• Journal of the Korean Data and Information Science Society
• /
• 제22권6호
• /
• pp.1029-1040
• /
• 2011

본 연구에서는 실제 환경에 적용 가능한 지능형 자율 이동 방법을 개발하기 위해 위치정보를 사용하지 않고 지도 작성이 가능한 지능형 이동 알고리즘을 제안한다. 제안한 알고리즘은 온라인으로 동작하면서 위치 정보를 사용하지 않고 지도 작성이 가능 할 뿐 아니라 현실 세계에 적용 가능하기 위해 많은 계산량을 요구하지도 않는다. 이는 이동 로봇의 실세계 주행과 같은 대용량의 이미지 처리가 필요한 경우에는 매우 유용하게 사용될 수 있다. 토이 자료와 대용량 자료에 대해 제안한 알고리즘을 적용한 결과 기존의 방법에 비해 적은 메모리와 새로운 입력에 대해 고유공간을 새로 계산하지 않아도 되어 로봇의 현실세계의 주행에도 문제가 없는 것으로 판단되었다.

• 자동차안전학회지
• /
• 제14권4호
• /
• pp.77-83
• /
• 2022

Occupant behaviors and body contact with vehicle interior parts are main injury mechanism in far-side collisions. In vehicle side impact accident where the crash accident occurs on the opposite side of the vehicle from the a particular occupant, it is exposed in terms of relatively larger lateral motion to interact with the opposite side of the vehicle structure. The challenge of minimizing motions of upper body and injury risk according to a direct contact is a primary occupant protection research. This study has performed a data analysis of real-world accident database extracted from the 2016~2020 CISS database and a parametric investigation of impact angles and occupant kinematics in far-side lateral and oblique impact simulations. A detailed data analysis was conducted to reveal the relationship among the accident and injury data. Database analysis and computational far-side impact results proposed the fundamental vehicle design for safety improvement in far-side collisions.

• Journal of Information Processing Systems
• /
• 제18권2호
• /
• pp.268-281
• /
• 2022

The development of information technology is bringing many changes to everyday life, and machine learning can be used as a technique to solve a wide range of real-world problems. Analysis and utilization of data are essential processes in applying machine learning to real-world problems. As a method of processing data in machine learning, we propose an approach based on applying multiple linear regression models by interlacing data to the task of classifying similar software. Linear regression is widely used in estimation problems to model the relationship between input and output data. In our approach, multiple linear regression models are generated by training on interlaced feature data. A combination of these multiple models is then used as the prediction model for classifying similar software. Experiments are performed to evaluate the proposed approach as compared to conventional linear regression, and the experimental results show that the proposed method classifies similar software more accurately than the conventional model. We anticipate the proposed approach to be applied to various kinds of classification problems to improve the accuracy of conventional linear regression.

• 대한원격탐사학회지
• /
• 제23권5호
• /
• pp.365-373
• /
• 2007

Car navigation system is a key application in geographic information system and telematics. A recent trend of car navigation system is using real video captured by camera equipped on the vehicle, because video has more representation power about real world than conventional map. In this paper, we suggest a visual car navigation system that visually represents route guidance. It can improve drivers' understanding about real world by capturing real-time video and displaying navigation information overlaid directly on the video. The system integrates real-time data acquisition, conventional route finding and guidance, computer vision, and augmented reality display. We also designed visual navigation controller, which controls other modules and dynamically determines visual representation methods of navigation information according to current location and driving circumstances. We briefly show implementation of the system.

• 한국멀티미디어학회논문지
• /
• 제19권1호
• /
• pp.22-29
• /
• 2016

Hidden Markov Model is one of the most successful and popular tools for modeling real world sequential data. Real world signals come in a variety of shapes and variabilities, among which temporal and spectral ones are the prime targets that the HMM aims at. A new problem that is gaining increasing attention is characterizing missing observations in incomplete data sequences. They are incomplete in that there are holes or omitted measurements. The standard HMM algorithms have been developed for complete data with a measurements at each regular point in time. This paper presents a modified algorithm for a discrete HMM that allows substantial amount of omissions in the input sequence. Basically it is a variant of Baum-Welch which explicitly considers the case of isolated or a number of omissions in succession. The algorithm has been tested on online handwriting samples expressed in direction codes. An extensive set of experiments show that the HMM so modeled are highly flexible showing a consistent and robust performance regardless of the amount of omissions.

