• Analytical Science and Technology
• /
• v.24 no.6
• /
• pp.544-555
• /
• 2011

The acute toxicity in the rainbow trout (Oncorhynchus mykiss) was analyzed and predicted using quantitative structure-activity relationships (QSAR). The aquatic toxicity, 96h $LC_{50}$ (median lethal concentration) of 275 organic pesticides, was obtained from EU-funded project DEMETRA. Prediction models were derived from 558 2D molecular descriptors, calculated in PreADMET. The linear (multiple linear regression) and nonlinear (support vector machine and artificial neural network) learning methods were optimized by taking into account the statistical parameters between the experimental and predicted p$LC_{50}$. After preprocessing, population based forward selection were used to select the best subsets of descriptors in the learning methods including 5-fold cross-validation procedure. The support vector machine model was used as the best model ($R^2_{CV}$=0.677, RMSECV=0.887, MSECV=0.674) and also correctly classified 87% for the training set according to EU regulation criteria. The MLR model could describe the structural characteristics of toxic chemicals and interaction with lipid membrane of fish. All the developed models were validated by 5 fold cross-validation and Y-scrambling test.

• Journal of KIISE:Software and Applications
• /
• v.37 no.2
• /
• pp.85-94
• /
• 2010

This paper introduces a novel way to leverage convolution parse tree kernel to extract the interaction information between two proteins in a sentence without multiple features, clues and complicated kernels. Our approach needs only the parse tree alone of a candidate sentence including pairs of protein names which is potential to have interaction information. The main contribution of this paper is two folds. First, we show that for the PPI, it is imperative to execute parse tree pruning removing unnecessary context information in deciding whether the current sentence imposes interaction information between proteins by comparing with the latest existing approaches' performance. Secondly, this paper presents that tree kernel decay factor can play an pivotal role in improving the extraction performance with the identical learning conditions. Consequently, we could witness that it is not always the case that multiple kernels with multiple parsers perform better than each kernels alone for PPI extraction, which has been argued in the previous research by presenting our out-performed experimental results compared to the two existing methods by 19.8% and 14% respectively.

• KIPS Transactions on Software and Data Engineering
• /
• v.6 no.4
• /
• pp.203-210
• /
• 2017

In this paper, we propose an effective neural network model for image caption generation and model transfer. This model is a kind of multi-modal recurrent neural network models. It consists of five distinct layers: a convolution neural network layer for extracting visual information from images, an embedding layer for converting each word into a low dimensional feature, a recurrent neural network layer for learning caption sentence structure, and a multi-modal layer for combining visual and language information. In this model, the recurrent neural network layer is constructed by LSTM units, which are well known to be effective for learning and transferring sequence patterns. Moreover, this model has a unique structure in which the output of the convolution neural network layer is linked not only to the input of the initial state of the recurrent neural network layer but also to the input of the multimodal layer, in order to make use of visual information extracted from the image at each recurrent step for generating the corresponding textual caption. Through various comparative experiments using open data sets such as Flickr8k, Flickr30k, and MSCOCO, we demonstrated the proposed multimodal recurrent neural network model has high performance in terms of caption accuracy and model transfer effect.

• Proceedings of the Korean Nuclear Society Conference
• /
• 1997.10a
• /
• pp.335-341
• /
• 1997

