• Smart Structures and Systems
• /
• 제26권1호
• /
• pp.23-33
• /
• 2020

Majority of the damage in engineering structures is nonlinear. Damage sensitive features (DSFs) extracted by traditional methods from linear time series models cannot effectively handle nonlinearity induced by structural damage. A new DSF is proposed based on vector space cosine similarity (VSCS), which combines K-means cluster analysis and Bayesian discrimination to detect nonlinear structural damage. A reference autoregressive moving average (ARMA) model is built based on measured acceleration data. This study first considers an existing DSF, residual standard deviation (RSD). The DSF is further advanced using the VSCS, and then the advanced VSCS is classified using K-means cluster analysis and Bayes discriminant analysis, respectively. The performance of the proposed approach is then verified using experimental data from a three-story shear building structure, and compared with the results of existing RSD. It is demonstrated that combining the linear ARMA model and the advanced VSCS, with cluster analysis and Bayes discriminant analysis, respectively, is an effective approach for detection of nonlinear damage. This approach improves the reliability and accuracy of the nonlinear damage detection using the linear model and significantly reduces the computational cost. The results indicate that the proposed approach is potential to be a promising damage detection technique.

• 전기학회논문지
• /
• 제64권1호
• /
• pp.82-89
• /
• 2015

The researches of image recognition have been processed traditionally. Especially, face recognition technology has been received attractions with advance and applied to various areas according as camera sensor embedded into many devices such as smart phone. In this study, we design and develop a feature vector generation technique of face for making animation caricatures using methods for face detection which are previous stage of face recognition. At first, we detect both face region and detailed eye region of component element by Viola&Johns's realtime detection method which are called as ROI(Region Of Interest). And then, we generate feature vectors of eye region by utilizing factors as opposed to the periphery and by using appearance information of eye. At this point, we focus on the embedded information in many color spaces to overcome the problems which can be occurred by using one color space. We propose a feature vector generation method using information from many color spaces. Finally, we experiment the test of feature vector generation by the proposed method with enough quantity of sample picture data and evaluate the proposed method for factors of estimating performance such as error rate, accuracy and generation time.

• 한국지능시스템학회논문지
• /
• 제13권3호
• /
• pp.266-274
• /
• 2003

본 논문은 비정상 상태 탐지 문제를 위한 점증적 서포트 벡터 학습을 다룬다. 비정상상태 탐지를 위한 서포트 벡터 학습 중 가장 잘 알려진 기법 중 하나는 SVDD(support vector data description)인데, 이 기법은 정상적인 데이터의 집합을 모든 가능한 비정상 개체로부터 구분하기 위하여 커널 특징공간(kernel feature space) 위에서 정의되는 볼(ball)을 이용하는 전략을 추구한다. 본 논문의 주된 관심사는 최적해와 점증적으로 주어지는 학습 데이터의 상관관계를 이용하는 방향으로 SVDD 기법을 수정하는 것이다. 본 논문에서는, 기존의 SVDD 기법을 상세히 복습한 후에, 라그랑제 쌍대 문제(Largrange dual problem)에 관한 관찰을 바탕으로 최적 해를 찾기 위한 점증적 풀이 기법을 제시한다. 그리고, 제시된 점증적 방법론의 적용 가능성이 예제를 통하여 보여진다.

• 한국통신학회논문지
• /
• 제26권11A호
• /
• pp.1946-1956
• /
• 2001

본 논문에서는 관계 벡터 공간상의 특징 대응에 관한 확률적 해석에 기반한 새로운 부분 인식 기법을 제안한다. 효과적인 인식을 위해 물체를 관계 속성 그래프(Attributed Relational Graph; ARG)와 관계 벡터 공간들의 집합으로 표현한다. 또한 잡음이나 특징 소실로 인한 왜곡을 관계 벡터 공간에서의 관계 벡터 분포에 대한 왜곡으로 확률적으로 모델링한다. 제안하는 부분 인식 기법은 두 단계로 이루어진다. 우선 지역적인 특징(local feature)과 구조적인 일관성(structural consistency)을 사용하여 후보집합을 추출한다. 이렇게 추출된 후보집합 각각에 대해 관계 벡터 공간상에서의 에러 분석과 반복적인 voting 알고리즘을 통해 특징 소실을 검출한다. 실제 영상에 대한 실험 결과를 통해 제안한 알고리즘이 잡음이나 가리어짐이 심한 경우에도 강건한 성능을 보임을 알 수 있으며, 릴렉세이션(relaxation) 기법과 수행 시간 비교 분석을 통해 계산량 측면에서의 성능 향상을 확인할 수 있다.

• Journal of Multimedia Information System
• /
• 제1권1호
• /
• pp.77-85
• /
• 2014

Usually, the skin pigmentation detection and diagnosis are made by clinicians. In this process it is subjective and non-quantitative. We develop an approach to detect and measure the different pigmentation lesions base on computer vision technology. In the paper we study several usually used skin-detecting color space like HSV, YCbCr and normalized RGB. We compare their performance with illumination influence for detecting the pigmentation lesions better. Base on a relatively stable color space, we propose an approach which is RGB channels vector difference characteristic for the detection. After the object region detection, we also use the difference to measure the difference between the lesion and the surrounding normal skin. From the experiment results, our approach can effectively detect the pigmentation lesion, and perform robustness with different illumination.

