• 제어로봇시스템학회논문지
• /
• 제7권12호
• /
• pp.985-992
• /
• 2001

This paper proposes a self-organizing fuzzy modeling(SOFUM)which an create a new hyperplane shaped cluster and adjust parameters of the fuzzy model in repetition. The suggested algorithm SOFUM is composed of four steps: coarse tuning. fine tuning cluster creation and optimization of learning rates. In the coarse tuning fuzzy C-regression model(FCRM) clustering and weighted recursive least squared (WRLS) algorithm are used and in the fine tuning gradient descent algorithm is used to adjust parameters of the fuzzy model precisely. In the cluster creation, a new hyperplane shaped cluster is created by applying multiple regression to input/output data with relatively large fuzzy entropy based on parameter tunings of fuzzy model. And learning rates are optimized by utilizing meiosis-genetic algorithm in the optimization of learning rates To check the effectiveness of the suggested algorithm two examples are examined and the performance of the identified fuzzy model is demonstrated via computer simulation.

• 대한의용생체공학회:의공학회지
• /
• 제17권3호
• /
• pp.395-401
• /
• 1996

In this paper a new neural network model, time delayed counterpropagation neural networks (TDCPN) which have high recognition rate and short total learning time, is proposed for electromyogram(EMG) recognition. Signals the proposed model increases the recognition rates after learned the regional temporal correlation of patterns using time delay properties in input layer, and decreases the learning time by using winner-takes-all learning rule. The ouotar learning rule is put at the output layer so that the input pattern is able to map a desired output. We test the performance of this model with EMG signals collected from a normal subject. Experimental results show that the recognition rates of the suggested model is better and the learning time is shorter than those of TDNN and CPN.

• 지적과 국토정보
• /
• 제49권1호
• /
• pp.65-84
• /
• 2019

본 연구의 목적은 기계학습 알고리즘을 이용하여 주택모기지 금리에 대한 시민들의 감정을 예측하는 것이었다. 연구목적을 달성하기 위해 본 연구는 관련문헌을 검토한 다음 두개의 연구 질문을 설정하였다. 또한 연구 질문에 대한 답을 구하기 위해 본 연구는 Akman의 분류에 따라 감정을 분류 한 다음 여섯 가지 기계학습 알고리즘을 이용하여 모기지 금리에 대한 시민들의 감정을 예측하였다. 분석결과 AdaBoost가 모든 평가범주에서 가장 우수한 분류기로 확인되었다. 그러나 Naive Bayes의 성능수준은 다른 분류기들의 성능수준보다 낮은 것으로 밝혀졌다. 또한 본 연구는 어느 분류기가 각 감정범주를 잘 예측해주는지를 파악하기 위해 ROC 분석을 실시하였다. 분석결과, AdaBoost가 모든 감정범주에서 주택모기지 금리에 대한 주민들의 감정을 가장 잘 예측해주는 것으로 확인되었다. 그러나 슬픔범주에서 여섯 가지 알고리즘의 성능수준은 다른 감정범주보다 훨씬 낮게 나타났다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제18권2호
• /
• pp.494-510
• /
• 2024

Internet users are exposed to sophisticated cyberattacks that intrusion detection systems have difficulty detecting. Therefore, research is increasing on intrusion detection methods that use artificial intelligence technology for detecting novel cyberattacks. Unsupervised learning-based methods are being researched that learn only from normal data and detect abnormal behaviors by finding patterns. This study developed an anomaly-detection method based on unsupervised machines and deep learning for a network intrusion detection system (NIDS). We present a hybrid anomaly detection approach based on unsupervised learning techniques using the autoencoder (AE), Isolation Forest (IF), and Local Outlier Factor (LOF) algorithms. An oversampling approach that increased the detection rate was also examined. A hybrid approach that combined deep learning algorithms and traditional machine learning algorithms was highly effective in setting the thresholds for anomalies without subjective human judgment. It achieved precision and recall rates respectively of 88.2% and 92.8% when combining two AEs, IF, and LOF while using an oversampling approach to learn more unknown normal data improved the detection accuracy. This approach achieved precision and recall rates respectively of 88.2% and 94.6%, further improving the detection accuracy compared with the hybrid method. Therefore, in NIDS the proposed approach provides high reliability for detecting cyberattacks.

• 대한기계학회논문집
• /
• 제18권10호
• /
• pp.2567-2576
• /
• 1994

In this paper we propose a new method to determine the learning rates of fuzzy learning algorithm(FLA) in nonlinear MIMO system. The state feedback gains are used from the linearized system of the nonlinear MIMO system. Through this method, it is easy to determine the learing rates. And it is quarauteed the good convergence and confirmed the performance of FLA is better than that of linear controller(LC) through the simulation. Acrobatic robot system is selected as an example(one-input two-output system), and FLA is implemented through the experiment.

