• 제어로봇시스템학회논문지
• /
• 제13권8호
• /
• pp.754-759
• /
• 2007

In this paper, we proposed the Bi-Modal Sensor Fusion Algorithm which is the emotional recognition method that be able to classify 4 emotions (Happy, Sad, Angry, Surprise) by using facial image and speech signal together. We extract the feature vectors from speech signal using acoustic feature without language feature and classify emotional pattern using Neural-Network. We also make the feature selection of mouth, eyes and eyebrows from facial image. and extracted feature vectors that apply to Principal Component Analysis(PCA) remakes low dimension feature vector. So we proposed method to fused into result value of emotion recognition by using facial image and speech.

• International Journal of Internet, Broadcasting and Communication
• /
• 제16권1호
• /
• pp.80-85
• /
• 2024

The concept of single-modal digital art originated in the 20th century and has evolved through three key stages. Over time, digital art has transformed into multi-modal interaction, representing a new era in art forms. Based on multi-modal theory, this paper aims to explore the characteristics of interactive digital art in innovative art forms and its impact on user experience. Through an analysis of practical application of multi-modal interactive digital art, this study summarises the impact of creative models of digital art on the physical and mental aspects of user experience. In creating audio-visual-based art, multi-modal digital art should seamlessly incorporate sensory elements and leverage computer image processing technology. Focusing on user perception, emotional expression, and cultural communication, it strives to establish an immersive environment with user experience at its core. Future research, particularly with emerging technologies like Artificial Intelligence(AR) and Virtual Reality(VR), should not merely prioritize technology but aim for meaningful interaction. Through multi-modal interaction, digital art is poised to continually innovate, offering new possibilities and expanding the realm of interactive digital art.

• 대한기계학회:학술대회논문집
• /
• 대한기계학회 2004년도 추계학술대회
• /
• pp.667-672
• /
• 2004

A modeling method for the modal analysis of cantilever plates undergoing in-plane translational acceleration is presented in this paper. Cartesian deformation variables are employed to derive the equations of motion and the resulting equations are transformed into dimensionless forms. To obtain the modal equation from the equations of motion, the in-plane equilibrium strain measures are substituted into the strain energy expression based on Von Karman strain measures. The effects of two dimensionless parameters (related to acceleration and aspect ratio) on the modal characteristics of accelerated plates are investigated through numerical studies.

• 대한기계학회논문집A
• /
• 제29권6호
• /
• pp.889-894
• /
• 2005

A modeling method for the modal analysis of cantilever plates undergoing in-plane translational acceleration is presented in this paper. Cartesian deformation variables are employed to derive the equations of motion and the resulting equations are transformed into dimensionless forms. To obtain the modal equation from the equations of motion, the in-plane equilibrium strain measures are substituted into the strain energy expression based on Von Karman strain measures. The effects of two dimensionless parameters (related to acceleration and aspect ratio) on the modal characteristics of accelerated plates are investigated through numerical studies.

• 한국소음진동공학회:학술대회논문집
• /
• 한국소음진동공학회 1996년도 추계학술대회논문집; 한국과학기술회관, 8 Nov. 1996
• /
• pp.217-223
• /
• 1996

A structure's vibration characteristic is determined by modal property of the system. Through proper vibration analysis or experiments, the structure can be modified to reduce of vibration and noise. This paper is concerned with the natural frequency and modal loss factor of sandwich plates with viscoelastic core. The effects of shear and normal strain in the viscoelastic layer are investigated on modal properties, natural frequency and modal loss factor, by changing geometry parameter and viscoelastic material property of sandwich plates. The errors of modal parameters resulting from neglecting the extension or compression in the core material for simply supported(S-S-S-S) case are compared with those for clamped(C-C-C-C) boundary condition. Finite difference method(FDM) is utilized as numerical analysis technique of square sandwich plates for fixed boundary conditions. In order to reduce computation time and increase accuracy, improved finite difference expression with fourth order truncation error was used.

• 한국정보과학회논문지:시스템및이론
• /
• 제26권12호
• /
• pp.1485-1492
• /
• 1999

대규모 시스템 명세의 올바름을 검증하기 위한 유한 상태 LTS에 기반을 둔 CTL논리 적용에 있어 가장 큰 문제점은, 시스템 내부의 병렬 프로세스간의 상호작용으로 인한 상태폭발이다. 그러나 Modal mu-calculus 논리를 시스템 안전성 및 필연성 특성 명세에 사용하면, 행위에 의한 순환적 정의가 가능하므로 상태폭발 문제가 해결 가능하다. 본 논문에서는 LTS로 명세화된 통신 프로토콜 시스템 모델의 안전성 및 필연성 특성을 모형 검사 기법에 의해 검증함에 있어, 시제 논리로 사용된 Modal mu-calculus 안전성 및 필연성 논리식과 CTL 의 안전성 및 필연성 논리식의 극한값이 동일함을 두 논리식을 만족하는 상태 집합이 같다는 것을 보임으로써 증명한다. 증명된 결과는 I/O FSM 모델로 표현된 통신 프로토콜의 안전성 및 필연성 검사를 위해 이론적인 기반으로서, 컴퓨터를 이용한 모형검사 기법에 효과적인 방법으로 응용이 가능하다.Abstract In applying CTL-based model checking approach to correctness verification of large state transition system specifications, the major obstacle is the combinational explosion of the state space arising due to interaction of many loosely coupled parallel processes. If, however, the modal mu-calculus viewed as a CTL-based logic with recursion, is used to specify the safety and liveness property of a given system, it is possible to resolve this problem. In this paper, we discuss the problem of verifying communication protocol system specified in LTS, and prove that a logic expression specifying safety and liveness in modal mu-calculus is semantically identical to the maximum value of the expression in CTL. This relation is verified by the proof that the sets of states satisfying the two logic expressions are equivalent. The proof can be used as a theoretical basis for verifying safety and liveness of communication protocols represented as I/O FSM model.

