• 제어로봇시스템학회:학술대회논문집
• /
• 2004.08a
• /
• pp.1711-1716
• /
• 2004

This paper presents identification and control of a 10-m antenna via accelerometers and angle encoder data. Artificial Neural Networks can be used effectively for the identification and control of nonlinear dynamical system such as a large flexible antenna. Some identification results are shown and compared with the results of conventional prediction error method. And we use a neural network inverse model for control the large flexible antenna. In the neural network inverse model, a neural network is trained, using supervised learning, to develop an inverse model of the antenna. The network input is the process output, and the network output is the corresponding process input. The control results show the validation of the ANN approach for identification and control of the 10-m flexible antenna.

• Proceedings of the IEEK Conference
• /
• 2002.07a
• /
• pp.262-264
• /
• 2002

The characteristic features of Malaysia's climate is has stable temperature, with high humidity and copious rainfall. Weather forecasting is an important task in Malaysia as it could affetcs man irrespective of mans job, lifestyle and activities especially in the agriculture. In Malaysia, numerical method is the common used method to forecast weather which involves a complex of mathematical computing. The models used in forecasting are supplied by other counties such as Europe and Japan. The goal of this project is to forecast weather using another technology known as artificial neural network. This system is capable to learn the pattern of rainfall in order to produce a precise forecasting result. The supervised learning technique is used in the loaming process.

• Communications for Statistical Applications and Methods
• /
• v.26 no.6
• /
• pp.591-610
• /
• 2019

Deep Learning is one of the machine learning methods to find features from a huge data using non-linear transformation. It is now commonly used for supervised learning in many fields. In particular, Convolutional Neural Network (CNN) is the best technique for the image classification since 2012. For users who consider deep learning models for real-world applications, Keras is a popular API for neural networks written in Python and also can be used in R. We try examine the parameter estimation procedures of Deep Neural Network and structures of CNN models from basics to advanced techniques. We also try to figure out some crucial steps in CNN that can improve image classification performance in the CIFAR10 dataset using Keras. We found that several stacks of convolutional layers and batch normalization could improve prediction performance. We also compared image classification performances with other machine learning methods, including K-Nearest Neighbors (K-NN), Random Forest, and XGBoost, in both MNIST and CIFAR10 dataset.

• Phonetics and Speech Sciences
• /
• v.7 no.4
• /
• pp.9-16
• /
• 2015

In this paper, several experiments are performed according to deep neural network (DNN) based features for the performance comparison of speaker verification (SV) systems. To this end, input features for a DNN, such as mel-frequency cepstral coefficient (MFCC), linear-frequency cepstral coefficient (LFCC), and perceptual linear prediction (PLP), are first compared in a view of the SV performance. After that, the effect of a DNN training method and a structure of hidden layers of DNNs on the SV performance is investigated depending on the type of features. The performance of an SV system is then evaluated on the basis of I-vector or probabilistic linear discriminant analysis (PLDA) scoring method. It is shown from SV experiments that a tandem feature of DNN bottleneck feature and MFCC feature gives the best performance when DNNs are configured using a rectangular type of hidden layers and trained with a supervised training method.

• Journal of Korean Society for Atmospheric Environment
• /
• v.12 no.1
• /
• pp.67-77
• /
• 1996

Total suspended particulate matters (TSP) were collected based on a size segregation method by a cascade impactor for 6 consecutive years (form Dec. 1989 to sep. 1994) in the Kyung Hee University-Suwon Campus, and 6 trace metals (Ca, Si, Fe, Pb, Cu, Zn) were determined by an x-ray fluorescence spectroscopy. Total number of samples collected during the study are 118 sets and each set of sample comsists of 9 filters. The levels of TSP and 6 trace metals were then used to examine seasonal and annual variations with respects to their size distributions. For statistical analyses, raw data were initially transformed by both logarithmic and root transformating to approximately normalize them, and then size distribution functions for each trace element were separately developed season-to-season by a regression analysis in order to obtain maximum amount of physical information, Subsequently, each developed model was verified by comparing with supervised data collected on 1994. The result showed that each prediction model was in good agreement except the fall, partly due to lack of the data collected on fall, 1994.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2022.06a
• /
• pp.212-213
• /
• 2022

