• Proceedings of the Acoustical Society of Korea Conference
• /
• 1994.06a
• /
• pp.698-703
• /
• 1994

In the actual sound environment, the random signal often shows a complex fluctuation pattern apart from a standard Gaussian distribution. In this study, an evaluation method for the sound environmnetal system is proposed in the generalized form applicable to the actual stochastic phenomena, by introducing two type information processing methods based on the regression model of expansion series type and the Fuzzy probability. The effectiveness of the proposed method are confirmed experimentally too by applying it to the observed data in the actual noise environment.

• Bulletin of the Society of Naval Architects of Korea
• /
• v.24 no.2
• /
• pp.11-19
• /
• 1987

A Series 60, $C_b=0.60$ model was tested in the towing tank of Seoul National University. Total resistance, hull attitude, wake distributions and wave measured at FR condition(free trim and sinkage) and FX condition(fixed trim and sinkage). From the measured data, residual, viscous and wave pattern resistance components were evaluated and compared. It is found that the changes in wetted surface area should be considered in predictions of frictional resistances, and can be easily found from hydrostatic data and measured mean sinkages without additional tests. Applications of the concept to the geosim tests of Series 60, Wigley, Lucy Ashton models show that the conventional extrapolation method can be improved considerably.

• International Journal of Contents
• /
• v.17 no.3
• /
• pp.1-14
• /
• 2021

Since the outbreak of the coronavirus disease 2019 (COVID-19) pandemic, a lot of efforts have been made in the field of data science to help combat against this disease. Among them, forecasting the number of cases of infection is a crucial problem to predict the development of the pandemic. Many deep learning-based models can be applied to solve this type of time series problem. In this research, we would like to take a step forward to incorporate spatial data (geography) with time series data to forecast the cases of region-level infection simultaneously. Specifically, we model a single spatio-temporal graph, in which nodes represent the geographic regions, spatial edges represent the distance between each pair of regions, and temporal edges indicate the node features through time. We evaluate this approach in COVID-19 in a Korean dataset, and we show a decrease of approximately 10% in both RMSE and MAE, and a significant boost to the training speed compared to the baseline models. Moreover, the training efficiency allows this approach to be extended for a large-scale spatio-temporal dataset.

• Journal of Korea Society of Digital Industry and Information Management
• /
• v.15 no.2
• /
• pp.19-28
• /
• 2019

The purpose of this study is to examine the trends on machine learning and deep learning research in the published journals from the Web of Science Database. To achieve the study purpose, we used the abstracts of 20,664 articles published between 1990 and 2017, which include the word 'machine learning', 'deep learning', and 'artificial neural network' in their titles. Twenty major research topics were identified from topic modeling analysis and they were inclusive of classification accuracy, machine learning, optimization problem, time series model, temperature flow, engine variable, neuron layer, spectrum sample, image feature, strength property, extreme machine learning, control system, energy power, cancer patient, descriptor compound, fault diagnosis, soil map, concentration removal, protein gene, and job problem. The analysis of the time-series linear regression showed that all identified topics in machine learning research were 'hot' ones.

• Structural Monitoring and Maintenance
• /
• v.6 no.3
• /
• pp.237-254
• /
• 2019

This paper presents an improved time series based damage detection approach with experimental verifications for detection, localization, and quantification of damage in shear-type structures under varying mass effects using output-only vibration data. The proposed method can be very effective for automated monitoring of buildings to develop proactive maintenance strategies. In this method, Auto-Regressive Moving Average models with eXogenous inputs (ARMAX) are built to represent the dynamic relationship of different sensor clusters. The damage features are extracted based on the relative difference of the ARMAX model coefficients to identify the existence, location and severity of damage of stiffness and mass separately. The results from a laboratory-scale shear type structure show that different damage scenarios are revealed successfully using the approach. At the end of this paper, the methodology limitations are also discussed, especially when simultaneous occurrence of mass and stiffness damage at multiple locations.

