• International Journal of Computer Science & Network Security
• /
• 제23권9호
• /
• pp.47-54
• /
• 2023

For Bengali music emotion classification, deep learning models, particularly CNN and RNN are frequently used. But previous researches had the flaws of low accuracy and overfitting problem. In this research, attention-based Conv1D and BiGRU model is designed for music emotion classification and comparative experimentation shows that the proposed model is classifying emotions more accurate. We have proposed a Conv1D and Bi-GRU with the attention-based model for emotion classification of our Bengali music dataset. The model integrates attention-based. Wav preprocessing makes use of MFCCs. To reduce the dimensionality of the feature space, contextual features were extracted from two Conv1D layers. In order to solve the overfitting problems, dropouts are utilized. Two bidirectional GRUs networks are used to update previous and future emotion representation of the output from the Conv1D layers. Two BiGRU layers are conntected to an attention mechanism to give various MFCC feature vectors more attention. Moreover, the attention mechanism has increased the accuracy of the proposed classification model. The vector is finally classified into four emotion classes: Angry, Happy, Relax, Sad; using a dense, fully connected layer with softmax activation. The proposed Conv1D+BiGRU+Attention model is efficient at classifying emotions in the Bengali music dataset than baseline methods. For our Bengali music dataset, the performance of our proposed model is 95%.

• 한국터널지하공간학회 논문집
• /
• 제3권4호
• /
• pp.35-55
• /
• 2001

최근 터널 구조물이 점차 노후화됨에 따라 터널의 안전성을 평가하기 위한 점검 및 진단이 많이 수행되고 있다. 그러나 터널구조물의 상태 및 안전성 평가에 대한 명확한 기준이 없어 조사자의 주관적인 판단에 의존할 수 밖에 없는 실정으로 이에 대한 체계적인 기준정립이 요구되고 있다. 또한 기존방법은 터널라이닝에 대한 평가에 많은 비중을 주고 있어 지반구조물로서의 터널특성을 제대로 반영하지 못하고 있으며, 상태평가요소과 터널등급산정과정이 체계적이지 못하여 이에 대한 보완이 필요하다 할 수 있다. 따라서 본 연구에서는 터널 상태 및 안전성 평가방법의 문제점을 개선하기 위한 새로운 터널구조물상태평가기준을 제시하였다. 본 기준은 국내외의 터널기준을 분석하여 상태평가요소를 선정하고 이를 점수화하였으며, 대표등급산정방법을 정량화하므로서 터널상태를 객관적으로 평가할 수 있도록 하였다. 본 기준과 방법은 터널구조물에 대한 상태평가에 객관성과 신뢰성을 확보하여 보다 효율적인 안전점검 및 진단업무에 활용될 수 있다.

• 한국화재소방학회논문지
• /
• 제15권4호
• /
• pp.64-70
• /
• 2001

지하공간 중 지하가의 사고 ,사례와 문헌 연구 및 실태를 조사, 검토하고, 운영, 관리 단계에서 위험요인을 추출하여 화재 폭발 안전대책의 평가요소 및 위험성 평가수법을 제시하고자 한다. 또한, 지하가의 대규모화, 심층화, 복합화에 대한특성 항목을 분류하고 7가지 대책의 중요도를 제시하여 지하가 계획단계의 지표로 삼고자 한다.

• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 2003년도 ISIS 2003
• /
• pp.632-635
• /
• 2003

This paper describes a system fur tracking multiple faces in an input video sequence using facial convex hull based facial segmentation and robust hausdorff distance. The algorithm adapts skin color reference map in YCbCr color space and hair color reference map in RGB color space for classifying face region. Then, we obtain an initial face model with preprocessing and convex hull. For tracking, this algorithm computes displacement of the point set between frames using a robust hausdorff distance and the best possible displacement is selected. Finally, the initial face model is updated using the displacement. We provide an example to illustrate the proposed tracking algorithm, which efficiently tracks rotating and zooming faces as well as existing multiple faces in video sequences obtained from CCD camera.

• 한국생물정보학회:학술대회논문집
• /
• 한국생물정보시스템생물학회 2005년도 BIOINFO 2005
• /
• pp.191-196
• /
• 2005

Genetic networks are a key to unraveling dynamic properties of biological processes and regulation of genes plays an essential role in dynamic behavior of the genetic networks. A popular characterization of regulation of the gene is a kinetic model. However, many kinetic parameters in the genetic regulation have not been available. To overcome this difficulty, in this report, state-space approach to modeling gene regulation is presented. Second-order systems are used to characterize gene regulation. Interpretation of coefficients in the second order systems as resistance, capacitance and inductance is studied. The mathematical methods for transient response analysis of gene regulation to external perturbation are investigated. Criterion for classifying gene into three categories: underdamped, overdamped and critical damped is discussed. The proposed models are applied to yeast cell cycle gene expression data.

