• Title/Summary/Keyword: Convergence Performance

Search Result 6,969, Processing Time 0.041 seconds

Automatic Extraction of Liver Region from Medical Images by Using an MFUnet

  • Vi, Vo Thi Tuong;Oh, A-Ran;Lee, Guee-Sang;Yang, Hyung-Jeong;Kim, Soo-Hyung
    • Smart Media Journal
    • /
    • v.9 no.3
    • /
    • pp.59-70
    • /
    • 2020
  • This paper presents a fully automatic tool to recognize the liver region from CT images based on a deep learning model, namely Multiple Filter U-net, MFUnet. The advantages of both U-net and Multiple Filters were utilized to construct an autoencoder model, called MFUnet for segmenting the liver region from computed tomograph. The MFUnet architecture includes the autoencoding model which is used for regenerating the liver region, the backbone model for extracting features which is trained on ImageNet, and the predicting model used for liver segmentation. The LiTS dataset and Chaos dataset were used for the evaluation of our research. This result shows that the integration of Multiple Filter to U-net improves the performance of liver segmentation and it opens up many research directions in medical imaging processing field.

A Study on Fast Convergence Algorithm of Block Adaptive Filter in Frequency Domain (주파수 영역에서 블럭적응 필터의 고속 수렴 알고리즘에 관한 연구)

  • 강철호;조해남
    • The Journal of Korean Institute of Communications and Information Sciences
    • /
    • v.10 no.6
    • /
    • pp.308-316
    • /
    • 1985
  • A new implementation of Block Adaptive filter in frequency domain is presented in this paper. Block digital filtering involves the calculation of a block or finite set of filter out put from a block of input values. A fast convergence algorithm of block adaptive filter is developed using Gordar theory and compared with the performance results of Satio algorithm and BLMS algorithm. Form the result we can be shown that the convergence state of given algorithm is not only faster than BLMS algorithm but also the resulting convergence error is less than the convergence error of Satio algorithm.

  • PDF

A Study on the Second-order Iterative Learning Control Algorithm with Feedback (궤환을 갖는 2차 반복 학습제어 알고리즘에 관한 연구)

  • Huh, Kyung-Moo
    • The Transactions of the Korean Institute of Electrical Engineers A
    • /
    • v.48 no.5
    • /
    • pp.629-635
    • /
    • 1999
  • A second-order iterative learning control algorithm with feedback is proposed in this paper, in which a feedback term is added in the learning control scheme for the enhancement of convergence speed and robustness to disturbances or system parameter variations. The convergence proof of the proposed algorithm is givenl, and the sufficient condition for the convergence of the algorithm is provided. And it also includes the discussions about the convergence performance of the algorithm when the initial condition at the beginning of each iteration differs from the previous value of the initial. Simulation results show the validity and efficiency of the proposed algorithm.

  • PDF

Construction and Performance Evaluation of Standard System for Medical Big Data (의료 빅데이터를 위한 표준화 시스템 구축 및 성능평가)

  • Kim, Seung-Jin;Jeong, Chang-Won;No, Si-Hyeong;Kim, Ji-Eon;Kim, Tae-Hoon;Jun, Hong Yong;Lee, Yun Oh;Yoon, Kwon-Ha
    • Proceedings of the Korea Information Processing Society Conference
    • /
    • 2018.05a
    • /
    • pp.275-276
    • /
    • 2018
  • 본 논문에서는 원광대학교병원 의료정보시스템의 임상데이터를 OHDSI 가 제안하는 공통데이터 모델로 변환하여 표준화 시스템 구축에 대해서 기술한다. 또한, 검색속도 향상을 위해 인덱싱 기법을 적용한 성능평가 결과를 보인다. 구축된 표준화 시스템은 다양한 임상연구에 활용될 것을 기대하고 있다.

