• Proceedings of the Korea Information Processing Society Conference
• /
• 2022.05a
• /
• pp.441-442
• /
• 2022

교통사고 예측은 차량의 블랙박스 동영상을 통해 사고 발생을 최대한 빨리 예측하는 것을 목표로 한다. 이는 안전한 자율주행 시스템을 보장하는 데 중요한 역할을 한다. 다양한 교통 상황과 카메라의 제한된 시야로 인해 프레임에서 사고 가능성을 조기에 관찰하는 것은 어려운 도전이다. 예측의 핵심 기술은 객체의 시공간 관계를 학습하는 것이다. 본 논문에서는 블랙박스 동영상에서 사고 예측을 위한 계산 모델을 제안한다. 이것을 사용하여 사고 예방을 강화한다. 이 모델은 사고 위험에 대한 운전자의 시각적 인식에서 영감을 받았다. 객체 탐지기는 동영상 프레임에서 다양한 객체를 탐지한다. 탐지한 객체는 노드 생성기와 특징 추출기 동시에 통과한다. 노드 생성기에서 생성한 노드는 GCN 실행기를 사용한다. GCN 실행기는 각 프레임에 대한 객체의 3D 위치 관계를 계산한 후 공간 특징을 취득한다. 동시에 공간 특징과 특징 추출기에서 얻은 객체의 특징은 GRU 실행기로 보내진다. GRU 실행기 안에 시공간 특징을 암기하고 분석하여 교통사고 확률을 예측한다.

• 한국공간정보시스템학회:학술대회논문집
• /
• 2007.06a
• /
• pp.390-394
• /
• 2007

시간과 장소에 구애받지 않고 실시간으로 정보를 전달받을 수 있는 유비쿼터스 시대가 도래함에 있어서 실시간으로 움직이는 대상물의 위치를 알아내는 기술은 가장 근본적이며 필수적인 요소라 할 수 있다. 추측항법(Dead Reckoning)은 움직이는 대상물에 외부의 도움 없이 자신의 방향각과 가속도, 시간을 관측할 수 있는 관성항법장치(Inertial Navigation System)를 장착하여 이전의 위치 정보를 바탕으로 현재의 위치를 관측하는 방법이다. 또한 RFID(Radio Frequency IDentification)는 이러한 유비쿼터스 근거리무선통신의 핵심 기술로서 본 논문에서는 RFID에 기반한 위치 결정 시스템에 실시간 변화하는 대상물의 위치를 예측하기 위해 추측항법과 칼만필터(Kalman-filter)의 개념을 적용시켰다. 또한 RMSE(Root Mean Square Error)값을 통해 칼만필터의 적용에 따른 정확도의 향상과 각 디자인 요소들의 변화에 따라 위치의 정확도가 어떠한 변화를 갖는지를 분석하였다. 시뮬레이션 결과 칼만필터를 적용했을 때 이전보다 RMSE값이 현저히 작아지는 결과를 통해 위치의 정확도가 크게 향상되는 것을 확인하였다. 또한 RFID의 탐지 범위는 정확도에 큰 영향을 미칠 수 있는 주된 요소가 아니며, RFID 탐지 범위의 표준편차가 작을수록 위치 정확도는 높아지고, RFID 태그의 탐지 확률이 높을수록 RMSE 값의 변동이 작은 안정된 시스템을 갖으며 위치의 정확도 또한 높아진다는 것을 확인하였다.

• The Journal of Korean Institute of Electromagnetic Engineering and Science
• /
• v.30 no.5
• /
• pp.365-372
• /
• 2019

We propose a method to estimate unknown parameters(e.g., target amplitude and clutter parameters) in the generalized likelihood ratio test(GLRT) using maximum likelihood estimation and the Newton-Raphson method. When detecting targets in a clutter environ- ment, it is important to establish a modular model of clutter similar to the actual environment. These correlated clutter models can be generated using spherically invariant random vectors. We obtain the GLRT of the generated clutter model and check its detection probability using estimated parameters.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2009.04a
• /
• pp.1214-1217
• /
• 2009

무선 센서 네트워크에서 각각의 센서 노드들은 무선 통신을 통해 서로 간에 통신을 수행한다. 과거에는 이러한 센서 노드간의 통신을 제 3 자로부터 안전하게 지키는 것이 중요한 보안 이슈였다. 특히 보안 서비스를 제공 하기 위한 키 관리 기법들이 주요 연구방향이었다. 하지만 안전하게 만들어진 확률론적 키(key)를 기반으로 하는 키 사전분배 방법은 공격받은 다른 노드로 인해 자신의 키가 노출 될 수 있다. 공격자는 노출된 공유키(shared key)를 통해 노출되지 않은 정상 노드(non-compromised node) 사이의 대칭키(pairwise key)를 얻을 수 있으며, 공격자는 네트워크에 심각한 영향을 줄 수 있는 메시지 삽입 및 수정 공격을 감행할 수 있다. 이와 같은 오용된 키를 폐기하고 메시지 삽입 및 수정 공격을 막기 위해 Liu and Dong 은 오용키 탐지 방법을 제안하였다. 하지만 이들의 방법에는 한계점이 있어 이를 보완하기 위한 에너지 효율적인 오용키 탐지 기법을 제안한다.

