• Title/Summary/Keyword: model-driven 방식

Search Result 113, Processing Time 0.029 seconds

A Data-Driven Jacobian Adaptation Method for the Noisy Speech Recognition (잡음음성인식을 위한 데이터 기반의 Jacobian 적응방식)

  • Chung Young-Joo
    • The Journal of the Acoustical Society of Korea
    • /
    • v.25 no.4
    • /
    • pp.159-163
    • /
    • 2006
  • In this paper a data-driven method to improve the performance of the Jacobian adaptation (JA) for the noisy speech recognition is proposed. In stead of constructing the reference HMM by using the model composition method like the parallel model combination (PMC), we propose to train the reference HMM directly with the noisy speech. This was motivated from the idea that the directly trained reference HMM will model the acoustical variations due to the noise better than the composite HMM. For the estimation of the Jacobian matrices, the Baum-Welch algorithm is employed during the training. The recognition experiments have been done to show the improved performance of the proposed method over the Jacobian adaptation as well as other model compensation methods.

A Data-driven Multiscale Analysis for Hyperelastic Composite Materials Based on the Mean-field Homogenization Method (초탄성 복합재의 평균장 균질화 데이터 기반 멀티스케일 해석)

  • Suhan Kim;Wonjoo Lee;Hyunseong Shin
    • Composites Research
    • /
    • v.36 no.5
    • /
    • pp.329-334
    • /
    • 2023
  • The classical multiscale finite element (FE2 ) method involves iterative calculations of micro-boundary value problems for representative volume elements at every integration point in macro scale, making it a computationally time and data storage space. To overcome this, we developed the data-driven multiscale analysis method based on the mean-field homogenization (MFH). Data-driven computational mechanics (DDCM) analysis is a model-free approach that directly utilizes strain-stress datasets. For performing multiscale analysis, we efficiently construct a strain-stress database for the microstructure of composite materials using mean-field homogenization and conduct data-driven computational mechanics simulations based on this database. In this paper, we apply the developed multiscale analysis framework to an example, confirming the results of data-driven computational mechanics simulations considering the microstructure of a hyperelastic composite material. Therefore, the application of data-driven computational mechanics approach in multiscale analysis can be applied to various materials and structures, opening up new possibilities for multiscale analysis research and applications.

Traceability Validation of Structured Behavioral Feature-Based Embedded SW Architecture Design Method (Structured Behavioral Feature기반 임베디드 SW 아키텍처 설계 방법의 추적성 검증)

  • Lee, Jung Tae;Jeong, Soyoung
    • Proceedings of the Korean Society of Computer Information Conference
    • /
    • 2017.07a
    • /
    • pp.281-284
    • /
    • 2017
  • 최근 임베디드 시스템 개발이 Model Driven Engineering 방식으로 변화하면서 요구사항과 모델 간의 추적성을 보장하는 것이 매우 중요해졌다. 이 논문에서는 기존의 FDD(Feature Driven Development)와 FOSE(Feature Oriented Software Engineering) 방법론에 적용된 feature 개념을 재정의하여 이를 AUTOSAR platform에 적용하는 방법을 제시하며 요구사항부터 model, code까지 추적성을 검증한다.

  • PDF

A Study on the Noisy Speech Recognition Based on the Data-Driven Model Parameter Compensation (직접데이터 기반의 모델적응 방식을 이용한 잡음음성인식에 관한 연구)

  • Chung, Yong-Joo
    • Speech Sciences
    • /
    • v.11 no.2
    • /
    • pp.247-257
    • /
    • 2004
  • There has been many research efforts to overcome the problems of speech recognition in the noisy conditions. Among them, the model-based compensation methods such as the parallel model combination (PMC) and vector Taylor series (VTS) have been found to perform efficiently compared with the previous speech enhancement methods or the feature-based approaches. In this paper, a data-driven model compensation approach that adapts the HMM(hidden Markv model) parameters for the noisy speech recognition is proposed. Instead of assuming some statistical approximations as in the conventional model-based methods such as the PMC, the statistics necessary for the HMM parameter adaptation is directly estimated by using the Baum-Welch algorithm. The proposed method has shown improved results compared with the PMC for the noisy speech recognition.

  • PDF

Fuzzy Variable Structure Control of Wheel-Driven Inverted Pendulum (바퀴구동 도립진자에 대한 퍼지 가변구조제어)

  • Yoo Byung-Kook
    • Journal of the Institute of Convergence Signal Processing
    • /
    • v.5 no.4
    • /
    • pp.301-307
    • /
    • 2004
  • This paper suggests a fuzzy variable structure control scheme for Takagi-Sugeno(T-S) fuzzy model and presents the attitude control of the wheel-driven inverted pendulum(WDIP) based on the proposed control algorithm. The proposed controller is designed based on the T-S fuzzy modeling of nonlinear system and the unification of gain matrices in linear subsystems that constitute the overall fuzzy model. The uncertainties generated in the gain matrix unifying procedure can be interpreted as the input disturbances of the conventional variable structure control. These unifying disturbances can be resolved by using the robustness property of the conventional variable structure system. Design example for wheel-driven inverted pendulum demonstrates the utility and validity of the proposed control scheme.

