• 대한임베디드공학회논문지
• /
• 제19권1호
• /
• pp.47-55
• /
• 2024

We spend a lot of time in indoor space, and the space has a huge impact on our lives. Interior design plays a significant role to make an indoor space attractive and functional. However, it should consider a lot of complex elements such as color, pattern, and material etc. With the increasing demand for interior design, there is a growing need for technologies that analyze these design elements accurately and efficiently. To address this need, this study suggests a deep learning-based design analysis system. The proposed system consists of a semantic segmentation model that classifies spatial components and an image classification model that classifies attributes such as color, pattern, and material from the segmented components. Semantic segmentation model was trained using a dataset of 30000 personal indoor interior images collected for research, and during inference, the model separate the input image pixel into 34 categories. And experiments were conducted with various backbones in order to obtain the optimal performance of the deep learning model for the collected interior dataset. Finally, the model achieved good performance of 89.05% and 0.5768 in terms of accuracy and mean intersection over union (mIoU). In classification part convolutional neural network (CNN) model which has recorded high performance in other image recognition tasks was used. To improve the performance of the classification model we suggests an approach that how to handle data that has data imbalance and vulnerable to light intensity. Using our methods, we achieve satisfactory results in classifying interior design component attributes. In this paper, we propose indoor space design analysis system that automatically analyzes and classifies the attributes of indoor images using a deep learning-based model. This analysis system, used as a core module in the A.I interior recommendation service, can help users pursuing self-interior design to complete their designs more easily and efficiently.

• 전기학회논문지
• /
• 제57권7호
• /
• pp.1247-1253
• /
• 2008

A design method of a T-S fuzzy model based reduced order nonlinear unknown input observer(NUIO) is presented. The fuzzy NUIO is designed based on the parallel distributed compensation(PDC) concept. It consists of a number of the linear UIOs, each of which is designed for each local linear model in the T-S fuzzy model of a class of nonlinear systems. The fuzzy NUIO provides not only the state estimates insensitive to the unknown inputs, for example, disturbances and faults etc., but also the estimates of the unknown inputs. Therefore, It can be employed in the state feedback control and disturbance rejection control of a class of nonlinear systems with unknown disturbances. It also applied to the robust residual generation for the fault detection and isolation systems and to the design of fault tolerant control systems. As an example, the NUIO is applied to an inverted pendulum system to show the state and disturbance estimation performance and to illustrate the fuzzy reduced order NUIO design method.

• 공학교육연구
• /
• 제23권4호
• /
• pp.28-36
• /
• 2020

Capstone design education is essential in the engineering design process according to the certification standards of ABEEK. Capstone design process should be properly trained in undergraduate courses in order to increase the design ability of systems, components and processes within realistic constraints. In this study, a modified design model as a capstone design education model was proposed to reduce the separation between the design process at industrial sites and the design process at university education. The modified design model based on 6-sigma methodology is composed of 6 design steps such as define, measure, analyse, design, verify, and report. Each step has appropriated design contents and tools, and is configured to generate design results. The proposed design model was directly applied to the capstone design class for automotive engineering in Kunsan National University, and it was confirmed that the proposed DMADVR methodology was a very useful design education model to enhance the design ability, teamwork ability and communication skills required by ABEEK.

• 한국안전학회지
• /
• 제27권6호
• /
• pp.115-121
• /
• 2012

This paper, being the second in a two-part series, presents the robust performance of the proposed design method which can enhance a reliability-based design optimization(RBDO) under the uncertainties of probabilistic models. The robust performances of the solutions obtained by the proposed method, described in the Part 1, are investigated through the parametric studies. A 10-bar truss example is considered, and the uncertain parameters include the number of data observed, and the variations of applied loadings and allowable stresses. The numerical results show that the proposed method can produce a consistent result despite of the large variations in the parameters. Especially, even with the relatively small data set, the analysis results show that the exact probabilistic model can be successfully predicted with optimized design sections. This consistency of estimating appropriate probability model is also observed in the case of the variations of other parameters, which verifies the robustness of the proposed method.

• 한국의상디자인학회지
• /
• 제21권1호
• /
• pp.115-129
• /
• 2019

This study aimed to develop methods for technical design education that can be intimately connected to the industrial field. For this, technical design jobs performed in the fields of the domestic and foreign fashion industries and their required competences were examined, and educational methods based on constructivism were proposed. Korean fashion technical designers' works were identified, and then the fashion technical designer's responsibilities and qualifications were collected and analyzed from global employment sites. On the basis of the collection and analysis, hands-on staff members and education experts were interviewed about required competences for the actual business and possible suitable methods for education. The results of research showed that in the case of the US, job systems and relevant duties for technical designers were clearly defined by clothing brands, whereas in Korea, businesses were systematized around vendors, not brands, and as a result the businesses of technical package composition and specification proposals were not performed properly. This study organized the contents of technical design education into fit development and specification, the composition of technical design packages, the evaluation and approval of samples, fit schedule management and fitting, block pattern setting and pattern correction, sewing specifications appropriate for styles and materials, grading, technical terms, and production management. As for the technical design education models, the cognitive apprenticeship model, resource-based learning, the problem-based and anchored model, and the problem-based and resource-based models were proposed.

