• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.10a
• /
• pp.133-135
• /
• 2022

With the development of IoT and AI technologies and media, various digital devices are being used, and unmanned and automation is progressing rapidly. In particular, high-level image processing technology is required in fields such as smart factories, autonomous driving technology, and intelligent CCTV. However, noise present in the image affects processes such as edge detection and object recognition, and causes deterioration of system accuracy and reliability. In this paper, we propose a filtering algorithm using fuzzy weights to reconstruct images damaged by complex noise. The proposed algorithm obtains a reference value using noise judgment and calculates the final output by applying a fuzzy weight. Simulation was conducted to verify the performance of the proposed algorithm, and the result image was compared with the existing filter algorithm and evaluated.

• Journal of the Korean Society of Industry Convergence
• /
• v.27 no.6_1
• /
• pp.1355-1364
• /
• 2024

This study aims to evaluate the risks associated with chemical substances used in the battery manufacturing industry through the application of the Chemical Hazard Risk Management (CHARM) automated program. Given the extensive use of chemicals in modern industries, ensuring the health and safety of workers has become a critical responsibility for employers. The CHARM system enables a comprehensive evaluation of chemical hazards by combining toxicity data, exposure levels, and workplace conditions to generate risk scores. The study assessed various processes within the battery manufacturing industry, including electrode winding, electrode manufacturing, powder input, and slurry coating. Among these, the powder input and electrode manufacturing processes were identified as high-risk due to frequent exposure to hazardous chemicals like organic solvents and heavy metals. As a result, improvement measures such as the automation of manual processes, enhanced ventilation systems, and the use of less toxic alternatives were proposed to mitigate the risks. This research highlights the importance of continuous risk assessment and the implementation of proactive safety measures in the battery manufacturing industry to ensure worker safety and prevent chemical accidents.

• Journal of Wellbeing Management and Applied Psychology
• /
• v.8 no.1
• /
• pp.55-61
• /
• 2025

This study presents a comprehensive analysis of AI service adoption in the food industry through a wellness-oriented perspective, utilizing a systematic literature review of publications from 2014 to 2024. Through an extensive examination of relevant literature, we identify three critical dimensions: the transformative impact of AI on consumer health and well-being, the fundamental challenges in AI service implementation, and strategic frameworks for successful adoption. Our findings demonstrate that AI services manifest primarily in three distinct forms: process automation, cognitive insights, and cognitive engagement, with cognitive insights emerging as the predominant form, particularly in quality control and supply chain optimization. The research reveals significant challenges, including data quality management, organizational resistance, and workforce adaptation, while emphasizing the critical importance of balancing technical innovation with wellness value creation. We contribute to the existing literature by developing an integrated theoretical framework that synthesizes technological, organizational, and wellness perspectives in AI adoption. The study provides both theoretical contributions through a novel wellness-centric approach to AI adoption research and practical implications by offering strategic guidelines for food industry practitioners. Our findings suggest that successful AI implementation requires a holistic strategy that encompasses technological advancement, organizational transformation, and sustainable wellness value creation, thereby advancing the theoretical understanding of AI.

• KIPS Transactions on Software and Data Engineering
• /
• v.8 no.12
• /
• pp.491-498
• /
• 2019

Digital twin is a technology that virtualizes physical objects of the real world on a computer. It is used by collecting sensor data through IoT, and using the collected data to connect physical objects and virtual objects in both directions. It has an advantage of minimizing risk by tuning an operation of virtual model through simulation and responding to varying environment by exploiting experiments in advance. Recently, artificial intelligence and machine learning technologies have been attracting attention, so that tendency to virtualize a behavior of physical objects, observe virtual models, and apply various scenarios is increasing. In particular, recognition of each robot's motion is needed to build digital twin for co-robot which is a heart of industry 4.0 factory automation. Compared with modeling based research for recognizing motion of co-robot, there are few attempts to predict motion based on sensor data. Therefore, in this paper, an experimental environment for collecting current and inertia data in co-robot to detect the motion of the robot is built, and a motion prediction model based on the collected sensor data is proposed. The proposed method classifies the co-robot's motion commands into 9 types based on joint position and uses current and inertial sensor values to predict them by accumulated learning. The data used for accumulating learning is the sensor values that are collected when the co-robot operates with margin in input parameters of the motion commands. Through this, the model is constructed to predict not only the nine movements along the same path but also the movements along the similar path. As a result of learning using SVM, the accuracy, precision, and recall factors of the model were evaluated as 97% on average.

