• Journal of Korean Library and Information Science Society
• /
• v.50 no.3
• /
• pp.293-315
• /
• 2019

Based on the current status of use of L-Commerce installed in the Yongsan Public Library and Mapo Lifelong Learning Center, this study suggested the direction of spatial design for the public library's makerspace with L-Commons model. To this end, we investigated the literature research on library makerspaces and the case studies of makerspaces installed in 25 public libraries in Korea and 18 public libraries in the US. And In-depth interviews and user surveys were conducted. The public library makerspace presented through this study should be an open space where everyone in the community can easily enter, break down barriers between all classes in the region, and lead to smooth communication. Second, it should be a learning, cooperation, and creative space where resources can be shared and cooperation for creative activities and projects can be carried out. Third, it should be a creative workspace where community members can turn ideas into physical things that anyone can't do elsewhere or work on something interesting.

• The Journal of the Korea Contents Association
• /
• v.19 no.1
• /
• pp.125-131
• /
• 2019

A vanishing point is a point on an image to which parallel lines projected from a real space gather. A vanishing point in a road space provides important spatial information. It is possible to improve the position of an extracted lane or generate a depth map image using a vanishing point in the road space. In this paper, we propose a method of detecting vanishing points on images taken from a vehicle's point of view using Deep Neural Network (DNN) and Histogram of Oriented Gradient (HoG). The proposed algorithm is divided into a HoG feature extraction step, in which the edge direction is extracted by dividing an image into blocks, a DNN learning step, and a test step. In the learning stage, learning is performed using 2,300 road images taken from a vehicle's point of views. In the test phase, the efficiency of the proposed algorithm using the Normalized Euclidean Distance (NormDist) method is measured.

• Korean Journal of Remote Sensing
• /
• v.38 no.5_1
• /
• pp.559-570
• /
• 2022

When a satellite image has low spatial resolution, it is difficult to detect small objects. In this research, we aim to check the effect of super resolution on object detection. Super resolution is a software method that increases the resolution of an image. Unpaired super resolution network is used to improve Sentinel-2's spatial resolution from 10 m to 3.2 m. Faster-RCNN, RetinaNet, FCOS, and S²ANet were used to detect vessels in the Sentinel-2 images. We experimented the change in vessel detection performance when super resolution is applied. As a result, the Average Precision (AP) improved by at least 12.3% and up to 33.3% in the ship detection models trained with the super-resolution image. False positive and false negative cases also decreased. This implies that super resolution can be an important pre-processing step in object detection, and it is expected to greatly contribute to improving the accuracy of other image-based deep learning technologies along with object detection.

• Journal of the Korean Institute of Educational Facilities
• /
• v.26 no.5
• /
• pp.17-23
• /
• 2019

The classroom is a learning space where students live mainly in school, and it is the most important space within the entire educational space of the school. Although our educational system has been trying to revise and change the curriculum many times, it still does not provide space for the educational concept of modern society. The impact of the abolished 'school facility standard design' in 1992 is still evident in the design of school facilities at present. Specifically, the uniformity of the educational space, the rigid boundary of the classroom unit, the blockage between the school facility and the outside, and the separation due to the break of the inner and outer spaces. In the future, we need a flexible space that can contain the contents of the future education, and it is necessary to study the composition and type of educational space that can escape uniformity and spatial breakdown. In this paper, we analyze the successful cases of Irvine school facilities and examine the type and composition of classroom space, and it will be a task to find the direction and change of thinking about our educational space.

• Korean Journal of Cognitive Science
• /
• v.23 no.3
• /
• pp.295-322
• /
• 2012

In this paper, we cluster similar word senses applying vector space model and HAL (Hyperspace Analog to Language). HAL measures corelation among words through a certain size of context (Lund and Burgess 1996). The similarity measurement between a word pair is cosine similarity based on the vector space model, which reduces distortion of space between high frequency words and low frequency words (Salton et al. 1975, Widdows 2004). We use PCA (Principal Component Analysis) and SVD (Singular Value Decomposition) to reduce a large amount of dimensions caused by similarity matrix. For sense similarity clustering, we adopt supervised and non-supervised learning methods. For non-supervised method, we use clustering. For supervised method, we use SVM (Support Vector Machine), Naive Bayes Classifier, and Maximum Entropy Method.

