• International Journal of Computer Science & Network Security
• /
• v.22 no.3
• /
• pp.273-275
• /
• 2022

Deep Learning is used nowadays in Nuclei segmentation. While recent developments in theory and open-source software have made these tools easier to implement, expert knowledge is still required to choose the exemplary model architecture and training setup. We compare two popular segmentation frameworks, U-Net and Mask-RCNN, in the nuclei segmentation task and find that they have different strengths and failures. we compared both models aiming for the best nuclei segmentation performance. Experimental Results of Nuclei Medical Images Segmentation using U-NET algorithm Outperform Mask R-CNN Algorithm.

• The Journal of Korea Robotics Society
• /
• v.17 no.3
• /
• pp.359-364
• /
• 2022

This study presents a nonlinear model predictive control (NMPC)-based obstacle avoidance and whole-body motion planning method for the mobile manipulators. For the whole-body motion control, the mobile manipulator with an omnidirectional mobile base was modeled as a nine degrees-of-freedom (DoFs) serial open chain with the PPR (base) plus 6R (arm) joints, and a swept sphere volume (SSV) was applied to define a convex hull for collision avoidance. The proposed receding horizon control scheme can generate a trajectory to track the end-effector pose while avoiding the self-collision and obstacle in the task space. The proposed method could be calculated using an interior-point (IP) method solver with 100[ms] sampling time and ten samples of horizon size, and the validation of the method was conducted in the environment of Pybullet simulation.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.18 no.4
• /
• pp.151-157
• /
• 2023

RPL (IPv6 Routing Protocol for Low-power Lossy Network) is a standardized routing protocol for LLNs (Low power and Lossy Networks) by the IETF (Internet Engineering Task Force). RPL creates routes and builds a DODAG (Destination Oriented Directed Acyclic Graph) through OF (Objective Function) defining routing metrics and optimization objectives. RPL supports a leaf mode which does not allow any child nodes. In this paper, we propose INFRA-RPL which provides a dynamic leaf mode functionality to a leaf node with the mobility. The proposed protocol is implemented in the open-source IoT operating system, Contiki-NG and Cooja simulator, and its performance is evaluated. The evaluation results show that INFRA-RPL outperforms the existing protocols in the terms of PDR, latency, and control message overhead.

• Annual Conference of KIPS
• /
• 2010.04a
• /
• pp.187-189
• /
• 2010

모바일 그리드 환경에서 작업 처리를 위해 노드로 활용되는 모바일 장치는 무선 인터넷 연결과 모바일 장치의 배터리 용량 등의 제약으로 인해 모바일 그리드 환경에서의 작업 처리는 기존 그리드 컴퓨팅 환경에 비해 신뢰성이 낮고 결함이 발생할 확률이 높다. 따라서 모바일 장치의 신뢰성을 고려한 작업 분배 방법이 요구된다. 이 논문에서는 모바일 장치의 신뢰성을 고려한 작업 분배 스케줄링을 제안하고자 한다. 제안 기법에서는 노드의 신뢰성을 바탕으로 작업량과 복제 개수를 서로 달리 설정하여 신뢰성이 우수한 노드에게 더 많은 작업량을 할당하고 작업 복제 개수를 적게 설정하도록 한다. 제안 기법의 타당성을 보이기 위한 성능 평가에서는 제안 기법이 기존 기법에 비해 성능이 향상됨을 보여준다.

• Educational Technology International
• /
• v.13 no.1
• /
• pp.79-100
• /
• 2012

The focus of this research is on identifying the problems that learners experience during online problem-based learning (e-PBL) from a cognitive perspective. The study is concentrated on learners' cognitive load level at each stage of e-PBL. The research questions are specifically as follows: What is the level of cognitive load at each stage of e-PBL and what is the relationship between cognitive load and group performance? What cognitive difficulties are experienced by learners in e-PBL and what causes cognitive difficulties? In this study, we found that cognitive load was the highest in stage 1 and there was negative relationship between cognitive load at stage 1 and group performance. In addition, learners experienced difficulties during e-PBL such as the complexity of task, the difficulty in collaboration, and the lack of appropriate references. For further study, we will investigate some strategies regarding adjusting learners' cognitive load in the early stages of e-PBL.

