• 한국축산식품학회지
• /
• 제38권2호
• /
• pp.362-375
• /
• 2018

This study proposed a rapid microscopic examination method for pork freshness evaluation by using the self-assembled hyperspectral microscopic imaging (HMI) system with the help of feature extraction algorithm and pattern recognition methods. Pork samples were stored for different days ranging from 0 to 5 days and the freshness of samples was divided into three levels which were determined by total volatile basic nitrogen (TVB-N) content. Meanwhile, hyperspectral microscopic images of samples were acquired by HMI system and processed by the following steps for the further analysis. Firstly, characteristic hyperspectral microscopic images were extracted by using principal component analysis (PCA) and then texture features were selected based on the gray level co-occurrence matrix (GLCM). Next, features data were reduced dimensionality by fisher discriminant analysis (FDA) for further building classification model. Finally, compared with linear discriminant analysis (LDA) model and support vector machine (SVM) model, good back propagation artificial neural network (BP-ANN) model obtained the best freshness classification with a 100 % accuracy rating based on the extracted data. The results confirm that the fabricated HMI system combined with multivariate algorithms has ability to evaluate the fresh degree of pork accurately in the microscopic level, which plays an important role in animal food quality control.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2001년도 제14회 신호처리 합동 학술대회 논문집
• /
• pp.411-414
• /
• 2001

목표물 인식(Target Recognition)에 사용되는 대표적인 특징 정보에는 밝기 (Intensity) 정보와 윤곽선(Boundary) 등의 모양(Shape) 정보가 있다. 그러나, 일반적으로 영상에서 바로 추출한 밝기 정보나 윤곽선 정보는 환경 변화에 의한 많은 오차 요인들을 포함하고 있기 때문에, 이들 특징 정보를 개별적으로 인식에 사용하는 것은 높은 인식 성능을 기대하기 어렵다. 따라서, 밝기 정보와 모양 정보를 인식에 함께 사용하는 기법이 요구된다. 본 논문에서는 밝기 정보와 윤곽선 기반의 모양 정보를 합성하여 동시에 인식에 사용하는 3단계 기법을 제안한다. 제안하는 기법에서 밝기 정보 추출에 는 PCA (Principal Component Analysis)기법을 사용하고 , 윤곽선 정보 추출에는 PDM(Point Distribution Model) 에 기반한 영역 분할(Segmentation) 기법과 Algebraic Curve Fitting기법을 사용하였다 추출된 밝기 정보와 윤곽선 정보는 FLD(Fisher Linear Discriminant) 기법을 통해 결합(integration)되어 인식에 사용 된다. 제안한 기법을 적외선 자동차 영상을 인식하는 실험에 적용한 결과, 기존기법에 비해 인식 성능이 개선됨을 확인할 수 있었다.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 1999년도 추계종합학술대회 논문집
• /
• pp.460-463
• /
• 1999

We present an efficient face recognition method that is robust to illumination changes. We named the proposed method as SKKUfaces. We first compute eigenfaces from training images and then apply fisher discriminant analysis using the obtained eigenfaces that exclude eigenfaces correponding to first few largest eigenvalues. This way, SKKUfaces can achieve the maximum class separability without considering eigenfaces that are responsible for illumination changes, facial expressions and eyewear. In addition, we have developed a method that efficiently computes beween-scatter and within-scatter matrices in terms of memory space and computation time. We have tested the performance of SKKUfaces on the YALE and the SKKU face databases. Initial Experimental results show that SKKUfaces performs greatly better over Fisherfaces on the input images of large variations in lighting and eyewear.

• Smart Structures and Systems
• /
• 제23권1호
• /
• pp.71-79
• /
• 2019

In general, it may be advantageous to measure the pressure pulsation near a valve to detect a valve defect in a linear compressor. However, the acceleration signals are more advantageous for rapid classification in a mass-production line. This paper deals with the performance improvement of fault classification using only the compressor-shell acceleration signal based on the relation between the refrigerant pressure pulsation and the shell acceleration of the compressor. A transfer function was estimated experimentally to take into account the signal noise ratio between the pressure pulsation of the refrigerant in the suction pipe and the shell acceleration. The shell acceleration signal of the compressor was modified using this transfer function to improve the defect classification performance. The defect classification of the modified signal was evaluated in the acceleration signal in the frequency domain using Fisher's discriminant ratio (FDR). The defect classification method was validated by experimental data. By using the method presented, the classification of valve defects can be performed rapidly and efficiently during mass production.

