• Transactions of the Korean Society for Noise and Vibration Engineering
• /
• v.14 no.11
• /
• pp.1091-1100
• /
• 2004

This paper presents an approach for the monitoring and detection of faults in induction machine by using data fusion technique and Dempster-Shafer theory Features are extracted from motor stator current and vibration signals. Neural network is trained and Hosted by the selected features of the measured data. The fusion of classification results from vibration and current classifiers increases the diagnostic accuracy. The efficiency of the proposed system is demonstrated by detecting motor electric and mechanical faults originated from the induction motors. The results of the test confirm that the proposed system has potential for real time application.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.11 no.12
• /
• pp.6133-6151
• /
• 2017

The field of periocular biometrics has gained wide attention as an alternative or supplemental means to conventional biometric traits such as the iris or the face. Periocular biometrics provide intermediate resolution between the iris and the face, which enables it to support both. We have developed a periocular recognition system by using uniform Multiscale Local Binary Pattern (uMLBP) and attribute features. The proposed system has been evaluated in terms of major factors that need to be considered on a mobile platform (e.g., distance and facial pose) to assess the feasibility of the use of periocular biometrics on mobile devices. Experimental results showed 98.7% of rank-1 identification accuracy on a subset of the Face Recognition Grand Challenge (FRGC) database, which is the best performance among similar studies.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.12 no.10
• /
• pp.5159-5178
• /
• 2018

Network Intrusion detection is a rapidly growing field of information security due to its importance for modern IT infrastructure. Many supervised and unsupervised learning techniques have been devised by researchers from discipline of machine learning and data mining to achieve reliable detection of anomalies. In this paper, a deep convolutional neural network (DCNN) based intrusion detection system (IDS) is proposed, implemented and analyzed. Deep CNN core of proposed IDS is fine-tuned using Randomized search over configuration space. Proposed system is trained and tested on NSLKDD training and testing datasets using GPU. Performance comparisons of proposed DCNN model are provided with other classifiers using well-known metrics including Receiver operating characteristics (RoC) curve, Area under RoC curve (AuC), accuracy, precision-recall curve and mean average precision (mAP). The experimental results of proposed DCNN based IDS shows promising results for real world application in anomaly detection systems.

• International journal of advanced smart convergence
• /
• v.9 no.1
• /
• pp.193-201
• /
• 2020

The main objective of this study is to investigate the impact of additional modalities on the performance of emotion recognition using speech, facial expression and physiological measurements. In order to compare different approaches, we designed a feature-based recognition system as a benchmark which carries out linear supervised classification followed by the leave-one-out cross-validation. For the classification of four emotions, it turned out that bimodal fusion in our experiment improves recognition accuracy of unimodal approach, while the performance of trimodal fusion varies strongly depending on the individual. Furthermore, we experienced extremely high disparity between single class recognition rates, while we could not observe a best performing single modality in our experiment. Based on these observations, we developed a novel fusion method, called parametric decision fusion (PDF), which lies in building emotion-specific classifiers and exploits advantage of a parametrized decision process. By using the PDF scheme we achieved 16% improvement in accuracy of subject-dependent recognition and 10% for subject-independent recognition compared to the best unimodal results.

• Journal of Institute of Control, Robotics and Systems
• /
• v.4 no.4
• /
• pp.499-505
• /
• 1998

In developing an automated surface inspect algorithm, we have designed a hierarchical classifier using neural network. The defects which exist on the surface of cold mill strip have a scattering or singular distribution. We have considered three major problems, that is preprocessing, feature extraction and defect classification. In preprocessing, Top-hit transform, adaptive thresholding, thinning and noise rejection are used Especially, Top-hit transform using local minimax operation diminishes the effect of bad lighting. In feature extraction, geometric, moment, co-occurrence matrix, and histogram ratio features are calculated. The histogram ratio feature is taken from the gray-level image. For defect classification, we suggest a hierarchical structure of which nodes are multilayer neural network classifiers. The proposed algorithm reduced error rate by comparing to one-stage structure.

• Proceedings of the IEEK Conference
• /
• 2003.07e
• /
• pp.2016-2019
• /
• 2003

In this paper, we take some features for face recognition out of face image, using a simple type of templates. We use the extracted features to do Adaboost learning for face recognition. Using a carefully-chosen feature among these features, we can make a weak face classifier for face recognition. And doing Adaboost learning on and on with those chosen several weak classifiers, we can get a strong face classifier. By using Adaboost Loaming, we can choose particular features which is not easily subject to changes in illumination and facial expression about several images of one person, and construct face recognition system. Therefore, the face classifier bulit like the above way has robustness in both facial expression and illumination variation, and it finally gives capability of recognizing face fast due to the simple feature.