• Journal of the Korean Institute of Educational Facilities
• /
• v.27 no.2
• /
• pp.35-47
• /
• 2020

The need for communication is emphasized in decision making, design methods and processes for the educational environment that contain new curricula and learning methods. In this study, we tried to find the direction and agenda of learner-centered environment restructuring through the 'user-integrated platform' in which various subjects related to school space environment understand each other's position and overcome the barriers and prejudices of each sector. The project was planned in a 'bottom-up process' method that uncovered the singularities of the previous stage and led the main contents of the next stage. The various subjects who participated in the project shared their own experiences and different positions regarding the school space. At the workshop, the topics of the participating teams were divided into two categories. The teams in the category of the 'school culture and space' insisted innovation of 'the school culture' as a premise for the restructuring of the 'school space', and proposed schools with different interpretations of 'authority and rules of school', 'the meaning of learning and play' and 'the main character of school. The teams in the category of the 'school borders and spaces' focused on 'communication' and proposed schools containing 'emotional care of students', 'borders between schools and villages', 'village community schools', and 'interspace and niche time'. After the workshop, we were able to derive the direction and architectural strategy of the school space restructuring by analyzing the works of the participants. Through this study, we confirmed the possibility of translating user's ideas into the professional domain through careful planning, preparation, facilitation, and analysis in Participatory Design.

• Journal of Information Management
• /
• v.41 no.4
• /
• pp.141-163
• /
• 2010

It's getting popularized to collect information connecting web sites with massive information through the internet and advanced search engines. Users can handle digital materials like E-book wherever the internet is available and they will demand digital information increasingly. This study analyzes literature investigation, statistics analyses of the attached library of Kyushu University, drawings and field investigation to suggest a new model of a library which handles traditional paper-formed materials and digital-formed materials at one place with growing importance of digital materials. It results that a library performs a important role like a learning space and functions as a sociocultural communication space. Also it shows that it is required to basically reinvestigate the role of 'space' in the library with a great importance of digital materials. In the hybrid library combined with subjects and reorganized at one place, One-stop services like library materials and manpower can be provided for users staying at the same area.

• International Journal of Control, Automation, and Systems
• /
• v.5 no.6
• /
• pp.674-680
• /
• 2007

The probabilistic roadmap (PRM) method, which is a popular path planning scheme, for a manipulator, can find a collision-free path by connecting the start and goal poses through a roadmap constructed by drawing random nodes in the free configuration space. PRM exhibits robust performance for static environments, but its performance is poor for dynamic environments. On the other hand, reinforcement learning, a behavior-based control technique, can deal with uncertainties in the environment. The reinforcement learning agent can establish a policy that maximizes the sum of rewards by selecting the optimal actions in any state through iterative interactions with the environment. In this paper, we propose efficient real-time path planning by combining PRM and reinforcement learning to deal with uncertain dynamic environments and similar environments. A series of experiments demonstrate that the proposed hybrid path planner can generate a collision-free path even for dynamic environments in which objects block the pre-planned global path. It is also shown that the hybrid path planner can adapt to the similar, previously learned environments without significant additional learning.

• Journal of Advanced Research in Ocean Engineering
• /
• v.3 no.3
• /
• pp.136-148
• /
• 2017

The paper presents dual arm ROV manipulation using deep reinforcement learning. The purpose of this underwater manipulator is to investigate and excavate natural resources in ocean, finding lost aircraft blackboxes and for performing other extremely dangerous tasks without endangering humans. This research work emphasizes on a self-learning approach using Deep Reinforcement Learning (DRL). DRL technique allows ROV to learn the policy of performing manipulation task directly, from raw image data. Our proposed architecture maps the visual inputs (images) to control actions (output) and get reward after each action, which allows an agent to learn manipulation skill through trial and error method. We have trained our network in simulation. The raw images and rewards are directly provided by our simple Lua simulator. Our simulator achieve accuracy by considering underwater dynamic environmental conditions. Major goal of this research is to provide a smart self-learning way to achieve manipulation in highly dynamic underwater environment. The results showed that a dual robotic arm trained for a 3DOF movement successfully achieved target reaching task in a 2D space by considering real environmental factor.

• Investigative Magnetic Resonance Imaging
• /
• v.25 no.4
• /
• pp.300-312
• /
• 2021

Compressed sensing (CS) has been investigated in magnetic resonance (MR) parametric mapping to reduce scan time. However, the relatively long reconstruction time restricts its widespread applications in the clinic. Recently, deep learning-based methods have shown great potential in accelerating reconstruction time and improving imaging quality in fast MR imaging, although their adaptation to parametric mapping is still in an early stage. In this paper, we proposed a novel deep learning-based framework DEMO for fast and robust MR parametric mapping. Different from current deep learning-based methods, DEMO trains the network in an unsupervised way, which is more practical given that it is difficult to acquire large fully sampled training data of parametric-weighted images. Specifically, a CS-based loss function is used in DEMO to avoid the necessity of using fully sampled k-space data as the label, thus making it an unsupervised learning approach. DEMO reconstructs parametric weighted images and generates a parametric map simultaneously by unrolling an interaction approach in conventional fast MR parametric mapping, which enables multi-tasking learning. Experimental results showed promising performance of the proposed DEMO framework in quantitative MR T1ρ mapping.