17권1호
• /
• pp.1-6
• /
• 2007

거리측도를 이용한 유사도를 구성하였고 제안된 유사도의 유용성을 증명을 통하여 확인 하였다. 퍼지 넘버와 무게 중심 법을 이용한 기존의 유사도 구성에 대한 결과를 소개하였고 두 가지의 유사도를 다양한 형태의 소속 함수에 대하여 유사도 계산을 통하여 비교하였다.

• Architectural research
• /
• 제17권2호
• /
• pp.57-64
• /
• 2015

In architectural planning, previous cases of similar spatial program provide important data for architectural design. Case-based reasoning (CBR) paradigm in the field of architectural design is closely related to the designing behavior of a planner who makes use of similar architectural designs and spatial programs in the past. In CBR, spatial graph can be constituted with most fundamental data, which can provide a method of searching spatial program by using visual graphs. This study developed a system for CBR that can analyze the similarity through graph comparison and search for buildings. This is an integrated system that is able to compare space similarity of different buildings and analyze their types, in addition to the analysis on a space within a single structure.

• Journal of Welding and Joining
• /
• 제12권3호
• /
• pp.63-70
• /
• 1994

Laser processing workmen should select the working condition for laser cutting of new materials by the preparatory experiments for that material or from the past experiences in cutting of other similar materials. This paper proposes a criterion to determine how much a material is similar to other materials by using the Sugeno fuzzy integral. With the proposed criterion the laser processing workman can objectify the considered material for his decision. The expert system programmer can give the system a high flexibility by experimenting with some materials in a large range of similarity and can support the laser processing workman by offering the similarity between materials.

• 한국컴퓨터정보학회논문지
• /
• 제21권11호
• /
• pp.121-126
• /
• 2016

In recommender systems based on collaborative filtering, measuring similarity is very critical for determining the range of recommenders. Data sparsity problem is fundamental in collaborative filtering systems, which is partly solved by Jaccard coefficient combined with traditional similarity measures. This study proposes a new coefficient for improving performance of Jaccard coefficient by compensating for its drawbacks. We conducted experiments using datasets of various characteristics for performance analysis. As a result of comparison between the proposed and the similarity metric of Pearson correlation widely used up to date, it is found that the two metrics yielded competitive performance on a dense dataset while the proposed showed much better performance on a sparser dataset. Also, the result of comparing the proposed with Jaccard coefficient showed that the proposed yielded far better performance as the dataset is denser. Overall, the proposed coefficient demonstrated the best prediction and recommendation performance among the experimented metrics.

• 산업경영시스템학회지
• /
• 제29권4호
• /
• pp.91-99
• /
• 2006

A POP system, which collects manufacturing data from the shop floors and supply them to higher level systems, should be maintained and upgraded according to the change of production environment such as new product introduction. This situation leads to the need of a cost-effective system development methodology. In this paper, a methodology based on the classification and the similarity comparison of manufacturing processes is proposed. In this, a new product is classified according to the similarity of its manufacturing processes, which enables recycling of existing system modules. The proposed methodology has been tested in the case of an electronics parts manufacturing company, where a POP system is implemented. The result shows that the proposed methodology can save time and efforts for system implementation.

• International Journal of Computer Science & Network Security
• /
• 제24권6호
• /
• pp.1-7
• /
• 2024

Comparing text features involves evaluating the "similarity" between texts. It is crucial to use appropriate similarity measures when comparing similarities. This study utilized various techniques to assess the similarities between newspaper articles, including deep learning and a previously proposed method: a combination of Pointwise Mutual Information (PMI) and Word Pair Matching (WPM), denoted as PMI+WPM. For performance comparison, law data from medical research in Japan were utilized as validation data in evaluating the PMI+WPM method. The distribution of similarities in text data varies depending on the evaluation technique and genre, as revealed by the comparative analysis. For newspaper data, non-deep learning methods demonstrated better similarity evaluation accuracy than deep learning methods. Additionally, evaluating similarities in law data is more challenging than in newspaper articles. Despite deep learning being the prevalent method for evaluating textual similarities, this study demonstrates that non-deep learning methods can be effective regarding Japanese-based texts.