• Journal of Information Processing Systems
• /
• 제10권4호
• /
• pp.589-601
• /
• 2014

The performance of edge detection often relies on its ability to correctly determine the dissimilarities of connected pixels. For grayscale images, the dissimilarity of two pixels is estimated by a scalar difference of their intensities and for color images, this is done by using the vector difference (color distance) of the three-color components. The Euclidean distance in the RGB color space typically measures a color distance. However, the RGB space is not suitable for edge detection since its color components do not coincide with the information human perception uses to separate objects from backgrounds. In this paper, we propose a novel method for color edge detection by taking advantage of the HSV color space and the Mahalanobis distance. The HSV space models colors in a manner similar to human perception. The Mahalanobis distance independently considers the hue, saturation, and lightness and gives them different degrees of contribution for the measurement of color distances. Therefore, our method is robust against the change of lightness as compared to previous approaches. Furthermore, we will introduce a noise-resistant technique for determining image gradients. Various experiments on simulated and real-world images show that our approach outperforms several existing methods, especially when the images vary in lightness or are corrupted by noise.

• 대한임베디드공학회논문지
• /
• 제7권4호
• /
• pp.163-172
• /
• 2012

A driver assistance system is critical to improve a convenience and stability of vehicle driving. Several systems have been already commercialized such as adaptive cruise control system and forward collision warning system. Efficient vehicle detection is very important to improve such driver assistance systems. Most existing vehicle detection systems are based on a radar system, which measures distance between a host and leading (or oncoming) vehicles under various weather conditions. However, it requires high deployment cost and complexity overload when there are many vehicles. A camera based vehicle detection technique is also good alternative method because of low cost and simple implementation. In general, night time vehicle detection is more complicated than day time vehicle detection, because it is much more difficult to distinguish the vehicle's features such as outline and color under the dim environment. This paper proposes a method to detect vehicles at night time using analysis of a captured color space with reduction of reflection and other light sources in images. Four colors spaces, namely RGB, YCbCr, normalized RGB and Ruta-RGB, are compared each other and evaluated. A suboptimal threshold value is determined by Otsu algorithm and applied to extract candidates of taillights of leading vehicles. Statistical features such as mean, variance, skewness, kurtosis, and entropy are extracted from the candidate regions and used as feature vector for SVM(Support Vector Machine) classifier. According to our simulation results, the proposed statistical feature based SVM provides relatively high performances of leading vehicle detection with various distances in variable nighttime environments.

• 전기학회논문지
• /
• 제60권8호
• /
• pp.1515-1522
• /
• 2011

This paper proposes the algorithm for the output AC voltage control of Z-source inverter by the detection of the input DC voltage and Z-network capacitor voltage. The actual modulation index of the proposed method is detected by the capacitor voltage in Z-network and input DC voltage of three-phase Z-source inverter. Control modulation index for the output voltage control is calculated by the detected actual modulation index and reference modulation index. And, calculated control modulation index is applied to the modified space vector modulation (SVM) for control the output voltage of Z-source inverter. To verify the validity of the proposed method, PSIM simulation was achieved and a DSP controlled 1[kW] three-phase Z-source inverter was producted. The simulation and experiment were performed under the condition that the load was changed in case of the constant input DC voltage and the input DC voltage was changed in case of the load was constant. As a result, we could know that the output phase voltage of Z-source inverter followed to the reference voltage 70[VRMS] despite the load or the input DC voltage were suddenly changed.

• International Journal of Computer Science & Network Security
• /
• 제22권8호
• /
• pp.242-248
• /
• 2022

The article presents the analysis of modern methods of automatic comparison of original and unoriginal text to detect textual plagiarism. The study covers two types of plagiarism - literal, when plagiarists directly make exact copying of the text without changing anything, and intelligent, using more sophisticated techniques, which are harder to detect due to the text manipulation, like words and signs replacement. Standard techniques related to extrinsic detection are string-based, vector space and semantic-based. The first, most common and most successful target models for detecting literal plagiarism - N-gram and Vector Space are analyzed, and their advantages and disadvantages are evaluated. The most effective target models that allow detecting intelligent plagiarism, particularly identifying paraphrases by measuring the semantic similarity of short components of the text, are investigated. Models using neural network architecture and based on natural language sentence matching approaches such as Densely Interactive Inference Network (DIIN), Bilateral Multi-Perspective Matching (BiMPM) and Bidirectional Encoder Representations from Transformers (BERT) and its family of models are considered. The progress in improving plagiarism detection systems, techniques and related models is summarized. Relevant and urgent problems that remain unresolved in detecting intelligent plagiarism - effective recognition of unoriginal ideas and qualitatively paraphrased text - are outlined.

• 한국항공우주학회지
• /
• 제49권1호
• /
• pp.63-73
• /
• 2021

본 논문은 공중 혹은 해상배경에 표적과 화염이 동시에 존재할 때, 무인항공기에 장착된 EOTS(Electro-Optical Targeting System; 전자광학 추적장비)가 표적을 추적하기 위해 화염의 영향에 강건하도록 표적을 자동 인식하는 기법을 제안한다. 제안한 기법은 표적과 화염의 적외선 영상을 Gradient Vector Field로 변환하고, 각 Gradient magnitude를 Polynomial Curve Fitting 도구에 적용하여 다항식 계수를 추출 및 얕은 신경망 모델에 학습함으로써, 표적과 화염을 자동으로 인식한다. 확보한 표적 및 화염의 다양한 적외선 영상 DB를 학습데이터, 검증데이터, 시험데이터로 분류하여 제안한 기법의 표적 및 화염 자동 인식 성능을 확인하였다. 본 알고리듬을 활용하여 무인항공기의 자동비행 중 충돌회피, 산불탐지, 공중 및 해상의 목표물을 자동탐지 및 인식하는 분야에 적용될 수 있다.