• Transactions of the Korean Society of Machine Tool Engineers
• /
• v.14 no.4
• /
• pp.22-31
• /
• 2005

The purpose of this study is to design a flexural structure that has a function of pan and tilt for an artificial eyeball. The artificial eyeball system has a function of image stabilization, which compensate panning and tilting vibration of the body on which the artificial eyeball is attached. The target closed loop control bandwidth is 50Hz, so the mechanical resonance frequency is required to be more than the control bandwidth, which is a tough design problem because of a big mass of camera and actuator. In this study, the design process including the selection of the principal parameters by numerical analysis with ANSYS will be described, as well as the design results and frequency response.

• Journal of the Korea Society of Computer and Information
• /
• v.21 no.12
• /
• pp.125-130
• /
• 2016

Automatic quality inspection by computer vision can be applied and give a solution to the pharmaceutical industry field. Pharmaceutical capsule can be easily affected by flaws like dents, cracks, holes, etc. In order to solve the quality inspection problem, it is required computationally efficient image processing technique like thresholding, boundary edge detection and segmentation and some automated systems are available but they are very expensive to use. In this paper, we have developed a dented capsule image processing technique using edge-based image segmentation, TLS(Total Least Squares) curve fitting technique and adopted low cost camera module for capsule image capturing. We have tested and evaluated the accuracy, training and testing time of the classification recognition algorithms like PCA(Principal Component Analysis), ICA(Independent Component Analysis) and SVM(Support Vector Machine) to show the performance. With the result, PCA, ICA has low accuracy, but SVM has good accuracy to use for classifying the dented capsule.

• Journal of the Semiconductor & Display Technology
• /
• v.15 no.3
• /
• pp.6-11
• /
• 2016

Silicon wafer is one of main materials in solar cell. Micro-cracks in silicon wafer are one of reasons to decrease efficiency of energy transformation. They couldn't be observed by human eye. Also, their shape is not only various but also complicated. Accordingly, their shape classification is absolutely needed for manufacturing process quality and its feedback. The performance of typical classification techniques which is principal component analysis(PCA), neural network, fusion model to integrate PCA with neural network, and support vector machine(SVM), are evaluated using pattern features of micro-cracks. As a result, it has been confirmed that the SVM gives good results in micro-crack classification.

• Journal of Institute of Control, Robotics and Systems
• /
• v.13 no.6
• /
• pp.513-518
• /
• 2007

In this paper, we propose a fault diagnosis scheme tor induction motor by adopting a hierarchical classifier consisting of k-Nearest Neighbors(k-NN) and Support Vector Machine(SVM). First, some motor conditions are classified by a simple k-NN classifier in advance. And then, more complicated classes are distinguished by SVM. To obtain the normal and fault data, we established an experimental unit with induction motor system and data acquisition module. Feature extraction is performed by Principal Component Analysis(PCA). To show its effectiveness, the proposed fault diagnostic system has been intensively tested with various data acquired under the different electrical and mechanical faults with varying load.

• Journal of the Korea Society of Computer and Information
• /
• v.20 no.11
• /
• pp.9-16
• /
• 2015

We propose a hybrid pattern recognition method that effectively combines two different features for improving data classification. We first extract the PCA (Principal Component Analysis) and LDA (Linear Discriminant Analysis) features, both of which are widely used in pattern recognition, to construct a set of basic features, and then evaluate the separability of each basic feature. According to the results of evaluation, we select only the basic features that contain a large amount of discriminative information for construction of the combined features. The experimental results for the various data sets in the UCI machine learning repository show that using the proposed combined features give better recognition rates than when solely using the PCA or LDA features.

• International Journal of Fluid Machinery and Systems
• /
• v.6 no.4
• /
• pp.189-199
• /
• 2013

A practical method of surge simulation in a system of a high-pressure-ratio multistage axial flow compressor and ducts, named SRGTRAN, is described about the principal procedures and the details. The code is constructed on the basis of one-dimensional stage-by-stage modeling and application of fundamental equations of mass, momentum, and energy. An example of analytical result on surge behaviors is included as an experimental verification. It will enable to examine the transient flow phenomena caused by possible compressor surges and their influences on the system components in plant systems including high-pressure-ratio axial compressors or gas turbines.

• IE interfaces
• /
• v.7 no.3
• /
• pp.239-248
• /
• 1994

The main objective of this study is to develop a model which describe and explain R&D productivity (Researchitivity measured by patents) in Korea four manufacturing industries-electric & electronic, machine, textile, industrial chemicals-during the last ten years. The model largely focuses on the variables related to R&D investment in order to investigate the efficiency of R&D. The results suggest that there is associated with a significant positive correlation between Researchitivity and industrial size. There are interaction effects between the Researchitivity and the sales volume. Researchitivity is positively correlated with the average wage of R&D employees. It also founded that Researchitivity is more closely associated with investment size than industrial nature.

• Preventive Nutrition and Food Science
• /
• v.2 no.3
• /
• pp.269-279
• /
• 1997

Various nondestructive technologies for quality inspection of fruits and vegetables were reviewed through published literatures and selected agricultural databases. These technologies were grouped into nine categories, including acoustic response, dielectric response, machine vision, magnetic response, mechanical vibration response, microwave response, optical properties, and other possible sensing technologies. Their principles and characteristics were investigated and these technologies were presented with their current and potential applications. The link of appropriate nondestructive technologies with common principal quality parameters of fruits and vegetables was summarized.

• 제어로봇시스템학회:학술대회논문집
• /
• 2001.10a
• /
• pp.35.2-35
• /
• 2001

This paper is concerned with the problem of how to detect paint type defects on painted slates using machine vision. We begin by outlining the motivations for this research and present a review of research in related areas before proceeding with a process description and a categorization of typical paint defects. We describe the test bed built to replicate factory conditions and the testing of image capture techniques. We discuss problems we confronted such as getting a sufficiently strong signal level from the slate, the effects of the slate surface profile on image capture and how we dealt with these problems. The third principal challenge was to generate a strong signal to noise ratio for each defect type so that a computationally inexpensive image processing method becomes viable. We demonstrate ...

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2022.07a
• /
• pp.245-246
• /
• 2022

최근 IoT 환경에서 기계학습을 이용한 공격 탐지 모델의 연구가 활발히 진행되고 있으며, 탐지 정확도도 점차 향상되고 있다. 하지만, IoT 환경의 특징인 저 사양 하드웨어, 고차원의 특징, 방대한 트래픽 등으로 인해 탐지성능이 저하되는 문제가 있다. 따라서 본 논문에서는 MQTT(Message Queuing Telementry Transport) 프로토콜 기반의 IoT 환경에서 수집된 데이터셋을 대상으로 주성분 분석(Principal Component Analysis)과 LightGBM을 이용하여 데이터셋 차원을 감소시키고, 공격 클래스를 분류하였다. 실험결과 원본 데이터셋 차원을 주성분 3개(약 9%)로 감소시켰음에도 모든 특징(33개)을 사용한 실험결과와 거의 유사한 성능을 보였다. 또한 기존 연구의 특징 선택을 통한 탐지 모델과 비교하였을 때도 분류성능이 더 우수한 것으로 나타났다.