• Bulletin of the Korean Chemical Society
• /
• 제30권11호
• /
• pp.2717-2722
• /
• 2009

The use of the classification and regression tree (CART) methodology was studied in a quantitative structure-activity relationship (QSAR) context on a data set consisting of the binding affinities of 39 imidazobenzodiazepines for the α1 benzodiazepine receptor. The 3-D structures of these compounds were optimized using HyperChem software with semiempirical AM1 optimization method. After optimization a set of 1481 zero-to three-dimentional descriptors was calculated for each molecule in the data set. The response (dependent variable) in the tree model consisted of the binding affinities of drugs. Three descriptors (two topological and one 3D-Morse descriptors) were applied in the final tree structure to describe the binding affinities. The mean relative error percent for the data set is 3.20%, compared with a previous model with mean relative error percent of 6.63%. To evaluate the predictive power of CART cross validation method was also performed.

• Water Engineering Research
• /
• 제2권1호
• /
• pp.33-48
• /
• 2001

For the design of suitable aquatic habitats and habitat management purposes, sensitive descriptors for aquatic areas were identified and analyzed. The classification system of the aquatic areas were developed for natural streams and modified streams in Korea. Relationships among the descriptors of an aquatic area such as channel width, meander wave length, and arc angle have been defined. The analysis indicates that the total mean sinuosity is 1.25 for the main channels of natural streams, whereas the mean value of the sinuosity of modified streams is 1.14. The mean values of the total area, the width, and the length for the sandbars of natural streams are larger than those of modified streams.

• Bulletin of the Korean Chemical Society
• /
• 제17권2호
• /
• pp.147-152
• /
• 1996

To see the quantitative relationship between the structures of the C-7 substituted quinolones and their antibacterial activities, theoretical parameters such as the molecular van der Waals volume, surface area and some electrostatic parameters based on the molecular electrostatic potential, which represent lipophilicity, and some quantum mechanical parameters are introduced as descriptors. The sixteen substituted quinolone derivatives and twenty bacteria are used for the study. It is found that the QSARs of C-7 substituted quinolones are obtained for eleven bacteria and our descriptors are more useful for Gram positive organisms than negative ones. It is also shown that molecular surface area (or molecular Waals volume) of the C-7 substituent and net charge of C-7 atom of the quinolones are the descriptors of utmost importance.

• 한국멀티미디어학회논문지
• /
• 제25권1호
• /
• pp.52-60
• /
• 2022

Few-shot learning is a sub-area of machine learning problems, which aims to classify target images that only contain a few labeled samples for training. As a representative few-shot learning method, the Prototypical network has been received much attention due to its simplicity and promising results. However, the Prototypical network uses the sample mean of samples from the same class as the prototypes of that class, which easily results in learning uncharacteristic features in the low-data scenery. In this study, we propose to use local descriptors (i.e., patches along the channel within feature maps) from the same class to explicitly obtain more representative prototypes for Prototypical Network so that significant intra-class feature information can be maintained and thus improving the classification performance on few-shot learning tasks. Experimental results on various benchmark datasets including mini-ImageNet, CUB-200-2011, and tiered-ImageNet show that the proposed method can learn more discriminative intra-class features by the local descriptors and obtain more generic prototype representations under the few-shot setting.

• ETRI Journal
• /
• 제27권6호
• /
• pp.806-809
• /
• 2005

The main goal of this research is automatic video analysis using a face recognition technique. In this paper, an automatic video management system is introduced with a variety of functions enabled, such as index, edit, summarize, and retrieve multimedia data. The automatic management tool utilizes MPEG-7 visual descriptors to generate a video index for creating a summary. The resulting index generates a preview of a movie, and allows non-linear access with thumbnails. In addition, the index supports the searching of shots similar to a desired one within saved video sequences. Moreover, a face recognition technique is utilized to personalbased video summarization and indexing in stored video data.

• Genomics & Informatics
• /
• 제7권4호
• /
• pp.212-216
• /
• 2009

WebChemDB is an integrated chemical database retrieval system that provides access to over 8 million publicly available chemical structures, including related information on their biological activities and direct links to other public chemical resources, such as PubChem, ChEBI, and DrugBank. The data are publicly available over the web, using two-dimensional (2D) and three-dimensional (3D) structure retrieval systems with various filters and molecular descriptors. The web services API also provides researchers with functionalities to programmatically manipulate, search, and analyze the data.