• Journal of the Korean Geographical Society
• /
• v.52 no.1
• /
• pp.123-141
• /
• 2017

This study predicted urban green spaces for 2020 based on two scenarios keeping or freeing the green-belt in the Daegu metropolitan city using a hybrid Cellular Automata(CA)-Markov model and analyzed the spatial dynamics of urban green spaces between 2009 and 2020 using a land cover change detection technique and spatial metrics. Markov chain analysis was employed to derive the transition probability for projecting land cover change into the future for 2020 based on two land cover maps in 1998 and 2009 provided by the Ministry of Environment. Multi-criteria evaluation(MCE) was adopted to develop seven suitability maps which were empirically derived in relation to the six restriction factors underlying the land cover change between the years 1998 and 2009. A hybrid CA-Markov model was then implemented to predict the land cover change over an 11 year period to 2020 based on two scenarios keeping or freeing the green-belt. The projected land cover for 2009 was cross-validated with the actual land cover in 2009 using Kappa statistics. Results show that urban green spaces will be remarkably fragmented in the suburban areas such as Dalseong-gun, Seongseo, Ansim and Chilgok in the year 2020 if the Daegu metropolitan city keeps its urbanization at current pace and in case of keeping the green-belt. In case of freeing the green-belt, urban green spaces will be fragmented on the fringes of the green-belt. It is thus required to monitor urban green spaces systematically considering the spatial change patterns identified by this study for sustainably managing them in the Daegu metropolitan city in the near future.

• Journal of the Institute of Convergence Signal Processing
• /
• v.12 no.3
• /
• pp.204-211
• /
• 2011

Embedded systems require intensively complex and high power dissipating modules that have the capability of real-time high performance data processing, wide bandwidth communication, and low power consumption. However, the current battery technology has not been developed as much as meeting the requirements of portable embedded systems for long system lifetime. In this paper, new approach that operates with low energy consumption is proposed to overcome the situation while guaranteeing detection accuracy. The designed method associates a variety of detection algorithms hierarchically to detect events happening around the system. The Change for energy consumption characteristics is shown with change for probabilistic characteristics and those relationships are analytically explained from experiments. Furthermore, several techniques to consume low energy and achieve high detection accuracy are described, depending on the event static or dynamic characteristics.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2012.10a
• /
• pp.744-748
• /
• 2012

Botnet is a network that consists of bot hosts infected by malware. The C&C server of centralized botnet, which is being used widely, is relatively easy to detect, while detecting P2P botnet is not a trivial problem because of the existence of many avoiding techniques. In this paper, we separate the network into inner and outer sub-network at the location of the router, and analyze the method of detecting botnet using path of packet and infection probability. We have extended Dye-Pumping algorithm in order to detect P2P botnet members more accurately, and we expect that the analysis of the results can be used as a basis of techniques that detect and block P2P botnet in the networks.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.16 no.10
• /
• pp.7211-7218
• /
• 2015

Tens of thousands of malicious codes are generated on average in a day. New types of malicious codes are surging each year. Diverse methods are used to detect such codes including those based on signature, API flow, strings, etc. But most of them are limited in detecting new malicious codes due to bypass techniques. Therefore, a lot of researches have been performed for more efficient detection of malicious codes. Of them, visualization technique is one of the most actively researched areas these days. Since the method enables more intuitive recognition of malicious codes, it is useful in detecting and examining a large number of malicious codes efficiently. In this paper, we analyze the relationships between malicious codes and Native API functions. Also, by applying the word cloud with text mining technique, major Native APIs of malicious codes are visualized to assess their maliciousness. The proposed malicious code analysis method would be helpful in intuitively probing behaviors of malware.

• Journal of Internet Computing and Services
• /
• v.9 no.6
• /
• pp.27-35
• /
• 2008

With the proliferation of wireless devices, mobile ad-hoc networking (MANETS) has become a very exciting and important technology. However, MANET is more vulnerable than wired networking. Existing security mechanisms designed for wired networks have to be redesigned in this new environment. In this paper, we discuss the problem of anomaly detection in MANET. The focus of our research is on techniques for automatically constructing anomaly detection models that are capable of detecting new or unseen attacks. We propose a new anomaly detection method for MANETs. The proposed method performs cross-feature analysis on the basis of Rough sets to capture the inter-feature correlation patterns in normal traffic. The performance of the proposed method is evaluated through a simulation. The results show that the performance of the proposed method is superior to the performance of Huang method that uses cross-feature based on the probability of feature attribute value. Accordingly, we know that the proposed method effectively detects anomalies.

• The Journal of the Acoustical Society of Korea
• /
• v.36 no.3
• /
• pp.218-227
• /
• 2017

In this paper, an algorithm to calculate both bearing and distance error for target detection and localization is proposed using the Cramer Rao lower bound to estimate the minium variance of their error in DOA (Direction Of Arrival) estimation. The performance of arrays in detection and localization depends on the accuracy of DOA, which is affected by a variation of SNR (Signal to Noise Ratio). The SNR is determined by sonar parameters such as a SL (Source Level), TL (Transmission Loss), NL (Noise Level), array shape and beam steering angle. For verification of the suggested method, a Monte Carlo simulation was performed to probabilistically calculate the bearing and distance error according to the SNR which varies with the relative position of the target in space and noise level.