• Korean Journal of Remote Sensing
• /
• v.38 no.6_1
• /
• pp.1329-1341
• /
• 2022

Destroying the marine environment and marine ecosystem and causing marine accidents, marine debris is generated every year, and among them, submerged marine debris is difficult to identify and collect because it is on the seabed. Therefore, deep-learning-based semantic segmentation was experimented on waste fish nets and waste ropes using underwater images to identify efficient collection and distribution. For segmentation, a high-resolution network (HRNet), a state-of-the-art deep learning technique, was used, and the performance of each optimizer was compared. In the segmentation result fish net, F1 score=(86.46%, 86.20%, 85.29%), IoU=(76.15%, 75.74%, 74.36%), For the rope F1 score=(80.49%, 80.48%, 77.86%), IoU=(67.35%, 67.33%, 63.75%) in the order of adaptive moment estimation (Adam), Momentum, and stochastic gradient descent (SGD). Adam's results were the highest in both fish net and rope. Through the research results, the evaluation of segmentation performance for each optimizer and the possibility of segmentation of marine debris in the latest deep learning technique were confirmed. Accordingly, it is judged that by applying the latest deep learning technique to the identification of submerged marine debris through underwater images, it will be helpful in estimating the distribution of marine sedimentation debris through more accurate and efficient identification than identification through the naked eye.

• Journal of the Korean Geotechnical Society
• /
• v.38 no.3
• /
• pp.35-42
• /
• 2022

The N-value from the Standard Penetration Test (SPT), which is one of the representative in-situ test, is an important index that provides basic geological information and the depth of the bearing layer for the design of geotechnical structures. In the aspect of time and cost-effectiveness, there is a need to carry out a representative sampling test. However, the various variability and uncertainty are existing in the soil layer, so it is difficult to grasp the characteristics of the entire field from the limited test results. Thus the spatial interpolation techniques such as Kriging and IDW (inverse distance weighted) have been used for predicting unknown point from existing data. Recently, in order to increase the accuracy of interpolation results, studies that combine the geotechnics and deep learning method have been conducted. In this study, based on the SPT results of about 22,000 holes of ground survey, a comparative study was conducted to predict the depth of the bearing layer using deep learning methods and IDW. The average error among the prediction results of the bearing layer of each analysis model was 3.01 m for IDW, 3.22 m and 2.46 m for fully connected network and PointNet, respectively. The standard deviation was 3.99 for IDW, 3.95 and 3.54 for fully connected network and PointNet. As a result, the point net deep learing algorithm showed improved results compared to IDW and other deep learning method.

• Korean Institute of Interior Design Journal
• /
• v.27 no.2
• /
• pp.86-97
• /
• 2018

In modern times, pluralistic social phenomena in which various values are pursed and recognized appear. The modern society called hyper-connected, intelligence information and zero marginal cost society in which shared value is commonly emphasized faces a paradigm shift to shared society system. In particular, sharing-based activities related with intelligence information sectors more prominently emerge in the high-tech informatization which has been accelerated. The purpose of this study is to understand design factors related with how attribution of the sharing culture is expressed in library spaces and examine how sharing infrastructure is established in users' spaces. As a research method, it initially conducted theoretical consideration of the sharing culture and information spaces, which can be regarded as sociocultural phenomena in modern times. Then, it drew sharing culture-based spatial design factors-access, openness and plurality. It analyzed configuration of spaces for sharing information-Cultural Commons (CC), Information Commons(IC) and Learning Commons (LC) - and infrastructure of information spaces, for library cases-five domestic and foreign public libraries-. The findings show that modern library spaces reflect historical needs for the sharing culture and actively serve their roles through spatial infrastructure including contents (programs) and services for sharing knowledge. The study is determined to be valuable as basic data in establishing the infrastructure of information spaces reflecting modern social trends and cultural phenomena, in expecting spatial structures in which knowledge is reproduced and planning spaces of libraries in the future.

• Journal of the Korean Institute of Educational Facilities
• /
• v.23 no.1
• /
• pp.13-22
• /
• 2016

Recently, Korea has been established and operated International Schools manifesting to improve the nation's capacity of the foreign languages skill and to cultivate internationally trained professional manpower. In order to achieve the vision of a world-class educational organization, it has to be designed for the facility standards to meet the international accreditation standards. Therefore, the main purpose of this study is to research about basic resources through comparison of facility conditions between public schools in Korea and international accredited schools. By comparing those two different plan drawings are found the following things. First, Schools which established with International Accreditation Standard are prepared detailed criteria for the facility, Furthermore information about the furnishings included, in addition to specific equipments for classes are stated to be prepared. Secondly, it is more effective when special classrooms such as music and science are equipped with various spatial elements, enough educational equipment storage, teacher's study rooms, practical training rooms and student's activity rooms to support various teaching programs and learning efficiently. Lastly, there was a clear tendency that not only hardware but also software standards for the audiovisual room and library have been more enhanced to enable multidisciplinary educational approaches with the recent education training trend.

