• Proceedings of the KIEE Conference
• /
• 2008.10b
• /
• pp.448-449
• /
• 2008

본 논문에서는 이동 로봇의 경로 추종을 위해서, 비선형 모델 예측 슬라이딩 모드 제어(nonlinear model predictive strung mode control) 기법을 제안한다. 본 논문에서 제안한 방법에서는 미래의 슬라이딩 평면을 예측하고, 이에 따른 최적화된 제어기를 유도함으로써 슬라이딩 모드 제어기 단독으로 사용하는 제언 시스템에 비해 성능을 향상시킬 수 있다. 마지막으로 컴퓨터 시뮬레이션을 통해 본 논문에서 제안한 제어기의 성능을 검증하고자한다.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2014.10a
• /
• pp.109-111
• /
• 2014

본 논문에서는 노드의 속성정보를 통해 노드의 움직임을 예측하는 PPoP(The Path Prediction algorithm based on Probability) 알고리즘을 제안한다. 기존 이동 예측 알고리즘들은 GPS(Global Positioning System)를 사용해 노드의 이동을 학습을 통해 패턴화 하여 예측한다. 이때, 노드들이 이동 패턴을 벗어날 경우 예측률이 떨어진다. 따라서 본 논문에서는 스테른 게를라흐의 실험(Stern-Gerlach experiment)을 분석하여 노드의 이동성을 예측하는 알고리즘을 제안한다. 본 논문에서 제안된 알고리즘에서는 노드의 이동 경로를 staore-carry-forward 방식으로 상황 인지에 의한 경로 설정 변경 예측 방법으로 이동 예측 확률 기법이다. 모의실험 결과 제안한 방법을 사용하여 노드의 이동성 및 패턴을 벗어난 상황에서도 노드의 예측 하고자 한다.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2012.05a
• /
• pp.848-849
• /
• 2012

In this paper, we developed a reverse parking guidance system with the path prediction methods which help the safe operation of driver when reversing, with rear camera display, and the expected path on navigation and handheld devices. This system can be applied to various types of vehicles, a variety of characteristics and installation of rear-view camera and navigation support systems, or portable devices are compatible and easily detachable, can be configured easily.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.20 no.8
• /
• pp.1581-1586
• /
• 2016

In this paper, we propose a central disaster monitoring system of the forest fire. This system provides the safe-zone and detection to reduce the suppression efforts. In existing system, it has a few providing the predicting of wildfire spread model and speed through topography, weather, fuel factor. This paper focus on the forest fire diffusion model and predictions of the path identified to ensure the safe zone. Also we have considering the forest fire of moving direction and speed for fire suppression and monitering. The proposed algorithm could provide the technique to analyze the attribute information that temperature, wind, smoke measured over time. This proposed central observing monitoring system could provide the moving direction of spred out forecast wildfire. This observing and monitering system analyze and simulation for the moving speed and direction forest fire, it could be able to predict and training the forest fire fighters in a given environment.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2017.11a
• /
• pp.1258-1261
• /
• 2017

1급 발암물질인 미세먼지 중 44.3%를 차지하고 있는 도로 비산먼지는 효과적인 미세먼지 농도 저감 대책의 방안 중 하나이다. 도로 비산먼지 제거는 일반적으로 특수 차량을 이용, 정해진 경로와 주기에 따라 운행된다. 이러한 운행방식은 도로의 오염 현황에 따른 효과적 경로 선정 및 운영이 어렵다. 본 논문에서는 도로 비산먼지 제거의 효율적인 경로 제안을 위해 대구지역에 분포된 KISTI 이동형 도시센싱 테스트베드에서 수집되는 고해상도의 실시간 지역별 오염 현황 데이터를 활용하여 실시간 오염도를 분석하고, LSTM(LONG SHORT-TERM MEMORY) 알고리즘을 활용하여 미래의 미세먼지 농도를 예측하였다. 기존 연구와 달리 지역별 상황을 고려한 데이터를 사용하여 선형 회귀 분석을 수행하였다. 실험 결과, 시간 속성을 고려한 LSTM이 MLP 보다 평균 제곱근 오차 값이 경우에 따라 최대 30% 더 작음을 확인했다. 본 연구를 기반으로 고해상도 사물 데이터 기반 예측 연구의 가능성을 보였으며, 미세먼지 예측 결과를 활용 유연하고 효과적인 도로 청소차량의 운행 경로를 설정에 활용될 수 있을 것으로 기대한다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2022.11a
• /
• pp.156-158
• /
• 2022

