• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제11권11호
• /
• pp.5459-5473
• /
• 2017

Recently, a tracking algorithm called the spatial-temporal context model has been proposed to locate a target by using the contextual information around the target. This model has achieved excellent results when the target undergoes slight occlusion and appearance changes. However, the target location in the current frame is based on the location in the previous frame, which will lead to failure in the presence of fast motion because of the lack of a prediction mechanism. In addition, the spatial context model is updated frame by frame, which will undoubtedly result in drift once the target is occluded continuously. This paper proposes two improvements to solve the above two problems: First, four possible positions of the target in the current frame are predicted based on the displacement between the previous two frames, and then, we calculate four confidence maps at these four positions; the target position is located at the position that corresponds to the maximum value. Second, we propose a target reliability criterion and design an adaptive threshold to regulate the updating speed of the model. Specifically, we stop updating the model when the reliability is lower than the threshold. Experimental results show that the proposed algorithm achieves better tracking results than traditional STC and other algorithms.

• 정보과학회 논문지
• /
• 제44권4호
• /
• pp.411-416
• /
• 2017

적외선 표적의 정밀한 모델링을 위해서는 정확한 표면온도 계산이 필요하다. 본 논문에서는 전도, 대류, 복사를 고려한 복합 열해석 모듈을 소프트웨어로 구현하고, 이를 통하여 표적 재질 및 자세, 환경 요건에 따른 표적의 표면온도 해석을 수행 하였다. 구현된 결과는 상용 소프트웨어인 OKTAL-SE 와의 비교를 통하여 결과의 신뢰성을 검증하였다. 그 결과 자체 검증이 완료된 상용 소프트웨어인 OKTAL-SE 와 약 1% 이내의 오차를 보였다. 계산된 온도 결과를 바탕으로 적외선 표적 모델링을 수행하였으며 OKTAL-SE와의 연동을 통해 적외선 신호 해석을 수행하였다.

• 한국컴퓨터정보학회논문지
• /
• 제8권2호
• /
• pp.31-36
• /
• 2003

본 논문은 주성분 분석에 의한 특징 탐색 기법의 가속화 방법을 제안하고 있다. 특징 탐색이란 주어진 영상이 찾고자 하는 특징을 포함하고 있는지의 여부를 판단하고, 만일 그 특징이 포함되어 있다면 그 위치와 영역을 결정하는 방법이다. 탐색 대상으로 하는 얼굴 또는 특징의 위치와 스케일을 미리 알 수 없으므로 모든 위치에서 다양한 스케일의 특징에 대한 존재 가능성을 계산해야하는데 이것은 방대한 공간에서의 탐색문제이다. 본 논문에서는 다단계 예측맵과 윤곽선 예측맵을 이용함으로써 탐색공간을 축소하고 빠른 얼굴 및 특징 탐색을 가능케하는 방법을 제안하고 있다. 실험결과, 제안된 방법이 기존의 전역탐색방법에 비하여 계산량을 10％이하로 줄일 수 있었다.

• 한국철도학회논문집
• /
• 제15권3호
• /
• pp.278-285
• /
• 2012

경전철 민자사업에서는 서비스 품질에 대한 핵심성과지표(KPI)로서 승객관점에서의 서비스가용도가 사용된다. 그러나 국내 경험이 부족한 서비스가용도는 목표 값 설정 시 많은 논쟁이 발생되어 왔다. 서비스가용도 목표값은 시스템 사양서 및 운전운영계획에 반영하기 위하여 프로젝트 초기단계에 설정되어야 한다. 따라서 본 논문에서는 경전철 프로젝트 초기단계에서 합리적으로 달성 가능한 서비스가용도 목표 값을 설정하기 위하여 서비스가용도를 정량적으로 예측할 수 있는 예측모델을 개발하였다. 또한 서비스가용도 목표 값 설정 시 가장 많이 비교되는 열차 정시성을 이론적으로 모델링하여 서비스 가용도와 열차정시성과의 관계와 차이점을 분석하였다.

• 제어로봇시스템학회논문지
• /
• 제9권12호
• /
• pp.1033-1041
• /
• 2003

A new visual tracking scheme is proposed for a mobile robot that tracks a moving object in 3D space in real time. Visual tracking is to control a mobile robot to keep a moving target at the center of input image at all time. We made it possible by simplifying the relationship between the 2D image frame captured by a single camera and the 3D workspace frame. To precisely calculate the input vector (orientation and distance) of the mobile robot, the speed vector of the target is determined by eliminating the speed component caused by the camera motion from the speed vector appeared in the input image. The problem of temporary disappearance of the target form the input image is solved by selecting the searching area based on the linear prediction of target motion. The experimental results have shown that the proposed scheme can make a mobile robot successfully follow a moving target in real time.

• 한국IT서비스학회지
• /
• 제13권3호
• /
• pp.221-233
• /
• 2014

Because people's interest of the stock market has been increased with the development of economy, a lot of studies have been going to predict fluctuation of stock prices. Latterly many studies have been made using scientific and technological method among the various forecasting method, and also data using for study are becoming diverse. So, in this paper we propose stock prices prediction models using sentiment analysis and machine learning based on news articles and SNS data to improve the accuracy of prediction of stock prices. Stock prices prediction models that we propose are generated through the four-step process that contain data collection, sentiment dictionary construction, sentiment analysis, and machine learning. The data have been collected to target newspapers related to economy in the case of news article and to target twitter in the case of SNS data. Sentiment dictionary was built using news articles among the collected data, and we utilize it to process sentiment analysis. In machine learning phase, we generate prediction models using various techniques of classification and the data that was made through sentiment analysis. After generating prediction models, we conducted 10-fold cross-validation to measure the performance of they. The experimental result showed that accuracy is over 80% in a number of ways and F1 score is closer to 0.8. The result can be seen as significantly enhanced result compared with conventional researches utilizing opinion mining or data mining techniques.

