• Journal of the Korea Society of Computer and Information
• /
• v.17 no.5
• /
• pp.21-28
• /
• 2012

Recently, the necessity for good techniques of detecting network traffic attack has increased. In this paper, we suggest a new method of detecting abnormal patterns of network traffic data by visualizing their IP and port information into two dimensional images. The proposed approach first generates four 2D images from IP data of transmitters and receivers, and makes one 2D image from port data. Analyzing those images, it then extracts their major features such as linear patterns or high intensity values, and determines if traffic data contain DDoS or DoS Attacks. To comparatively evaluate the performance of the proposed algorithm, we show that our abnormal pattern detection method outperforms the existing algorithm in terms of accuracy and speed.

• Journal of Cadastre & Land InformatiX
• /
• v.51 no.1
• /
• pp.53-65
• /
• 2021

C-ITS(Cooperative Intelligent Transport System) that pursues traffic safety and convenience uses various sensors to generate traffic information. Therefore, it is necessary to improve the sensor-related technology to increase the efficiency and reliability of the traffic information. Recently, the role of CCTV in collecting video information has become more important due to advances in AI(Artificial Intelligence) technology. In this study, we propose to identify and track dynamic objects(vehicles, people, etc.) in CCTV images, and to analyze and provide information about them in various environments. To this end, we conducted identification and tracking of dynamic objects using the Yolov4 and Deepsort algorithms, establishment of real-time multi-user support servers based on Kafka, defining transformation matrices between images and spatial coordinate systems, and map-based dynamic object visualization. In addition, a positional consistency evaluation was performed to confirm its usefulness. Through the proposed scheme, we confirmed that CCTVs can serve as important sensors to provide relevant information by analyzing road conditions in real time in terms of road infrastructure beyond a simple monitoring role.

• Journal of Navigation and Port Research
• /
• v.42 no.2
• /
• pp.97-106
• /
• 2018

Despite the development of safety measures and improvements in preventive systems technologies, maritime traffic accidents that involve ships carrying hazardous and noxious substances (HNS) continuously occur owing to increased amount of HNS goods transported and the growing number of HNS fleet. To prevent maritime traffic accidents involving ships carrying HNS, this study proposes an intuitive route risk assessment technique using risk contours that can be visually and quantitatively analyzed. The proposed technique offers continuous information based on quantified values. It determines and structures route risk factors classified as absolute danger, absolute factors, and influential factors within the assessment area. The route risk is assessed in accordance with the proposed algorithmic procedures by means of contour maps overlaid on electronic charts for visualization. To verify the effectiveness of the proposed route risk assessment technique, experimental case studies under various conditions were conducted to compare results obtained by the proposed technique to actual route plans used by five representative companies operating the model ship carrying HNS. This technique is beneficial not only for assessing the route risk of ships carrying HNS, but also for identifying better route options such as recommended routes and enhancing navigation safety. Furthermore, this technique can be used to develop optimized route plans for current maritime conditions in addition to future autonomous navigation application.

• Proceedings of the Korea Society for Simulation Conference
• /
• 1997.04a
• /
• pp.86-89
• /
• 1997

This paper presents an algorithm for visualizing the traffic condition. The load of each road is updated using the incoming data collected by the devices placed at specific road crossings and junctions. The data includes the road occupancy, average speed, and vehicle types. They are analyzed to produce the 3D animation sequence of the traffic in real-time. This visualization maximizes the value of the collected data by aiding the end-users to grasp the current road situation intuitively. The traffic of a particular lane are based on the actual number of vehicles of that type passed during the last 5 minutes. This system was used in the Ministry of Construction and Public Transportation to visualize the Korean roads during the holidays around the lunar new year of 1997.

• Journal of the Korea Society of Computer and Information
• /
• v.17 no.3
• /
• pp.67-76
• /
• 2012

Traffic classification plays an important role in traffic management. To traditional methods, P2P and encryption traffic may become a problem. Support Vector Machine (SVM) is a useful classification tool which is able to overcome the traditional bottleneck. The main disadvantage of SVM algorithms is that it's time-consuming to train large data set because of the quadratic programming (QP) problem. However, the useful support vectors are only a small part of the whole data. If we can discard the useless vectors before training, we are able to save time and keep accuracy. In this article, we discussed the feasibility to remove the useless vectors through a sequential method to accelerate training speed when dealing with large scale data.

