• 한국지능시스템학회논문지
• /
• 제16권5호
• /
• pp.568-574
• /
• 2006

사용자에게 적응된 서비스를 제공하기 위하여 환경으로부터 얻어지는 다양한 형태의 데이터를 이용한 다양한 방법이 연구되고 있다. 그 중 과거 이동 경로 자료는 사용자의 현재 이동 위치를 예측하고 이와 관련된 서비스를 제공하는데 유용하게 사용될 수 있다. 본 논문에서는 사용자의 과거 이동 경로의 분석을 통하여 이동중인 사용자의 시공간 위치예측 기술을 제안한다. 환경으로부터 발생한 사용자의 이동 경로를 수집하고, 수집된 데이터에서 이동 경로 선택(Path Selection) 방법을 이용한다. 이동 경로 선택 방법은 이동 중에 발생한 경로의 거리, 시간, 방향의 요소와 동적정합법을 사용하여 유사성(Similarity)을 측정하며 유사성이 가장 높은 경로를 선택한다. 선택된 경로는 시간에 따른 공간 정보 및 위치에 따른 시간 예측 서비스를 위하여 사용가능 하며, 실험을 통하여 유사성이 높은 이동 경로를 선택하는 모습을 확인하였다.

• International Journal of Control, Automation, and Systems
• /
• 제3권4호
• /
• pp.509-523
• /
• 2005

We are developing a novel framework, PRIDE (PRediction In Dynamic Environments), to perform moving object prediction (MOP) for autonomous ground vehicles. The underlying concept is based upon a multi-resolutional, hierarchical approach which incorporates multiple prediction algorithms into a single, unifying framework. The lower levels of the framework utilize estimation-theoretic short-term predictions while the upper levels utilize a probabilistic prediction approach based on situation recognition with an underlying cost model. The estimation-theoretic short-term prediction is via an extended Kalman filter-based algorithm using sensor data to predict the future location of moving objects with an associated confidence measure. The proposed estimation-theoretic approach does not incorporate a priori knowledge such as road networks and traffic signage and assumes uninfluenced constant trajectory and is thus suited for short-term prediction in both on-road and off-road driving. In this article, we analyze the complementary role played by vehicle kinematic models in such short-term prediction of moving objects. In particular, the importance of vehicle process models and their effect on predicting the positions and orientations of moving objects for autonomous ground vehicle navigation are examined. We present results using field data obtained from different autonomous ground vehicles operating in outdoor environments.

• 한국지반공학회:학술대회논문집
• /
• 한국지반공학회 2009년도 세계 도시지반공학 심포지엄
• /
• pp.233-242
• /
• 2009

Based on the data obtained from field investigation and soil testing to slope hazards occurrence section and non-occurrence section in crystalline rocks like gneiss, granite, and so on, a prediction model was developed by the use of a decision tree model. The classification standard of the selected prediction model is composed of the slope angle, the coefficient of permeability and the void ratio in the order. The computer program, SHAPP ver. 1.0 for prediction of slope hazards around an important national facilities using GIS technique and the developed model. To prove the developed prediction model and the computer program, the field data surveyed from Jumunjin, Gangneung city were compared with the prediction result in the same site. As the result of comparison, the real occurrence location of slope hazards was similar to the predicted section. Through the continuous study, the accuracy about prediction result of slope hazards will be upgraded and the computer program will be commonly used in practical.

• Journal of Communications and Networks
• /
• 제6권3호
• /
• pp.245-257
• /
• 2004

Driven by the growing number of the mobile subscribers, efficient channel resource management plays a key role for provisioning multimedia service in the next generation personal communication systems. To reuse limited channel resources, diminishing the coverage areas of cells seems to be the ultimate solution. Thus, however, causes more handover events. To provide seamless connection environment for mobile terminals and applications, this article presents a novel handover scheme called the intelligent channel reservation (ICR) scheme, which exploits the location prediction technologies to accurately reserve channel resources for handover connections. Considering the fact that each mobile terminal has its individual mobility characteristic, the ICR scheme utilizes a channel reserving notification procedure (CRNP) to collect adequate parameters for predicting the future location of individual mobile terminals. These parameters will be utilized by the handover prediction function to estimate the expected handover blocking rate and the expected number of idle channels. Based on the handover prediction estimations, a cost function for calculating the damages from blocking the handover connections and idling channel resources, and a corresponding algorithm for minimizing the cost function are proposed. In addition, a guard channel decision maker (GCDM) determines the appropriate number of guard channels. The experimental results show that the ICR scheme does reduce the handover-blocking rate while keeping the number of idle channels small.

• 한국해양공학회지
• /
• 제36권5호
• /
• pp.295-302
• /
• 2022

The initial response to a marine accident can play a key role to minimize the accident. Therefore, various decision support systems have been developed using sensors, simulations, and active response equipment. In this study, we developed an algorithm to predict damage locations using ship motion data with bidirectional long short-term memory (BiLSTM), a type of recurrent neural network. To reflect the low frequency ship motion characteristics, 200 time-series data collected for 100 s were considered as input values. Heave, roll, and pitch were used as features for the prediction model. The F1-score of the BiLSTM model was 0.92; this was an improvement over the F1-score of 0.90 of a prior model. Furthermore, 53 of 75 locations of damage had an F1-score above 0.90. The model predicted the damage location with high accuracy, allowing for a quick initial response even if the ship did not have flood sensors. The model can be used as input data with high accuracy for a real-time progressive flooding simulator on board.

• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2021년도 춘계학술대회
• /
• pp.389-391
• /
• 2021

국민의 안전을 위해 교통사고를 방지하고자 교통 규제는 계속 확대되고 있지만, 교통사고는 여전히 줄어들지 않고 있다. 본 연구에서는 기상청의 날씨 예측 데이터, 도로교통공단의 요일, 시간대, 장소별 교통사고 발생 데이터, 특정 위치 정보 등 다양한 요인들의 연관관계를 인공지능을 활용하여 분석함으로써 특정 시간, 장소에 대한 교통사고 발생 확률을 예측하고자 한다. 본 연구는 이전의 수많은 교통사고 발생에 대한 객관적인 데이터와 기존의 다른 연구들에서 활용되지 않은 다양한 추가 요소들을 접목시켜 더욱 향상된 교통사고 발생 확률 예측 모델을 도출한다. 본 연구 결과는 국민의 안전한 삶을 위한 다양한 교통 관련 서비스에 유용하게 활용될 수 있을 것이다.

• 한국전산구조공학회논문집
• /
• 제33권5호
• /
• pp.303-310
• /
• 2020

본 연구에서는 인공신경망을 이용해 건물 구조물의 가속도계 설치 위치 및 개수를 선정하는 방법을 제안한다. 인공신경망의 입력층에는 층에 설치되는 가속도계로부터 얻는 가속도이력데이터가 입력되며, 출력층에는 구조물을 정의하는 각 층의 질량과 강성 값을 출력하도록 신경망을 구성한다. 가속도계의 설치 위치 및 개수를 선정하기 위해 여러 설치 시나리오를 가정하고 훈련을 통해 인공신경망을 구한다. 훈련에 사용되지 않은 예제를 이용해 예측 성능을 비교하였다. 센서 개수 및 위치에 따른 예측 성능을 비교하여 설치위치 및 개수를 선정한다. 6층과 10층 예제 적용을 통해 제안하는 방법을 검증하였다.

• Journal of Communications and Networks
• /
• 제17권2호
• /
• pp.126-132
• /
• 2015

In mobile computing research area, it is highly desirable to understand the characteristics of user movement so that the user friendly location aware services could be rendered effectively. Location based social networks (LBSNs) have flourished recently and are of great potential for movement behavior exploration and datadriven application design. While there have been some efforts on user check-in movement behavior in LBSNs, they lack comprehensive analysis of social influence on them. To this end, the social-spatial influence and social-temporal influence are analyzed synthetically in this paper based on the related information exposed in LBSNs. The check-in movement behaviors of users are found to be affected by their social friendships both from spatial and temporal dimensions. Furthermore, a probabilistic model of user mobile behavior is proposed, incorporating the comprehensive social influence model with extent personal preference model. The experimental results validate that our proposed model can improve prediction accuracy compared to the state-of-the-art social historical model considering temporal information (SHM+T), which mainly studies the temporal cyclic patterns and uses them to model user mobility, while being with affordable complexity.

• 한국정보통신학회논문지
• /
• 제25권8호
• /
• pp.1005-1012
• /
• 2021

최근 웹에서 지도(Map)를 이용한 Location based Services 기반의 다양한 위치정보시스템 활용이 점점 확대되고 있으며 에너지 절약을 위한 대안으로 전력 수요 현황을 실시간으로 확인할 수 있는 모니터링 시스템의 필요성이 요구되고 있다. 본 연구에서는 딥러닝과 같은 기계학습을 이용하여 전력 수요 데이터의 특성을 분석하고 예측하는 모듈을 개발하여 지역 단위별 전력 에너지 사용 현황과 예측 추세를 실시간으로 확인할 수 있는 오픈소스 기반 지도 서비스를 이용한 딥러닝 실시간 가상 전력수요예측 웹 시스템을 개발하였다. 특히 제안한 시스템은 LSTM 딥러닝 모델을 이용하여 지역적으로 전력 수요량과 예측 분석이 실시간으로 가능하고 분석된 정보를 가시화하여 제공한다. 향후 제안된 시스템을 통해 지역별 에너지의 수급 및 예측 현황을 확인하고 분석하는데 활용될 수 있을 뿐만 아니라 다른 산업 에너지에도 적용될 수 있을 것이다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제18권7호
• /
• pp.1726-1748
• /
• 2024

Trajectory planning is vital for autonomous systems like robotics and UAVs, as it determines optimal, safe paths considering physical limitations, environmental factors, and agent interactions. Recent advancements in trajectory planning and future location prediction stem from rapid progress in machine learning and optimization algorithms. In this paper, we proposed a novel framework for Spatial-temporal transformer-based feed-forward neural networks (STTFFNs). From the traffic flow local area point of view, skip-gram model is trained on trajectory data to generate embeddings that capture the high-level features of different trajectories. These embeddings can then be used as input to a transformer-based trajectory planning model, which can generate trajectories for new objects based on the embeddings of similar trajectories in the training data. In the next step, distant regions, we embedded feedforward network is responsible for generating the distant trajectories by taking as input a set of features that represent the object's current state and historical data. One advantage of using feedforward networks for distant trajectory planning is their ability to capture long-term dependencies in the data. In the final step of forecasting for future locations, the encoder and decoder are crucial parts of the proposed technique. Spatial destinations are encoded utilizing location-based social networks(LBSN) based on visiting semantic locations. The model has been specially trained to forecast future locations using precise longitude and latitude values. Following rigorous testing on two real-world datasets, Porto and Manhattan, it was discovered that the model outperformed a prediction accuracy of 8.7% previous state-of-the-art methods.