Analysis of the impact relationship between business culture's type and creating performance of convergence corporate (융합기업의 기업문화형태와 성과창출과의 영향 관계 분석)

  • Choi, Seung-Il;Kim, Dong-Il
    • Journal of Digital Convergence
    • /
    • v.13 no.8
    • /
    • pp.169-176
    • /
    • 2015
  • This study try to analyze the relationship between the corporate culture type and performance about convergence corporate. In addition, we developed a model that fix this research to analyze the business culture and firms type in order to perform this study overall. In the daily operations of an organization's culture can be a source of corporate competitiveness, it may be classified as an important factor in the performance of the organization to promote. In other words, the organizational culture as well as be able to describe an individual's attitudes and behavior, microscopic, macroscopic analysis of organizational behavior can serve to connect conceptually each others and through this process can be seen as contributing to the achievement creation. Therefore, analyzed the influence of the relationship between corporate culture and performance form the basis of this study and research model was validated. Corporate culture in the form of the convergency enterprise found out the strong relationship with job satisfaction and organizational commitment in the research result. Finally, this research results are expected to be a useful guide as a basis for the creation and management of companies with a corporate culture in the near future convergence corporation.

Performance Evaluation of Domestic Prototype Dose Area Product Meter SFT-1 (국산 프로토타입 면적선량계 SFT-1의 성능평가)

  • Lee, Ho-Sun;Han, Seong-Gyu;Roh, Young-Hoon;Lim, Hyun-Jong;Kim, Jung-Min;Kim, Jong-Uk;Chae, Hyun-Sik;Yoon, Yong-Su
    • Journal of radiological science and technology
    • /
    • v.39 no.3
    • /
    • pp.435-441
    • /
    • 2016
  • The importance of radiation dose display of medical X-ray equipment was emphasized, while third edition of IEC(International Electrotechnical Commission) 60601 started to apply. The existing medical X-ray equipment selected a method for attaching the DAP(Dose Area Product) meter when the dose display. However, because the DAP meter was dependent on all of the income, And it did not yet produced in Korea. So, we received the support of Seoul R&BD Program(Grants No. C1152055) to produce DAP meter prototype of the Domestically technology. In this study, the performance of this prototype was evaluated by comparing the German company's product Evaluation item was an electronic capture performance, radiation dose dependence, radiation quality dependence, energy transmittance, repeatability, light transmittance of 6 entries. And IEC 60580 was based on this evaluation. Evaluation results were electronic capture performance intrinsic error 9.5%, radiation dose dependence limits of variation 1%, repeatability coefficient of variation 2%, energy transmittance 91% each assessment was passed. However radiation quality dependence limits of variation 29%, light transmittance 55% was less than acceptance criteria.

Effects of Convergence-based Integrated simulation Practice program on the Clinical decision making, Problem solving process, Clinical competence and Confidence of core fundamental nursing skill performance for Nursing Students (융복합 기반 통합시뮬레이션실습 교육이 간호대학생의 임상의사결정능력, 문제해결과정, 임상수행능력, 핵심기본간호술 수행 자신감에 미치는 효과)

  • Moon, Mi-Young
    • Journal of Digital Convergence
    • /
    • v.15 no.7
    • /
    • pp.271-284
    • /
    • 2017
  • This study was performed to examine that convergence-based integrated simulation practice program curriculum effects the clinical decision making, problem solving competence, clinical competence and confidence of core fundamental nursing skill performance for nursing students. After the convergence-based integrated simulation practice program, there were significant increased in problem solving process(t=-3.052, p<.01), clinical competence(t=-4.279, p=.000), and confidence of core fundamental nursing skill performance(t=-2.416, p<.05). The finding of this study verified that the integrated simulation practice program curriculum can be used for improvements of problem solving competence, clinical competence and confidence of core fundamental nursing skill performance for nursing students. It is necessary to develop a scientific analytical evaluation tool and program, and it would be necessary to have a system for scientifically analyzing the integration of simulation practical courses by nursing college students by grade level and subjects.

