• 한국방송∙미디어공학회:학술대회논문집
• /
• 한국방송공학회 2014년도 추계학술대회
• /
• pp.49-52
• /
• 2014

본 논문에서는 비문(鼻紋)을 이용한 개의 개체인식 시스템을 제안하고자 한다. 기존의 비문을 기반으로 한신원 확인 시스템에서는 종이에 비문을 찍어내어 일반화(generalization)된 데이터를 만드는 과정을 거치거나, 기계학습을 위해 한 개체에 대한 여러 장의 사진을 요구하는 문제점을 가지고 있다. 본 논문에서는 한 개체에 대한 두 장의 사진과 SURF(Speeded-Up Robust Features) 알고리듬을 이용한 특징점 추출(feature detection), FREAK(Fast Retina Keypoint) 특징 기술자(feature descriptor)를 사용한 개체인식 시스템을 제안한다. 비문 이미지에는 개 코의 특성상 반사로 인한 다수의 노이즈가 생기게 되는데 이를 극복하기 위한 전처리 과정이 제안 알고리듬에 포함되어 있다. 실험결과 두 장의 사진으로도 비문 기반의 개체인식을 할 수 있다는 것을 알 수 있다.

• 전자공학회논문지SC
• /
• 제47권1호
• /
• pp.7-16
• /
• 2010

패턴 인식은 얼굴인식 영역에서 중요한 분야로 널리 사용 되고 있으며, 많은 연구가 이루어지고 있다. 얼굴 특징 점의 추출은 얼굴 인식 과정에서 중요한 단계로 정확한 얼굴 특징 추출은 인식기의 인식률에 가장 큰 영향을 미친다. 본 논문 에서는 능동형 이산 웨이브렛 변환을 통한 얼굴 특징 점 추출 방법을 제안했다. PC 카메라를 이용하여 취득된 얼굴 영상을 능동형 이산 웨이브렛 변환을 취하여 얼굴 영상 신호변환을 하였다. 변환된 영상 신호에 대하여 수직, 수평 투영법을 이용하여 얼굴 특징 추출을 하였으며, 추출 결과로부터 얼굴인식을 하였다. 제안된 능동형 이산 웨이브렛 변환은 얼굴 인식률 향상을 가져왔으며, 특징 점을 신속하고 정확하게 추출할 수 있었으며, 기존 이산 웨이브렛 변환을 이용한 특징 점 추출방식에 대하여 향상된 정확도와 안전성을 보였다.

• 품질경영학회지
• /
• 제50권3호
• /
• pp.459-471
• /
• 2022

Purpose: The purpose of this study was to increase prediction accuracy for an anomaly interval identified using an artificial intelligence-based time series anomaly detection technique by establishing a pre-processing process. Methods: Significant variables were extracted by applying feature selection techniques, and anomalies were derived using the TadGAN time series anomaly detection algorithm. After applying machine learning and deep learning methodologies using normal section data (excluding anomaly sections), the explanatory power of the anomaly sections was demonstrated through performance comparison. Results: The results of the machine learning methodology, the performance was the best when SHAP and TadGAN were applied, and the results in the deep learning, the performance was excellent when Chi-square Test and TadGAN were applied. Comparing each performance with the papers applied with a Conventional methodology using the same data, it can be seen that the performance of the MLR was significantly improved to 15%, Random Forest to 24%, XGBoost to 30%, Lasso Regression to 73%, LSTM to 17% and GRU to 19%. Conclusion: Based on the proposed process, when detecting unsupervised learning anomalies of data that are not actually labeled in various fields such as cyber security, financial sector, behavior pattern field, SNS. It is expected to prove the accuracy and explanation of the anomaly detection section and improve the performance of the model.

• 한국IT서비스학회지
• /
• 제18권2호
• /
• pp.143-159
• /
• 2019

Machine learning (ML) is a method of fitting given data to a mathematical model to derive insights or to predict. In the age of big data, where the amount of available data increases exponentially due to the development of information technology and smart devices, ML shows high prediction performance due to pattern detection without bias. The feature engineering that generates the features that can explain the problem to be solved in the ML process has a great influence on the performance and its importance is continuously emphasized. Despite this importance, however, it is still considered a difficult task as it requires a thorough understanding of the domain characteristics as well as an understanding of source data and the iterative procedure. Therefore, we propose methods to apply deep learning for solving the complexity and difficulty of feature extraction and improving the performance of ML model. Unlike other techniques, the most common reason for the superior performance of deep learning techniques in complex unstructured data processing is that it is possible to extract features from the source data itself. In order to apply these advantages to the business problems, we propose deep learning based methods that can automatically extract features from transaction data or directly predict and classify target variables. In particular, we applied techniques that show high performance in existing text processing based on the structural similarity between transaction data and text data. And we also verified the suitability of each method according to the characteristics of transaction data. Through our study, it is possible not only to search for the possibility of automated feature extraction but also to obtain a benchmark model that shows a certain level of performance before performing the feature extraction task by a human. In addition, it is expected that it will be able to provide guidelines for choosing a suitable deep learning model based on the business problem and the data characteristics.

