• 한국콘텐츠학회:학술대회논문집
• /
• 한국콘텐츠학회 2018년도 춘계 종합학술대회 논문집
• /
• pp.7-8
• /
• 2018

본 연구에서는 Word2vec을 머신러닝 분류기를 이용해 효율적인 오피니언 마이닝 방법을 제안한다. 본 연구의 목적을 위해 BOW(Bag-of-Words) 방법과 Word2vec방법을 이용해 속성 셋을 구성했다. 구성된 속성 셋은 Decision tree, Logistic regression, Support vector machine, Random forest를 이용해 오피니언 마이닝을 수행했다. 연구 결과, Word2vec 방법과 RF분류기가 가장 높은 정확도를 나타냈다. 그리고 Word2vec 방법이 BOW방법 보다 각 분류기에서 높은 성능을 나타냈다.

• 전력전자학회:학술대회논문집
• /
• 전력전자학회 2014년도 전력전자학술대회 논문집
• /
• pp.341-342
• /
• 2014

VSC-HVDC system based on Modular Multilevel Converter (MMC) is an emerging technology since compared to the conventional VSC-HVDC system an MMC presents several advantages such as modularity, low dv/dt, low harmonics, and low switching losses. In this paper, a comprehensive control strategy of an MMC-based VSC-HVDC system is proposed. In contrast to the conventional system control strategy, the DC side of the MMC operates as a controlled voltage source by the proposed method, and the dynamics of the transmission line voltage and current can be actively controlled. Validity of the proposed strategy was verified by 201-level full-scale computer simulation.

• 산업경영시스템학회지
• /
• 제18권35호
• /
• pp.1-8
• /
• 1995

Automatic inspection system software for display image characteristic of CRT is developed. There are two major contributions of this software development. One is that the data from measuring equipments which was usually collected manually is automatically collected through RS-232C port and is saved in computer, then, trend analysis graph and final reports are generated. The other is that evauation of characteristic of electron gun was automatically processed by CCD camera and image processing technique. The system is developed under MS-Windows environment utilizing Borland C++4.0 Compiler and DT 3852-8 image processor board. This system can save the time and man power to measure and to anayze the image characteristics relative to current method.

• 한국광학회지
• /
• 제12권5호
• /
• pp.425-428
• /
• 2001

본 논문에서는 감색 혼법을 이용하는 3층 구조 LCD를 제시하였다. 제안된 구조는 1장의 무색 편광판과 3장의 색 편광판을 이용하여, 색 편광판만을 이용할 때 생기는 빛의 누설현상을 줄여, 명암 대비비를 향상시키는 효과를 얻었다. 그리고, 높은 색 특성을 나타내기 위해 색 편광판의 순서를 최적화 하였다.

• 대한수학회보
• /
• 제58권3호
• /
• pp.669-688
• /
• 2021

The aim of this paper is to prove the existence of an admissible inertial manifold for mild solutions to infinite delay evolution equation of the form $$\{{\frac{du}{dt}}+Au=F(t,\;u_t),\;t{\geq}s,\\\;u_s({\theta})={\phi}({\theta}),\;{\forall}{\theta}{\in}(-{{\infty}},\;0],\;s{\in}{\mathbb{R}},$$ where A is positive definite and self-adjoint with a discrete spectrum, the Lipschitz coefficient of the nonlinear part F may depend on time and belongs to some admissible function space defined on the whole line. The proof is based on the Lyapunov-Perron equation in combination with admissibility and duality estimates.

• International Journal of Computer Science & Network Security
• /
• 제23권4호
• /
• pp.39-47
• /
• 2023

This study compares various transformation techniques for multifocus image fusion. Multi-focus image fusion is a procedure of merging multiple images captured at unalike focus distances to produce a single composite image with improved sharpness and clarity. In this research, the purpose is to compare different popular frequency domain approaches for multi-focus image fusion, such as Discrete Wavelet Transforms (DWT), Stationary Wavelet Transforms (SWT), DCT-based Laplacian Pyramid (DCT-LP), Discrete Cosine Harmonic Wavelet Transform (DC-HWT), and Dual-Tree Complex Wavelet Transform (DT-CWT). The objective is to increase the understanding of these transformation techniques and how they can be utilized in conjunction with one another. The analysis will evaluate the 10 most crucial parameters and highlight the unique features of each method. The results will help determine which transformation technique is the best for multi-focus image fusion applications. Based on the visual and statistical analysis, it is suggested that the DCT-LP is the most appropriate technique, but the results also provide valuable insights into choosing the right approach.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2023년도 춘계학술발표대회
• /
• pp.539-541
• /
• 2023

