• Journal of Power Electronics
• /
• 제16권2호
• /
• pp.760-768
• /
• 2016

Three-phase grid-connected inverters are widely applied in the fields of new energy power generation, electric vehicles and so on. Islanding detection is necessary to ensure the stability and safety of such systems. In this paper, feature recognition technology is applied and a novel islanding detection method is proposed. It can identify the features of inverter systems. The theoretical values of these features are defined as codebooks. The difference between the actual value of a feature and the codebook is defined as the quantizing distortion. When islanding happens, the sum of the quantizing distortions exceeds the threshold value. Thus, islanding can be detected. The non-detection zone can be avoided by choosing reasonable features. To accelerate the speed of detection and to avoid miscalculation, an active islanding detection method based on feature recognition technology is given. Compared to the active frequency or phase drift methods, the proposed active method can reduce the distortion of grid-current when the inverter works normally. The principles of the islanding detection method based on the feature recognition technology and the improved active method are both analyzed in detail. An 18 kVA DSP-based three-phase inverter with the SVPWM control strategy has been established and tested. Simulation and experimental results verify the theoretical analysis.

• 한국HCI학회:학술대회논문집
• /
• 한국HCI학회 2007년도 학술대회 1부
• /
• pp.667-674
• /
• 2007

Facial expressions provide significant clues about one's emotional state; however, it always has been a great challenge for machine to recognize facial expressions effectively and reliably. In this paper, we report a method of feature-based adaptive motion energy analysis for recognizing facial expression. Our method optimizes the information gain heuristics of ID3 tree and introduces new approaches on (1) facial feature representation, (2) facial feature extraction, and (3) facial feature classification. We use minimal reasonable facial features, suggested by the information gain heuristics of ID3 tree, to represent the geometric face model. For the feature extraction, our method proceeds as follows. Features are first detected and then carefully "selected." Feature "selection" is finding the features with high variability for differentiating features with high variability from the ones with low variability, to effectively estimate the feature's motion pattern. For each facial feature, motion analysis is performed adaptively. That is, each facial feature's motion pattern (from the neutral face to the expressed face) is estimated based on its variability. After the feature extraction is done, the facial expression is classified using the ID3 tree (which is built from the 1728 possible facial expressions) and the test images from the JAFFE database. The proposed method excels and overcomes the problems aroused by previous methods. First of all, it is simple but effective. Our method effectively and reliably estimates the expressive facial features by differentiating features with high variability from the ones with low variability. Second, it is fast by avoiding complicated or time-consuming computations. Rather, it exploits few selected expressive features' motion energy values (acquired from intensity-based threshold). Lastly, our method gives reliable recognition rates with overall recognition rate of 77%. The effectiveness of the proposed method will be demonstrated from the experimental results.

• 전력전자학회논문지
• /
• 제27권4호
• /
• pp.332-338
• /
• 2022

This study proposes a battery state-of-health estimation method by applying a feature extraction technique. The technique that can improve estimation performance is the process of identifying and extracting meaningful data. To apply a data-driven-based aging state estimation method to batteries, health indicators are used as training data. However, limitations occur in extracting health indicators from charge/discharge cycles. This study proposes a deep-learning-based battery state-of-health estimation method that applies feature extraction techniques to compensate for this problem. According to the performance evaluation result of the proposed method, it has a low estimation error of 0.3887% based on an absolute error evaluation method.

• 한국공작기계학회:학술대회논문집
• /
• 한국공작기계학회 1999년도 추계학술대회 논문집 - 한국공작기계학회
• /
• pp.544-548
• /
• 1999

This study is about development of Feature-based Solid Modeling system in integrated CAD/CAM environment. Parasolid modeling kernel and HOOPS/3D graphics library was used to develop this system in PC level. System feature library was defined using both procedural and declarative approach method. The raw stock is created by boolean operator using design primitives, and a part is designed that pre-defined feature is removed from the raw stock. This method is called "DSG(Destructive Solid Geometry)" and basic constructive operator of this system. This is not complete system and only the first step to develop Feature-based Solid Modeling System using Parasolid. We will add more powerful functionality and flexible GUI in Windows.n Windows.

• 한국인터넷방송통신학회논문지
• /
• 제13권6호
• /
• pp.63-69
• /
• 2013

특징 기반 영상 인식 방법은 객체의 특징을 이용하므로 템플릿 정합에 비해 고속으로 수행될 수 있다. 불변 특징 기반의 파노라마 생성은 영상 인식의 한 응용으로서, 두 영상 간의 특징점 정합에 많은 처리 시간이 필요하다. 본 논문에서는 특징 강도 정보를 이용하여 특징점 정합 속도를 향상시키는 방법을 제안한다. SURF 알고리즘으로 특징점들을 추출한 후, 특징 강도 정보를 계산하여 강한 특징점들을 선택하여 특징 정합에 사용한다. 특징 강도가 강한 특징점들은 그렇지 않은 특징점들 보다 더 의미 있다고 볼 수 있다. 실험에서 $320{\times}240$ 크기의 칼라 영상에 대해 제안한 방법은 특징 강도 정보를 사용하지 않았을 때보다 40% 이상 처리 속도의 향상을 보였다.

