• 대한의용생체공학회:의공학회지
• /
• 제43권4호
• /
• pp.185-192
• /
• 2022

Early detection of mild cognitive impairment can help prevent the progression of dementia. The purpose of this study was to design and validate a machine learning model that automatically differential diagnosed patients with mild cognitive impairment and identified cognitive decline characteristics compared to a control group with normal cognition using resting-state quantitative electroencephalogram (qEEG) with eyes closed. In the first step, a rectified signal was obtained through a preprocessing process that receives a quantitative EEG signal as an input and removes noise through a filter and independent component analysis (ICA). Frequency analysis and non-linear features were extracted from the rectified signal, and the 3067 extracted features were used as input of a linear support vector machine (SVM), a representative algorithm among machine learning algorithms, and classified into mild cognitive impairment patients and normal cognitive adults. As a result of classification analysis of 58 normal cognitive group and 80 patients in mild cognitive impairment, the accuracy of SVM was 86.2%. In patients with mild cognitive impairment, alpha band power was decreased in the frontal lobe, and high beta band power was increased in the frontal lobe compared to the normal cognitive group. Also, the gamma band power of the occipital-parietal lobe was decreased in mild cognitive impairment. These results represented that quantitative EEG can be used as a meaningful biomarker to discriminate cognitive decline.

• 한국산업정보학회논문지
• /
• 제14권3호
• /
• pp.106-113
• /
• 2009

본 논문에서는 통계적 분류방법을 이용하여 문화재 자료의 분석을 수행하였다. 분류방법으로는 선형판별분석, 로지스틱회귀분석, 의사결정나무분석, 신경망분석, SVM분석을 사용하였다. 각각의 분류방법에 대한 개념 및 이론에 대해 간략히 소개하고, 실제자료 분석에서는 국내 I시 자료를 사용하여 매장문화재에 대한 분류방법별 적합모형을 구축하였다. 구축된 모형에 대한 성능비교와 함께, 새로운 자료에 대한 적용성 평가를 위해 모의실험을 수행하였다. 분석에 사용된 도구로는 최근 가장 관심을 갖는 R 언어를 사용하였으며, 구체적 분석과정을 제시하였다.

• 한국도서관정보학회지
• /
• 제48권2호
• /
• pp.215-236
• /
• 2017

이 연구의 목적은 개인별 성향이나 성격 유형에 따라 선호하는 도서에 차이가 있음을 전제로, 어린이 청소년을 위한 추천도서의 책소개 정보를 활용하여 개인별 성격유형에 적합한 도서를 합리적으로 추천할 수 있는 서평 자동분류시스템을 개발하는 것이다. 연구에서 사용한 데이터는 국립어린이청소년도서관에서 제공하는 501권의 유아 및 아동도서를 대상으로 하였다. 실험에 활용된 2가지 기계학습 모델(비선형 커널 및 선형 커널) 각각에 대해서 총 6가지의 색인어 가중치 계산 방법과 자질 선택 방법, 그리고 10가지의 자질 선정 임계치 조합으로 구성된 360개의 분류 모델들을 구성하고 각각의 성능을 측정하였다. 전체적으로는 선형 커널을 이용한 SVM 기반 학습 방법(LIBLINEAR)이 비선형 분류를 지원하는 LibSVM(RBF 커널) 모델보다 더 나은 성능을 보이는 것으로 나타났다. 다만 성능 측정 결과는 뉴스 기사나 논문을 대상으로 한 문헌 분류 성능에 비해서 낮은 것으로 나타났으나, 합리적인 분류 기준이 존재하는 뉴스기사나 주제 분류에 비해서 성격 유형 기반 분류는 그 난이도가 높다는 것을 감안할 때, 초기 실험 결과로서의 의미는 있다.