• Journal of Korean Institute of Industrial Engineers
• /
• v.23 no.1
• /
• pp.129-146
• /
• 1997

In traditional approaches to scheduling problems, a single dispatching rule was used by all machines in a system. However, since the situation of each machine generally differs from those of other machines, it is reasonable to apply a different dispatching rule to each machine responding to its given situation. In this regard, we introduce the concept of spatial adaptation and examine its effectiveness by simulation. In the spatial adaptation, each machine in a system selects an appropriate dispatching rule in order to improve productivity while it strives to be in harmony with other machines. This study proposes an adaptive procedure which produces a reliable dispatching rule for each machine beginning with the bottleneck machine. The dispatching rule is composed of several criteria of which priorities are adaptively weighted. The weights are learned for each machine through systematic simulations. The simulations are conducted according to a Taguchi experimental design in order to find appropriate sets of criteria weights in an efficient and robust way in the context of environmental variations. The proposed method was evaluated in an application to a semiconductor wafer fabrication system. The method achieved reliable performance compared to traditional dispatching rules, and the performance quickly approached the peak after learning for only a few bottleneck machines.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2019.07a
• /
• pp.317-318
• /
• 2019

가상/증강현실로 대표되는 공간정보 기반 실감형 콘텐츠에 대한 관심이 증대되면서 객체인식 등의 지능형 공간인지 기술에 대한 연구가 활발히 진행되고 있다. 특히 HMD등의 영상 시각화 장치의 발달 및 5G 통신기술의 출현으로 인해 실시간 대용량 영상정보의 송, 수신 및 가시화 처리 기술의 기반이 구축됨에 따라, $360^{\circ}$ 스트리밍 영상정보 처리와 같은 고자유도 콘텐츠를 위한 관련 연구의 필요성이 증대되고 있다. 하지만 지능형 영상정보 처리의 대표적 연구인 딥 러닝(Deep Learning) 기반 객체 인식 기술의 경우 대부분 일반적인 평면 영상(Planar Image)에 대한 처리를 다루고 있고, 파노라마 영상(Panorama Image) 특히, $360^{\circ}$ 스트리밍 영상 처리를 위한 연구는 미비한 상황이다. 본 논문에서는 딥 러닝을 이용하여 $360^{\circ}$ 스트리밍 영상에서의 객체인식 연구 방법에 대해 서술한다. 이를 위해 $360^{\circ}$ 카메라 영상에서 딥 러닝을 위한 학습 데이터를 획득하고, 실시간 객체 인식이 가능한 YOLO(You Only Look Once)기법을 이용하여 학습을 한다. 실험 결과에서는 학습 데이터를 이용하여 $360^{\circ}$영상에서 객체 인식 결과와, 학습 횟수에 따른 객체 인식에 대한 결과를 보여준다.

• Journal of Korea Multimedia Society
• /
• v.25 no.4
• /
• pp.649-659
• /
• 2022

The most important factor in pre-school children's psychological perception is ease of learning, and the closest measure is "natural" interaction. This study aims to explore the potential of tangible user interfaces (TUI) for AR collaboration for children's cognitive development. The conceptual model is constructed by analyzing physical interaction, spatial perception and social collaboration on the usability of TUI, to explore the role of TUI in pre-school children's cognition. In the empirical study, children aged 3-6 were taken as research objects. The experimental tool is "Plugo" education application. Parents answered questionnaires after observing their children's use. Research shows that physical interaction are the most critical factor in TUI. TUI is beneficial to the cultivation of spatial ability. The results are as follows: 1. Cronbach's Alpha and KMO were 0.921 and 0.965, which were significant and passed the reliability and validity test. 2. Through confirmatory factor analysis (model fit index, combinatorial validity), we found that physical interaction were closely related to usability. 3. The path analysis of the relationship proves that usability has a significant impact on the cultivation of pre-school children's spatial ability.

• IEIE Transactions on Smart Processing and Computing
• /
• v.6 no.3
• /
• pp.193-199
• /
• 2017

Instead of using only spatial features from a single frame for person re-identification, a combination of spatial and temporal factors boosts the performance of the system. A recurrent neural network (RNN) shows its effectiveness in generating highly discriminative sequence-level human representations. In this work, we implement RNN, three Long Short Term Memory (LSTM) network variants, and Gated Recurrent Unit (GRU) on Caffe deep learning framework, and we then conduct experiments to compare performance in terms of size and accuracy for person re-identification. We propose using GRU for the optimized choice as the experimental results show that the GRU achieves the highest accuracy despite having fewer parameters than the others.

• Proceedings of the PSK Conference
• /
• 2002.10a
• /
• pp.304.3-305
• /
• 2002

The present study investigated the passive avoidance and spatial learning in the ${\mu}$-opioid receptor gene knockout mice and wild type mice. In the step-through passive avoidance task. the ${\mu}$-opioid receptor knockout mice did not differ from the wild type mice. In Morris water maze. however. the ${\mu}$-opioid receptor knockout mice showed significant memory deficit compared to wild type mice. (omitted)

• Journal of Korean Association for Spatial Structures
• /
• v.8 no.3
• /
• pp.75-82
• /
• 2008

In this study, the modified genetic algorithm, D-GA, is proposed. D-GA is a hybrid genetic algorithm combined a simple genetic algorithm and the local search algorithm using direction vectors. Also, two types of direction vectors, learning direction vector and random direction vector, are defined without the sensitivity analysis. The accuracy of D-GA is compared with that of simple genetic algorithm. It is demonstrated that the proposed approach can be an effective optimization technique through a minimum weight structural optimization of ten bar truss.