• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2015년도 춘계학술대회
• /
• pp.421-422
• /
• 2015

최근 신경망 분석의 향상된 성능을 보여주는 심화 신경망 기술인 딥 러닝(Deep learning)이 각광을 받고 있는 실정이다. 이에 본 논문에서는 딥 러닝을 기반으로 분석 시각화 툴인 R을 이용한 특정 변수의 오류율 검증과 빅 데이터 예측 프로세스 설계를 제안한다. 딥 러닝에 적용된 알고리즘은 RBM(Restricted Boltzmann Machine)을 적용하였다. 특정 입력 변수에 대한 종속 변수 구분 후 각 종속 변수의 가중치를 적용한다. RBM 알고리즘을 통해 최종 데이터의 검증 및 오류율 검출과정을 R 프로그래밍에 적용하여 설계한다.

• International Journal of Computer Science & Network Security
• /
• 제22권3호
• /
• pp.276-284
• /
• 2022

The research aims to study the dynamics of academic procrastination and its impact on the mental health of students during the transition to distance learning during the COVID-19 pandemic. At the beginning of the COVID-19 pandemic, it was identified a declining tendency of overall rates of academic procrastination and at the same time increase in the number of carriers of mid and high levels of academic procrastination. The decline in the general rates of academic procrastination at the beginning of 2021 testifies to the adaptation processes experienced by students to the conditions of distance learning. It was documented that students' academic procrastination is accompanied by a steady negative emotional tension. During the transition to distance learning, the intensity of students' learning activity has increased, which altogether causes stress as one of the main reasons for the academic procrastination among future psychologists. The study identified a risk of academic procrastination manifestation among students for their mental health, which provides a basis for developing and testing a program to prevent the phenomenon of academic procrastination among degree-seeking students.

• 경영과학
• /
• 제28권1호
• /
• pp.53-60
• /
• 2011

Time series analysis methods have been traditionally used in stock price prediction. However, most of the existing methods represent some methodological limitations in reflecting influence from external factors that affect the fluctuation of stock prices, such as oil prices, exchange rates, money interest rates, and the stock price indexes of other countries. To overcome the limitations, we propose a network based method incorporating the relations between the individual company stock prices and the external factors by using a graph-based semi-supervised learning algorithm. For verifying the significance of the proposed method, it was applied to the prediction problems of company stock prices listed in the KOSPI from January 2007 to August 2008.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2003년도 ICCAS
• /
• pp.316-321
• /
• 2003

This paper presents a design method of the wavelet neural network based controller using direct adaptive control method to deal with a stable intelligent control of chaotic systems. The various uncertainties, such as mechanical parametric variation, external disturbance, and unstructured uncertainty influence the control performance. However, the conventional control methods such as optimal control, adaptive control and robust control may not be feasible when an explicit, faithful mathematical model cannot be constructed. Therefore, an intelligent control system that is an on-line trained WNN controller based on direct adaptive control method with adaptive learning rates is proposed to control chaotic nonlinear systems whose mathematical models are not available. The adaptive learning rates are derived in the sense of discrete-type Lyapunov stability theorem, so that the convergence of the tracking error can be guaranteed in the closed-loop system. In the whole design process, the strict constrained conditions and prior knowledge of the controlled plant are not necessary due to the powerful learning ability of the proposed intelligent control system. The gradient-descent method is used for training a wavelet neural network controller of chaotic systems. Finally, the effectiveness and feasibility of the proposed control method is demonstrated with application to the chaotic systems.

• 한국정보처리학회논문지
• /
• 제5권10호
• /
• pp.2609-2614
• /
• 1998

본 연구에서는 신경망 모형을 이용한 시계열 예측에 있어서 분석할 시계열의 특성에 맞는 적응적 학습률을 구하고 초기 값의 동적인 적용을 통한 개선된 학습방법을 이용하여 신경망 예측을 하고 통계적인 Box-Jenkins예측 결과와 비교해 봄으로써 두 방법간의 시계열 예측 효율성을 비교한다. 신경망 모형에 맞는 적응적 학습률은 표준 직교 배열표에 의해 실험계획을 한 25가지의 모수 조합으로부터 구하고, 신경망 학습의 초기값은 Easton의 제어상자를 동적으로 적용하여 실시간으로 선택할 수 있도록한다. 실증분석에 적용된 시계열자료는 1700년부터 1988년까지의 태양 흑점 자료이다.

• Journal of Korean Dental Science
• /
• 제16권1호
• /
• pp.47-62
• /
• 2023

Purpose: We aimed to investigate the objective cutoff values of unstimulated flow rates (UFR) and stimulated salivary flow rates (SFR) in patients with xerostomia and to present an optimal machine learning model with a classification and regression tree (CART) for all ages. Materials and Methods: A total of 829 patients with oral diseases were enrolled (591 females; mean age, 59.29±16.40 years; 8~95 years old), 199 patients with xerostomia and 630 patients without xerostomia. Salivary and clinical characteristics were collected and analyzed. Result: Patients with xerostomia had significantly lower levels of UFR (0.29±0.22 vs. 0.41±0.24 ml/min) and SFR (1.12±0.55 vs. 1.39±0.94 ml/min) (P<0.001), respectively, compared to those with non-xerostomia. The presence of xerostomia had a significantly negative correlation with UFR (r=-0.603, P=0.002) and SFR (r=-0.301, P=0.017). In the diagnosis of xerostomia based on the CART algorithm, the presence of stomatitis, candidiasis, halitosis, psychiatric disorder, and hyperlipidemia were significant predictors for xerostomia, and the cutoff ranges for xerostomia for UFR and SFR were 0.03~0.18 ml/min and 0.85~1.6 ml/min, respectively. Conclusion: Xerostomia was correlated with decreases in UFR and SFR, and their cutoff values varied depending on the patient's underlying oral and systemic conditions.