• 대한치과교정학회지
• /
• 제27권1호
• /
• pp.45-54
• /
• 1997

본 연구의 목적은 bionator를 사용한 II급 1류 부정교합 환자의 치료후 결과를 토대로 치료전에 치료후 결과를 예측할 수 있는 항목들을 알아봄으로써 성장하는 II급 1류 부정교합을 가진 환자들의 치료에 도움을 얻는데 있다. bionator를 사용한 앵글 II급 1류 부정교합 환자 48명의 치료후 두부방사선계측사진을 통해 치료결과가 양호한 군(1군)과 치료결과가 불량한 군(2군)으로 나눈 후 양군의 치료전 측모두부방사선계측사진의 비교분석을 통해 두군 사이에 차이를 보이는 계측항목들을 알아보았고, 판별분석을 통해 다음의 결과를 얻을 수 있었다. 1. 치료전 골격계측 항목으로는 ANB, facial convexity angle, AB to facial plane angle 등이, 치성계측 항목으로는 L1 to A-Pog, U1 to facial plane, L1 to facial plane 등이, 연조직 계측항목으로는 Ricketts esthetic line 상에서 상, 하순의 돌출도가 양군 사이에 유의한 차를 보였다(SAS t-test, p<0.05). 2. 판별분석을 통해 유의성있게 나타나는 항목의 순위를 본 결과 L1 to facial plane, 하순의 돌출도, ANB과 FMIA 등이 양군의 치료결과의 예측에 도움을 주는 것으로 나타났다. 3. 증감판별분석을 통해 서로 독립적이며 상관계수가 높은 3개의 변수 - L1 to facial plane, articular angle, ANB- 를 선택하였으며, 이를 토대로 판별식을 도출하였다.

• Journal of Communications and Networks
• /
• 제11권6호
• /
• pp.544-555
• /
• 2009

This work continues a trend of developments aimed at exploiting the physical layer of the open systems interconnection (OSI) model to enhance wireless network security. The goal is to augment activity occurring across other OSI layers and provide improved safeguards against unauthorized access. Relative to intrusion detection and anti-spoofing, this paper provides details for a proof-of-concept investigation involving "air monitor" applications where physical equipment constraints are not overly restrictive. In this case, RF fingerprinting is emerging as a viable security measure for providing device-specific identification (manufacturer, model, and/or serial number). RF fingerprint features can be extracted from various regions of collected bursts, the detection of which has been extensively researched. Given reliable burst detection, the near-term challenge is to find robust fingerprint features to improve device distinguishability. This is addressed here using wavelet domain (WD) RF fingerprinting based on dual-tree complex wavelet transform (DT-$\mathbb{C}WT$) features extracted from the non-transient preamble response of OFDM-based 802.11a signals. Intra-manufacturer classification performance is evaluated using four like-model Cisco devices with dissimilar serial numbers. WD fingerprinting effectiveness is demonstrated using Fisher-based multiple discriminant analysis (MDA) with maximum likelihood (ML) classification. The effects of varying channel SNR, burst detection error and dissimilar SNRs for MDA/ML training and classification are considered. Relative to time domain (TD) RF fingerprinting, WD fingerprinting with DT-$\mathbb{C}WT$ features emerged as the superior alternative for all scenarios at SNRs below 20 dB while achieving performance gains of up to 8 dB at 80% classification accuracy.

