• 정보보호학회논문지
• /
• 제25권5호
• /
• pp.1131-1141
• /
• 2015

본 논문에서는 MMORPG에서 각 캐릭터의 소지금 증가/감소 이벤트 로그 데이터를 위주로 플레이어의 액션 로그 데이터를 조사하여 게임봇을 탐지하는 기계 학습 기반의 새로운 접근 방법을 제안한다. 게임봇 계정과 일반 계정을 구분하는 주요 피쳐를 추출하기 위해 밀도 기반 군집화 알고리즘의 하나인 DBSCAN (Density Based Spatial Clustering of Application with Noise)를 이용하였다. DBSCAN 알고리즘을 통해 각 플레이어의 소지금 증가/감소 위치 좌표를 클러스터링하고, 그 결과 생성된 클러스터의 수, 코어 포인트의 비율, 멤버 포인트의 비율, 노이즈 포인트의 비율과 같은 공간적 특성을 나타내는 값들을 추출하였다. 해당 피쳐들을 사용하면 게임봇 개발자들이 게임봇 탐지 시스템의 원리를 알더라도 넓은 지역을 돌아다니며 사냥을 하도록 게임봇 프로그램을 제작하는 것은 매우 비효율적이기 때문에 탐지 시스템을 우회하기 어렵게 된다. 결과적으로, 게임봇은 소지금 변동 좌표 데이터로부터 추출한 공간적 특성에서 일반유저와 명확한 차이를 보였다. 예를 들면, DBSCAN 클러스터링 결과 중 노이즈 포인트의 비율에서 게임봇은 5% 이하의 낮은 값을 가지는 반면에 일반 유저들은 대부분 높은 값을 갖는다. 실제 MMORPG의 액션 로그 데이터를 이용한 게임봇 탐지에서, 본 논문에서 제안된 시스템은 높은 탐지율의 우수한 성능을 보였다.

• 한국빅데이터학회지
• /
• 제6권2호
• /
• pp.29-38
• /
• 2021

항공안전관리에서 항공기 경로 이탈은 큰 사고로 이어질 수 있는 위험한 요인이다. 본 연구에서는 항공기 경로 이탈 문제를 예방하기 위해 클러스터링을 통해 항적을 분류하고, 클러스터 중심과의 거리를 계산하여 이상 점수를 산출하고자 한다. 1년 동안 수신된 ADS-B 항적 자료에서 공항을 기준으로 근방 100km 이내 항적을 추출하여 연구를 진행했다. 항적은 선형 보간법을 이용하여 벡터화하였다. 위도·경도·고도 3차원 좌표 자료를 사용하였다. PCA를 통해 전체 데이터 분산 90% 이상을 나타내는 축으로 차원을 축소하였고, k-평균 군집화, 계층적 군집화, PAM 기법을 적용하였다. 클러스터 개수는 실루엣 측도를 사용하여 선택하였고, 클러스터 중심과의 거리를 계산하여 이상 점수를 산출하였다. 본 연구에서는 각 클러스터 기법별로 클러스터 개수를 비교해보고, 실루엣 측도를 통해 클러스터링 결과를 평가하고자 한다.

• 드라이브 ㆍ 컨트롤
• /
• 제20권2호
• /
• pp.15-23
• /
• 2023

In this study, two-dimensional location of crops for auto weeding was detected using deep learning. To construct a dataset for soybean detection, an image-capturing system was developed using a mono camera and single-board computer and the system was mounted on a weeding robot to collect soybean images. A dataset was constructed by extracting RoI (region of interest) from the raw image and each sample was labeled with soybean and the background for classification learning. The deep learning model consisted of four convolutional layers and was trained with a weakly supervised learning method that can provide object localization only using image-level labeling. Localization of the soybean area can be visualized via CAM and the two-dimensional position of the soybean was estimated by clustering the pixels associated with the soybean area and transforming the pixel coordinates to world coordinates. The actual position, which is determined manually as pixel coordinates in the image was evaluated and performances were 6.6(X-axis), 5.1(Y-axis) and 1.2(X-axis), 2.2(Y-axis) for MSE and RMSE about world coordinates, respectively. From the results, we confirmed that the center position of the soybean area derived through deep learning was sufficient for use in automatic weeding systems.

