• Proceedings of the Korea Information Processing Society Conference
• /
• 2021.05a
• /
• pp.441-442
• /
• 2021

본 논문에서는 고해상도의 시계열 위성영상을 딥러닝 알고리즘으로 학습하여 도시 변화탐지를 수행한다. 고해상도 위성영상을 활용한 서비스는 4 차 산업혁명 융합 신사업 중 하나인 스마트시티에 적용하여 도시 노후화, 교통 혼잡, 범죄 등 다양한 도시 문제 해결 및 효율적인 도시를 구축하는데 활용이 가능하다. 이에 본 연구에서는 도시 변화탐지를 위한 딥러닝 알고리즘으로 DeepLabV3+를 사용한다. 이는 인코더-디코더 구조로, 공간 정보를 점진적으로 회복함으로써 더욱 정확한 물체의 경계면을 찾을 수 있다. 제안하는 방법은 DeepLabV3+의 레이어와 loss function 을 수정하여 기존보다 좋은 결과를 얻었다. 객관적인 성능평가를 위해, 공개된 데이터셋 LEVIR-CD 으로 학습한 결과로 평균 IoU 는 0.87, 평균 Dice 는 0.93 을 얻었다.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.40 no.2
• /
• pp.334-348
• /
• 2015

Widespread use of smart devices accompanies increase of use of access point (AP), which enables the connection to the wireless network. If the appropriate security is not served when a user tries to connect the wireless network through an AP, various security problems can arise due to the rogue APs. In this paper, we are going to examine the threat by evil-twin, which is a kind of rogue APs. Most of recent researches for detecting rogue APs utilize the measured time difference, such as round trip time (RTT), between the evil-twin and authorized APs. These methods, however, suffer from the low detection rate in the network congestion. Due to these reasons, in this paper, we suggest a new factor, packet inter-arrival time (PIAT), in order to detect evil-twins. By using both RTT and PIAT as the learning factors for the support vector machine (SVM), we determine the non-linear metric to classify evil-twins and authorized APs. As a result, we can detect evil-twins with the probability of up to 96.5% and at least 89.75% even when the network is congested.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.11a
• /
• pp.705-708
• /
• 2023

다중밀집 사고를 사전에 방지하기 위해 군중 밀집도를 정확하게 파악하는 것은 중요하다. 기존 방법 중 일부는 군중 계수를 기반으로 군중 밀집도를 추정하거나 원근 왜곡이 있는 데이터를 그대로 학습한다. 이 방식은 물체의 거리에 따라 크기가 달라지는 원근 왜곡에 큰 영향을 받는다. 본 연구는 보행자 깊이 정보를 이용한 군중 밀집도 알고리즘을 제안한다. 보행자의 깊이 정보를 계산하기 위해 편차가 적은 머리 크기를 이용한다. 머리를 탐지하기 위해 OC-Sort를 학습모델로 사용한다. 탐지된 머리의 경계박스 좌표, 실제 머리 크기, 카메라 파라미터 등을 이용하여 보행자의 깊이 정보를 추정한다. 이후 깊이 정보를 기반으로 밀도 맵을 추정한다. 제안 알고리즘은 혼잡한 환경에서 객체의 위치와 밀집도를 정확하게 분석하여 군중밀집 사고를 사전에 방지하는 지능형 CCTV시스템의 기반 기술로 활용될 수 있으며, 더불어 보안 및 교통 관리 시스템의 효율성을 향상하는 데 중요한 역할을 할 것으로 기대한다.

• Journal of Digital Convergence
• /
• v.15 no.4
• /
• pp.259-266
• /
• 2017

The massive traffic interferences in the wireless home IoT provides the reason for packet losses, and it degrades the QoS (Quality of Service) and throughput on the home network. This paper propose a new adaptive traffic interference control system, ATICS, for enhancing QoS and throughput for IoT services as detecting a traffic process and non-traffic process in the wireless home network. The proposed system control the traffic interferences as distinguishing the short-term traffic process and long-term traffic process by traffic characteristics in wireless home networks. The simulation results shows that the proposed scheme have more efficient traffic control performance than the other schemes.

• Journal of the Korea Society for Simulation
• /
• v.32 no.3
• /
• pp.43-53
• /
• 2023

In this detailed and comprehensive study, our primary focus has been placed on accurately gauging the number of visitors and their real-time locations in commercial spaces. Particularly, in a real cafe, using security cameras, we have developed a system that can offer live updates on available seating and predict future congestion levels. By employing YOLO, a real-time object detection and tracking algorithm, the number of visitors and their respective locations in real-time are also monitored. This information is then used to update a cafe's indoor map, thereby enabling users to easily identify available seating. Moreover, we developed a model that predicts the congestion of a cafe in real time. The sophisticated model, designed to learn visitor count and movement patterns over diverse time intervals, is based on Long Short Term Memory (LSTM) to address the vanishing gradient problem and Sequence-to-Sequence (Seq2Seq) for processing data with temporal relationships. This innovative system has the potential to significantly improve cafe management efficiency and customer satisfaction by delivering reliable predictions of cafe congestion to all users. Our groundbreaking research not only demonstrates the effectiveness and utility of indoor location tracking technology implemented through security cameras but also proposes potential applications in other commercial spaces.