• 시스템엔지니어링학술지
• /
• 제13권1호
• /
• pp.1-6
• /
• 2017

A stores management software which is embedded in the stores management system requires high-level reliability and real-time processing. It also required to implement and verify protocols which requires timing constraints to control various weapons. In this paper, we propose design methodology to design a stores management software and its support middleware based on the TMO (Time-triggered Message-triggered Object) model.

• 한국의류학회지
• /
• 제42권1호
• /
• pp.40-57
• /
• 2018

This study investigated the design practice model based on the creative fashion designer's methodology in fashion education. 'The Design Cycle' was the criterion used to analyze the design method of Demna Gvasalia who is one of the outstanding contemporary designers. After that, this study's practice model was then developed and experimented to verify its effectiveness in design practice as based on Gvasalia's method where ready-to-wear products were firstly dissembled then re-constructed with new designs created based on re-constructed results. To test its effectiveness, a student oriented design workshop was held to extract design results through the practice model; in addition, the students also conducted a survey to evaluate the effectiveness of the method. According to the self-evaluation result, the participants generally accept the design efficiency through the distinctive process. An evaluation by three fashion experts was also conducted. Experts assessed that the model is recommendable for seniors having knowledges on 'Construction', it is appropriate to deal with the trickled-down copying trend that could promote student interest and generate separate results according to different visions. Therefore, it could be accepted that the applicability of this study's practice model was confirmed.

• 한국산학기술학회논문지
• /
• 제11권8호
• /
• pp.2975-2982
• /
• 2010

본 논문에서는 모델기반 설계를 이용한 이륜 도립진자 로봇의 설계방법에 대해 제시한다. 임베디드 시스템의 제어 프로그램 설계는 MATLAB/SIMULINK를 사용한 모델기반 설계에 의해 간편하고 손쉽게 구현되었으며, 로봇은 NXT 마인드스톰, 서보 직류전동기, 초음파센서, 자이로센서, 광센서로 구성되었다. 이 로봇은 불안정한 비선형시스템이며 몸체 경사각 제어문제를 가지고 있는데, 제어기 설계는 상태궤환 LQR 제어를 이용하였다. 타겟이 되는 프로세서에 종속적이지 않은 모델기반 설계는 문서기반 설계보다 프로그램 개발, 오류 발견 및 수정, 소프트웨어 구조 파악의 측면에서 장점을 가지고 있음을 제어기 설계와 실험을 통해서 확인할 수 있었다.

• 대한산업공학회지
• /
• 제28권3호
• /
• pp.331-343
• /
• 2002

This paper proposes a fuzzy rule-based model as a means to build usability models between emotional satisfaction and design variables of consumer products. Based on a subtractive clustering algorithm, this model obtains partially overlapping rules from existing data and builds multiple local models each of which has a form of a linear regression equation. The best subset procedure and cross validation technique are used to select appropriate input variables. The proposed technique was applied to the modeling of luxuriousness, balance, and attractiveness of office chairs. For comparison, regression models were built on the same data in two different ways; one using only potentially important variables selected by the design experts, and the other using all the design variables available. The results showed that the fuzzy rule-based model had a great benefit in terms of the number of variables included in the model. They also turned out to be adequate for predicting the usability of a new product. Better yet, the information on the product classes and their satisfaction levels can be obtained by interpreting the rules. The models, when combined with the information from the regression models, are expected to help the designers gain valuable insights in designing a new product.

• Nuclear Engineering and Technology
• /
• 제53권12호
• /
• pp.4166-4178
• /
• 2021

The Control Rod Drive Mechanism (CRDM) is an essential part of the reactor, which realizes the start-stop and power adjustment of the reactor by lifting and lowering the control rod assembly. As a moving part in CRDM, the latch directly contacts with the control rod assembly, and the life of latch is closely related to the service life of the reactor. In this paper, the relationship between the life of the latch and the step stress, friction stress, and impact stress in the process of movement is analyzed, and the optimization methodology and process of latch life based on the approximate model are proposed. The design variables that affect the life of the latch are studied through the experimental design, and the optimization objective of design variables based on the latch life is established. Based on this, an approximate model of the life of the latch is built, and the multi-objective optimization of the life of the latch is optimized through the NSGA-II algorithm.