• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 1998년도 추계종합학술대회 논문집
• /
• pp.1277-1280
• /
• 1998

We propose a structural learning method of MLP classifiers for a given application using PfSGA (parameter-free species genetic algorithm), which is a combining of species genetic algorithm(SGA) and parameter-free genetic algorithm(PfGA). experimental results show that PfSGA can reduce the learing time of SGA and has no influence of parameter values on structural learning. And we also convince that PfSGA is more efficient than the other methods in the aspect of misclassification ratio, learning rate, and complexity of MLP structure.

• Journal of Computing Science and Engineering
• /
• 제5권4호
• /
• pp.305-313
• /
• 2011

Due to the expansion of high-speed Internet access, the need for secure and reliable networks has become more critical. The sophistication of network attacks, as well as their severity, has also increased recently. As such, more and more organizations are becoming vulnerable to attack. The aim of this research is to classify network attacks using neural networks (NN), which leads to a higher detection rate and a lower false alarm rate in a shorter time. This paper focuses on two classification types: a single class (normal, or attack), and a multi class (normal, DoS, PRB, R2L, U2R), where the category of attack is also detected by the NN. Extensive analysis is conducted in order to assess the translation of symbolic data, partitioning of the training data and the complexity of the architecture. This paper investigates two engines; the first engine is the back-propagation neural network intrusion detection system (BPNNIDS) and the second engine is the radial basis function neural network intrusion detection system (BPNNIDS). The two engines proposed in this paper are tested against traditional and other machine learning algorithms using a common dataset: the DARPA 98 KDD99 benchmark dataset from International Knowledge Discovery and Data Mining Tools. BPNNIDS shows a superior response compared to the other techniques reported in literature especially in terms of response time, detection rate and false positive rate.

• 한국멀티미디어학회논문지
• /
• 제3권4호
• /
• pp.416-423
• /
• 2000

기존 Kohonen의 자기조직화 지도(self-organizing feature map)는 학습시 많은 입력 패턴이 필요하며 이에 따른 학습 시간 역시 증가하는 단점이 있다. 이러한 단점을 보완하기 위해 B. Bavarian은 위상학적 위치에 따라 각기 다른 학습률(learning rate)을 갖도록 하였으나 자기조직화가 정밀하게 되지 않는 단점을 갖고 있다. 본 논문에서는 자기조직화 지도의 학습시 계산량이 많은 가우시안 함수를 근사곡선(approximate curve)으로 변형하여 수렴속도를 향상시켰고 학습 횟수에 따라 근사곡선의 폭을 동적으로 변화시킴으로써 자기조직화지도의 수렴도를 개선하였다.

• 방사선산업학회지
• /
• 제17권4호
• /
• pp.551-557
• /
• 2023

In recent years, radiation has become a socially important issue, increasing the need for accurate prediction of radiation levels. In this study, machine learning-based models such as Multiple Linear Regression (MLR), Random Forest (RF), XGBoost, and LightGBM, which predict the dose rate by time(nSv h^-1) by selecting only important variables, were used, and the correlation between temperature, humidity, cumulative precipitation, wind direction, wind speed, local air pressure, sea pressure, solar radiation, and radiation dose rate (nSv h^-1) was analyzed by collecting weather data and radiation dose rate for about 6 months in Jangseong, Jeollanam-do. As a result of the evaluation based on the RMSE (Root Mean Squared Error) and R-Squared (R-Squared coefficient of determination) scores, the RMSE of the XGBoost model was 22.92 and the R-Squared was 0.73, showing the best performance among the models used. As a result of optimizing hyperparameters of all models using the GridSearch method and comparing them by adding variables inside the measuring instrument, it was confirmed that the performance improved to 2.39 for RMSE and 0.99 for R-Squared in both XGBoost and LightGBM.

• 디지털융복합연구
• /
• 제13권10호
• /
• pp.517-525
• /
• 2015

본 연구자는 TOEIC 블렌디드 학습을 운영하면서 면대면 학습과 학습효과를 비교할 필요성을 느꼈다. 학습효과가 떨어질 경우에는 블렌디드 학습을 중단하기 위해서였다. 따라서 본 연구자는 학습자들의 한 학기 동안의 성적 향상도, 학습자들의 자가진단 점수, 온라인 과제 참여도와 문제풀이 평균점수를 활용하여 두 학습을 비교하였다. 이러한 비교를 하기 위해 t-test, 피어슨 상관관계, 회귀분석을 실시하였다. 그 결과 큰 차이는 아니라 할지라도 블렌디드 학습이 면대면 학습보다 효과가 있는 것으로 나타났다. 그 이유는 블렌디드 학습의 학습자들이 오프라인 수업과 수업 게시판을 통해 교수자와 소통할 수 있는 반면, 매주 온라인 수업의 출석을 독려하는 문자를 받았으며, 학습자들의 온라인 수업의 참여가 온라인 과제 또한 적극적으로 참여할 수 있게 영향을 끼친 탓이라고 분석하였다. 이러한 연구결과는 향후 TOEIC 블렌디드 학습을 운영하고자 하는 교수자들에게 많은 참고가 될 것이다.