• The Journal of the Acoustical Society of Korea
• /
• v.15 no.3E
• /
• pp.31-36
• /
• 1996

In this paper, a two-stage recognition approach based on error pattern hypotheses is proposed to reduce errors of a connected digit recognizer. In the approach, a conventional recognizer is first used to produce N-best candidate strings, and then error patterns are hypothesized by examining the candidate strings. For substitution error pattern hypotheses, error-pattern-dependent classifiers having more discriminative power than the first-stage classifier are used ; and for insertion and deletion errors, word duration and energy contour information are exploited are exploited to discriminated confusing pairs. Simulation results showed that the proposed approach achieves 15% decrease in word error rate for speaker-independent Korean connected digit recognition when a hidden Markov model-based recognizer is used for the first-stage classifier.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2009.01a
• /
• pp.223-228
• /
• 2009

We propose an on-line machine learning approach for object recognition, where new images are continuously added and the recognition decision is made without delay. Random forest (RF) classifier has been extensively used as a generative model for classification and regression applications. We extend this technique for the task of building incremental component-based detector. First we employ object descriptor model based on bag of covariance matrices, to represent an object region then run our on-line RF learner to select object descriptors and to learn an object classifier. Experiments of the object recognition are provided to verify the effectiveness of the proposed approach. Results demonstrate that the propose model yields in object recognition performance comparable to the benchmark standard RF, AdaBoost, and SVM classifiers.

• Proceedings of the Korean Information Science Society Conference
• /
• 2006.06a
• /
• pp.79-81
• /
• 2006

커널(Kernel)을 이용한 분류 방법은 넓은 마진(large margin) 분류기로서 SVM(Support Vector Machine)을 주로 사용하게 된다 하지만, 이 방법은 라그랑제 파라미터(Lagrange Parameter)의 최적화 과정을 포함함으로써 학습 과정을 쉽지 않게 만든다. 이 최적화 과정은 특히 DNA computing과 같은 단순한 과정의 설계를 통해 결과를 얻어야 하는 새로운 계산 모델에 커널을 적용하고자 했을 경우 큰 장벽이 된다. 본 논문에서는 넓은 마진을 목표로 하는 최적화 과정이 아닌 다른 라벨(label)의 데이터간의 경계 파악을 위한 간단한 커널 갱신 방법의 도입을 통해 분류기를 설계한다. 이 방법을 가우시안 커널에 적용시켜 본 결과, 반복을 통해 데이터의 구조를 찾아갈 수 있는 특성을 보여주며, 결국 넓은 마진의 최적화된 파라미터를 찾게 됨을 보여준다. 본 논문에서는 이 최적화 방법을 DNA 분자를 이용한 커널 생성 모델인 DNA 커널에 적용시켰을 때 잘 알려진 AML/ALL 데이터를 잘 분류해 냄을 보여준다.

• 한국IT서비스학회:학술대회논문집
• /
• 2002.11a
• /
• pp.411-416
• /
• 2002

인터넷의 발전과 더불어 전자메일 사용자가 증가하게 되고, 기업의 고객접촉채널로서 전자메일에 대한 중요성 또한 증가되고 있다. 고객의 요구에 대해 적시에 적절하게 응답하지 못하면 고객의 불만족이 증가하게 되고, 충성도를 감소시켜 결국 장기적 매출 및 수익성 악화를 초래하게 된다. 따라서 고객의 전자메일에 신속, 정확하게 응답할 수 있는 전자 메일 자동관리 시스템의 필요성이 증가되고 있다. 본 연구에서는 나이브 베이지안 학습과 중심점 기반 분류 방법을 이용하여 전자메일 자동관리 시스템에서 전자메일 분류를 수행하는 분류기를 구현한다. 구현된 분류기를 이용하여 실제 기업의 고객 전자메일을 분류하는 실험을 수행하고 두 분류기의 성능을 비교하였다. 실험결과 두 분류기 모두 전자메일 분류에 비교적 우수한 성능을 보였다. 그러나, 클래스 수가 적은 경우 중심점 기반 분류기가 좋은 성능을 보였으나, 학습집합이 작아지면서 두 분류기의 성능 차이는 없었으며, 클래스의 수가 많아지면서 나이브 베이지안 분류기가 더 우수한 성능을 보였다.