• KIPS Transactions on Software and Data Engineering
• /
• v.5 no.8
• /
• pp.393-400
• /
• 2016

Recently, there have been various researches on efficient and automatic analysis on urban environment methods that utilize the computer vision and machine learning technology. Among many new analyses, urban safety analysis has received a major attention. In order to predict more accurately on safety score and reflect the human visual perception, it is necessary to consider the generic and local information that are most important to human perception. In this paper, we use Double-column Convolutional Neural network consisting of generic and local columns for the prediction of urban safety. The input of generic and local column used re-sized and random cropped images from original images, respectively. In addition, a new learning method is proposed to solve the problem of over-fitting in a particular column in the learning process. For the performance comparison of our Double-column Convolutional Neural Network, we compare two Support Vector Regression and three Convolutional Neural Network models using Root Mean Square Error and correlation analysis. Our experimental results demonstrate that our Double-column Convolutional Neural Network model show the best performance with Root Mean Square Error of 0.7432 and Pearson/Spearman correlation coefficient of 0.853/0.840.

• KIPS Transactions on Software and Data Engineering
• /
• v.2 no.10
• /
• pp.697-704
• /
• 2013

The identification of haplotypes, which encode SNPs in a single chromosome, makes it possible to perform haplotype-based association tests with diseases. Minimum Error Correction model, one of models to computationally assemble a pair of haplotypes for a given organism from Single Nucleotide Polymorphism fragments, has been known to be NP-hard even for gapless cases. In the previous work, an improved branch and bound algorithm was suggested and showed that it is more efficient than naive branch and bound algorithm by performing experiments for Apis mellifera (honeybee) data set. In this paper, to show the extensibility of the algorithm to other organisms we apply the improved branch and bound algorithm to the human data set and confirm the efficiency of the algorithm.

• Annual Conference on Human and Language Technology
• /
• 2023.10a
• /
• pp.80-85
• /
• 2023

기계 번역에서 품질 검증은 정답 문장 없이 기계 번역 시스템에서 생성된 번역의 품질을 자동으로 추정하는 것을 목표로 한다. 일반적으로 이 작업은 상용화된 기계 번역 시스템에서 후처리 모듈 역할을 하여 사용자에게 잠재적인 번역 오류를 경고한다. 품질 검증의 하위 작업인 치명적인 오류 탐지는 번역의 오류 중에서도 정치, 경제, 사회적으로 문제를 일으킬 수 있을 만큼 심각한 오류를 찾는 것을 목표로 한다. 본 논문은 치명적인 오류의 유무를 분류하는 것을 넘어 문장에서 치명적인 오류가 존재하는 부분을 제시하기 위한 새로운 데이터셋과 모델을 제안한다. 이 데이터셋은 거대 언어 모델을 활용하는 구축 방식을 채택하여 오류의 구체적인 범위를 표시한다. 또한, 우리는 우리의 데이터를 효과적으로 활용할 수 있는 다중 작업 학습 모델을 제시하여 오류 범위 탐지에서 뛰어난 성능을 입증한다. 추가적으로 언어 모델을 활용하여 번역 오류를 삽입하는 데이터 증강 방법을 통해 보다 향상된 성능을 제시한다. 우리의 연구는 기계 번역의 품질을 향상시키고 치명적인 오류를 줄이는 실질적인 해결책을 제공할 것이다.

• KDI Journal of Economic Policy
• /
• v.32 no.4
• /
• pp.35-73
• /
• 2010

This paper examines consumption dynamics in relation to asset prices in Korea. Empirical analysis based on the error correction model shows that personal consumption is affected by changes in asset prices but the consumption converges to the long-run level of consumption corresponding to the total income flow in two years. This adjustment in consumption implies that the consumption error, reflected in the error correction term, should have predictability for the future consumption growth during the adjustment period. It is found that the error correction term has a long-run predictability for consumption over up to about 3 years; thus, confirming the error correction model. It is also found that housing prices have larger effects on consumption compared with stock prices in Korea. In addition, the effects of income and asset prices on consumption show bigger effects during contractionary period than expansionary period in business cycles. This paper also analyzes effects of asset wealth that reflects changes in both price and quantity. It is found that asset wealth has a long-run effect on consumption in addition to total income as determinants of consumption. Since wealth effects usually indicate the long-run effect of changes in asset wealth on consumption that is not explained by labor income, which is the proxy for human source of wealth, it is estimated with labor income used as a control variable. According to the estimation, the marginal propencity to consume out of asset wealth is approximately 2%. It means that 1,000won increase in asset wealth may lead to 20 won increase in consumption.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2006.05a
• /
• pp.527-528
• /
• 2006

In the proposed research plan, the effects of anisotropic and time-dependent mechanical properties on nanoindentation measurements of osteonic lamellae in a human cortical bone are investigated. The most popular method(Oliver-Pharr method) in nanoindentation data analysis is based on the assumption of elastic isotropy. Since cortical bone has exhibited anisotropy, it is necessary to consider the effects of anisotropy on nanoindentation measurement for cortical bone. By comparison with the contact area obtained from monitoring the contact profile in FEA simulations, the Oliver-Pharr method was found to underpredict or overpredict the contact area due to effects of anisotropy. The mount of error depended on the indentation orientation. The indentation modulus results and were also similar to moduli calculated from mathematical model. The Oliver-Pharr method has been shown to be useful for providing first order approximations in analysis of anisotropic mechanical properties of cortical bone, although the indentation modulus is influenced by anisotropy.