• 한국의류학회지
• /
• 제19권2호
• /
• pp.366-379
• /
• 1995

This study was performed to provide fundamental data on middle-aged women's upper torso by classifying the upper torso somatotype and analyzing the characteristics of their somatotype. Factor analysis of principal component model was used to 38 directly measured items, and cluster analysis was applied for classification of upper torso forms. Seven factors were extracted from the factor analysis. The first factor represented the items of circumference, breadth, and depth which were related with body size. On the basis of the cluster analysis using factor scores trom factor analysis as being independent variables, the subjects were classified into three groups. Three dress forms were constructed according to the characteristics for each somatotype of subjects, the three-dimensional characteristics of somatotype were analyzied by the moire pattern and horizontal section map of proposed dress forms. Wearing test by moire topography was used to evaluate wearing outline, the ease of clothes and garment space. Moire pattern and horizontal section map were useful to evaluate wearing conditions, and garment space was changed by the characteristics of the body shape.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• 제3권1호
• /
• pp.87-92
• /
• 2003

This paper describes a system for tracking multiple faces in an input video sequence using facial convex hull based facial segmentation and robust hausdorff distance. The algorithm adapts skin color reference map in YCbCr color space and hair color reference map in RGB color space for classifying face region. Then, we obtain an initial face model with preprocessing and convex hull. For tracking, this algorithm computes displacement of the point set between frames using a robust hausdorff distance and the best possible displacement is selected. Finally, the initial face model is updated using the displacement. We provide an example to illustrate the proposed tracking algorithm, which efficiently tracks rotating and zooming faces as well as existing multiple faces in video sequences obtained from CCD camera.

• 한국농촌건축학회논문집
• /
• 제8권2호
• /
• pp.27-35
• /
• 2006

The park in city, is more than just ecological function, contributes emotional refinement and psychological stability to citizens, and give satisfaction of social and recreational activities to the citizens. And it is the place of leisure and the place to raise up the quality of urban environment. Especially, the neighborhood park among urban parks occupies the most important position as a leisure space for local resident, but it can not perform its purpose and function as a leisure space, due to its too formal and insufficient facilities. This study, approaching from point of physical method, intends to make types through classifying each parks by built-type and installed facilities which affect human-beings, approaching from point of human-beings, intends to make the using-type analysis of park-users, and the questionnaire.By grasping of their requirements regarding to the characters and facilities what they want, willing to present the fundamental data for effective utility-activating method of small-scaled neighborhood park.

• Journal of information and communication convergence engineering
• /
• 제22권1호
• /
• pp.70-79
• /
• 2024

Bad weather conditions such as haze lead to a significant lack of visibility in images, which can affect the functioning and reliability of image processing systems. Accordingly, various single-image dehazing (SID) methods have recently been proposed. Existing SID methods have introduced effective visibility improvement algorithms, but they do not reflect the image's perspective, and thus have limitations that distort the sky area and nearby objects. This study proposes a new SID method that reflects the sense of space by defining the correlation between image brightness and haze. The proposed method defines the haze intensity by calculating the airlight brightness deviation and sets the weight factor of the depth map by classifying images based on the defined haze intensity into images with a large sense of space, images with high intensity, and general images. Consequently, it emphasizes the contrast of nearby images where haze is present and naturally smooths the sky region to preserve the image's perspective.

• 대한전자공학회논문지SP
• /
• 제47권6호
• /
• pp.82-90
• /
• 2010

본 논문에서는 2차원 이미지로 부터 3차원 정보를 획득하기 위한 신뢰도 공간(reliability space)에 기반 한 스테레오 정합기법을 제안한다. 일반적으로 기존의 기법들은 정확도가 높은 경우 연산 량이 많아 속도가 느려지는 문제를 안고 있다. 따라서 논문에서는 정확도는 유지하면서 속도를 높이는 기법을 구현하고자 다음과 같은 방법을 제안하였다. 먼저 스테레오 영상에서 모든 화소를 비교하기 위해 변이 공간 영상(disparity space image)을 생성하고 이 값의 분석을 통해 신뢰도 공간을 생성한다. 이어서 변이에 따른 신뢰도 공간의 비교를 통해서 변이 지도를 작성하였다. 또한 보조적으로 컬러 에지를 참조하여 각 영역의 경계를 확실히 분류함을 통해서 국부적으로 발생하는 영역 경계 오류를 일정 부분 개선하였다. 제안된 스테레오 정합 기법은 다양한 실험을 통하여 기존의 기법과 비교함으로써 그 성능을 입증하였다. 그 결과 제안된 기법의 연산 비용이 약 31.6%가량 개선됨을 확인할 수 있었다. 또한 연산 비용 감소에도 불구하고 영상의 품질에 있어서 기존과 대등한 성능을 나타내는 것을 확인할 수 있었다.