• Proceedings of the IEEK Conference
• /
• summer
• /
• pp.371-375
• /
• 2004

Fault diagnosis is one of the most studied problems in process engineering. Recently, great research interest has been devoted to approaches that use classification methods to detect faults. This paper presents an application of a newly developed classification method - support vector machines - for fault diagnosis in an industrial case. A real set of operation data of a motor pump was used to train and test the support vector machines. The experiment results show that the support vector machines give higher correct detection rate of faults in comparison to rule-based diagnostics. In addition, the studied method can work with fewer training instances, what is important for online diagnostics.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.21 no.7
• /
• pp.1677-1684
• /
• 1996

The theory of optimal stack filtering has been used in difference of estimates(DoE) approach to the detection of intensity edges in noisy image. In this approach, stack filters are applied to a noisy image to obtain local estimates of the dilated and eroded versions of the noise-free image. Thresholding the difference between these two estimates produces the estimated edge map. In this paper, the DoE approach is modified by imposing a symmetry condition of the data used to train the two stack filers. Under this condition, the stack filters obtained are duals of each other. Only one filter must therefore be trained;the other is simply its dual. They also produce statistially unbiased estimates. This new technique is called the symmetric Difference of Estimates (SDoE) approach.

• Journal of Communications and Networks
• /
• v.13 no.2
• /
• pp.125-131
• /
• 2011

Rapid strides are being made to bring to reality the technology of wearable sensors for monitoring patients' physiological data.We study the problem of automatically detecting anomalies in themeasured blood glucose levels. The normal daily measurements of the patient are used to train a hidden Markov model (HMM). The structure of the HMM-its states and output symbols-are selected to accurately model the typical transitions in blood glucose levels throughout a 24-hour period. The learning of the HMM is done using historic data of normal measurements. The HMM can then be used to detect anomalies in blood glucose levels being measured, if the inferred likelihood of the observed data is low in the world described by the HMM. Our simulation results show that our technique is accurate in detecting anomalies in glucose levels and is robust (i.e., no false positives) in the presence of reasonable changes in the patient's daily routine.

• Proceedings of the KSR Conference
• /
• 2005.11a
• /
• pp.915-920
• /
• 2005

Passenger safety is a primary concern of railway system but, it has been urgent issue that dozens of people are killed every year when they fall off from train platforms. Recently, advancements in IT have enabled applying vision sensors to railway environments, such as CCTV and various camera sensors. The objective of this work is to propose technical and system requirements for establishing intelligent monitoring system using camera equipments in urban transit system. We suppose the system is to determine automatically and in real-time whether anyone or anything is in monitoring area. To achieve the goal, we analyze recent image processing technologies for detection and recognition, and suggest possible direction of system development for applying urban transit system. According to the results, we expect the proposed system requirements will playa key role for establishing highly intelligent monitoring system in railway.

• Speech Sciences
• /
• v.13 no.3
• /
• pp.7-18
• /
• 2006

Diagnosis of pathological voice is one of the important issues in biomedical applications of speech technology. This study focuses on the discrimination of voice disorder using HMM (Hidden Markov Model) for automatic detection between normal voice and vocal fold disorder voice. This is a non-intrusive, non-expensive and fully automated method using only a speech sample of the subject. Speech data from normal people and patients were collected. Mel-frequency filter cepstral coefficients (MFCCs) were modeled by HMM classifier. Different states (3 states, 5 states and 7 states), 3 mixtures and left to right HMMs were formed. This method gives an accuracy of 93.8% for train data and 91.7% for test data in the discrimination of normal and vocal fold disorder voice for sustained /a/.

• Journal of the Semiconductor & Display Technology
• /
• v.19 no.2
• /
• pp.88-91
• /
• 2020

Image segmentation is the task of partitioning an image into multiple sets of pixels based on some characteristics. The objective is to simplify the image into a representation that is more meaningful and easier to analyze. In this paper, we apply deep-learning to pre-train the learning model, and implement an algorithm that performs image segmentation in real time by extracting frames for the stream input from the Android device. Based on the open source of DeepLab-v3+ implemented in Tensorflow, some convolution filters are modified to improve real-time operation on the Android platform.

• Proceedings of the KIEE Conference
• /
• 2003.07b
• /
• pp.1267-1269
• /
• 2003

경량전철시스템의 개발시험을 수행하기 위하여 시험선을 구축하는데 있어서 각 하부시스템별로 요구사항을 도출하고 이를 설계에 반영하여야 한다. 이에 따라 본 논문에서는 신호제어시스템에 대하여 성능 및 기능시험을 감안한 요구사항을 도술하고 시험환경 및 시험조건에 따라 연차 검지 및 안전제동거리의 시험방법에 대해 검토하여 최적의 시험기법을 제안하고자 한다.

• International Journal of Internet, Broadcasting and Communication
• /
• v.11 no.1
• /
• pp.47-53
• /
• 2019

The idea of ensemble learning is to train multiple models, each with the objective to predict or classify a set of results. Most of the errors from a model's learning are from three main factors: variance, noise, and bias. By using ensemble methods, we're able to increase the stability of the final model and reduce the errors mentioned previously. By combining many models, we're able to reduce the variance, even when they are individually not great. In this paper we propose an ensemble model and applied it to classification problem. In iris, Pima indian diabeit and semiconductor fault detection problem, proposed model classifies well compared to traditional single classifier that is logistic regression, SVM and random forest.

• Journal of Korea Multimedia Society
• /
• v.25 no.10
• /
• pp.1524-1534
• /
• 2022

This study proposes the classification model of Minhwa genre based on object detection of deep learning. To detect unique Korean traditional objects in Minhwa, we construct custom datasets by labeling images using object keywords in Minhwa DB. We train YOLOv5 models with custom datasets, and classify images using predicted object labels result, the output of model training. The algorithm consists of two classification steps: 1) according to the painting technique and 2) genre of Minhwa. Through classifying paintings using this algorithm on the Internet, it is expected that the correct information of Minhwa can be built and provided to users forward.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• fall
• /
• pp.91-94
• /
• 2021

As deep learning technologies becoming developed, realistic fake videos synthesized by deep learning models called "Deepfake" videos became even more difficult to distinguish from original videos. As fake news or Deepfake blackmailing are causing confusion and serious problems, this paper suggests a novel model detecting Deepfake videos. We chose Residual Convolutional Neural Network (Resnet50) as an extraction model and Long Short-Term Memory (LSTM) which is a form of Recurrent Neural Network (RNN) as a classification model. We adopted cosine similarity with hinge loss to train our extraction model in embedding the features of Deepfake and original video. The result in this paper demonstrates that temporal features in the videos are essential for detecting Deepfake videos.