• Journal of the Korean Data and Information Science Society
• /
• v.22 no.6
• /
• pp.1153-1166
• /
• 2011

Detecting misbehavior in vehicular ad-hoc networks is very important problem with wide range of implications including safety related and congestion avoidance applications. Most misbehavior detection schemes are concerned with detection of malicious nodes. In most situations, vehicles would send wrong information because of selfish reasons of their owners. Because of rational behavior, it is more important to detect false information than to identify misbehaving nodes. In this paper, we propose the variable precision rough sets based misbehavior detection scheme which detects false alert message and misbehaving nodes by observing their action after sending out the alert messages. In the proposed scheme, the alert information system, alert profile is constructed from valid actions of moving nodes in vehicular ad-hoc networks. Once a moving vehicle receives an alert message from another vehicle, it finds out the alert type from the alert message. When the vehicle later receives a beacon from alert raised vehicle after an elapse of time, then it computes the relative classification error by using variable precision rough sets from the alert information system. If the relative classification error is lager than the maximum allowable relative classification error of the alert type, the vehicle decides the message as false alert message. Th performance of the proposed scheme is evaluated as two metrics: correct ratio and incorrect ratio through a simulation.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.12 no.2
• /
• pp.1-7
• /
• 2012

DDoS attack is a malicious attempt to exhaust resources of target system and network capacities using lots of distributed zombi systems. DDoS attack introduced in early 2000 has being evolved over time and presented in a various form of attacks. This paper proposes a scheme to detect DDoS attacks and to reduce possibility of such attacks that are especially based on vulnerabilities presented by using control packets of existing network protocols. To cope with DDoS attacks, the proposed scheme utilizes a buffer management techniques commonly used for congestion control in Internet. Our scheme is not intended to detect DDoS attacks perfectly but to minimize possibility of overloading of internal system and to mitigate possibility of attacks by discarding control packets at the time of detecting DDoS attacks. In addition, the detection module of our scheme can adapt dynamically to instantly increasing traffic unlike previously proposed schemes.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.26 no.9A
• /
• pp.1542-1552
• /
• 2001

MPLS 망에서 설정된 LSP (Label Switched Path)내에 링크/노드 장애나 혼잡이 발생한 트래픽을 대체 경로로 우회시킴으로써 신뢰성 있는 서비스를 제공하는 것은 필수적이다. 기존에 제안된 기법들은 장애가 발생하기 전에 대체 경로를 미리 설정하기 때문에 빠른 장애 복구를 제공할 수 있지만 자원 낭비가 심하며 기본 LSP와 대체 LSP가 모두 장애인 경우에는 대처할 수가 없는 문제점을 가지고 있다. 본 논문에서는 장애를 탐지한 노드가 기본 경로상에 존재할 수 있는 가능한 모든 대체 경로 중에서 비용이 최소인 대체 경로를 계산한 후에 그 경로를 따라서 대체 LSP를 설정하는 동적 복구 기법을 제안한다. 제안된 기법은 최소 비용인 대체 경로를 계산하기 위하여 제안된 알고리즘을 사용함으로써 비교적 빠른 시간 내에 대체 LSP를 설정할 수 있으며, 자원 효율성이 높고, 기본경로와 대체 경로가 장애인 경우에도 대처할 수 있다. 제안된 기법의 성능을 평가하기 위하여 링크 장애, 노드 장애, 대체 경로 장애, 그리고 동시 발생 장애에 대하여 각각 시뮬레이션 하였다. 실험 결과, 제안된 기법은 기존의 기법들과 비교해서 동시 발생 장애에서는 성능이 좋지 않았지만, 링크 장애와 노드 장애의 경우에 비교적 성능이 좋았고, 기본 경로와 대체 경로가 장애인 경우에도 복구할 수 있었으며 자원 효율성에서는 월등히 우수했다.

• KIPS Transactions on Software and Data Engineering
• /
• v.7 no.4
• /
• pp.135-144
• /
• 2018

The domestic pigsty environment is highly vulnerable to the spread of respiratory diseases such as foot-and-mouth disease because of the small space. In order to manage this issue, a variety of studies have been conducted to automatically analyze behavior of individual pigs in a pig pen through a video surveillance system using a camera. Even though it is required to correctly segment touching pigs for tracking each pig in complex situations such as aggressive behavior, detecting the correct boundaries among touching pigs using Kinect's depth information of lower accuracy is a challenging issue. In this paper, we propose a segmentation method using motion information of the touching pigs. In addition, our proposed method can be applied for detecting tracking errors in case of tracking individual pigs in the complex environment. In the experimental results, we confirmed that the touching pigs in a pig farm were separated with the accuracy of 86%, and also confirmed that the tracking errors were detected accurately.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.13 no.1
• /
• pp.81-87
• /
• 2020

Recently, the network configuration is being rapidly changed to enable easy and free network service configuration based on SDN/NFV. Despite the many advantages and applications of SDN, many security issues such as Distributed Denial of Service (DDoS) attacks are being constantly raised as research issues. In particular, the effectiveness of DDoS attacks is much faster, SDN is causing more and more fatal damage. In this paper, we propose an entropy-based technique to detect and mitigate DDoS attacks in SDN, and prove it through experiments. The proposed scheme is designed to mitigate these attacks by detecting DDoS attacks on single and multiple victim systems and using time - specific techniques. We confirmed the effectiveness of the proposed scheme to reduce packet loss rate by 20(19.86)% while generating 3.21% network congestion.