• 한국멀티미디어학회논문지
• /
• 제14권10호
• /
• pp.1252-1261
• /
• 2011

본 논문은 내용기반 동영상 분할을 위한 장면의 유사도 패턴 비교 방법을 제안한다. 동영상 장면 전환의 종류는 크게 급진적 전환과 디졸브(dissolve), 페이드인(fade-in), 페이드아웃(fade-out), 와이프 전환(wipe transition)을 포함하는 점진적 전환 형태로 나눌 수 있다. 제안하는 방법은 모든 종류의 장면 전환 검출 문제를 단지 발생 유무의 문제로 간단 정의하고, 장면 전환 종류는 별도로 구분하지 않는다. 장면 전환을 검출하기 위해서는 프레임간의 유사도를 정의해야 한다. 본 논문에서는 장면 내 유사도(within similarity)와 장면 간 유사도(between similarity)를 정의하며 두 유사도의 통계적 패턴 비교를 통하여 최종적으로 장면 전환을 검출하게 된다. 장면 내 유사도와 장면 간 유사도의 비율을 구하는 방법을 통해 플래시라이트나영상 내 물체 움직임에 대한 거짓 양성 검출을 별도의 후처리 과정 없이도 방지할 수 있음을 확인하였다. 프레임의 특징 값으로는 컬러 히스토그램과 프레임 내 평균 화소값을 이용하였다. TREC-2001, TREC-2002 동영상 셋을 포함한 실험 셋에서 성능을 평가한 결과 제안하는 알고리즘의 경우 총 91.84%의 재현율(recall)과 86.43%의 정확도(precision)의 성능을 보임을 확인할 수 있었다.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• 제15권2호
• /
• pp.96-101
• /
• 2015

Support vector machine (SVM) has a strong theoretical foundation and also achieved excellent empirical success. It has been widely used in a variety of pattern recognition applications. Unfortunately, SVM also has the drawback that it is sensitive to outliers and its performance is degraded by their presence. In this paper, a new outlier detection method based on genetic algorithm (GA) is proposed for a robust SVM. The proposed method parallels the GA-based feature selection method and removes the outliers that would be considered as support vectors by the previous soft margin SVM. The proposed algorithm is applied to various data sets in the UCI repository to demonstrate its performance.

• 한국HCI학회:학술대회논문집
• /
• 한국HCI학회 2007년도 학술대회 3부
• /
• pp.322-325
• /
• 2007

Graphics processing unit (GPU) is used for a faster artificial neural network. It is used to implement the matrix multiplication of a neural network to enhance the time performance of a text detection system. Preliminary results produced a 20-fold performance enhancement using an ATI RADEON 9700 PRO board. The parallelism of a GPU is fully utilized by accumulating a lot of input feature vectors and weight vectors, then converting the many inner-product operations into one matrix operation. Further research areas include benchmarking the performance with various hardware and GPU-aware learning algorithms. (c) 2004 Pattern Recognition Society. Published by Elsevier Ltd. All rights reserved.

• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2022년도 춘계학술대회
• /
• pp.636-638
• /
• 2022

본 논문은 의료진단 검출 분야에서 혈관, 신경조직, 망막 손상 그리고 다양한 심혈관계 질환과 치매까지 진단하는 데 유용하게 사용하고 있는 안저 영상에 CNN(Convolution Neural Network) 알고리즘을 적용하고 녹내장 병변을 검출하기 위한 연구를 진행한다. 실험을 위하여 정상 안저 영상과 녹내장 병변이 있는 안저 영상으로 구성된 데이터 세트를 AlexNet으로 분류하고 그 성능을 확인하였다.

• 전기학회논문지P
• /
• 제57권1호
• /
• pp.56-59
• /
• 2008

We have designed 4 types(void in insulation paper, protrusion electrode, floating electrode, surface discharge) of partial discharge(PD) defect to simulate typical faults found in oil filled power transformers. Ultra-high frequency(UHF) radiation due to PD was measured using a UHF measuring system and a conventional PD measuring system, simultaneously. Electromagnetic radiation spectra of these defects show UHF radiation up to about 1.5-2 GHz range. The phase resolved partial discharge(PRPD) patterns of UHF radiation from the PD defects were also measured and the pattern reveals distinct feature for each defect types. The UHF measuring could be used to detect PDs in oil filled transformers and analysis of the PRPD pattern should provide useful information on origin of PD signal.

• Journal of applied mathematics & informatics
• /
• 제40권5_6호
• /
• pp.897-914
• /
• 2022

Pythagorean fuzzy sets (PFSs) are capable of modelling information with more uncertainties in decision-making problems. The essential feature of PFSs is that they are described by three parameters: membership function, non-membership function and hesitant margin, with the total of the squares of each parameter equal to one. The purpose of this article is to suggest some new similarity measures and weighted similarity measures for PFSs. Numerical computations have been carried out to validate our proposed measures. Applications of these measures have been applied to some real-life decision-making problems of pattern detection and medicinal investigations. Moreover, a descriptive illustration is employed to compare the results of the proposed measures with the existing analogous similarity measures to show their effectiveness.