• 한국인터넷방송통신학회논문지
• /
• 제18권4호
• /
• pp.55-60
• /
• 2018

본 논문은 전력선 통신에서 딥 러닝 기술 적용시킨 연구의 초기 결과를 보여준다. 본 논문에서는 전력선 통신의 성능을 감소시키는 원인인 잡음을 제거하기 위해 딥 러닝 기술을 적용시켜 효과적인 잡음 제거를 목표로 하고 수신 단에서 딥 러닝 모델을 추가하여 잡음을 효과적으로 제거하는 시스템을 제안한다. 딥 러닝 모델을 학습시키기 위해서는 데이터가 필요하므로 기존의 데이터들을 저장하고 있다고 가정하고 제안하는 시스템에 대해 시뮬레이션을 진행하여 부가 백색 가우시안 잡음 채널의 이론적 결과와 비트 에러률을 비교하여 제안하는 시스템 모델이 잡음을 제거하여 통신 성능을 향상시킨 것을 확인한다.

• 산업경영시스템학회지
• /
• 제38권1호
• /
• pp.152-161
• /
• 2015

Until a recent date, Toyota Production System (called TPS) was introduced by many domestic companies to remove waste and reduce manufacturing cost. However, cases of substantial and effective improvement after the introduction are not much. Even though many companies have actively conducted TPS during that time, the outcome is not satisfactory. In this paper, we show the problems and core contents to consider in applying of TPS as follows. First, the innovative organizational culture formed by active participation of employees and leadership of the CEO is very important for a successful introduction of TPS above all. Second, it is necessary to prepare various training programs optimized for the field in order to continuously improve the competency of employees in each class, and to train skilled personnel through that programs. Third, it is necessary to improve the maturity level of TPS application through the construction of correct evaluation system on accomplishment of the production system. In addition, the problems that occur should be solved through the continuous improvement activities. These results will help to TPS introduction of the domestic small-medium companies. Therefore, this study will contribute to strengthen and improve the global competitiveness in the related industries.

• 한국철도학회:학술대회논문집
• /
• 한국철도학회 2003년도 춘계학술대회 논문집
• /
• pp.567-573
• /
• 2003

Korean High Speed Train (KHST) has been tested on high speed line in JungBu site since it was developed in 2002. The data acquisition system was developed to accomplish successfully this on-line test for proving the dynamic Performance of KHST. This system was consist of the personal computers based on National Instrument PXI modules and the test programs based on Labview 6i. This paper shows that this system is efficient to acquire the test data through the multi-channels connected the accelerometers which located in long distance places and flexible to change and add channels for data acquisition. The dynamic analysis of an on-line test is very complicate because the environmental conditions, as examples radius of curve, inclination of the track, tunnels, bridges, and so forth, and running conditions, as examples driving, braking, the number of working motors, and so forth, have an effect on the results. Therefor, the analysis method is important and this paper proposes the efficient procedure graphically, showing the proposed method simplify the accelerations of 5th bogie frame acquired during the on-line test for KHST.

• Industrial Engineering and Management Systems
• /
• 제11권4호
• /
• pp.371-384
• /
• 2012

This study proposes a multi-level data analysis approach to identify both superficial and latent relationships among variables in the data set obtained from a vocational rehabilitation (VR) services program of people with significant disabilities. At the first layer, data mining and statistical predictive models are used to extract the superficial relationships between dependent and independent variables. To supplement the findings and relationships from the analysis at the first layer, association rule mining algorithms at the second layer are employed to extract additional sets of interesting associative relationships among variables. Finally, nonlinear nonparametric canonical correlation analysis (NLCCA) along with clustering algorithm is employed to identify latent nonlinear relationships. Experimental outputs validate the usefulness of the proposed approach. In particular, the identified latent relationship indicates that disability types (i.e., physical and mental) and severity (i.e., severe, most severe, not severe) have a significant impact on the levels of self-esteem and self-confidence of people with disabilities. The identified superficial and latent relationships can be used to train education program designers and policy developers to maximize the outcomes of VR training programs.

• 실천공학교육논문지
• /
• 제6권2호
• /
• pp.91-97
• /
• 2014

FPGA를 이용해서 다양한 멀티미디어 데이터 처리가 가능한 교육장비를 소개한다. 이 장비를 이용해서 영상인식 기반의 하드웨어 설계의 한 사례를 소개하고 그 설계를 기반으로 "FPGA를 이용한 디지털시스템 설계" 교과목의 교육 가능한 사례를 소개한다. 학생들에 의해서 새롭게 설계한 하드웨어를 본 FPGA를 이용해서 하드웨어 장비에 적용시키는 능력을 배양할 수 있고, 또한 개념 설계, 부분설계, 상세설계를 통해서 FPGA 기반 하드웨어의 창의적 종합설계 능력을 키울 수 있다. 그리고 오디오 코덱을 제어하는 부분은 FPGA내에 있는 소프트 마이크로프로세서인 NIOS II를 이용해서 한 칩에 디지털 하드웨어와 마이크로컨트롤러를 결합한 SOC 설계 능력을 키울 수 있다. 또한, 무선통신, Labivew와 FPGA 설계 능력을 결합하는 적용능력도 키울 수 있다.