• International Journal of Internet, Broadcasting and Communication
• /
• 제12권3호
• /
• pp.108-115
• /
• 2020

Blended learning is a teaching method utilizing all the advantages in 'on and off-line' learning circumstances in order to enhance the learning effect and efficiency, more than the simple use of online factors in the classroom education. In this paper, we present the realization and simulation of algorithm for the realtime evaluation of low-grade and high-grade subjects in order to implement smart e-learning system, considering a lecture intelligibility. In order to grasp the levels of student's intelligibility, we simulated a function that automatically summarizes the study contents of class given by a lecturer. Especially, in administrator mode of smart e-learning system, we suggested and simulated a system in order to help the lecturer to easily manage the student's grades, and we have provided software to tell the student's intelligibility of lecture, analyzed the rate of incorrect answers, automatic judgment of lecture intelligibility and judge the weakest subject.

• 한국지능시스템학회논문지
• /
• 제17권4호
• /
• pp.472-476
• /
• 2007

학습법칙은 신경회로망의 성능에 중요한 영향을 미친다. 본 논문은 데이터와 클래스들의 대표값들 사이의 거리를 고려하여 학습률을 정하는 새로운 퍼지 학습법칙을 제안한다. 클래스들의 대표값을 조정할 때, 이러한 고려는 outlier에 비하여 결정경계선 근처에 있는 데이터의 반영도를 높임으로써 outlier의 클래스의 대표값에 미치는 영향도를 낮출 수 있다. 따라서 outlier들이 결정경계선을 악화시키는 것을 방지할 수 있다. 이 새로운 퍼지 학습법칙을 IAFC(Integrated Adaptive Fuzzy Clustering) 신경회로망에 적용하였다. 제안한 퍼지 신경회로망과 다른 감독 신경회로망들의 성능을 비교하기 위하여 iris 데이터를 사용하였다. iris 데이터를 사용하여 테스트한 결과 제안한 퍼지 신경회로망의 성능이 우수함을 보였다.

• 미생물학회지
• /
• 제49권1호
• /
• pp.51-57
• /
• 2013

대학 구내 학습시설과 집기들은 다중에 의해 이용되기 때문에 그 표면들은 감염성 병원체의 교차감염의 경로로 작용할 수 있다. 그러나 구내 집단급식소 등의 주요 위생관리 시설과 달리 정기적 위생관리의 대상이 아니며, 위생상태 현황이 잘 파악되지 않고 있다. 본 연구는 한 대학 단과대학 1,500여 명의 학생들이 강의실, 도서관 등 학습시설을 이용하면서 병원체에 노출될 수 있는 미생물학적 위해도를 구내급식소에서 집기 접촉을 통해 위해도와 정량적으로 비교하였다. 총대장균군을 병원성의 미생물의 대리모델로 간주하고, 학생들이 공통적으로 이용하는 대학구내 집기별로, 표면의 세균농도에 접촉률, 전이율 등을 적용한 노출알고리즘을 설정하여 결정론적 방법에 의한 노출량을 산정하였다. 급식소 집기의 세균에 대한 노출량은 약 1.0 CFU/day이었으며, 학습시설의 세균에 대한 노출량은 0.5 CFU/day로 급식소에서 노출량의 절반에 해당하였다. 그러나, 개인별 급식소 이용 정도가 달라, 약 70%의 학생들은 급식시설보다 학습시설의 인체접촉면에서 교차감염에 더 많이 노출되는 것으로 나타났다. 결론적으로, 승강기버턴을 비롯한 일부 학습 시설의 인체접촉면은 급식소와 마찬가지로 주기적 위생관리를 필요로 하는 것으로 판단되며, 학생들의 개인위생 관리 이외에, 계절적으로 변동하는 교차감염 가능 병원체의 종류에 부합하도록 인체접촉면 위생관리를 효율적으로 실시하는 것이 권고된다.

• 한국과학교육학회지
• /
• 제12권3호
• /
• pp.61-76
• /
• 1992

The purpose of this study was to develop the instructional model and teaching material to change the middle school students'conceptions of electric current into the scientific ones and to investigate the effects of the model in actual classrooms. We identified the students' ideas and their misunderstanding about the concept of eIectic current through reviewing the literatures and our in this study. Based on the above results, we developed the instructional model and designed the teaching sequence and prepare the learning materials about the unit of the electric current in middle school Our instructional model was based on 'learning cycle' developed by Lawson, but the new stage called "exploration through qualitative questions" to elicit the students' own conceptions was inserted to it. To investigate the effects or the new teaching model, the pre- and post-test using the POE type were administered to experimental group(52 students) taught with learning cycles and control group(52 students) taught with traditional styles. The results are as follows; 1) The rates of correct. predictions was varying according to the kinds of problems. And the rates of the correct. reasons of their predictions were lower than those of the predictions. 2) The mean scores of the post-test of both groups were significantly higher than those of the pre-test. We could not find statistically significant difference in theme an score between experimental group and control group after implementation of the model. But the experimental group gained higher scores than those of the control group on two problem. Therefore, although we cannot show the prominent effects of our teaching model based on learning cycles, there are some effects of our model on changing the middle school students' conceptions of electric current.