• Annual Conference of KIPS
• /
• 2023.11a
• /
• pp.81-84
• /
• 2023

최근의 인텔의 새로운 CPU 아키텍처의 도입으로 Singularity 컨테이너 내에서 cgroup 설정으로 인해 특정 작업의 성능에 영향을 초래할 수 있다. 특히 Singularity 컨테이너에서 HPC(고성능 컴퓨팅) 작업은 cgroup 정책에 의해 작업 효율이 달라질 수 있고 아직 새로운 CPU 환경에서의 HPC 작업에 대한 연구가 충분치 않다. 따라서, 본 논문은 Singularity 컨테이너 생성 시 새로운 CPU 아키텍처에 설계된 CPU 코어 유형별 cgroup 지정이 HPC 응용을 포함하여 다양한 유형의 작업 성능에 미치는 영향을 비교 분석하였고, 이를 통해 HPC 사용자에게 가이드라인을 제공하는 것이 목적이다.

• Spatial Information Research
• /
• v.7 no.2
• /
• pp.175-190
• /
• 1999

Recently , as GIS technology is rapidly improved and stabilized, there are some needs to reuse pre-developed and powerful GIS technology. GIS standardization based on components and open interfaces becomes a way to solve those reusability of previous GIS technology. This GIS standardization currently focuses on building the GIS Data Infrastructure that is being deployed globally. Especially, OpenGIS consortium which is mainly made up of international GIS leading vendors is announcing some GIS abstract specifications and implementation specifications. This study focuses on how could we design and implement the OLE/COM-based data provider component based on various DBMS or file systems, how could these data provider components be used for enterprise UIS(Urban Information Systems) and how could various formatted GIS data be shared in one system. Also some problems practically caused by an implementation process of data provider component are listed up and some solutions are given. Furthermore, design and analysis of UML(Unified Modeling Language) was reformed through the data provider component development task and this UML methodology is able to indicate a standardized model for newly developed data provider component.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.20 no.6
• /
• pp.85-91
• /
• 2020

Recently, video-taping equipment such as CCTV have been seeing more use for crime prevention and general safety concerns. Since these video-taping equipment operates all throughout the day, the need for security personnel is lessened, and naturally costs incurred from managing such manpower should also decrease. However, technology currently used predominantly lacks self-sufficiency when given the task of searching for a specific object in the recorded video such as a person, and has to be done manually; current security-based video equipment is insufficient in an environment where real-time information retrieval is required. In this paper, we propose a technology that uses the latest deep-learning technology and OpenCV library to quickly search for a specific person in a video; the search is based on the clothing information that is inputted by the user and transmits the result in real time. We implemented our system to automatically recognize specific human objects in real time by using the YOLO library, whilst deep learning technology is used to classify human clothes into top/bottom clothes. Colors are also detected through the OpenCV library which are then all combined to identify the requested object. The system presented in this paper not only accurately and quickly recognizes a person object with a specific clothing, but also has a potential extensibility that can be used for other types of object recognition in a video surveillance system for various purposes.

• Science of Emotion and Sensibility
• /
• v.20 no.2
• /
• pp.87-102
• /
• 2017

With increasing interest in 3D printing, the interest in the 3D modelling training that should precede the 3D printing is increasing. However, the existing 3D modelling software is developed mostly by foreign brands. Thus, the interfaces are all in English. 3D modelling software training for Korean novices who are not familiar with these terms has constraints. This study aims to explore what to consider when developing a Korean model for 3D modelling educational software for 3D printing in the face of such reality. For this goal, after having novices with no experience in 3D modeling to perform a house building task using either 12D Design or Tinker CAD, we conducted a survey. It was found in the result that more users favored Tinker CAD over 123D Design, and the errors involved while working with the Tinker CAD were less than those with the 123D Design, and the ratio of people who completed the task with the Tinker CAD was higher than that with the 123D Design. In general discussion, an introductory level educational 3D modeling software development is proposed which utilize characteristics of Tinker CAD (easy modelling is possible by three-dimensional figures) and web-based method. Also, a beginner/intermediate level educational 3D modeling software development is proposed which utilize characteristics of 123D Design (with finer measurement manipulations and figure alignment) and Windows-based method.

• Journal of Digital Convergence
• /
• v.13 no.9
• /
• pp.397-407
• /
• 2015

The purpose of this study was to investigate the relationships among daily hassles, self-efficacy, and stress responses of RN-BSN (Registered Nurses-Bachelor of Science in Nursing) students in juggling both their jobs and learning as an adult learner of distance education in digital convergence era. The data were collected by a questionnaire from 229 nurses in a RN-BSN course of an open university from October to November, 2013. The mean score of facing task dimension was much higher than the interpersonal dimension score among daily hassles. The academic problem of the facing task and the family relationship of the interpersonal were the highest respectively. The mean score of self-efficacy was slightly higher than the median. Multiple regression showed that perceived health status, workload, occupation satisfaction, and values problem of daily hassles explained 44.2% of stress reponses and values problem was the main factor influencing stress responses. The distance education policies and strategies were required to manage their stress for the adult learners of distance education in digital convergence era.