내시경 검사는 내장기관의 이상 유무를 점검할 수 있는 효과적인 의료 기술이다. 해당 논문에서는 자가지도 방식의 직접 감쇠 모델(DAM, Direct Attenuation Model)[3]을 사용한 내시경 비디오 기반 깊이 예측을 제안한다. 단안 카메라의 비디오 영상에서 DAM 을 이용한 빛의 밝기에 따른 깊이 변화 정보와 Normal 정보를 사용하여 깊이와 자세 예측 네트워크 모델 학습을 효과적으로 수행한다. 실험을 통해 제안하는 방법은 기존의 깊이 추정 네트워크 대비 다양한 내시경 비디오 영상에서 더 정확하게 깊이를 추정함을 확인하였다.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2022.07a
• /
• pp.63-66
• /
• 2022

본 논문에서는 분자의 특성을 정확하게 예측하기 위해 효과적인 사전학습(pretraining) 전략과 트랜스포머(Transformer) 모델을 활용한 방법을 제시한다. 딥러닝을 활용한 분자의 성능을 예측하는 연구는 그동안 레이블이 부족한 분자데이터의 특성에 의해 학습 때 사용된 데이터이외의 분자데이터에 대해 일반화 능력이 떨어지는 어려움을 겪었다. 이 논문에서 제시한 모델은 사전학습(pretraining)을 수행할 때 자기지도학습(self-supervised training)을 사용하여 부족한 레이블에 의한 문제점을 피할 수 있다. 대규모 분자 데이터셋으로부터 학습된 이 모델은 4가지 다운스트림 데이터셋에 대해 모두 우수한 성능을 보여주어 일반화 성능이 뛰어나며 효과적인 분자표현을 얻을 수 있음을 보인다.

• Korean Journal of Acupuncture
• /
• v.33 no.3
• /
• pp.102-113
• /
• 2016

Objectives : This study is aimed at developing and discussing the prediction model of blood stasis pattern of traditional Korean medicine(TKM) using machine learning algorithms: multiple logistic regression and decision tree model. Methods : First, we reviewed the blood stasis(BS) questionnaires of Korean, Chinese, and Japanese version to make a integrated BS questionnaire of patient-reported outcomes. Through a human subject research, patients-reported BS symptoms data were acquired. Next, experts decisions of 5 Korean medicine doctor were also acquired, and supervised learning models were developed using multiple logistic regression and decision tree. Results : Integrated BS questionnaire with 24 items was developed. Multiple logistic regression models with accuracy of 0.92(male) and 0.95(female) validated by 10-folds cross-validation were constructed. By decision tree modeling methods, male model with 8 decision node and female model with 6 decision node were made. In the both models, symptoms of 'recent physical trauma', 'chest pain', 'numbness', and 'menstrual disorder(female only)' were considered as important factors. Conclusions : Because machine learning, especially supervised learning, can reveal and suggest important or essential factors among the very various symptoms making up a pattern identification, it can be a very useful tool in researching diagnostics of TKM. With a proper patient-reported outcomes or well-structured database, it can also be applied to a pre-screening solutions of healthcare system in Mibyoung stage.

• The KIPS Transactions:PartB
• /
• v.11B no.2
• /
• pp.207-212
• /
• 2004

This paper presents a reinforcement learning framework for stock trading systems. Trading system parameters are optimized by Q-learning algorithm and neural networks are adopted for value approximation. In this framework, cooperative multiple agents are used to efficiently integrate global trend prediction and local trading strategy for obtaining better trading performance. Agents Communicate With Others Sharing training episodes and learned policies, while keeping the overall scheme of conventional Q-learning. Experimental results on KOSPI 200 show that a trading system based on the proposed framework outperforms the market average and makes appreciable profits. Furthermore, in view of risk management, the system is superior to a system trained by supervised learning.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.14 no.1
• /
• pp.14-21
• /
• 2021

Green networking has become a issue to reduce energy wastes and CO2 emission by adding energy managing mechanism to wired data networks. Energy consumption of the overall wired data networks is driven by access networks, expect for end devices. However, on a global scale, it is more difficult to manage centrally energy, measure and model the real energy use and energy savings potential of the access networks. This paper presented the multiple linear regression model to predict energy consumption of wired access networks using supervised learning of machine learning with data collected by existing investigated materials, actual measured values and results of many models. In addition, this work optimized the performance of it by various experiments and predict energy consumption of wired access networks. The performance evaluation of the regression model was achieved by well-knowned evaluation metrics.