• Convergence Security Journal
• /
• v.23 no.1
• /
• pp.117-123
• /
• 2023

To detect advanced ransomware attacks with machine learning-based models, the classification model must train learning data with high-dimensional feature space. And in this case, a 'curse of dimension' phenomenon is likely to occur. Therefore, dimensionality reduction of features must be preceded in order to increase the accuracy of the learning model and improve the execution speed while avoiding the 'curse of dimension' phenomenon. In this paper, we conducted classification of ransomware by applying three machine learning models and two feature extraction techniques to two datasets with extremely different dimensions of feature space. As a result of the experiment, the feature dimensionality reduction techniques did not significantly affect the performance improvement in binary classification, and it was the same even when the dimension of featurespace was small in multi-class clasification. However, when the dataset had high-dimensional feature space, LDA(Linear Discriminant Analysis) showed quite excellent performance.

• Journal of Advanced Navigation Technology
• /
• v.27 no.2
• /
• pp.190-196
• /
• 2023

Recently, following the development of LIDAR technology which can detect distance from the object, the interest for LIDAR based 3D object detection network is getting higher. Previous networks generate inaccurate localization results due to spatial information loss during voxelization and downsampling. In this study, we propose an attention-based convergence method and a camera-LIDAR convergence system to acquire high-level features and high positional accuracy. First, by introducing the attention method into the Voxel-RCNN structure, which is a grid-based 3D object detection network, the multi-scale sparse 3D convolution feature is effectively fused to improve the performance of 3D object detection. Additionally, we propose the late-fusion mechanism for fusing outcomes in 3D object detection network and 2D object detection network to delete false positive. Comparative experiments with existing algorithms are performed using the KITTI data set, which is widely used in the field of autonomous driving. The proposed method showed performance improvement in both 2D object detection on BEV and 3D object detection. In particular, the precision was improved by about 0.54% for the car moderate class compared to Voxel-RCNN.

• Journal of Convergence for Information Technology
• /
• v.9 no.3
• /
• pp.22-29
• /
• 2019

Due to the development of ICT technology, convergence reality contents are utilized as technology for providing services in various industrial fields by visualizing various information such as sensor information and shared information in a service platform showing only simple three-dimensional contents. Research is underway to reduce the weight of applications by transmitting the resources of the object to be enhanced to the network as the information and the contents to be provided increase. In order to provide resources through the network, servers for processing various information such as pattern information, content information, and sensor information must be constructed in a cloud environment. However, in order to authenticate data transmitted and received in real-time in a cloud environment, there is a problem in that the processing is delayed and a delay phenomenon occurs in the rendering process and QoS is lowered. In this paper, we propose a system to distribute cloud server which provides augmented contents of convergent reality service that provides various contents such as sensor information and three - dimensional model, and shorten the processing time of reliable data through distributed relay between servers Respectively.

• Review of KIISC
• /
• v.31 no.6
• /
• pp.47-57
• /
• 2021

사용자들의 간접 경험 및 다양한 커뮤니티 생성을 위해 사용되었던 기존의 2차원 온라인 세상은 시각적 표현 및 사람의 특징을 반영하는 것에 한계점이 뚜렷하다. 따라서, 보다 현실과 유사한 환경을 구축하기 위해 많은 연구가 수행되었으며 특히, 사람의 행동 및 상태 등을 수집하고 활용할 수 있는 기술이 발전하였다. 그 결과 현실과 유사한 3차원 세계인 메타버스가 새롭게 주목받고 있다. 메타버스는 새로운 신분인 아바타로 사용자들의 높은 자유도를 보장하며 현실 세계와 유사한 활동과 함께 현실에서 경험할 수 없는 서비스를 제공하고 있다. 이러한 메타버스의 발전을 위한 연구가 활발히 수행되고 있지만, 메타버스에서 발생할 수 있는 보안 위협에 관한 연구는 상대적으로 부족하다. 현재, 3차원 세계 구축을 위해 기존보다 많은 종류의 데이터 수집으로 새로운 보안 이슈가 꾸준히 발생하고 있으며, AR, VR 등의 다양한 디바이스 활용과 사용자들의 자유도 보장에 따른 보안 위협이 존재한다. 이에, 본 논문에서는 메타버스에서 발생할 수 있는 보안 위협에 대해 분석하고, 이전의 다양한 연구들을 정리하여 새로운 관점에서 보안 위협을 분류한다. 그리고 해당 위협의 대응방안과 함께 앞으로의 연구 방향을 제시한다.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.27 no.3
• /
• pp.393-400
• /
• 2009

Recently demand for the 3D modeling technology to reconstruct real world is getting increasing. However, existing geospatial data are mainly based on the 2D space. In addition, most of the geospatial data provide geometric information only. In consequence, there are limits in various applications to utilize information from those data and to reconstruct the real world in 3D space. Therefore, it is required to develop efficient 3D mapping methodology and data for- mat to establish geospatial database. Especially digital elevation model(DEM) is one of the essential geospatial data, however, DEM provides only spatially distributed 3D coordinates of the natural and artificial surfaces. Moreover, most of DEMs are generated without considering terrain properties such as surface roughness, terrain type, spatial resolution, feature and so on. This paper suggests adaptive and flexible geospatial data format that has possibility to include various information such as terrain characteristics, multiple resolutions, interpolation methods, break line information, model keypoints, and other physical property. The study area was categorized into mountainous area, gently rolling area, and flat area by taking the terrain characteristics into account with respect to terrain roughness. Different resolutions and interpolation methods were applied to each area. Finally, a 3D digital map derived from aerial photographs was integrated with the geospatial data and visualized.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.42 no.5
• /
• pp.689-699
• /
• 2022