• 대한인간공학회지
• /
• 제30권6호
• /
• pp.705-713
• /
• 2011

Objective: The aim of this study is to compare results of emotion recognition by several algorithms which classify three different emotional states(happiness, neutral, and surprise) using physiological features. Background: Recent emotion recognition studies have tried to detect human emotion by using physiological signals. It is important for emotion recognition to apply on human-computer interaction system for emotion detection. Method: 217 students participated in this experiment. While three kinds of emotional stimuli were presented to participants, ANS responses(EDA, SKT, ECG, RESP, and PPG) as physiological signals were measured in twice first one for 60 seconds as the baseline and 60 to 90 seconds during emotional states. The obtained signals from the session of the baseline and of the emotional states were equally analyzed for 30 seconds. Participants rated their own feelings to emotional stimuli on emotional assessment scale after presentation of emotional stimuli. The emotion classification was analyzed by Linear Discriminant Analysis(LDA, SPSS 15.0), Support Vector Machine (SVM), and Multilayer perceptron(MLP) using difference value which subtracts baseline from emotional state. Results: The emotional stimuli had 96% validity and 5.8 point efficiency on average. There were significant differences of ANS responses among three emotions by statistical analysis. The result of LDA showed that an accuracy of classification in three different emotions was 83.4%. And an accuracy of three emotions classification by SVM was 75.5% and 55.6% by MLP. Conclusion: This study confirmed that the three emotions can be better classified by LDA using various physiological features than SVM and MLP. Further study may need to get this result to get more stability and reliability, as comparing with the accuracy of emotions classification by using other algorithms. Application: This could help get better chances to recognize various human emotions by using physiological signals as well as be applied on human-computer interaction system for recognizing human emotions.

• Journal of Power Electronics
• /
• 제15권1호
• /
• pp.190-201
• /
• 2015

This paper uses the switching function approach to present a simple state model of the Vienna-type rectifier. The approach introduces the relationship between the DC-link neutral point voltage and the AC side phase currents. A novel direct power control (DPC) strategy, which is based on the sliding mode control (SMC) for Vienna I rectifiers, is developed using the proposed power model in the stationary ${\alpha}-{\beta}$ reference frames. The SMC-based DPC methodology directly regulates instantaneous active and reactive powers without transforming to a synchronous rotating coordinate reference frame or a tracking phase angle of grid voltage. Moreover, the required rectifier control voltages are directly calculated by utilizing the non-linear SMC scheme. Theoretically, active and reactive power flows are controlled without ripple or cross coupling. Furthermore, the fixed-switching frequency is obtained by employing the simplified space vector modulation (SVM). SVM solves the complicated designing problem of the AC harmonic filter. The simplified SVM is based on the simplification of the space vector diagram of a three-level converter into that of a two-level converter. The dwelling time calculation and switching sequence selection are easily implemented like those in the conventional two-level rectifier. Replacing the current control loops with power control loops simplifies the system design and enhances the transient performance. The simulation models in MATLAB/Simulink and the digital signal processor-controlled 1.5 kW Vienna-type rectifier are used to verify the fast responses and robustness of the proposed control scheme.

• 한국정보통신학회논문지
• /
• 제11권8호
• /
• pp.1596-1603
• /
• 2007

본 논문에서는 음성인식 시스템을 구현함에 있어 중요한 특징 파라미터와 학습, 인식 알고리즘의 선택을 위한 제안을 하기 위하여 각각 세 가지의 방법을 조합하여 인식 실험을 수행하고 검토하였다. 두 종류의 실험을 통하여 하드웨어 장치로 구현할 경우 보다 효과적인 음성 인식 시스템을 제안한다. 첫 번째로는 특징 파라미터의 성능을 평가하기 위하여 기존의 MFCC와 MFCC를 PCA와 ICA를 이용하여 특징 공간을 변화시킨 새로운 특징 파라미터를 제안하여 총 3종류의 특징파라미터에 대한 인식 실험을 수행하였으며, 두 번째로는 학습데이터 수에 따른 HMM, SVM, RVM의 인식 성능을 실험하였다. 이상의 실험에 의하여 ICA에 의한 특징 파라미터가 특징 공간상에서의 높은 선형 분별성에 의해 MFCC와 비교하여 평균 1.5%의 성능향상을 확인할 수 있었으며 학습데이터의 감소에 따른 인식실험에서는 HMM과 비교하여 RVM에서 최고 3.25%의 성능향상을 확인하였다. 이에 근거하여 TI사의 DSP(TMS320C32)를 사용하여 음성 인식기를 구현하여 실시간으로 실험하여 시뮬레이션과 비교하였다. 이와 같은 결과로서 본 논문에서 제안하는 음성인식시스템을 위한 효과적인 방법은 ICA를 이용한 특징 파라미터를 추출하고 RVM을 이용하여 인식을 수행하는 것이라 판단한다.