Numerical Modeling and Experiment for Single Grid-Based Phase-Contrast X-Ray Imaging

  • Lim, Hyunwoo;Lee, Hunwoo;Cho, Hyosung;Seo, Changwoo;Lee, Sooyeul;Chae, Byunggyu
    • Progress in Medical Physics
    • /
    • v.28 no.3
    • /
    • pp.83-91
    • /
    • 2017
  • In this work, we investigated the recently proposed phase-contrast x-ray imaging (PCXI) technique, the so-called single grid-based PCXI, which has great simplicity and minimal requirements on the setup alignment. It allows for imaging of smaller features and variations in the examined sample than conventional attenuation-based x-ray imaging with lower x-ray dose. We performed a systematic simulation using a simulation platform developed by us to investigate the image characteristics. We also performed a preliminary PCXI experiment using an established a table-top setup to demonstrate the performance of the simulation platform. The system consists of an x-ray tube ($50kV_p$, 5 mAs), a focused-linear grid (200-lines/inch), and a flat-panel detector ($48-{\mu}m$ pixel size). According to our results, the simulated contrast of phase images was much enhanced, compared to that of the absorption images. The scattering length scale estimated for a given simulation condition was about 117 nm. It was very similar, at least qualitatively, to the experimental contrast, which demonstrates the performance of the simulation platform. We also found that the level of the phase gradient of oriented structures strongly depended on the orientation of the structure relative to that of linear grids.

FC-MMA Adaptive Equalization Algorithm to improve the Convergence Speed of MMA in 16-QAM System (16-QAM 시스템에서 MMA의 수렴 속도를 개선시킨 FC-MMA 적응 등화 알고리즘)

  • Lim, Seung-Gag
    • The Journal of the Institute of Internet, Broadcasting and Communication
    • /
    • v.14 no.1
    • /
    • pp.93-99
    • /
    • 2014
  • This paper deals with the FC-MMA (Fast Convergence-Multi Modulus Algorithm) which is improving the convergence characteristics of the MMA (Multiple Modulus Algorithm) adaptive equalization algorithm that is used for the minimization of the intersymbol interference which occurs in the time dispersive communication channel. In the time varying charateristics and the abnormal situation like as outage of the communication channel, the adaptive equalizer needs to adapting the new environment more rapidly. For this problem, the residual isi and the maximum distortion performance index which are meaning the convergence characteristics are widely adapted in the adaptive equalizer. The 16-QAM signal is transmitted and it was confirmed that the proposed algorithm, the FC-MMA has the fast convergence performance such as in the 1.75 times fast in residual isi and 2.5 times fast in the maximum distortion in order to reaching the steady state compare to the MMA algorithm in the same channel environment by the computer simulation.

Sales Prediction of Electronic Appliances using a Convergence Model based on Artificial Neural Network and Genetic Algorithm (인공신경망과 유전자 알고리즘 기반의 융합모델을 이용한 가전제품의 판매예측)

  • Seo, Kwang-Kyu
    • Journal of Digital Convergence
    • /
    • v.13 no.9
    • /
    • pp.177-182
    • /
    • 2015
  • The brand and product awareness of Korean electronics companies in the North American market has grown significantly and North American consumers has been recognized as an innovative technology products good performance of Korean electronics appliances. The consumer need of energy saving has led to a rise in market share because Korean electronics appliances have the excellence in energy saving aspects. The expansion of smartphones and mobile devices and the development of smart grid technology can affect electronics market. Domestic companies are continuously develop new product to provide consumers convenient with a variety of additional features combined consumer products. This study proposes a convergence model for sales prediction of electronic appliances using sales data of A company from the North American market. We develop the convergence model for sales prediction based on based on artificial neural network and genetic algorithm. In addition, we validate the superiority of the proposed convergence model by comparing the prediction performance of traditional prediction models.