• 한국정보과학회논문지:소프트웨어및응용
• /
• 제34권11호
• /
• pp.991-1000
• /
• 2007

본 논문에서는 단일 프레임의 교통 영상에서 차량을 검출하는 새로운 기법을 제안한다. 제안하는 기법은 동작 환경에 관계없이 여러 형태로 분류된 그림자를 추출한다. 차량의 색상과 조명 조건에 관계없이 차량이 도로와 접한 부분에는 어두운 그림자 형상을 가진다는 사실을 이용하여 그림자 분류를 수행한다. 추출된 그림자는 차량의 존재 유무를 판단할 강력한 능력을 가지고 있으며, 배경 영상과 다른 시간적 정보들을 이용하지 않으므로, 기상 및 교통 정체가 빠르게 변화하는 상황에서도 높은 검출 성능을 보장한다. 차량 위치에 존재하는 자은 정보와 그림자 영역과의 간단한 증거 추론 기법에 의해 차량을 검출할 수 있다. 6개의 다른 동작 환경의 실험에서 4% 이하의 오검출율을 보이고, 0.9%에서 7.2%의 미검출율을 보였다. 또한, 작은 크기의 영상에 대해 초당 70 프레임 이상의 처리가 가능하므로, 다양한 교통 정보를 실시간으로 측정하는 기법에 사용될 수 있다.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2022년도 추계학술발표대회
• /
• pp.478-480
• /
• 2022

This paper studies human activity image classification using deep transfer learning techniques focused on the inception convolutional neural networks (InceptionV3) model. For this, we used UFC-101 public datasets containing a group of students' behaviors in mathematics classrooms at a school in Thailand. The video dataset contains Play Sitar, Tai Chi, Walking with Dog, and Student Study (our dataset) classes. The experiment was conducted in three phases. First, it extracts an image frame from the video, and a tag is labeled on the frame. Second, it loads the dataset into the inception V3 with transfer learning for image classification of four classes. Lastly, we evaluate the model's accuracy using precision, recall, F1-Score, and confusion matrix. The outcomes of the classifications for the public and our dataset are 1) Play Sitar (precision = 1.0, recall = 1.0, F1 = 1.0), 2), Tai Chi (precision = 1.0, recall = 1.0, F1 = 1.0), 3) Walking with Dog (precision = 1.0, recall = 1.0, F1 = 1.0), and 4) Student Study (precision = 1.0, recall = 1.0, F1 = 1.0), respectively. The results show that the overall accuracy of the classification rate is 100% which states the model is more powerful for learning UCF-101 and our dataset with higher accuracy.

• The Journal of the Acoustical Society of Korea
• /
• 제24권4E호
• /
• pp.144-151
• /
• 2005

We evaluate the performance of emotion recognition via speech signals when a plain speaker talks to an entertainment robot. For each frame of a speech utterance, we extract the frame-based features: pitch, energy, formant, band energies, mel frequency cepstral coefficients (MFCCs), and velocity/acceleration of pitch and MFCCs. For discriminative classifiers, a fixed-length utterance-based feature vector is computed from the statistics of the frame-based features. Using a speaker-independent database, we evaluate the performance of two promising classifiers: support vector machine (SVM) and hidden Markov model (HMM). For angry/bored/happy/neutral/sad emotion classification, the SVM and HMM classifiers yield $42.3\%\;and\;40.8\%$ accuracy, respectively. We show that the accuracy is significant compared to the performance by foreign human listeners.

• 대한전기학회논문지
• /
• 제41권4호
• /
• pp.433-441
• /
• 1992

This paper describes an algorithm that can efficiently analyze the ECG signal using frame knowledge representation technique. Input to the analysis process is a set of significant points which have been extracted from an original sampled signal(lead II) by the syntactic peak recognition algorithm. The hierarchical property of ECG signal is represented by hierarchical AND/OR graph. The semantic information and constraints of the ECG signal are desctibed by frame. As the control mechanism for labeling points, the search mechanism with the mixed paradigms of data-driven and model driven hypothesis formation, scoring function, hypothesis modification network and instance inheritance are used. We used the CSE database in order to evaluate the performance of the proposed algorithm.