• 한국측량학회지
• /
• 제25권6_1호
• /
• pp.507-516
• /
• 2007

Segmentation and organization of the LiDAR (Light Detection and Ranging) data of the Earth's surface are difficult tasks because the captured LiDAR data are composed of irregularly distributed point clouds with lack of semantic information. The reason for this difficulty in processing LiDAR data is that the data provide huge amount of the spatial coordinates without topological and/or relational information among the points. This study introduces LiDAR data segmentation technique by utilizing histograms of the LiDAR height image data and analyzing roof shape for 3D reconstruction and visualization of the buildings. One of the advantages in utilizing LiDAR height image data is no registration required because the LiDAR data are geo-referenced and ortho-projected data. In consequence, measurements on the image provide absolute reference coordinates. The LiDAR image allows measurement of the initial building boundaries to estimate locations of the side walls and to form the planar surfaces which represent approximate building footprints. LiDAR points close to each side wall were grouped together then the least-square planar surface fitting with the segmented point clouds was performed to determine precise location of each wall of an building. Finally, roof shape analysis was performed by accumulated slopes along the profiles of the roof top. However, simulated LiDAR data were used for analyzing roof shape because buildings with various shapes of the roof do not exist in the test area. The proposed approach has been tested on the heavily built-up urban residential area. 3D digital vector map produced by digitizing complied aerial photographs was used to evaluate accuracy of the results. Experimental results show efficiency of the proposed methodology for 3D building reconstruction and large scale digital mapping especially for the urban area.

• ETRI Journal
• /
• 제36권4호
• /
• pp.662-672
• /
• 2014

Human action recognition is used in areas such as surveillance, entertainment, and healthcare. This paper proposes a system to recognize both single and continuous human actions from monocular video sequences, based on 3D human modeling and cyclic hidden Markov models (CHMMs). First, for each frame in a monocular video sequence, the 3D coordinates of joints belonging to a human object, through actions of multiple cycles, are extracted using 3D human modeling techniques. The 3D coordinates are then converted into a set of geometrical relational features (GRFs) for dimensionality reduction and discrimination increase. For further dimensionality reduction, k-means clustering is applied to the GRFs to generate clustered feature vectors. These vectors are used to train CHMMs separately for different types of actions, based on the Baum-Welch re-estimation algorithm. For recognition of continuous actions that are concatenated from several distinct types of actions, a designed graphical model is used to systematically concatenate different separately trained CHMMs. The experimental results show the effective performance of our proposed system in both single and continuous action recognition problems.

• 한국컴퓨터정보학회논문지
• /
• 제28권12호
• /
• pp.191-199
• /
• 2023

본 논문에서는 자율협력주행을 위한 인프라로써 제작된 5가지 센서 전용 시설물들에 대해 라이다로 취득한 포인트 클라우드 데이터로부터 시설물들의 특징을 추출하는 방법을 제안한다. 자율주행차량에 장착된 영상 취득 센서의 경우에는 기후 환경 및 카메라의 특성 등으로 인해 취득 데이터의 일관성이 낮기 때문에 이를 보완하기 위해서 라이다 센서를 적용했다. 또한, 라이다로 기존의 다른 시설물들과의 구별을 용이하게 하기 위해서 고휘도 반사지를 시설물의 용도별로 디자인하여 부착했다. 이렇게 개발된 5가지 센서 전용 시설물들과 데이터 취득 시스템으로 취득한 포인트 클라우드 데이터로부터 측정 거리별 시설물의 특징을 추출하는 방법으로 해당 시설물에 부착된 고휘도 반사지의 평균 반사강도을 기준으로 특징 포인트들을 추출하여 DBSCAN 방법으로 군집화한 후 해당 포인트들을 투영법으로 2차원 좌표로 변경했다. 거리별 해당 시설물의 특징은 3차원 포인트 좌표, 2차원 투영 좌표, 그리고 반사강도로 구성되며, 추후 개발될 시설물 인식을 위한 모형의 학습데이터로 활용될 예정이다.