• 한국소음진동공학회논문집
• /
• 제12권7호
• /
• pp.542-549
• /
• 2002

Computer simulation is essential to design the suspension elements of railway vehicle. By computer simulation, engineers can assess the feasibility of given design variables and chance them to get a bettor design. Even though commercial simulation codes are used, the computational time and cost remains non-trivial. Therefore, malty researchers have used a mesa model made by sampling data through simulation. In this paper, four mesa-models for each index group such as ride comfort, derailment Quotient, unloading radio and stability index, are constructed by use of neural network. After these meta models are constructed, multi-objective optimization are achieved by using the differential evolution. This paper shows that the optimization of design variables using the neural network model is very efficient to solve the complex optimization Problem.

• Journal of Information Processing Systems
• /
• 제13권5호
• /
• pp.1126-1134
• /
• 2017

A variety of medical service applications in the field of the Internet of Things (IoT) are being studied. Segmentation is important to identify meaningful regions in images and is also required in 3D images. Previous methods have been based on gray value and shape. The Visible Korean dataset consists of serially sectioned high-resolution color images. Unlike computed tomography or magnetic resonance images, automatic segmentation of color images is difficult because detecting an object's boundaries in colored images is very difficult compared to grayscale images. Therefore, skilled anatomists usually segment color images manually or semi-automatically. We present an out-of-core 3D segmentation method for large-scale image datasets. Our method can segment significant regions in the coronal and sagittal planes, as well as the axial plane, to produce a 3D image. Our system verifies the result interactively with a multi-planar reconstruction view and a 3D view. Our system can be used to train unskilled anatomists and medical students. It is also possible for a skilled anatomist to segment an image remotely since it is difficult to transfer such large amounts of data.

• International Journal of Knowledge Content Development & Technology
• /
• 제9권1호
• /
• pp.81-108
• /
• 2019

This research has investigated the perceptions of subject specialization services and the opinions of students majoring in library and information science preparing for librarianship, librarians operating in the field, and library directors on the status and ways of nurturing subject specialization for librarians, among others. To this end, based on the results of previous research and the survey questionnaire analysis, we have presented a policy to train subject librarians. First, we have proposed a plan for systematizing the current educational system within the department of library and information science. We have also suggested ways to secure subject expertise based on curriculum management, minor programs, multi-major programs, and interdisciplinary major programs based on the standard curriculum model. Second, we have presented a subject specialization educational system for field librarians, and further suggested details for the development of an educational program that can help build subject expertise and the operation of educational methods as well as the personnel in charge of implementing the educational programs. Third, we have proposed institutionalization of the qualifications of the subject librarian where the qualification requirements have been organized considering academic background, major program, library career, and career experience in the subject specialization service, further suggesting the implementation and maintenance of the system.

• International Journal of Naval Architecture and Ocean Engineering
• /
• 제12권1호
• /
• pp.617-635
• /
• 2020

The purpose of this study is to discuss how to improve the maneuverability of lifting and diving for underwater vehicle's vertical motion. Therefore, to solve these problems, applied the 3-D numerical simulation, Taguchi's Design of Experiment (DOE), and intelligent parameter design methods, etc. We planned four steps as follows: firstly, we applied the 2-D flow simulation with NACA series, and then through the Taguchi's dynamic method to analyze the sensitivity (β). Secondly, take the data of pitching torque and total resistance from the Taguchi orthogonal array (L9), the ignal-to-noise ratio (SNR), and analysis each factorial contribution by ANOVA. Thirdly, used Radial Basis Function Network (RBFN) method to train the non-linear meta-modeling and found out the best factorial combination by Particle Swarm Optimization (PSO) and Weighted Percentage Reduction of Quality Loss (WPRQL). Finally, the application of the above methods gives the global optimum for multi-quality characteristics and the robust design configuration, including L/D is 9.4:1, the foreplane on the hull (Bow-2), and position of the sail is 0.25 Ls from the bow. The result shows that the total quality is improved by 86.03% in comparison with the original design.

• Nuclear Engineering and Technology
• /
• 제54권8호
• /
• pp.3027-3033
• /
• 2022

Background: In this study, various types of deep-learning models for predicting in vitro radiosensitivity from gene-expression profiling were compared. Methods: The clonogenic surviving fractions at 2 Gy from previous publications and microarray gene-expression data from the National Cancer Institute-60 cell lines were used to measure the radiosensitivity. Seven different prediction models including three distinct multi-layered perceptrons (MLP), four different convolutional neural networks (CNN) were compared. Folded cross-validation was applied to train and evaluate model performance. The criteria for correct prediction were absolute error < 0.02 or relative error < 10%. The models were compared in terms of prediction accuracy, training time per epoch, training fluctuations, and required calculation resources. Results: The strength of MLP-based models was their fast initial convergence and short training time per epoch. They represented significantly different prediction accuracy depending on the model configuration. The CNN-based models showed relatively high prediction accuracy, low training fluctuations, and a relatively small increase in the memory requirement as the model deepens. Conclusion: Our findings suggest that a CNN-based model with moderate depth would be appropriate when the prediction accuracy is important, and a shallow MLP-based model can be recommended when either the training resources or time are limited.