• 대한기계학회:학술대회논문집
• /
• 대한기계학회 2000년도 추계학술대회논문집A
• /
• pp.766-771
• /
• 2000

As using of insulating material of plastic to industrial electric field, thermoset has been gradually substituted for thermoplastic. But changing the material with crystalline has some problem, which is strength or warpage, Especially getting a strength to endure inner pressure is necessary when arc is occurred. So we use the material that is composed of glass fiber to compensate strength. By the way as the reinforced glass-fiber material is used in injection molding, unstableness of dimension is appeared frequently and it is difficult to know warpage pattern. So this paper will be contributed to know warpage pattern of mold product that is upper frame of magnetic contactor caused by glass-fiber orientation with fixed gate-system, when glass-fiber reinforced material with classification of poly-amide is used in injection molding.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 1988년도 전기.전자공학 학술대회 논문집
• /
• pp.624-627
• /
• 1988

This paper describes the implementation of recognition of speaker - dependent Korean spoken continuous digits. The recognition system can be divided into two parts, acoustic - phonetic processor and lexical decoder. Acoustic - phonetic processor calculates the feature vectors from input speech signal and the performs frame labelling and phone labelling. Frame labelling is performed by Bayesian classification method and phone labelling is performed using labelled frame and posteriori probability. The lexical decoder accepts segments (phones) from acoustic - phonetic processor and decodes its lexical structure through phone network which is constructed from phonetic representation of ten digits. The experiment carried out with two sets of 4continuous digits, each set is composed of 35 patterns. An evaluation of the system yielded a pattern accuracy of about 80 percent resulting from a word accuracy of about 95 percent.

• 농촌계획
• /
• 제13권1호
• /
• pp.41-50
• /
• 2007

Recently, it is demanded to study about landscape. Landscape is an environment factor for improving life, a social resource for establishing image and identity of the area and also a tourist resource for earning profit. With this importance, landscape planning is being performed by local governments. However, classification for a rule about landscape planning is not prepared yet. For this purpose, classification of landscape is definitely required. Therefore, this article focuses on presenting method of classification Natural and Rural Landscape. We used Arcview 3.2 to draw watershed of the site, and calculated the percent of landform. We also took a picture which explain the landscape and made a survey of classifying the landscape. Due to this study, we were able to frame an algorithm of the landscape classification. This will contribute to classify the landscape type. This study needs more specific researches because it was supposed to target the entire Gyeonggi-Do however it only covered several regions. Through this results, it would be expected to develop the map of landscape character.

• 대한수학회보
• /
• 제59권1호
• /
• pp.227-239
• /
• 2022

In this paper, we consider Legendre trajectories of trans-S-manifolds. We obtain curvature characterizations of these curves and give a classification theorem. We also investigate Legendre curves whose Frenet frame fields are linearly dependent with certain combination of characteristic vector fields of the trans-S-manifold.

• 한국전자통신학회논문지
• /
• 제8권4호
• /
• pp.555-560
• /
• 2013

본 논문에서는 거리측정, 로그전력, 실효치 방법에 의하여 유성음, 무성음, 묵음 구간을 검출하여, 서브밴드 필터에 의한 잡음제거 알고리즘을 제안한다. 제안한 알고리즘은 각 프레임에서 서브밴드 필터를 사용하여 잡음으로 오염된 음성신호로부터 백색잡음 및 도로잡음의 스펙트럼을 차감하는 방법이다. 본 실험에서는 Aurora-2 데이터베이스에 포함된 음성신호와 잡음신호를 사용하여 스펙트럼 차감 알고리즘의 결과를 나타낸다. 잡음에 의하여 오염된 음성신호에 대하여 신호대잡음비를 사용하여 본 알고리즘이 유효하다는 것을 확인한다. 실험으로부터 백색잡음에 대하여 평균 2.1 dB, 도로잡음에 대하여 평균 1.91 dB의 출력 신호대잡음비가 개선된 것을 확인할 수 있었다.

• 한국산업융합학회 논문집
• /
• 제24권1호
• /
• pp.31-43
• /
• 2021

In this study, approximate design optimization using various meta-models was performed for the structural design of active type deck support frame. The active type deck support frame was newly developed to facilitate both transportation and installation of 20,000 ton class offshore plant topside. Structural analysis was carried out using the finite element method to evaluate the strength performance of the active type deck support frame in its initial design stage. In the structural analysis, the strength performances were evaluated for various design load conditions that were regulated in ship classification organization. The approximate optimum design problem based on meta-model was formulated such that thickness sizing variables of main structure members were determined by achieving the minimum weight of the active type deck support frame subject to the strength performance constraints. The meta-models used in the approximate design optimization were response surface method, Kriging model, and Chebyshev orthogonal polynomials. The results from approximate design optimization were compared to actual non-approximate design optimization. The Chebyshev orthogonal polynomials among the meta-models used in the approximate design optimization represented the most pertinent optimum design results for the structure design of the active type deck support frame.