• Journal of the Korea Convergence Society
• /
• v.10 no.12
• /
• pp.315-325
• /
• 2019

The purpose of this study is to design and construct a data mart that anyone can easily analyze subway OD movement patterns. Subway OD data of the year 2017 was downloaded from the Seoul Open Data Plaza and used as the source data. A multidimensional model was designed, and Gaussian mixed cluster analysis and visualization analysis using Tableau were performed. Interestingly, movement between suburban and Seoul accounts for 23% of the total traffic. The passengers of Suwon Station move to the suburbs much more than Seoul, while Pangyo Station mostly moves to Seoul. As a result of Gaussian mixed cluster, eight clusters of OD segments were found, and the characteristics of each cluster were characterized by segment distance and passenger size.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.12 no.2
• /
• pp.213-221
• /
• 2009

An aircraft collision accident is a disaster that causes great losses of inventories and lives. Though a collision avoidance warning function is provided automatically to pilots in the aircrafts by the enhancement of the aircraft capability, achieving fast decision-making to escape a collision situation is a complex and dangerous work for pilots. If an in-flight collision situation is controlled by the air traffic control system which monitors all airplanes in the air, it would be more efficient to prevent in-flight collisions because it can handle the emergency before the pilot's action. In this paper, we develop the collision avoidance warning function in the air traffic control system. Specifically, we design and implement the five stages of the collision avoidance function, and propose a visualization method which could effectively provide the operators with the trajectories and altitudes of the aircrafts in a collision situation. By developing an in-flight collision warning function in the air traffic control system that visualizes flight patterns through the state transition data of in-flight aircrafts on the flight path lines, it can effectively prevent in-flight collisions with traffic alerts. The developed function allows operators to effectively select and control the aircraft in a collision situation by providing the operators with the expected collision time, the relative distance, and the relative altitude while assessing the level of alert, and visualizing the alert information which includes the Attention-Warning-Alert phase via embodying the TCAS standard. With the developed function the air traffic control system could sense an in-flight collision situation before the pilot's decision-making moment.

• The KIPS Transactions:PartA
• /
• v.13A no.7 s.104
• /
• pp.639-646
• /
• 2006

Data compression technologies enable us to store and transfer large amount of data efficiently, and become more and more important due to increasing data size and the network traffic. Moreover, as a result of the increase of computing power, volumetric data produced from various applied science and engineering fields has been getting much larger. In this Paper, we present a volume compression scheme which exploits Daubeches wavelet transform. The proposed scheme basically supports lossy compression for 3D volume data, and provides unit-wise random accessibility. Since our scheme shows far lower error rates than the previous compression methods based on Haar filter, it could be used well for interactive visualization applications as well as large volume data compression requiring image fidelity.

• 한국공간정보시스템학회:학술대회논문집
• /
• 2005.11a
• /
• pp.61-66
• /
• 2005

Spatiotemporal data mining represents the confluence of several fields including spatiotemporal databases, machine loaming, statistics, geographic visualization, and information theory. Exploration of spatial data mining and temporal data mining has received much attention independently in knowledge discovery in databases and data mining research community. In this paper, we introduce an algorithm Max_MOP for discovering moving sequences in mobile environment. Max_MOP mines only maximal frequent moving patterns. We exploit the characteristic of the problem domain, which is the spatiotemporal proximity between activities, to partition the spatiotemporal space. The task of finding moving sequences is to consider all temporally ordered combination of associations, which requires an intensive computation. However, exploiting the spatiotemporal proximity characteristic makes this task more cornputationally feasible. Our proposed technique is applicable to location-based services such as traffic service, tourist service, and location-aware advertising service.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2011.04a
• /
• pp.771-774
• /
• 2011

센서 네트워크 환경에서 센서 노드 간의 데이터 전송 중에 트래픽이 발생하거나 토폴로지가 수시로 변하게 됨에 따라 패킷의 손실이 자주 발생하게 된다. 본 논문에서 설계한 VSDR(Visualization Sensing Data Routing)은 GML 문서를 통해 실제 지형을 가시화 하고, Map Object의 장애물 여부를 설정하여 타겟 지역을 구성한다. 또한, AODV와 DSR을 사용하여 센서 노드간의 패킷의 이동경로와 트래픽의 양을 가시화하며, 과다 트래픽이 발생하는 구간은 경로를 변경하여 효율적으로 데이터 전송을 할 수 있다.