• 한국멀티미디어학회논문지
• /
• 제23권7호
• /
• pp.870-882
• /
• 2020

It is that failure of equipment at the factory site causes personal injury and property damage. We are required a real-time monitoring and risk forecasting techniques to prevent for equipment failure. In this paper, we proposed a 3-phase smart plug and real-time monitoring system that can be used in factories, and collected environmental information and power information using a smart plug to analyze the data. In order to analyze the correlation between the risk situation and the collected data, we predicted the risk situation using Linear Regression, SVM, and ANN algorithms. As a result, the SVM and ANN algorithms obtained high predictive accuracy and developed a mobile app that could use it to check the risk forecast results.

• 한국정보시스템학회지:정보시스템연구
• /
• 제26권3호
• /
• pp.273-293
• /
• 2017

Purpose The purpose of this study is to introduce a framework that helps Muslims to determine whether a food can be consumed. It can complement existing Halal food classification services having a difficulty of constructing Halal food database. Design/methodology/approach The proposed framework includes two components. First, OCR(Optical Character Recognition) technique is utilized to read the food additive information. Second, machine learning methods were used to trained and predicted to determine whether a food can be consumed using the provided information. Findings Among the compared machine learning methods, SVM(Support Vector Machine), DT(Decision Tree), and NB(Naive Bayes), SVM with linear kernel and DT had excellent performance in the Halal food classification. The framework which adopting the proposed framework will enhance the tourism experiences of Muslim tourists who consider keeping the Islamic law most importantly. Furthermore, it can eventually contribute to the enhancement of smart tourism ecosystem.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2016년도 춘계학술발표대회
• /
• pp.612-615
• /
• 2016

본 논문에서는 EPIC(Electric Potential Integrated Circuit) 센서를 통해 추출된 동작신호에 대해 이산 웨이블릿 변환（Discrete Wavelet Transform : DWT)과 선형 판별분석（Linear Discriminant Analysis : LDA), Support Vector Machine(SVM)을 사용하는 동작 분류 시스템을 제안한다. EPIC 센서 신호에 대해 이산 웨이블릿 변환을 사용하여 웨이블릿 계수인 근사계수(approximation coefficients)와 상세계수(detail coefficients)를 구한 후, 각각의 웨이블릿 계수에 대해 특징 파라미터를 추출한다. 이 때, 특징 파라미터는 14개의 통계적 특징 추출 파라미터 중에 유전자 알고리즘(Genetic Algorithm : GA)을 통하여 선택한 우수한 특징 파라미터이다. 웨이블릿 계수들에서 추출한 특징 파라미터는 선형 판별분석을 적용하여 차원을 축소하고 SVM의 훈련 및 분류에 사용한다. 실험결과, 4가지 동작에 대한 EPIC 센서 신호분류에서 제안된 방법의 분류율이 99.75%로 원신호에 대한 HMM 분류율 97% 보다 높은 정확률을 보여주었다.

• Computers and Concrete
• /
• 제11권4호
• /
• pp.337-350
• /
• 2013

The sensitivity of compressive strength of no-slump concrete to its ingredient materials and proportions, necessitate the use of robust models to guarantee both estimation and generalization features. It was known that the problem of compressive strength prediction owes high degree of complexity and uncertainty due to the variable nature of materials, workmanship quality, etc. Moreover, using the chemical and mineral additives, superimposes the problem's complexity. Traditionally this property of concrete is predicted by conventional linear or nonlinear regression models. In general, these models comprise lower accuracy and in most cases they fail to meet the extrapolation accuracy and generalization requirements. Recently, artificial intelligence-based robust systems have been successfully implemented in this area. In this regard, this paper aims to investigate the use of optimized support vector machine (SVM) to predict the compressive strength of no-slump concrete and compare with optimized neural network (ANN). The results showed that after optimization process, both models are applicable for prediction purposes with similar high-qualities of estimation and generalization norms; however, it was indicated that optimization and modeling with SVM is very rapid than ANN models.