• 한국게임학회 논문지
• /
• 제16권6호
• /
• pp.69-78
• /
• 2016

FPS 게임 속 시가지 맵에서 간판, 현수막, 벽보 등의 옥외광고가 흔히 등장한다. 본 논문은 실제 상권들의 옥외광고를 FPS 게임의 시가지 맵에 자동으로 배치하는 방법을 제안한다. 옥외광고는 실제 제품이나 기업의 광고이며 서버에서 관리된다. 실제 광고가 업데이트 되는 경우 게임 소스를 수정하지 않고도 자동으로 배치된다. 광고의 배치에 있어서 플레이어의 위치와 실제 상권의 위치의 관계, 실제 상점의 서비스 형태 등을 활용한다. 수집한 속성들에 우선순위 점수를 부여하여 높은 순위가 우선적으로 맵에 배치된다. 제안하는 배치 방법은 플레이어의 위치를 기반으로 광고를 배치하므로 친근감 유발과 함께 광고 효과를 높일 수 있다.

• 기술혁신연구
• /
• 제16권2호
• /
• pp.65-94
• /
• 2008

There has been rapid diffusion of digital innovation technology(DIT) such as 3 D CAD, CAE, simulation software which enable firms to see the future results of intended product designs through 3 D diagram and simulated results. This technology helps firms to reduce trial and error process by solving later stage problems in earlier stages. The DIT being the technology reflecting the real world, as a tool representing the simplified form of the real world, the degree of reflecting the real world(fidelity) is important in utilizing the DIT. This study is an exploratory research examining the process of reviewing the fidelity of the DITs and developing the complementary process necessary for utilizing the DIT with 'not good enough' fidelity. This study could draw out, from its case study, an exploratory hypothesis about the process of developing the complementary process. In the process, there is an analysis of the corresponding relationship between the actual data and the output data of the DIT, e.g. simulated result. Then the input data or output data are adjusted on the basis of the analysis of the corresponding relationship so that the discrepancy between the actual data and the expected interpretation of the output data, through the adjustment, of the DIT, can be reduced. This process is sometimes accompanied by the process of generating experimental data, which reflect the unique situation of the product development process of a company, to be put to the data base of DIT. The complementary process is the process requiring knowledge sharing and adjustment activities across different divisions. This study draw outs implications for effective management of the fidelity of DIT tools.

• 로봇학회논문지
• /
• 제3권2호
• /
• pp.117-122
• /
• 2008

This paper presents a multi-robot localization based on multidimensional scaling (MDS) in spite of the existence of incomplete and noisy data. While the traditional algorithms for MDS work on the full-rank distance matrix, there might be many missing data in the real world due to occlusions. Moreover, it has no considerations to dealing with the uncertainty due to noisy observations. We propose a robust MDS to handle both the incomplete and noisy data, which is applied to solve the multi-robot localization problem. To deal with the incomplete data, we use the Nystr$\ddot{o}$m approximation which approximates the full distance matrix. To deal with the uncertainty, we formulate a Bayesian framework for MDS which finds the posterior of coordinates of objects by means of statistical inference. We not only verify the performance of MDS-based multi-robot localization by computer simulations, but also implement a real world localization of multi-robot team. Using extensive empirical results, we show that the accuracy of the proposed method is almost similar to that of Monte Carlo Localization(MCL).

• Communications for Statistical Applications and Methods
• /
• 제31권3호
• /
• pp.323-336
• /
• 2024

The accurate forecasting of insurance claims is a critical component for insurers' risk management decisions. Hierarchical Bayesian parametric (BP) models can be used for health insurance claims forecasting, but they are unsatisfactory to describe the claims distribution. Therefore, Bayesian nonparametric (BNP) models can be a more suitable alternative to deal with the complex characteristics of the health insurance claims distribution, including heavy tails, skewness, and multimodality. In this study, we apply both a BP model and a BNP model to predict group health claims using simulated and real-world data for a private life insurer in Indonesia. The findings show that the BNP model outperforms the BP model in terms of claims prediction accuracy. Furthermore, our analysis highlights the flexibility and robustness of BNP models in handling diverse data structures in health insurance claims.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2002년도 ITC-CSCC -2
• /
• pp.1248-1251
• /
• 2002

Logistics optimization problems related with vehicle routing such as warehouse locating, track scheduling, customer order delivery, wastage pickup etc. are very interesting and important issues to date. Many Vehicle Routing and Scheduling Systems (VRSS) have been developed/proposed to optimize the logistics problems. But majority of them are dedicated to a particular problem and are unable to handle the real world spatial data directly. The system developed for one problem may not be suitable for others due to inter-problem constraint variations. The constraints may include geographical, environmental and road traffic nature of the working region along with other constraints related with the problem. So the developer always needs to modify the original routing algorithm in order to fulfill the purpose. In our study, we propose a general-purpose platform by combining GIS road map and Database Management System (DBMS), so that VRSS can interact with real world spatial data directly to solve different kinds of vehicle routing problems. Using the features of our developed system, the developer can frequently modify the existing algorithm or create a new one to serve the purpose.