  • PDF

A Study on Computational Thinking based Test-Driven Problem Solving Learning Model (컴퓨팅 사고력 기반 테스트 중심 문제해결 학습 모형 연구)

  • Kim, Young-Jik;Kim, Seong-Sik
    • The Journal of Korean Association of Computer Education
    • /
    • v.22 no.6
    • /
    • pp.43-55
    • /
    • 2019
  • In the Fourth Industrial Revolution, a super-intelligent and super-connected society has arrived. Software is an important part of the core technologies of the Fourth Industrial Revolution. The ability to solve problems through software requires software education in that it is a core competency that everyone should have. Software education aims to improve Computational Thinking, which is the ability to solve problems through programming. Until now, most problem-solving programming learning models follow the traditional method of development: Waterfall model (Analysis-Design-Development-Test). In this model, if there is a problem in the preceding step, That could be found in the test phase. This takes a considerable amount of time and effort to find a solution to the problem and can be a burden on the programming learning. In this study, we proposed a Test-Driven Problem-Solving learning model using TDD (Test Driven Development) as Agile development method, and reviewed the appropriateness of the model through experts review. The verification results of the model showed positive evaluation results. In particular, the learning phase configuration of the model, helping in programming learning, helping of Computational Thinking improvement showed high rating, it is determined that there will be positive effects on Computational Thinking improvement through problem-solving programming learning when applying future learning.

Object-Oriented Graphical User Interface Model for Visualization of Ship Conceptual Design (객체지향 개념과 가시화 기법에 의한 선박 개념설계용 그래픽 사용자 인터페이스 모델)

  • Kyung-Ho Lee;Soon-Hung Han;Dong-Kon Lee;Kyu-Yeul Lee
    • Journal of the Society of Naval Architects of Korea
    • /
    • v.29 no.4
    • /
    • pp.27-35
    • /
    • 1992
  • By the help of computer graphics and rapid development of hardwares. GUI(Graphic User Interface) represented by WYSIWYG(What You See Is What You Get) changed user interface from liguistic model(e.g : command, etc.) to spatial model(e.g : pulldown menu, scroll bar, icon, itc.). This graphical user interface model for the ship conceptual design(MBASWIN) adopted event-driven programming technique and object-oriented concepts. Different from traditional design programs, MBASWIN is separate from the design program completely and controls all design modules. This enable a designer to accomplish a flexible designs.

  • PDF

Context Driven Component Model Supporting Scalability of Context (상황정보의 확장성을 지원하는 상황정보 기반 컴포넌트 모델)

  • Yoon, Hoi-Jin;Choi, Byoung-Ju
    • Journal of KIISE:Computing Practices and Letters
    • /
    • v.13 no.1
    • /
    • pp.24-34
    • /
    • 2007
  • Since Context Driven Component model is based on the idea that a context-aware application consists of the components that are context sensitive and the components that do not depend on the context, it divides the context sensitive part into components according to which context information they are related to. The model supports the scalability of context information by building an application through composing Context Driven Components. Furthermore, it solves the embeddedness of context information inside the application logic. To show the contributions of the model, this paper applies it to Call-forwarding application, and analyses how the model supports the scalability and the embeddedness.

Research on Event Mechanism for Reducing Power Overheads in Cache Memory Synchronization (캐시 메모리 동기화 전력 감소를 위한 이벤트 메커니즘에 대한 연구)

  • Pak, Young-Jin;Jeong, Ha-Young;Lee, Yong-Surk
    • Journal of the Institute of Electronics Engineers of Korea CI
    • /
    • v.48 no.3
    • /
    • pp.69-75
    • /
    • 2011
  • In this paper, we propose an anycast event driven synchronization mechanism to reduce power overheads. Our proposed mechanism can reduce unnecessary polling operations on SHI(Snoop Hit Invalidate) or SHR(Snoop Hit Read) states. It prevents waisting bandwidth and reduces power overheads on polling operation. Also it decreases transition power of state change compared to broadcast model. Simulation results indicated that the proposed architecture had about 15.3% of power decrease compared to spin-lock model and about 4.7% of power decrease compared to broadcast model. Overall results indicated that proposed synchronization mechanism could increase power efficiency of multi-core system by reducing power overheads.

Development of a tool for managing component model based on Model Driven Architecture (MDA기반 컴포넌트 설계정보 관리도구의 개발에 관한 연구)

  • Ahn, Yong-Soo;Hwang, Sang-Won;Nam, Young-Kwang;Lee, Byeong-Yun;Kwon, Oh-Cheon
    • Proceedings of the Korea Information Processing Society Conference
    • /
    • 2011.04a
    • /
    • pp.1371-1374
    • /
    • 2011
  • MDA(Model Driven Architecture)는 추상적인 모델 계층을 사용하기 때문에 다양한 플랫폼에 적용가능하고, 각 모델 계층과 코드 생성의 자동화를 통해 개발의 효율성을 극대화한다. 본 연구에서는 XML 형태로 저장된 설계정보를 분석하여 MDA 기반 컴포넌트 설계 정보를 관리하는 도구를 개발하였다. 이 도구는 UML로 작성된 설계모델를 XMI(XML Metadata Interchage) 형태로 저장하여 각종 설계도구에서 Java, C++과 같은 언어에 대한 실제 프로그램 골격코드가 자동으로 생성되도록 하였다. 역으로 골격코드를 기반으로 구현된 콤포넌트의 원시코드를 수집하여 다시 컴포넌트 설계모델 정보를 추출하는 기능을 구현하였고, 이를 다시 시각적 정보로 재구성 하였다. 이러한 기능들은 기존의 단방향적 개발 구조 방식에서 벗어나 이미 개발되거나 개발 중인 프로그램에 대한 분석 및 평가 등을 통해서 재사용성을 높여주는 순환적인 개발 구조 방식을 제공한다.