• 한국정보통신학회논문지
• /
• 제24권10호
• /
• pp.1341-1347
• /
• 2020

부정맥 분류를 위한 기존 연구들은 분류의 정확성을 높이기 위해 신경회로망(Artificial Neural Network), 기계학습(Machine Learning) 등을 이용한 방법이 연구되어 왔다. 특히 딥러닝은 신경회로망의 문제인 은닉층 개수의 한계를 해결함으로 인해 인공 지능 기반의 부정맥 분류에 많이 사용되고 있다. 본 연구에서는 AR 기반의 특징점 추출과 딥러닝을 통한 부정맥 분류 방법을 제안한다. 이를 위해 먼저 잡음을 제거한 ECG 신호에서 R파를 검출하고 자기 회귀 모델을 통하여 최적의 QRS와 RR간격을 추출하였다. 이후 딥러닝을 통한 지도학습 방법으로 가중치를 학습시키고 부정맥을 분류하였다. 제안된 방법의 타당성 평가를 위해 MIT-BIH 부정맥 데이터베이스를 통해 각 파라미터에 따른 훈련 및 분류 정확도를 확인하였다. 성능 평가 결과 PVC는 약 97% 이상의 평균 분류율을 나타내었다.

• 한국정보통신학회논문지
• /
• 제25권8호
• /
• pp.1046-1052
• /
• 2021

4차 산업의 발전과 고성능의 컴퓨팅 환경 구축으로 다양한 산업분야에서 인공지능이 적용되고 있다. 의료분야에서는 X-Ray, MRI, PET 등의 의료 영상 및 임상 자료를 이용하여 암, COVID-19, 골 연령 측정 등의 딥 러닝 학습이 진행되었다. 또한 스마트 의료기기, IoT 디바이스와 딥 러닝 알고리즘을 적용하여 ICT 의료 융합 기술 등이 연구되고 있다. 이러한 기술 중 의료 영상 기반 딥 러닝 학습은 의료 영상의 바이오마커를 정확히 찾아내고, 최소한의 손실률과 높은 정확도가 필요하다. 따라서 본 논문은 흉부 X-Ray 이미지 기반 딥 러닝 학습 과정에서 손실률을 도출하는 손실 함수 중 영상분류 알고리즘에서 사용되는 Cross-Entropy 함수들의 성능을 비교·분석하고자 한다.

• International Journal of Computer Science & Network Security
• /
• 제22권3호
• /
• pp.77-88
• /
• 2022

In response to the significant COVID-19 outbreak, countries have enforced the use of E-learning systems as an alternative to traditional learning; to contain the virus and minimize the infection rate while maintaining the continuity of the learning experience. However, the effective adoption of E-learning systems requires a well-understanding of critical factors, especially in times of crisis. In this regard, this study intends to assess the success of the E-learning system adoption by Higher Education Institutions (HEIs) during the crisis of COVID-19 by utilizing the Information Systems Success (ISS) model. This study's adopted model consists of nine interdependent dimensions, namely: Technical System Quality, Information Quality, Service Quality, Learner Quality, Perceived Satisfaction, Perceived Usefulness, System Use, Intention to Use, and System Success. An electronic survey was distributed among higher education students from different universities in Saudi Arabia to explore each model's dimension. Structural Equation Modeling (SEM) has been applied via SmartPLS software to test the causal relationships between dimensions. This study's main results revealed that students' Service Quality, Learner Quality, and the Intention to Use by students are essential drives for E-learning System Use during the Covid-19 pandemic. Meanwhile, the Intention to Use the system is significantly influenced by Perceived Satisfaction and Perceived Usefulness dimensions. Further, Perceived Satisfaction, Perceived Usefulness, and System Use are interdependent, and all three have a significant positive impact on E-learning System Success.

• The Journal of Asian Finance, Economics and Business
• /
• 제9권5호
• /
• pp.455-463
• /
• 2022

The current study adds to the body of knowledge about the mediation in the causal link between students' perceptions of the utility of eLearning and their learning performance. The data was collected from 500 questionnaires that were delivered to the students at the Vietnam National University of Ho Chi Minh City. Only 422 finished questionnaires were usable for analyses, indicating a responding rate of 84.4%. Multiple regressions were used to investigate causal correlations, whereas Goodman's (1960) techniques were used to investigate mediating relationships. The major findings reveal that both the utility and adoption of eLearning have an impact on students' learning performance, with usefulness being a crucial determinant of eLearning adoption for study. More meaningfully, statistical evidence on the mediation of adopting eLearning for study in the causal linkage from the usefulness of eLearning perceived by students to their learning performance was provided. The relevance of using eLearning for study is stressed in this study, where it is not only one of the key antecedents of their learning performance, but also acts as a mediator between the usefulness of eLearning and learning performance in the research model.

• 한국컴퓨터정보학회:학술대회논문집
• /
• 한국컴퓨터정보학회 2022년도 제66차 하계학술대회논문집 30권2호
• /
• pp.713-715
• /
• 2022

Video learning through YouTube has emerged as one of the most widely used instructional methods, yet relatively little research has been conducted on YouTube video users' willingness to use or behavior, so it is important to examine how to make and keep users' willingness to continue learning and to improve their retention rate for effective online learning. With reference to perceived value theory and utilizing an ECM perspective, the authors construct a model of YouTube video continuous learning intention and investigate the influence of perceived value and satisfaction on users' willingness to use YouTube videos for continuous learning.