Recently, high productivity capabilities have been improved due to the application of advanced technologies in various industries, but in the construction industry, productivity improvements have been relatively low. Research on advanced technology for the construction industry is being conducted quickly to overcome the current low productivity. Among advanced technologies, 3D scan technology is widely used for creating 3D digital terrain models at construction sites. In particular, the 3D digital terrain model provides basic data for construction automation processes, such as earthwork machine guidance and control. The quality of the 3D digital terrain model has a lot of influence not only on the performance and acquisition environment of the 3D scanner, but also on the denoising, registration and merging process, which is a preprocessing process for creating a 3D digital terrain model after acquiring terrain scan data. Therefore, it is necessary to improve the terrain scan data processing performance. This study seeks to solve the problem of density inhomogeneity in terrain scan data that arises during the pre-processing step. The study suggests a 'pixel-based point cloud comparison algorithm' and verifies the performance of the algorithm using terrain scan data obtained at an actual earthwork site.

• Journal of the Institute of Convergence Signal Processing
• /
• v.23 no.4
• /
• pp.234-240
• /
• 2022

This paper proposes a customized AI exercise recommendation service for balancing the relative amount of exercise according to the working environment by each occupation. WISDM database is collected by using acceleration and gyro sensors, and is a dataset that classifies physical activities into 18 categories. Our system recommends a adaptive exercise using the analyzed activity type after classifying 18 physical activities into 3 physical activities types such as whole body, upper body and lower body. 1 Dimensional convolutional neural network is used for classifying a physical activity in this paper. Proposed model is composed of a convolution blocks in which 1D convolution layers with a various sized kernel are connected in parallel. Convolution blocks can extract a detailed local features of input pattern effectively that can be extracted from deep neural network models, as applying multi 1D convolution layers to input pattern. To evaluate performance of the proposed neural network model, as a result of comparing the previous recurrent neural network, our method showed a remarkable 98.4% accuracy.

• Journal of the Institute of Electronics Engineers of Korea SC
• /
• v.45 no.6
• /
• pp.26-34
• /
• 2008

The information of traversability and path planning is essential for UGV(Unmanned Ground Vehicle) navigation. Such information can be obtained by analyzing 3D terrain. In this paper, we present the method of 3D terrain modeling with color information from a camera, precise distance information from a 2D Laser Range Finder(LRF) and wheel encoder information from mobile robot with less data. And also we present the method of 3B terrain modeling with the information from GPS/IMU and 2D LRF with less data. To fuse the color information from camera and distance information from 2D LRF, we obtain extrinsic parameters between a camera and LRF using planar pattern. We set up such a fused system on a mobile robot and make an experiment on indoor environment. And we make an experiment on outdoor environment to reconstruction 3D terrain with 2D LRF and GPS/IMU(Inertial Measurement Unit). The obtained 3D terrain model is based on points and requires large amount of data. To reduce the amount of data, we use cubic grid-based model instead of point-based model.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.24 no.4
• /
• pp.136-147
• /
• 2021

Autonomous driving-related technologies are developing step by step by applying the degree of driving. It is essential that operational management technology for roads where autonomous vehicles move should also develop in line with autonomous driving technology. However, in the case of road operation management, it is currently managed using only two-dimensional information, showing limitations in the systematic operation management of lane and facility information and maintenance. This study proposed a plan to construct an operation management system architecture capable of 3D spatial information-based operation management by designing a convergence database that can process real-time big data with high-definition road map data. Through this study, when using a high-definition road map based operation management system for lane and facility maintenance in the future, it is possible to visualize and manage facilities, edit and analyze data of multiple users, link various GIS S/W and efficiently process large scale of real-time data.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.11a
• /
• pp.1230-1233
• /
• 2023

최근, 65세 이상의 1인 가구가 급증함에 따라 노인을 대상으로 한 다양한 연구 및 서비스가 활발히 이루어지고 있다. 이에 본 논문에서는 시계열 센서 데이터를 이용하여 CNN-LSTM 기반의 노인 활동 인식 시스템을 제안한다. 수집된 데이터는 3축 가속도 센서가 내장된 2개의 디바이스를 등과 허벅지에 부착하였다. 수집 주기는 50hz로 진행되었으며, 각 행동은 2초를 기준으로 산정하였다. 학습데이터의 입력값으로 사용하기 위해, 슬라이딩 윈도우를 50%로 적용하여 시퀀스를 구성하였다. 모델은 특징을 반영하기 위한 CNN(Convolutional Neural Networks)과 시계열적 특성을 반영하기 위한 LSTM(Long-Short Term Memory)을 하이브리드한 1차원 형태의 CNN-LSTM 모델을 사용한다. 행동은 4가지로 분류하였으며, 97%의 정확도를 나타내고 있다.