• 방송공학회논문지
• /
• 제4권2호
• /
• pp.187-196
• /
• 1999

본 논문에서는 내용 기반 동영상 검색을 위하여 컬러 정보 및 모션 정보를 사용하는 효율적인 자동 특징 추출 알고리즘을 제안하고, 이를 동영상 검색 시스템에 적용한다. 컬러 정보의 경우 기존의 key-frame단위의 컬러 특징 추출의 한계를 극복하고, 동영상의 컬러 히스토그램 정보와 컬러의 공간분포 정보를 반영할 수 있는 컬러 특징 추출 알고리즘을 제안한다. 또한 MPEG-1 동영상 내의 모션 벡터와 컬러 정보를 조합한 컬러-모션 특징을 추출하여, 기존의 위치 기반 특징 추출 알고리즘의 한계를 극복하였다. 최종적으로 추출된 특징을 이용한 검색 시스템을 구현하여, 제안된 알고리즘의 성능을 평가하였다.

• 융합신호처리학회논문지
• /
• 제15권2호
• /
• pp.37-41
• /
• 2014

The vector Taylor series (VTS) based method usually employs clean speech Hidden Markov Models (HMMs) when compensating speech feature vectors or adapting the parameters of trained HMMs. It is well-known that noisy speech HMMs trained by the Multi-condition TRaining (MTR) and the Multi-Model-based Speech Recognition framework (MMSR) method perform better than the clean speech HMM in noisy speech recognition. In this paper, we propose a method to use the noise-adapted HMMs in the VTS-based speech feature compensation method. We derived a novel mathematical relation between the train and the test noisy speech feature vector in the log-spectrum domain and the VTS is used to estimate the statistics of the test noisy speech. An iterative EM algorithm is used to estimate train noisy speech from the test noisy speech along with noise parameters. The proposed method was applied to the noise-adapted HMMs trained by the MTR and MMSR and could reduce the relative word error rate significantly in the noisy speech recognition experiments on the Aurora 2 database.

• 한국CDE학회논문집
• /
• 제2권3호
• /
• pp.142-149
• /
• 1997

This study is intended to develop a Feature based modeler. It is difficult to integrate CAD and CAM/CAPP with information that is given only by a conventional CAD system. Therefore a lot of studies have concentrated on a Feature based CAD system. But conventional Feature based modelers have had limitation on providing sufficient information related to Feature interaction. If a Feature based modeler is to be used in assembly simulation, a new Feature-based modeling method needs to be developed. Also to support collision detection between parts, we have to handle Feature interaction systematically. Therefore we suggest Cell data structure which handles interaction of Features by volume. The volume created by Feature interaction is saved as a Cell. With the Cell structure we solve problems involved with Feature interaction. This study shows how the Cell data structure can manage Feature interaction and give enough information in assembly simulation.

• 대한원격탐사학회:학술대회논문집
• /
• 대한원격탐사학회 2003년도 Proceedings of ACRS 2003 ISRS
• /
• pp.1111-1113
• /
• 2003

In this paper, we investigated a method for feature - based classification to develop software which is suitable to the classification of high resolution satellite imagery . So, we developed related algorithm and designed user interfaces of convenience, considering various elements require for the feature - based classification. The software was tested with eCognition software which is unique commercial software for feature - based classification.

• 한국방송∙미디어공학회:학술대회논문집
• /
• 한국방송공학회 2009년도 IWAIT
• /
• pp.418-422
• /
• 2009

Generally, algorithms for generating disparity maps can be clssified into two categories: region-based method and feature-based method. The main focus of this research is to generate a disparity map with an accuracy depth information for 3-dimensional reconstructing. Basically, the region-based method and the feature-based method are simultaneously included in the proposed algorithm, so that the existing problems including false matching and occlusion can be effectively solved. As a region-based method, regions of false matching are extracted by the proposed MMAD(Modified Mean of Absolute Differences) algorithm which is a modification of the existing MAD(Mean of Absolute Differences) algorithm. As a feature-based method, the proposed method eliminates false matching errors by calculating the vector with SIFT and compensates the occluded regions by using a pair of adjacent SIFT matching points, so that the errors are reduced and the disparity map becomes more accurate.