• Interdisciplinary Bio Central
• /
• 제3권4호
• /
• pp.14.1-14.9
• /
• 2011

Protein homology detection is an important issue in comparative genomics. Because of the exponential growth of sequence databases, fast and efficient homology detection tools are urgently needed. Currently, for homology detection, sequence comparison methods using local alignment such as BLAST are generally used as they give a reasonable measure for sequence similarity. However, these methods have drawbacks in offering overall sequence similarity, especially in dealing with eukaryotic genomes that often contain many insertions and duplications on sequences. Also these methods do not provide the explicit models for speciation, thus it is difficult to interpret their similarity measure into homology detection. Here, we present a novel method based on Word Conservation Score (WCS) to address the current limitations of homology detection. Instead of counting each amino acid, we adopted the concept of 'Word' to compare sequences. WCS measures overall sequence similarity by comparing word contents, which is much faster than BLAST comparisons. Furthermore, evolutionary distance between homologous sequences could be measured by WCS. Therefore, we expect that sequence comparison with WCS is useful for the multiple-species-comparisons of large genomes. In the performance comparisons on protein structural classifications, our method showed a considerable improvement over BLAST. Our method found bigger micro-syntenic blocks which consist of orthologs with conserved gene order. By testing on various datasets, we showed that WCS gives faster and better overall similarity measure compared to BLAST.

• 한국멀티미디어학회논문지
• /
• 제8권11호
• /
• pp.1439-1448
• /
• 2005

본 논문에서는 입력된 영상에서 색상 정보와 얼굴에서 주요한 특징정보의 기하 위치 분석과 추출 객체의 유사도 비교를 이용해서 얼굴 영역을 검출한 후 비율정보와 유사도를 이용해 사용자 인증을 하는 방법에 대해서 기술한다. 색상 정보를 이용한 얼굴 추출 알고리즘은 얼굴의 기울어진 정도나 크기 등에 영향을 받지 않는 장점을 가지고 있으므로 형태정보를 이용한 얼굴 추출 알고리즘에 비해 비교우위를 가진다. 하지만 색상 정보를 기반으로 하기 때문에 조명의 변화나, 피부색과 유사한 배경 등 색상에 대해 민감해서 정확한 성능을 유지하기 어렵다. 따라서 색상 정보 이외에 얼굴의 주요 특징 요소인 눈과 입술 등의 특징 정보를 검출하고 각 객체에 대한 유사도 비교를 수행함으로서 색상 정보를 이용한 방법에 비해 더 효율적으로 사용될 수 있다. 본 논문에서는 얼굴을 각각의 개체단위로 분할한 후 각 개체의 비율적인 특징을 계산하고 특정 계산식에 가중치를 부여하며 분할된 눈과 입의 유사도 검색을 통해 유사성을 확인함으로써 사용자를 인식하는 시스템을 제안한다. 제안한 방법을 실험하고 그 결과의 분석을 통해 인식률이 높아짐을 알 수 있었다.

• Genomics & Informatics
• /
• 제11권3호
• /
• pp.135-141
• /
• 2013

Gene set analysis is a powerful tool for interpreting a genome-wide association study result and is gaining popularity these days. Comparison of the gene sets obtained for a variety of traits measured from a single genetic epidemiology dataset may give insights into the biological mechanisms underlying these traits. Based on the previously published single nucleotide polymorphism (SNP) genotype data on 8,842 individuals enrolled in the Korea Association Resource project, we performed a series of systematic genome-wide association analyses for 49 quantitative traits of basic epidemiological, anthropometric, or blood chemistry parameters. Each analysis result was subjected to subsequent gene set analyses based on Gene Ontology (GO) terms using gene set analysis software, GSA-SNP, identifying a set of GO terms significantly associated to each trait ($p_{corr}$ < 0.05). Pairwise comparison of the traits in terms of the semantic similarity in their GO sets revealed surprising cases where phenotypically uncorrelated traits showed high similarity in terms of biological pathways. For example, the pH level was related to 7 other traits that showed low phenotypic correlations with it. A literature survey implies that these traits may be regulated partly by common pathways that involve neuronal or nerve systems.

• 산업경영시스템학회지
• /
• 제44권2호
• /
• pp.15-23
• /
• 2021

Most of the open-source decision tree algorithms are based on three splitting criteria (Entropy, Gini Index, and Gain Ratio). Therefore, the advantages and disadvantages of these three popular algorithms need to be studied more thoroughly. Comparisons of the three algorithms were mainly performed with respect to the predictive performance. In this work, we conducted a comparative experiment on the splitting criteria of three decision trees, focusing on their interpretability. Depth, homogeneity, coverage, lift, and stability were used as indicators for measuring interpretability. To measure the stability of decision trees, we present a measure of the stability of the root node and the stability of the dominating rules based on a measure of the similarity of trees. Based on 10 data collected from UCI and Kaggle, we compare the interpretability of DT (Decision Tree) algorithms based on three splitting criteria. The results show that the GR (Gain Ratio) branch-based DT algorithm performs well in terms of lift and homogeneity, while the GINI (Gini Index) and ENT (Entropy) branch-based DT algorithms performs well in terms of coverage. With respect to stability, considering both the similarity of the dominating rule or the similarity of the root node, the DT algorithm according to the ENT splitting criterion shows the best results.