• Journal of Korea Multimedia Society
• /
• v.15 no.9
• /
• pp.1156-1164
• /
• 2012

Hanok is a cultural heritage containing our ancestor's life style intact and breathing alive with us until now. As Hanok has been concerned as a echo-friendly architecture, a new methodology for efficient construction without damaging the traditional construction process comes into request. The goal of this research is development of a architectural design tool based on the BIM(Building Information Modeling) for satisfying these demands. It will be usable to support whole process of the traditional building from digital design to production and construction. Firstly, we take a consideration of the traditional architecture reflecting the spirit of the age and suggest efficient design method for architectural components. Each components is pre-fabricated as a template representing similar components. All pre-fabricated components are designed by object-oriented concepts so, many variations for a component can be derived from the pre-fabricated component. Our method is helpful for reducing design errors because that it considers combining rule between connecting components in the template design. Moreover it is plugged in the commercial architectural CAD, so it can supports digital design not only traditional architecture but also fusion style mixed with modern architecture.

• Korean Journal of Soil Science and Fertilizer
• /
• v.39 no.6
• /
• pp.396-402
• /
• 2006

Soil organic carbon has long been considered as the most critical factor to evaluate the soil quality, fertility, and fertilizer prescription. In addition, soil organic carbon may impact on greenhouse gas effects and global warming. Because of that, the management of soil organic carbon is increasingly important not only for improving soil quality but also for managing soil as a greenhouse gas source. Both wet and dry combustion have been used to determine soil organic carbon. Many benefits, such as automation and less labor, could the dry combustion method become more popular. Inorganic form of carbon could overestimate soil organic carbon when the dry combustion method was applied. Determination of soil inorganic carbon may contribute to the improved accuracy of soil organic carbon analysis using dry combustion method. Objectives of this research were 1) to develop soil inorganic carbon determination method using modified digital pressure calcimeter and 2) to evaluate soil organic carbon from calcareous soils using the dry and wet combustion method. Results showed that the significant linear relationship was found between soil inorganic carbon content and pressure calcimeter output. Inorganic carbon ranged from 22% to 28% of total carbon in the calcareous soil samples. Soil organic carbon content by dry combustion for calcareous soil was determined by subtracting inorganic carbon measured by the digital pressure calcimeter from total carbon. Soil organic carbon determined by dry combustion method was significantly correlated with that by wet combustion method. In conclusion, the digital pressure calcimeter may use to improve soil organic carbon determination for the calcareous soils by subtracting of soil inorganic carbon from total carbon determined by dry combustion method.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2023.05a
• /
• pp.14-14
• /
• 2023

산업발전에 따른 인구증가, 기후위기에 따른 가뭄 및 물 부족심화, 그리고 수질오염 등은 2015년 제79차 UN총회의 물 안보측면에서 국제사회의 물 분야 위기관리를 위해 2030년을 지속가능한 발전 목표(Sustainable Development Goals)로 하였다. 또한, 현재 물 산업은 빠르게 성장하고 있으며, 2016년 세계경제포럼(World Economic Forum) 의장 클라우스 슈밥(Klaus Schwab)부터 주창된 제4차 산업혁명로 인해 현재 물 산업의 패러다임 또한 급속히 변화하고 있다. 이는 컴퓨터를 기반으로 하는 CPS(Cyber Physical System) 및 DT(Digital Twin) 연계 분석방식의 혁신을 일컫는다. 2002년경에 DT의 기본개념이 제시되었고, 2006년경에는 Embedded System에서의 DT와 같은 개념으로 CPS의 용어가 등장했다. DT는 현실세계에 존재하는 사물, 시스템, 환경 등을 S/W시스템의 가상공간에 동일하게 모사(Virtualization) 및 모의(Simulation)할 수 있도록 하고, 모의결과를 가상시스템으로 현실세계를 최적화 체계 구현 기술을 말한다. DT의 6가지 기능은 ① 실제 데이터(Live Data), ② 모사, ③ 분석정보(Analytics), ④ 모의, ⑤ 예측(Predictions), ⑥ 자동화(Automation) 이다. 또한, CPS는 대규모 센서 및 액추에이터(Actuator)를 가지는 물리적 요소와 이를 실시간으로 제어하는 컴퓨팅 요소가 결합된 복합시스템을 말한다. CPS는 물리세계에서 발생하는 변화를 감지할 수 있는 다양한 센서를 통해 환경인지 기능을 수행한다. 센서로부터 수집된 정보와 물리세계를 재현 및 투영하는 고도화된 시스템 모델들을 기반으로 사이버 물리공간을 인지·분석·예측할 수 있다. CPS의 6가지 구성요소는 ① 상호 운용성(Interoperability), ② 가상화(Virtualization), ③ 분산화(Decentralization), ④ 실시간(Real-time Capability), ⑤ 서비스 오리엔테이션(Service Orientation), ⑥ 모듈화(Modularity)이다. DT와 CPS는 본질적으로 같은 목적, 내용, 그리고 결과를 만들어내고자 하는 같은 종류의 기술이라고 할 수 있다. CPS 및 DT는 물리세계에서 발생하는 변화를 감지할 수 있으며, 토양-지하수 센서를 포함한 관측기술을 통해 환경인지 기능을 수행한다. 지하수 관측기술로부터 수집된 정보와 물리세계를 재현 및 투영하는 고도화된 시스템 모델들을 기반으로 사이버 물리공간 및 디지털 트윈 공간을 인지·분석·예측할 수 있다. CPS 및 DT의 기본 요소들을 실현시키는 것은 양질의 데이터를 모니터링할 수 있는 정확하고 정밀한 1차원 연직 프로파일링 관측기술이며, 이를 토대로 한 수자원 관련 빅데이터의 증가, 빅데이터의 저장과 분석을 가능하게 하는 플랫폼의 개발이다. 본 연구는 CPS 및 DT 기반 토양수분-지하수 관측기술을 이용한 지표수-지하수 연계, 지하수 순환 및 관리, 정수 운영 및 진단프로그램 개발을 위한 토양수분-지하수 관측장치를 지하수 플랫폼 동시성과 디지털 트윈 시뮬레이터 시스템 개발 방향으로 제시하고자 한다.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.47 no.6
• /
• pp.75-81
• /
• 2010