• Bulletin of the Korean Chemical Society
• /
• 제22권4호
• /
• pp.388-394
• /
• 2001

Quantitative Structure-Activity Relationship (QSAR) have been established of 57 fluorovinyloxyacetamides compounds to correlate and predict EC50 values. Genetic algorithm (GA) and multiple linear regression analysis were used to select the descriptors and to generate the equations that relate the structural features to the biological activities. This equation consists of three descriptors calculated from the molecular structures with molecular mechanics and quantum-chemical methods. The results of MLR and GA show that dipole moment of z-axis, radius of gyration and logP play an important role in growth inhibition of barnyard grass.

• Bulletin of the Korean Chemical Society
• /
• 제26권12호
• /
• pp.2007-2016
• /
• 2005

An artificial neural network (ANN) is successfully presented for prediction acidity constant (pKa) of various benzoic acids and phenols with diverse chemical structures using a nonlinear quantitative structure-property relationship. A three-layered feed forward ANN with back-propagation of error was generated using six molecular descriptors appearing in the multi-parameter linear regression (MLR) model. The polarizability term $(\pi_1)$, most positive charge of acidic hydrogen atom $(q^+)$, molecular weight (MW), most negative charge of the acidic oxygen atom $(q^-)$, the hydrogen-bond accepting ability $(\epsilon_B)$ and partial charge weighted topological electronic (PCWTE) descriptors are inputs and its output is pKa. It was found that properly selected and trained neural network with 205 compounds could fairly represent dependence of the acidity constant on molecular descriptors. For evaluation of the predictive power of the generated ANN, an optimized network was applied for prediction pKa values of 37 compounds in the prediction set, which were not used in the optimization procedure. Squared correlation coefficient $(R^2)$ and root mean square error (RMSE) of 0.9147 and 0.9388 for prediction set by the MLR model should be compared with the values of 0.9939 and 0.2575 by the ANN model. These improvements are due to the fact that acidity constant of benzoic acids and phenols in water shows nonlinear correlations with the molecular descriptors.

• 방송공학회논문지
• /
• 제13권6호
• /
• pp.962-965
• /
• 2008

2차원 형상기술자는 형상의 특성을 수치화하여 형상의 분류와 비교를 가능하게 하며, 영상 검색 및 3차원 모델 검색 등에 적용되어왔다. 기존에 개발된 기술자들은 한 형상의 외곽선에 해당하는 폐곡선만을 기술하거나 정밀성이 떨어진다는 한계가 있었다. 이에 따라 본 논문에서는 하나 이상의 폐곡선으로 이루어진 다중형상에 적용하기 위한 다중 곡률-단계 공간 (Multi Curvature-Scale Space) 기술자를 제안한다. 구체적으로, 하나의 폐곡선을 기술하는데 뛰어난 곡률-단계공간 기술자를 각 폐곡선에 적용하고, 이와 함께 전체 형상내의 각 폐곡선들의 배치 형태를 수치화하여 전체 형상을 기술한다. 또한, 기술자를 구성하는 각 값의 가중치를 조절할 수 있게 하여 사용자에 따른 유사도의 모호함을 극복할 수 있게 하였다. 제시하는 다양한 실험 결과는 제안하는 기술자의 유용함을 나타낸다.

• 한국문헌정보학회지
• /
• 제35권4호
• /
• pp.97-122
• /
• 2001

본 연구에서는 레코드필드 선택이 대규모 서지 데이터베이스 탐색시 미치는 검색 성능에 대하여 관찰하였다. 실험의 구성 요소는 크게 (1) 대규모 상업용 데이터베이스 INSPEC. (2) 관련된 레코드들 (target sets이라고 정의함). (3) 4개의 키워드가 한 세트로 이루어진 4개의 서로 다른 형태의 질의어들 (CT_TF, CT_IDF, UT_TF, UT_IDF), (4) 최적의 질의를 위한 알고리즘, (5) 가능한 모든 경우의 탐색식을 생성해내는 블리언 탐색식 생성기, 그리고 (6) 실제 운영중인 웹 기반의 검색 시스템으로 이뤄졌다. 실험에서의 레코드 필드 선택은 (1) Abstract, (2) Descriptors, (3) Identifiers, (4) 'Subject'(Descriptors + Identifiers). (5) Title. (6) 'All fields'로 정의하여 독립변수로 채택하였다. 검색 성능은 재현율, 정도율을 모두 반영한 Heine의 D측정에 의하여 평가 되었다. 본 연구에서 얻은 주된 결과로는 (1) 필드선택은 검색성능에 중요한 영향을 미치며, (2) 각 검색 성능에서 보여준 순위는 질의어에 따라 민감한 결과를 보였고 (3) 제목(Title)필드 선택이 D측정에서 최적의 결과를 보였다.