차량이 사용자에게 다양한 서비스를 제공하기 위해서 차량의 위치 정보를 요구하는 환경에서 차량의 위치를 예측해 미리 알 수 있다면 높은 품질의 서비스를 만드는 것에 도움이 된다. 차량은 도시 환경에서 비교적 느린 속도를 갖는다는 특징이 있고 차량의 위치를 표시하는 방법도 여러 가지다. 본 논문은 Long Short-Term Memory(LSTM)을 사용해 차량의 이동 경로를 예측하는 과정에서 이동 속도와 위치 표현 방법이 미치는 영향을 분석하였다. 실험 결과 차량의 속도가 증가할수록, 차량의 이동 표현 방법이 세밀할수록 차량 이동 경로 예측이 어렵다는 것을 확인하였다.

• Journal of Korea Spatial Information System Society
• /
• v.8 no.2 s.17
• /
• pp.109-120
• /
• 2006

This paper addresses techniques for predicting a future path of an object moving on a road network. Most prior methods for future prediction mainly focus their attention on objects moving in Euclidean space. A variety of applications such as telematics, however, deal with objects that move only over road networks in most cases, thereby requiring an effective method of future prediction of moving objects on road networks. In this paper, we propose a novel method for predicting a future path of an object by analyzing past trajectories whose changing pattern is similar to that of a current trajectory of a query object. We devise a new function that measures a similarity between trajectories by reflecting the characteristics of road networks. By using this function, we predict a future path of a given moving object as follows: First, we search for candidate trajectories that contain subtrajectories similar to a given query trajectory by accessing past trajectories stored in moving object databases. Then, we predict a future path of a query object by analyzing the moving paths along with a current position to a destination of candidate trajectories thus retrieved. Also, we suggest a method that improves the accuracy of path prediction by regarding moving paths that have just small differences as the same group.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.10a
• /
• pp.264-266
• /
• 2022

In order to apply the RNN model to the radio fingerprint-based indoor path generation technology, the data set must be continuous and sequential. However, Wi-Fi radio fingerprint data is not suitable as RNN data because continuity is not guaranteed as characteristic information about a specific location at the time of collection. Therefore, continuity information of sequential positions should be given. For this purpose, clustering is possible through classification of each region based on signal data. At this time, the continuity information between the clusters does not contain information on whether actual movement is possible due to the limitation of radio signals. Therefore, correlation information on whether movement between adjacent clusters is possible is required. In this paper, a deep learning network, a recurrent neural network (RNN) model, is used to predict the path of a moving object, and it reduces errors that may occur when predicting the path of an object by generating continuous location information for path generation in an indoor environment. We propose a method of giving correlation between clustering for generating an improved moving path that can avoid erroneous path prediction that cannot move on the predicted path.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.16 no.2
• /
• pp.185-190
• /
• 2006

Most systems in ubiquitous computing analyze context information of users which have similar propensity with demographics methods and collaborative filtering to provide personalized recommendation services. The systems have mostly used static context information such as sex, age, job, and purchase history. However the systems have limitation to analyze users' propensity accurately and to provide personalized recommendation services in real-time, because they have difficulty in considering users situation as moving path. In this paper we use users' moving path of dynamic context to consider users situation. For the prediction accuracy we complete with a path completion algorithm to moving path which is inputted to RSOM. We train the moving path to be completed by RSOM, analyze users' moving pattern and predict a future moving path. Then we recommend the nearest product on the prediction path with users' high preference in real-time. As the experimental result, MAE is lower than 0.5 averagely and we confirmed our method can predict users moving path correctly.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.1 no.2
• /
• pp.81-89
• /
• 2008

Improved EKF suggests variable path prediction to reduce the event traffic caused by the information sharing among multi-users in networked virtual environment. The three dimensional virtual space is maintained consistently by endless status information exchange among dispersed users, and periodic status transmission brings traffic overhead in network. By using the error between the measured movement trace of dynamic information and the EKF predicted, we propose the method applied to predict the mobile packet of dynamic data which is simultaneously changing. And, the simulation results of DIS dead reckoning algorithms and EKF path prediction is compared here. It followed the specific path and while moving, the proposed method which it proposes predicting with DIS dead reckoning algorithm and to compare to the mobile path of the actual object and it got near it predicts the possibility of knowing it was.