• Journal of Information Processing Systems
• /
• 제17권4호
• /
• pp.754-771
• /
• 2021

In the task of continuous dimension emotion recognition, the parts that highlight the emotional expression are not the same in each mode, and the influences of different modes on the emotional state is also different. Therefore, this paper studies the fusion of the two most important modes in emotional recognition (voice and visual expression), and proposes a two-mode dual-modal emotion recognition method combined with the attention mechanism of the improved AlexNet network. After a simple preprocessing of the audio signal and the video signal, respectively, the first step is to use the prior knowledge to realize the extraction of audio characteristics. Then, facial expression features are extracted by the improved AlexNet network. Finally, the multimodal attention mechanism is used to fuse facial expression features and audio features, and the improved loss function is used to optimize the modal missing problem, so as to improve the robustness of the model and the performance of emotion recognition. The experimental results show that the concordance coefficient of the proposed model in the two dimensions of arousal and valence (concordance correlation coefficient) were 0.729 and 0.718, respectively, which are superior to several comparative algorithms.

• The Journal of the Acoustical Society of Korea
• /
• 제19권1E호
• /
• pp.27-37
• /
• 2000

This paper presents a simplified analytical formulation for computing acoustic power radiation from a rectangular plate exposed to random forces such as turbulent boundary layer pressure fluctuations and arbitrary mechanical force in a subsonic flow field. The expression for the acoustic power is derived using modal expansion method and light fluid loading is assumed on the plate. In order to simplify the formulation for acoustic power due to combined excitations of mechanical forces and turbulent pressures, it is assumed that the structural damping of the plate is small and excitations are broadband random forces having frequency spectra above the convective coincidence. Under these assumptions, an approximate solution for the broadband acoustic power radiation from a plate excited by both turbulent pressures and arbitrary mechanical forces is obtained and evaluated considering the effect of modal coupling on the radiated acoustic power. An efficient method is also suggested to compute modal acoustic impedance in a moving fluid medium by using averaged Green function.

• 대한조선학회지
• /
• 제25권2호
• /
• pp.19-30
• /
• 1988

Sectional added masses of an elastic beam vibrating vertically on the free surface in higher harmonic modes are evaluated. Hydrodynamic interactions between neighboring sections, which strip theory ignores, are considered for modal wave lengths of the order of magnitude of cross-sectional dimensions of the body. An approximate solution of modified Helmholtz equation which becomes a singular perturbation problem at small wave lengths is secured to get an analytic expression for added masses attending higher harmonic modes. As a bound of the present theory, the modified Helmholtz equation is solved for the long flat plate vibrating at high frequency on the water surface without any limitations on modal frequency. Finally, extensive series of numerical calculations are carried out for ship-like forms. It is found that when modal wave length is comparable to or shorter than a typical cross-sectional dimension of a body, sectional interaction effects are large which result in considerable reductions in added masses. For a fuller section, the ratio of added mass reduction is greater. In the limit of vanishing sectional area, the added masses approach to that of flat plate of equal beam. It is shown that the added mass distribution for a Legendre modal from can be determined form the present theory and that the results agree with the extensive three-dimensional determination of Vorus and Hilarides.

• 인터넷정보학회논문지
• /
• 제13권5호
• /
• pp.9-19
• /
• 2012

디지털 콘텐츠에서 HCI로 활용되는 가상 인간은 얼굴 표정과 신체자세와 같은 모달을 이용하여 다양한 감정을 표현하지만 비언어적 다중모달의 조합에 대한 연구는 많지 않다. 감정을 표현하는 가상 인간을 제작하려면 계산 엔진 모델은 얼굴 표정과 신체자세와 같은 비언어적 모달의 조합이 사용자에 의해 어떻게 인식되는지를 고려해야 하기 때문에 본 연구는 가상 인간의 감정 표현 디자인에 필요한 비언어적 다중모달의 영향을 분석하여 제시한다. 먼저 가상 인간에 대한 다중모달 별 감정 인식을 평가하여 다른 모달간의 상대적 영향성을 분석하였다. 그리고 일치하는 얼굴과 자세 모달을 통해 기본 감정 및 정서가와 활성화 인식에 대한 영향을 평가하며 감정이 불일치하는 다중모달을 통해 일상생활에서 빈번하게 드러나는 중첩된 감정의 인식 정도를 관측하였다. 실험 결과, 가상 인간의 얼굴과 신체자세의 표정이 일치하면 감정 인식이 용이하며, 얼굴 표정으로 감정 카테고리를 판별하지만 감정의 활성화 차원 판단에는 자세 모달리티가 선호됨을 확인하였다. 본 연구 결과는 감정을 드러내는 가상 인간의 행동 동기화 및 애니메이션 엔진 시스템 구현에 활용할 수 있다.