운전중 노심의 출력변화를 감시하는 노외계측기(Excore Detector)는 노내계측기(Incore Detector)를 통하여 측정되어진 축방향 출력편차(Axial Offset)를 이용하여 교정되고 있다. 노외 계측기의 전류와 축방향출력편차의 선형적인 관계를 가정하여 노내계측기로 최소한 4회 노심출력을 측정한후 최소자승법(Least Square Method)으로 비례상수들을 구하는 기존의 방법을 대신하여, 단순 노외계측기 교정법은 노내계측기로 1회 측정되어진 자료들을 이용하여 계측기 반응상수(Detector Response Factor)를 계산한 후 비례상수를 계산한다. 계측기반응상수는 2차원 중성자수송모델로부터 계산된 weighting factor와 3차원 확산이론으로부터 구한 노심출력을 이용하여 계산된다. 중성자수송계산은 (R-Z)와 (R-$ heta$)모델을 합성하여 3차원 weighting factor를 계산하므로 축방향 영향뿐만 아니라 집합체별 영향을 고려하였다. 또한 노심의 복잡한 구조로 인하여 근사적인 weighting (actor와 노심출력분포의 사용은 노외계측기의 전류와 계측기반응율의 불일치를 초래하며, 이를 해결하는 상수를 소개하여 보다 정확한 교정결과를 얻도록하였다. 이와 같은 방법을 고리 3호기 9, 10주기 전주기와 11주기초에 적용하여 노심의 연소분포, 냉각수의 온도분포, 노심의 연소도, 노심출력준위등에 대한 단순 노외계측기 교정법의 오차를 분석하여 최적의 노외계측기 교정모델을 제시하였다. 2차원 중성자수송모델 합성법에 의한 단순노외계측기 교정법은 2차원 (R-Z) 중성자수송모델보다 개선된 결과와 평균오차 0.179% 최대 오차 0.624%를 보여주고 있다.하면 조사 후의 조직안정성에도 크게 기여할 것으로 기대된다.EX>O가 각각 첨가된 경우, Ar-4vol.%H$_2$ 분위기보다 H$_2$분위기에서 소결했을 때 밀도가 더 높았다. 그러나, 결정립은 $UO_2$와 $UO_2$-Li$_2$O의 경우, 수소분위기에서 소결했을 때, (U,Ce)O$_2$와 (U,Ce)O$_2$-Li$_2$O에서는 Ar-4vol.%H$_2$분위기에서 소결했을 때 더욱 성장하였다.설명해 줄 수 있다. 넷째, 불규칙적이며 종잡기 힘들고 단편적인 것으로만 보이던 중간언어도 일정한 체계 속에서 변화한다는 사실을 알 수 있다. 다섯째, 종전의 오류 분석에서는 지나치게 모국어의 영향만 강조하고 다른 요인들에 대해서는 다분히 추상적인 언급으로 끝났지만 이 분석을 통 해서 배경어, 목표어, 특히 중간규칙의 역할이 괄목할 만한 것임을 가시적으로 관찰할 수 있 다. 이와 같은 오류분석 방법은 학습자의 모국어 및 관련 외국어의 음운규칙만 알면 어느 학습대상 외국어에라도 적용할 수 있는 보편성을 지니는 것으로 사료된다.없다. 그렇다면 겹의문사를 [-wh]의리를 지 닌 의문사의 병렬로 분석할 수 없다. 예를 들어 누구누구를 [주구-이-ν가] [누구누구-이- ν가]로부터 생성되었다고 볼 수 없다. 그러므로 [-wh] 겹의문사는 복수 의미를 지닐 수 없 다. 그러면 단수 의미는 어떻게 생성되는가\ulcorner 본 논문에서는 표면적 형태에도 불구하고 [-wh]의미의 겹의문사는 병렬적 관계의 합성어가 아니라 내부구조를 지

• Journal of The Korean Association For Science Education
• /
• v.33 no.2
• /
• pp.229-248
• /
• 2013

The purpose of this study is to develop sequential concept tests (ConcepTest) for teachers' conceptual change on the straight propagation of light through in-service training of science teachers by peer instruction. We revised the ConcepTests for attaining the goal concept by implementing similar training courses for teachers three times and analyzing the results using both Hake gain and verbal protocol. The final form helped most teachers to reach the goal concept. While teachers are solving a given concept problem test, they had shown not only significant cognitive conflict to select one among candidate answers, but also used the concept obtained through the previous problem. The sequential ConcepTests developed in this study can be useful for training elementary and secondary teachers or pre-service teacher education.

• Journal of Broadcast Engineering
• /
• v.17 no.1
• /
• pp.73-80
• /
• 2012

Recently, medical equipments are developed and used for diagnosis or studies. In addition, demand of techniques which automatically deal with three dimensional medical images obtained from the medical equipments is growing. One of the techniques is automatic bone segmentation which is expected to enhance the diagnosis efficiency of osteoporosis, fracture, and other bone diseases. Although various researches have been proposed to solve it, they are unable to be used in practice since a size of the medical data is large and there are many low contrast boundaries with other tissues. In this paper, we present a fast and accurate automatic framework for bone segmentation based on multi-resolutions. On a low resolution step, a position of the bone is roughly detected using constrained branch and mincut which find the optimal template from the training set. Then, the segmentation and the registration are iteratively conducted on the multiple resolutions. To evaluate the performance of the proposed method, we make an experiment with femur and tibia from 50 test knee magnetic resonance images using 100 training set. The proposed method outperformed the constrained branch and mincut in aspect of segmentation accuracy and implementation time.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.22 no.3
• /
• pp.471-479
• /
• 2018