• 한국IT서비스학회지
• /
• 제11권4호
• /
• pp.233-250
• /
• 2012

In this paper, credit card delinquency means the possibility of occurring bad debt within the certain near future from the normal accounts that have no debt and the problem is to predict, on the monthly basis, the occurrence of delinquency 3 months in advance. This prediction is typical binary classification problem but suffers from the issue of data imbalance that means the instances of target class is very few. For the effective prediction of bad debt occurrence, Support Vector Machine (SVM) with kernel trick is adopted using credit card usage and payment patterns as its inputs. SVM is widely accepted in the data mining society because of its prediction accuracy and no fear of overfitting. However, it is known that SVM has the limitation in its ability to processing the large-scale data. To resolve the difficulties in applying SVM to bad debt occurrence prediction, two stage clustering is suggested as an effective data reduction method and ensembles of SVM models are also adopted to mitigate the difficulty due to data imbalance intrinsic to the target problem of this paper. In the experiments with the real world data from one of the major domestic credit card companies, the suggested approach reveals the superior prediction accuracy to the traditional data mining approaches that use neural networks, decision trees or logistics regressions. SVM ensemble model learned from T2 training set shows the best prediction results among the alternatives considered and it is noteworthy that the performance of neural networks with T2 is better than that of SVM with T1. These results prove that the suggested approach is very effective for both SVM training and the classification problem of data imbalance.

• 한국정밀공학회:학술대회논문집
• /
• 한국정밀공학회 2003년도 춘계학술대회 논문집
• /
• pp.133-136
• /
• 2003

In these days, the reliability analysis and prediction are applied for many industrial products and many products require guaranteeing the quality and efficiency of their products. In this study reliability prediction for core units of machine tools has been performed in order to improve and analyze its reliability. ATC(Automatic Tool Changer) and interface Card of PC-NC that are core component of the machine tools were chosen as the target of the reliability prediction. A reliability analysis tool was used to obtain the reliability data(failure rate database) for reliability prediction. It is expected that the results of reliability prediction be applied to improve and evaluate its reliability. Failure rate, MTBF (Mean Time Between Failure) and reliability for core units of machine tools were evaluated and analyzed in this study.

• 한국농공학회지
• /
• 제44권5호
• /
• pp.96-105
• /
• 2002

As an useful water purification system for non-point source pollution in rural watersheds, interests in constructed wetlands are growing at home and abroad. It is well known that constructed wetlands are easily installed, no special managemental needs, and more flexible at fluctuating influent loads. They have a capacity for purification against nutrient materials such as phosphorus and nitrogen causing eutrophication of lentic water bodies. The Constructed Wetland Design Model (CWDM), developed through this study is consisted mainly of Database System, Runoff-discharge Prediction Submodel, Water Quality Prediction Submodel, and Area Assessment Submodel. The Database System includes data of watershed, discharge, water quality, pollution source, and design factors for the constructed wetland. It supplies data when predicting water quality and calculating the required areas of constructed wetlands. For the assessment of design flow, the GWLF (Generalized Watershed Loading Function) is used, and for water quality prediction in streams estimating influent pollutant load, Water Quality Prediction Submodel, that is a submodel of DSS-WQMRA model developed by previous works is amended. The calculation of the required areas of constructed wetlands is achieved using effluent target concentrations and area calculation equations that developed from the monitoring results in the United States. The CWDM is applied to Bokha watershed to appraise its application by assessing design flow and predicting water quality. Its application is performed through two calculations: one is to achieve each target effluent concentrations of BOD, SS, T-N and T-P, the other is to achieve overall target effluent concentrations. To prove the validity of the model, a comparison of unit removal rates between the calculated one from this study and the monitoring result from existing wetlands in Korea, Japan and United States was made. As a result, the CWDM could be very useful design tool for the constructed wetland in rural watersheds and for the non-point source pollution management.

• 한국통신학회논문지
• /
• 제31권8A호
• /
• pp.745-751
• /
• 2006

OFDM 시스템에 적응전송방식을 적용하기 위해서 송신단은 사용자의 정확한 채널 정보를 획득하여야 하지만, 고속의 이동성을 가지는 실외 환경의 경우, 실제 채널과 적응 전송시 고려하는 채널이 달라지기 때문에 시스템 성능열화가 발생하게 된다. 이를 해결하기 위하여 채널예측 기법을 적응전송방식에 적용하는 연구가 시작되고 있다. 그러나 대부분의 채널 예측 기법은 정해진 시간동안, 예를 들면 한 슬롯동안 채널의 변화가 없다는 가정에서 제안되었다. 따라서 이러한 기술들은 한 슬롯 내에서 빠르게 변하는 채널에 기인하여 발생하는 Packet Error Rate 성능 열화 문제를 해결할 수 없다. 본 논문에서는 빠른 시변채널에서 적응전송방식을 적용하기 위한 새로운 OFDM/FDD 시스템 기반 채널 예측 기법을 제안한다. 제안하는 채널 예측 기법은 한 슬롯 내에서 변하는 채널의 시변 특성을 고려하여 채널을 예측하는 특징을 가진다. 시뮬레이션 결과에 의하면 ITU-R Veh A 30km/h 채널에서 제안하는 채널 예측 기법을 이용하여 적응 변조 및 코딩을 수행하는 OFDM/FDD 시스템은 기존의 일반적인 채널예측 방식을 이용하는 경우에 비하여 시스템 Throughput의 손실이 없이 Target PER 1%를 보장할 수 있다.