COVID-19 is a viral pandemic disease that spreads widely all around the world. The only way to identify COVID-19 patients at an early stage is to stop the spread of the virus. Different approaches are used to diagnose, such as RT-PCR, Chest X-rays, and CT images. However, these are time-consuming and require a specialized lab. Therefore, there is a need to develop a time-efficient diagnosis method to detect COVID-19 patients. The proposed machine learning (ML) approach predicts the presence of coronavirus based on clinical symptoms. The clinical dataset is collected from the Israeli Ministry of Health. We used different ML classifiers (i.e., XGB, DT, RF, and NB) to diagnose COVID-19. Later, classifiers are optimized with the Bayesian hyperparameter optimization approach to improve the performance. The optimized RF outperformed the others and achieved an accuracy of 97.62% on the testing data that help the early diagnosis of COVID-19 patients.

• 센서학회지
• /
• 제32권6호
• /
• pp.378-385
• /
• 2023

Human biosignals provide essential information for diagnosing diseases such as dementia and Parkinson's disease. Owing to the shortcomings of current clinical assessments, noninvasive solutions are required. Machine learning (ML) on wearable sensor data is a promising method for the real-time monitoring and early detection of abnormalities. ML facilitates disease identification, severity measurement, and remote rehabilitation by providing continuous feedback. In the context of wearable sensor technology, ML involves training on observed data for tasks such as classification and regression with applications in clinical metrics. Although supervised ML presents challenges in clinical settings, unsupervised learning, which focuses on tasks such as cluster identification and anomaly detection, has emerged as a useful alternative. This review examines and discusses a variety of ML algorithms such as Support Vector Machines (SVM), Random Forests (RF), Decision Trees (DT), Neural Networks (NN), and Deep Learning for the analysis of complex clinical data.

• Asian-Australasian Journal of Animal Sciences
• /
• 제17권11호
• /
• pp.1608-1614
• /
• 2004

This study was performed to evaluate the accuracy, validation and applicability of UV spectrophotometer (UV), Ion Chromatography (IC), and Detector tube (DT) methods for measuring ammonia (NH3) concentration in a swine confinement house and swine slurry storage tank. The mean values of $NH_{3}$ emitted from the house and slurry were 5.333 ppm and 42.192 ppm for the IC method; 4.13 ppm and 36.29 ppm for the Detector tube; and 5.417 ppm and 34.193 ppm for the UV method. The accuracy and the correlation of an ammonia level analyzed by the IC method compared to the UV method were 98% and 0.998($R^{2}$) in the swine confinement house and 94% and 0.997($R^{2}$) in the swine slurry storage tank. On the other hand, those of ammonia level measured by the Detector tube compared to the UV method were 77% and 0.957($R^{2}$) in the swine confinement house and 82% and 0.941($R^{2}$) in the swine slurry storage tank. This indicated that the accuracy and the correlation of the IC method compared to the UV method were higher than those of the Detector tube method compared to the UV method. Therefore, it was concluded that the IC method was more accurate in measuring ammonia concentration in a swine house and a swine slurry storage tank. The Detector tube method should not be applied to the swine slurry storage tank in which ammonia concentration is generally higher than 30 ppm because low accuracy is caused by a gross space between scales inscribed in the Detector tube.

• 전기학회논문지
• /
• 제60권9호
• /
• pp.1770-1776
• /
• 2011

In this study, a new method that can estimate ICG data from a subject's both hands to measure Cardiac Output under convenient sensor environment. With this aim, a grip-type electrode was implemented to measure ICG. To improve the accuracy of measurement, the regression equation was extracted using multiple bio-parameters and our result was compared with the thoracic ICG equipment(Physio Flow$^{(R)}$, PF104D, Manatec Biomedical, France), which is being used in clinics. The subjects consist of 26 men and 4 women(age in $22.0{\pm}3.32$). They are no cardiac disease. Parameters available for regression model were used gender, BMI, MBP, LVET, dZ/dt(max), distance between the measured electrodes, body impedance, and PTT. As a result of analyzing the ICG measurement value on thorax and both hands, the correlation with stroke volume, heart rate, and cardiac output was $R^2$=0.853, $R^2$=0.958 and $R^2$=0.899, respectively.