• Annual Conference on Human and Language Technology
• /
• 2016.10a
• /
• pp.165-170
• /
• 2016

본 논문에서 제안하는 문맥의존 철자오류 교정은 통계 정보를 이용한 방법으로 통계적 언어처리에서 가장 널리 쓰이는 샤논(Shannon)이 발표한 노이지 채널 모형(noisy channel model)을 기반으로 한다. 선행연구에서 부족하였던 부분의 성능 향상을 위해 교정대상단어의 오류생성 및 통계 데이터의 저장 방식을 개선하여 Default 연산을 적용한 모델을 제안한다. 선행 연구의 모델은 교정대상단어의 오류생성 시 편집거리의 제약을 1로 하여 교정 실험을 하지만 제안한 모델은 같은 환경에서 더욱 높은 검출과 정확도를 보였으며, 오류단어의 편집거리(edit distance) 제약을 넓게 적용하더라도 신뢰도가 있는 검출과 교정을 보였다.

• Journal of Institute of Control, Robotics and Systems
• /
• v.22 no.1
• /
• pp.24-30
• /
• 2016

The accuracy of small and low-cost CCD cameras is insufficient to provide data for precisely tracking unmanned aerial vehicles (UAVs). This study shows how a quad rotor UAV can hover on a human targeted tracking object by using data from a CCD camera rather than imprecise GPS data. To realize this, quadcopter UAVs need to recognize their position and posture in known environments as well as unknown environments. Moreover, it is necessary for their localization to occur naturally. It is desirable for UAVs to estimate their position by solving uncertainty for quadcopter UAV hovering, as this is one of the most important problems. In this paper, we describe a method for determining the altitude of a quadcopter UAV using image information of a moving object like a walking human. This method combines the observed position from GPS sensors and the estimated position from images captured by a fixed camera to localize a UAV. Using the a priori known path of a quadcopter UAV in the world coordinates and a perspective camera model, we derive the geometric constraint equations that represent the relation between image frame coordinates for a moving object and the estimated quadcopter UAV's altitude. Since the equations are based on the geometric constraint equation, measurement error may exist all the time. The proposed method utilizes the error between the observed and estimated image coordinates to localize the quadcopter UAV. The Kalman filter scheme is applied for this method. Its performance is verified by a computer simulation and experiments.

• Journal of IKEEE
• /
• v.26 no.3
• /
• pp.494-499
• /
• 2022

It is reported that genome-wide RNA-seq profiles has potential as biomarkers of aging. A number of researches achieved promising prediction performance based on gene expression profiles. We develop an age prediction method based on the transcriptome of human dermal fibroblasts by selecting a proper age interval. The proposed method executes multiple rules in a sequential manner and a rule utilizes a classifier and a regression model to determine whether a given test sample belongs to the target age interval of the rule. If a given test sample satisfies the selection condition of a rule, age is predicted from the associated target age interval. Our method predicts age to a mean absolute error of 5.7 years. Our method outperforms prior best performance of mean absolute error of 7.7 years achieved by an ensemble based prediction method. We observe that it is possible to predict age based on genome-wide RNA-seq profiles but prediction performance is not stable but varying with age.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2003.06a
• /
• pp.1294-1297
• /
• 2003

With the development of medical field, many kinds of operations have been performed on human articulation. Arthroscopic surgery, which has Irrigation Pumping System for security of operator vision and washing spaces of operation, has been used for more merits than others. In this paper, it is presented that the research on a reliable control algorithm of the pumping system instrument for arthroscopic surgery. Before clinical operation, the flexible artificial articulation model is used for realizing the model the most same as human's and the algorithm has been exploited for it. This system is considered of the following; limited sensing point, dynamic effect by compliance, time delay by fluid flow and so on. The system is composed with a pressure controller, a regulator for keeping air pressure, an airtight tank that can have distilled water packs, artificial articulation and a measuring system, and has controlled by the feedback of pressure sensor on the artificial articulation. Also the system has applied to Smith Predictor for time delay and the parameter estimation method for the most suitable system with both the experiment data and modeling. In this paper, the pressure error that is between an air pressure tank and an artificial articulation was measured so that the system could be presumed and then the controller had developed for performing State-Feedback. Finally, the controller with a real microprocessor has realized. The confidence of system can be proved by applying this control algorithm to an artificial articulation experiment material.

• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• 2015.10a
• /
• pp.175-178
• /
• 2015

This paper presents a VR-simulated sailor training platform for emergency in order to prevent a human error that causes 60~80% of domestic/ abroad marine accidents. Through virtual reality technology, the proposed platform provides an interaction method for proficiency of procedures in emergency, and a crowd control method for controlling crowd agents in a virtual ship environment. The interaction method uses speech recognition and gesture recognition to enhance the immersiveness and efficiency of the training. The crowd control method provides natural simulations of crowd agents by applying a behavior model that reflects the social behavior model of human. To examine the efficiency of the proposed platform, a prototype whose virtual training scenario describes the outbreak of fire in a ship was implemented as a standalone system.