The segmentation of cartilage is crucial for the diagnose and treatment of osteoarthritis (OA), and has mostly been done manually by an expert, requiring a considerable amount of time and effort due to the thin shape and vague boundaries of the cartilage in MR (magnetic resonance) images. In this paper, we propose a fully automatic method to segment cartilage in a knee joint on MR images. The proposed method is based on a small number of manually segmented images as the training set and comprised of an initial per patch segmentation process and a global refinement process on the cumulative per patch results. Each patch for per patch segmentation is positioned by classifying the bone-cartilage interface on the pre-segmented bone surface. Next, the shape and intensity priors are constructed for each patch based on information extracted from reference patches in the training set. The ratio of influence between the shape and intensity priors is adaptively determined per patch. Each patch is segmented by graph cuts, where energy is defined based on constructed priors. Finally, global refinement is conducted on the global cartilage using the results of per patch segmentation as the shape prior. Experimental evaluation shows that the proposed framework provide accurate and clinically useful segmentation results.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.27 no.5
• /
• pp.619-628
• /
• 2009

LiDAR has capability of rapid data acquisition and provides useful information for reconstructing surface of the Earth. However, Extracting information from LiDAR data is not easy task because LiDAR data consist of irregularly distributed point clouds of 3D coordinates and lack of semantic and visual information. This thesis proposed methods for automatic extraction of buildings and 3D detail modeling using airborne LiDAR data. As for preprocessing, noise and unnecessary data were removed by iterative surface fitting and then classification of ground and non-ground data was performed by analyzing histogram. Footprints of the buildings were extracted by tracing points on the building boundaries. The refined footprints were obtained by regularization based on the building hypothesis. The accuracy of building footprints were evaluated by comparing with 1:1,000 digital vector maps. The horizontal RMSE was 0.56m for test areas. Finally, a method of 3D modeling of roof superstructure was developed. Statistical and geometric information of the LiDAR data on building roof were analyzed to segment data and to determine roof shape. The superstructures on the roof were modeled by 3D analytical functions that were derived by least square method. The accuracy of the 3D modeling was estimated using simulation data. The RMSEs were 0.91m, 1.43m, 1.85m and 1.97m for flat, sloped, arch and dome shapes, respectively. The methods developed in study show that the automation of 3D building modeling process was effectively performed.

• Journal of Broadcast Engineering
• /
• v.17 no.1
• /
• pp.73-80
• /
• 2012

Recently, medical equipments are developed and used for diagnosis or studies. In addition, demand of techniques which automatically deal with three dimensional medical images obtained from the medical equipments is growing. One of the techniques is automatic bone segmentation which is expected to enhance the diagnosis efficiency of osteoporosis, fracture, and other bone diseases. Although various researches have been proposed to solve it, they are unable to be used in practice since a size of the medical data is large and there are many low contrast boundaries with other tissues. In this paper, we present a fast and accurate automatic framework for bone segmentation based on multi-resolutions. On a low resolution step, a position of the bone is roughly detected using constrained branch and mincut which find the optimal template from the training set. Then, the segmentation and the registration are iteratively conducted on the multiple resolutions. To evaluate the performance of the proposed method, we make an experiment with femur and tibia from 50 test knee magnetic resonance images using 100 training set. The proposed method outperformed the constrained branch and mincut in aspect of segmentation accuracy and implementation time.