• 전자공학회논문지
• /
• 제54권1호
• /
• pp.111-120
• /
• 2017

본 논문에서는 해저 퇴적물 분류를 위한 특징 추출 기법을 제안하고 검증한다. 기존 연구에서는 주파수의 영향이 없는 반사계수를 이용하여 퇴적물을 분류해 왔다. 그러나 해저 퇴적물의 음향 감쇠계수는 주파수의 함수이며 퇴적 성분에 따라 서로 다른 특성을 나타낸다. 따라서 주파수에 따른 감쇠계수 변화량을 이용하여 특징벡터를 생성하였다. 감쇠계수 변화량은 Chirp 신호에 의해 생성된 두 번째 층 반사신호를 이용하여 추정한다. Chirp 신호의 다중대역 특징이 다차원 벡터를 형성하기 때문에 기존의 방법에 비해 우수한 특성을 갖는다. 반사계수에 의한 분류 성능과 비교하기 위해 선형 판별 분석법 (LDA, Linear Discriminant Analysis)를 이용하여 차원을 축소하였다. Biot 모델을 이용하여 모의실험 환경을 구축하고 Fisher score와 MLD(Maximum Likelihood Decision)를 기반의 분류 정확도를 이용해 제안된 특징을 평가하였다. 그 결과, 제안된 특징은 반사계수에 비해 높은 변별력을 보이며, 측정 및 깊이 추정오차에도 강인한 특성을 보였다.

• 한국산학기술학회논문지
• /
• 제13권8호
• /
• pp.3779-3784
• /
• 2012

산업체 공정의 실시간 공정 모니터링과 진단은 생산 제품의 품질과 안전을 보장하는데 반드시 필요한 활동들의 하나이다. 그중에서 공정 진단은 공정에 발생된 특정 이상상황의 원인을 밝혀내는 것으로서 조업자들이 이상상황의 근본원인을 보다 효과적으로 도출하는데 도움을 줄 수 있다. 본 논문에서는 비선형 KFDA 기법과 데이터 전처리기법을 이용한 이상원인 진단방법을 적용하고 이의 진단 성능을 기존 선형 기법에 기반한 PCA 진단방법과 비교한다. 실제 공정을 모사한 Tennessee Eastman 공정 시뮬레이터의 공정 데이터를 통한 사례연구를 수행한 결과 기존 선형 진단 방법론 대비 신뢰할 수 있는 진단 결과를 얻을 수 있었다.

• Journal of Electrical Engineering and Technology
• /
• 제9권6호
• /
• pp.2118-2125
• /
• 2014

Gait Recognition is a new technique to identify the people by the way they walk. Human gait is a spatio-temporal phenomenon that typifies the motion characteristics of an individual. The proposed method makes a simple but efficient attempt to gait recognition. For each video file, spatial silhouettes of a walker are extracted by an improved background subtraction procedure using Gaussian Mixture Model (GMM). Here GMM is used as a parametric probability density function represented as a weighted sum of Gaussian component densities. Then, the relevant features are extracted from the silhouette tracked from the given video file using the Principal Component Analysis (PCA) method. The Fisher Linear Discriminant Analysis (FLDA) classifier is used in the classification of dimensional reduced image derived by the PCA method for gait recognition. Although gait images can be easily acquired, the gait recognition is affected by clothes, shoes, carrying status and specific physical condition of an individual. To overcome this problem, it is combined with footprint as a multimodal biometric system. The minutiae is extracted from the footprint and then fused with silhouette image using the Discrete Stationary Wavelet Transform (DSWT). The experimental result shows that the efficiency of proposed fusion algorithm works well and attains better result while comparing with other fusion schemes.

• 대한기계학회:학술대회논문집
• /
• 대한기계학회 2008년도 추계학술대회A
• /
• pp.1588-1593
• /
• 2008

This paper describes a real-time isometric pinch force prediction algorithm from surface electromyogram (sEMG) using multilayer perceptron (MLP) for human robot interactive applications. The activities of seven muscles which are observable from surface electrodes and also related to the movements of the thumb and index finger joints were recorded during pinch force experiments. For the successful implementation of the real-time prediction algorithm, an off-line analysis was performed using the recorded activities. Four muscles were selected for the force prediction by using the Fisher linear discriminant analysis among seven muscles, and the four muscle activities provided effective information for mapping sEMG to the pinch force. The MLP structure was designed to make training efficient and to avoid both under- and over-fitting problems. The pinch force prediction algorithm was tested on five volunteers and the results were evaluated using two criteria: normalized root mean squared error (NRMSE) and correlation (CORR). The training time for the subjects was only 2 min 29 sec, but the prediction results were successful with NRMSE = 0.112 ${\pm}$ 0.082 and CORR = 0.932 ${\pm}$ 0.058. These results imply that the proposed algorithm is useful to measure the produced pinch force without force sensors in real-time. The possible applications include controlling bionic finger robot systems to overcome finger paralysis or amputation.