• 대한원격탐사학회:학술대회논문집
• /
• 대한원격탐사학회 1999년도 Proceedings of International Symposium on Remote Sensing
• /
• pp.386-389
• /
• 1999

In this study, visible and near infrared channels of NOAA/AVHRR data were used to classify land use and vegetation types over Korean peninsula. Analyzing forest stand structures and prediction of forest productivity using satellite data were also reviewed. Land use and land cover classification was made by unsupervised clustering methods. After monthly Normalized Difference Vegetation Index (NDVI) composite images were derived from April to November 1998, the derived composite images were used as temporal feature vector's in this clustering analysis. Visually interpreted, the classification result was satisfactory in overall for it matched well with the general land cover patterns. But subclassification of forests into coniferous, deciduous, and mixed forests were much confused due to the effects of low ground resolution of AVHRR data and without defined classification scheme. To investigate into the forest stand structures, digital forest type maps were used as an ancillary data. Forest type maps, which were compiled and digitalized by Forestry Research Institute, were registered to AVHRR image coordinates. Two data sets were compared and percent forest cover over whole region was estimated by multiple regression analysis. Using this method, other forest stand structure characteristics within the primary data pixels are expected to be extracted and estimated.

• 한국공작기계학회논문집
• /
• 제15권5호
• /
• pp.104-113
• /
• 2006

The main objective of this study is to investigate the effect of compounded welding by using acoustic emission (AE) signals and doing a source location for weld heat affected zone (HAZ) through tensile testing. This study was carried out an SWS 490A high strength steel for electric shield metal arc welding, SMAW; $CO_2$ gas metal arc welding, GMAW($CO_2$); and gas tungsten arc welding, GTAW/TIG. Data displays are based on the measured parameters of the AE signals, along with environmental variables such as time and load. For instance, Gutenberg-Richter magnitude-frequency relationship (G-R MFR) offers useful b-value in data analysis. Namely event identification, source location gives the X- and Y-coordinates of the AE source. And K-means clustering analysis by Euclidean distance confirmed that was powerful to source location. Generally, strength of welded metal zone was stronger than strength of base metal. As the result, confirmed certainly that fracture is produced in HAZ instead of welded metal zone from source location.

• 제어로봇시스템학회논문지
• /
• 제12권2호
• /
• pp.119-129
• /
• 2006

Art psychotherapy is widely accepted as an effective tool for diagnosis and treatment of psychological disorders. Important factors for art psychotherapy diagnosis, based on the projection theory that the world of the inner mind appears in drawings, include main color and imbalance of a drawing. This paper develops a system for a machine to determine the main color and the imbalance of a drawing by color recognition and edge detection. Our proposed color recognition procedure adopts NBS(National Bureau of Standards) distance between colors in HVC(Hue, Value, Chroma) color space which is most similar to the human eye's color perception. Our edge detection procedure applies blurring, clustering and transformation to a standard color in a series. Our system considers the numbers of pixels and clusters for each color as a criterion for main color and the frequency of edge coordinates for each region for imbalance. The proposed machine procedure, verified through case studies, can help overcome the subjectivity, ambiguity and uncertainty in human decision involved in art psychotherapy.

• ETRI Journal
• /
• 제38권2호
• /
• pp.314-325
• /
• 2016

This paper examines the resource gain that can be obtained from the creation of clusters of nodes in densely populated areas. A single node within each such cluster is designated as a "hotspot"; all other nodes then communicate with a destination node, such as a base station, through such hotspots. We propose a semi-distributed algorithm, referred to as coordinated cognitive tethering (CCT), which clusters all nodes and coordinates hotspots to tether over locally available white spaces. CCT performs the following these steps: (a) groups nodes based on a modified k-means clustering algorithm; (b) assigns white-space spectrum to each cluster based on a distributed graph-coloring approach to maximize spectrum reuse, and (c) allocates physical-layer resources to individual users based on local channel information. Unlike small cells (for example, femtocells and WiFi), this approach does not require any additions to existing infrastructure. In addition to providing parallel service to more users than conventional direct communication in cellular networks, simulation results show that CCT can increase the average battery life of devices by 30%, on average.