• 산업경영시스템학회지
• /
• 제47권1호
• /
• pp.41-50
• /
• 2024

Korea is facing a significant problem with historically low fertility rates, which is becoming a major social issue affecting the economy, labor force, and national security. This study analyzes the factors contributing to the regional gap in fertility rates and derives policy implications. The government and local authorities are implementing a range of policies to address the issue of low fertility. To establish an effective strategy, it is essential to identify the primary factors that contribute to regional disparities. This study identifies these factors and explores policy implications through machine learning and explainable artificial intelligence. The study also examines the influence of media and public opinion on childbirth in Korea by incorporating news and online community sentiment, as well as sentiment fear indices, as independent variables. To establish the relationship between regional fertility rates and factors, the study employs four machine learning models: multiple linear regression, XGBoost, Random Forest, and Support Vector Regression. Support Vector Regression, XGBoost, and Random Forest significantly outperform linear regression, highlighting the importance of machine learning models in explaining non-linear relationships with numerous variables. A factor analysis using SHAP is then conducted. The unemployment rate, Regional Gross Domestic Product per Capita, Women's Participation in Economic Activities, Number of Crimes Committed, Average Age of First Marriage, and Private Education Expenses significantly impact regional fertility rates. However, the degree of impact of the factors affecting fertility may vary by region, suggesting the need for policies tailored to the characteristics of each region, not just an overall ranking of factors.

• International Journal of Contents
• /
• 제5권2호
• /
• pp.1-5
• /
• 2009

This study was to analyze important dimensions and its factors of micro level of e-learning determining the quality of e-learning. E-learning dimensions and their factors were identified and developed from the analytical review of related researches. From literature review and survey as well as expert interview, six categories of e-learning identified from this study were: 1) curriculum content, 2) usability, 3) instructional design, 4) evaluation -both process and results, 5) management, and 6) refinement and improvement. A total of thirty-seven factors determining the quality of the e-learning six categories were identified. The rank order and contribution rates for each categories and factors were calculated to explain how importantly they contribute to the quality of e-learning. Also three dimensions such as controlling the e-learning quality, e-learning fundamental dimension e-learning process dimension, and e-learning product dimension, were explained. This study suggests a useful guidance for e-learning quality and evaluation framework for better results.

• 한국수학교육학회지시리즈C:초등수학교육
• /
• 제17권1호
• /
• pp.1-16
• /
• 2014

본 연구는 유추 거리 및 수학적 지식과 학습의 전이 사이의 관계를 규명하기 위해 수행되었다. 구체적으로 유추적 거리에 따라 구분된 세 가지 전이 문제 해결에서 차이를 보이는지, 그리고 각 전이 문제를 성공적으로 해결하는데 기여하는 수학적 지식은 무엇인지를 분석하였다. 분석 결과 세 가지 종류의 전이 문제 해결에서 통계적으로 유의한 차이를 보였으며 유추 거리가 증가할수록 성공률은 점차적으로 감소하였다. 또한 사실 지식 보다는 개념적 지식이 전이 문제를 해결하는데 긍정적으로 기여하였다. 이상의 결과를 토대로 본 연구는 학습의 전이를 위해 수학 수업은 어떠한 점에 초점을 맞추어야 하는지, 그리고 유추 거리라는 새로운 구인을 찾고 그것이 전이에 미치는 영향을 실증적으로 규명했다는 점에서 의의를 찾을 수 있었다.

• 대한교통학회지
• /
• 제22권5호
• /
• pp.111-122
• /
• 2004

본 연구에서는 운전자들의 경로선택 행태에서 교통정보 수신율이 네트워크 전반에 미치는 영향과 각 경로의 주행조건에 대한 운전자의 학습과정에 대해서 살펴보았으며, 교통상황이 정상성 및 비정상성을 따르는 경우, 공공기관의 유입교통량의 대소에 의해 유도되는 정보의 수신율이 증가함으로써 운전자의 경로선택행동이 네트워크에 미치는 영향을 분석하고 정보의 역효과가 나타남을 밝혔다. 또한, 정보수신율이 최적비율 이하인 경우에는 총통행시간이 정보가 없이 오직 자신의 경험에만 의존하는 경우보다 감소하여 정보제공의 효과가 있었지만, 최적비율 이상으로 유동정보에 따라 경로선택을 하는 운전자가 많아지면 정보의 역효과가 발생함도 증명하였다. 나아가, 교통환경이 정상성을 /따르는 경우에는 모든 운전자의 경로조건에 대한 학습과정과 이 경험을 축적함에 따라 어느 일정한 값으로 수렴해감을 알 수 있었다. 교통환경이 비정상성을 따르는 경우에는 주행조건에 대해 돌발적인 진동과 혼란상태가 발생하고 이 경우에도 무정보 환경보다는 어느정도의 비율로 유도정보가 주어지는 것이 네트워크 전체의 통행시간을 감소시킴으로써 정보의 효과가 있음도 확인하였다. 향후, 다양한 교통류 환경을 적용한 대규모 네트워크를 대상으로 한 운전자의 경로선택과 학습행동에 대한 연구와 정보의 정도에 따른 운전자의 행동을 고려한 정보의 제공방안에 대한 연구도 필요할 것으로 판단된다.

• International Journal of Control, Automation, and Systems
• /
• 제6권4호
• /
• pp.526-533
• /
• 2008

We propose a wavelet neural network (WNN) control method for active queue management (AQM) in an end-to-end TCP network, which is trained by adaptive learning rates (ALRs). In the TCP network, AQM is important to regulate the queue length by passing or dropping the packets at the intermediate routers. RED, PI, and PID algorithms have been used for AQM. But these algorithms show weaknesses in the detection and control of congestion under dynamically changing network situations. In our method, the WNN controller using ALRs is designed to overcome these problems. It adaptively controls the dropping probability of the packets and is trained by gradient-descent algorithm. We apply Lyapunov theorem to verify the stability of the WNN controller using ALRs. Simulations are carried out to demonstrate the effectiveness of the proposed method.