Recently, the spread of smart TV based Android iOS Set Top box has become common. This paper propose a new approach to control the TV using gestures away from the era of controlling the TV using remote control. In this paper, the AdaBoost algorithm is applied to gesture recognition by using a mono camera. First, we use Camshift-based Body tracking and estimation algorithm based on Gaussian background removal for body coordinate extraction. Using global and local feature vectors, we recognized gestures with speed change. By tracking the time interval trajectories of hand and wrist, the AdaBoost algorithm with CART algorithm is used to train and classify gestures. The principal component feature vector with high classification success rate is searched using CART algorithm. As a result, 24 optimal feature vectors were found, which showed lower error rate (3.73%) and higher accuracy rate (95.17%) than the existing algorithm.

• KIPS Transactions on Software and Data Engineering
• /
• v.2 no.10
• /
• pp.723-730
• /
• 2013

This paper presents the design of an arm gesture recognition system using Kinect sensor. A variety of methods have been proposed for gesture recognition, ranging from the use of Dynamic Time Warping(DTW) to Hidden Markov Models(HMM). Our system learns a unique HMM corresponding to each arm gesture from a set of sequential skeleton data. Whenever the same gesture is performed, the trajectory of each joint captured by Kinect sensor may much differ from the previous, depending on the length and/or the orientation of the subject's arm. In order to obtain the robust performance independent of these conditions, the proposed system executes the feature transformation, in which the feature vectors of joint positions are transformed into those of angles between joints. To improve the computational efficiency for learning and using HMMs, our system also performs the k-means clustering to get one-dimensional integer sequences as inputs for discrete HMMs from high-dimensional real-number observation vectors. The dimension reduction and discretization can help our system use HMMs efficiently to recognize gestures in real-time environments. Finally, we demonstrate the recognition performance of our system through some experiments using two different datasets.

• Journal of the Korean School Mathematics Society
• /
• v.24 no.1
• /
• pp.39-57
• /
• 2021

In this study, mathematical analysis is conducted by focusing to the 'size' of the 'point' and the 'line'. The textbook descriptions of the 'point' and the 'line' in the geometry content area of middle school mathematics 1 by the 2015 revised Korean mathematics curriculum and US geometry textbooks were compared and analyzed between. First, as a result of mathematical analysis of' 'the size of a point and a segment', it was found that the mathematical perspectives could be different according to 1) the size of a point is based on the recognition and exclusion of 'infinitesimal', and 2) the size of the segment is based on the 'measure theory' and 'set theory'. Second, as a result of analyzing textbook descriptions of the 'point' and the 'line', 1) in the geometry content area of middle school mathematics 1 by the 2015 revised Korean mathematics curriculum, after presenting a learning activity that draws a point with 'physical size' or line, it was developed in a way that describes the 'relationship' between points and lines, but 2) most of the US geometry textbooks introduce points and lines as 'undefined terms' and explicitly states that 'points have no size' and 'lines have no thickness'. Since the description of points and lines in the geometry content area of middle school mathematics 1 by the 2015 revised Korean mathematics curriculum may potentially generate mathematical intuitions that do not correspond to the perspective of Euclid geometry, this study suggest that attention is needed in the learning process about points and lines.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2014.10a
• /
• pp.733-735
• /
• 2014

Example based Super Resolution(SR) is using the correspondence between the low and high resolution image from a database. This method uses only one image to estimate a high resolution image and can get the larger image than 2 times. Example based SR is proposed to solve the problem of classical SR. Neighbor embedding(NE) has been inspired by manifold learning method, particularly locally linear embedding. However, the poor generalization of NE decreases the performance of such algorithm. The sizes of local training sets are always too small to improve the performance of NE. We propose the advanced NE baesd on SVR having an excellent generalization ability to solve this problem. Given a low resolution image, we estimate a pixel in its high resolution version by using SVR based NE. Through experimental results, we quantitatively and qualitatively confirm the improved results of the proposed algorithm when comparing with conventional interpolation methods and NE.