• Communications for Statistical Applications and Methods
• /
• v.28 no.4
• /
• pp.329-338
• /
• 2021

Deep learning methods have been developed, used in various fields, and they have shown outstanding performances in many cases. Many studies predicted a daily stock return, a classic example of time-series data, using deep learning methods. We also tried to apply deep learning methods to Korea's stock market data. We used Korea's stock market index (KOSPI) and several individual stocks to forecast daily returns and directions. We compared several deep learning models with other machine learning methods, including random forest and XGBoost. In regression, long short term memory (LSTM) and gated recurrent unit (GRU) models are better than other prediction models. For the classification applications, there is no clear winner. However, even the best deep learning models cannot predict significantly better than the simple base model. We believe that it is challenging to predict daily stock return data even if we use the latest deep learning methods.

• Journal of the Korean Society for Precision Engineering
• /
• v.14 no.3
• /
• pp.147-155
• /
• 1997

Optimal trajectory for a robot manipulator minimizing actuator torques or energy consumptions ina fixed traveling time is obtained in the presence of obstacles. All joint displacements are represented in finite terms of Fourier cosine series and the coefficients of the series are obtained optimally by nonlinear programming. Thus, the geometric path need not be prespecified and the full dynamic model is employed. To avoid the obstacles, the concept of the penalty area is newly introduced and this penalty area is includ- ed in the performance index with an appropriate weighting coefficient. This optimal trajectory will be useful as a geometric path in the minimum-time trajectory planning problem.

• International Journal of Computer Science & Network Security
• /
• v.23 no.4
• /
• pp.166-171
• /
• 2023

The Stock price analysis is an increasing concern in a financial time series. The purpose of the study is to analyze the price parameters of date, high, low, and news feed about the stock exchange price. Long short term memory (LSTM) is a cutting-edge technology used for predicting the data based on time series. LSTM performs well in executing large sequence of data. This paper presents the Long Short Term Memory Model has used to analyze the stock price ranges of 10 days and 20 days by exponential moving average. The proposed approach gives better performance using technical indicators of stock price with an accuracy of 82.6% and cross entropy of 71%.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2022.01a
• /
• pp.45-48
• /
• 2022

IoT 기술의 발전 및 확산으로 다양한 도메인에서 서로 다른 특성의 시계열 데이터가 수집되고 있다. 이에 따라 단일 목적으로 수집된 시계열 데이터만 아니라, 다른 목적으로 수집된 시계열 데이터들 또한 통합하여 분석활용하려는 수요 또한 높아지고 있다. 본 논문은 파편화된 시계열 데이터들을 선택하여 통합한 후 딥러닝 모델을 생성하고 활용할 수 있는 해시함수 기반 학습 모델 관리 플랫폼을 설계하고 구현하였다. 특정되지 않은 데이터들을 기반하여 모델을 학습하고 활용할 경우 생성 모델이 개별적으로 어떤 데이터로 어떻게 생성되었는지 기술되어야 향후 활용에 용이하다. 특히 시계열 데이터의 경우 학습 데이터의 시간 정보에 의존적일 수밖에 없으므로 해당 정보의 관리도 필요하다. 본 논문에서는 이러한 문제를 해결하기 위해 해시 함수를 이용해서 생성된 모델을 계층적으로 저장하여 원하는 모델을 쉽게 검색하고 활용할 수 있도록 하였다.

• Communications for Statistical Applications and Methods
• /
• v.31 no.1
• /
• pp.87-104
• /
• 2024

Most functional magnetic resonance imaging (fMRI) studies in resting state have assumed that the functional connectivity (FC) between time series from distinct brain regions is constant. However, increased interest has recently been in quantifying possible dynamic changes in FC during fMRI experiments. FC study may provide insight into the fundamental workings of brain networks to brain activity. In this work, we focus on the specific problem of estimating the dynamic behavior of pairwise correlations between time courses extracted from two different brain regions. We compare the sliding-window techniques such as moving average (MA) and exponentially weighted moving average (EWMA), dynamic causality with vector autoregressive (VAR) model, dynamic conditional correlation (DCC) based on volatility, and the proposed alternative methods to use differencing and recursive residuals. We investigate the properties of those techniques in a series of simulation studies. We also provide an application with major depressive disorder (MDD) patient fMRI data to demonstrate studying dynamic correlations.