• The Journal of the Acoustical Society of Korea
• /
• v.22 no.2
• /
• pp.135-144
• /
• 2003

A method for the automatic segmentation of speech signals is described. The method is dedicated to the construction of a large database for a Text-To-Speech (TTS) synthesis system. The main issue of the work involves the refinement of an initial estimation of phone boundaries which are provided by an alignment, based on a Hidden Market Model(HMM). Multi-layer perceptron (MLP) was used as a phone boundary detector. To increase the performance of segmentation, a technique which individually trains an MLP according to phonetic transition is proposed. The optimum partitioning of the entire phonetic transition space is constructed from the standpoint of minimizing the overall deviation from hand labelling positions. With single speaker stimuli, the experimental results showed that more than 95% of all phone boundaries have a boundary deviation from the reference position smaller than 20 ms, and the refinement of the boundaries reduces the root mean square error by about 25%.

• Journal of Korean Society for Quality Management
• /
• v.48 no.3
• /
• pp.511-520
• /
• 2020

Purpose: The purpose of this study was to devise an accurate machine learning model for predicting silica concentrations following the addition of impurities, through time series analysis of mining data. Methods: The mining data were preprocessed and subjected to time series analysis using the machine learning model. Through correlation analysis, valid variables were selected and meaningless variables were excluded. To reflect changes over time, dependent variables at baseline were treated as independent variables at later time points. The relationship between independent variables and the dependent variable after n point was subjected to Pearson correlation analysis. Results: The correlation (R2) was strongest after 3 hours, which was adopted as a dependent variable. According to root mean square error (RMSE) data, the proposed method was superior to the other machine learning methods. The XGboost algorithm showed the best predictive performance. Conclusion: This study is important given the current lack of machine learning studies pertaining to the domestic mining industry. In addition, using time series analysis in mining data will show further improvement. Before establishing a predictive model for the proposed method, predictions should be made using data with time series characteristics. After doing this work, it should also improve prediction accuracy in other domains.

• International Journal of Aeronautical and Space Sciences
• /
• v.16 no.3
• /
• pp.380-393
• /
• 2015

This study presents how we can evaluate stereo camera systems for the structural deformation monitoring. A stereo camera system, consisting of a set of stereo cameras and reflective markers attached on the structure, is introduced for the measurement and the stereo pattern recognition (SPR) method is utilized for the full-field structural deformation estimation. Performance of this measurement system depends on many parameters including types and specifications of the cameras, locations and orientations of them, and sizes and positions of markers; it is difficult to experimentally identify the effects of each parameter on the measurement performance. In this study, a simulation framework for evaluating performance of the stereo camera systems with various parameters has been developed. The maximum normalized root-mean-square (RMS) error is defined as a representative index of stereo camera system performance. A plate structure is chosen for an introductory example. Its several modal harmonic vibrations are generated and estimated in the simulation framework. Two cases of simulations are conducted to see the effects of camera locations and the resolutions of the cameras. An experimental validation is carried out for a few selected cases from the simulations. Using the simultaneous laser displacement sensor (LDS) measurements as the reference, the measurement errors are obtained and compared with the simulations.

• Korean Journal of Remote Sensing
• /
• v.36 no.4
• /
• pp.587-607
• /
• 2020

Soil moisture is essential information for meteorological and hydrological analyses. To date, many efforts have been made to achieve the two goals for soil moisture data, i.e., the improvement of accuracy and resolution, which is very challenging. We presented an ensemble downscaling method for quality improvement of gridded soil moisture data in terms of the accuracy and the spatial resolution by the integration of BMA (Bayesian model averaging) and ATPRK (area-to-point regression kriging). In the experiments, the BMA ensemble showed a 22% better accuracy than the data sets from ESA CCI (European Space Agency-Climate Change Initiative), ERA5 (ECMWF Reanalysis 5), and GLDAS (Global Land Data Assimilation System) in terms of RMSE (root mean square error). Also, the ATPRK downscaling could enhance the spatial resolution from 0.25° to 0.05° while preserving the improved accuracy and the spatial pattern of the BMA ensemble, without under- or over-estimation. The quality-improved data sets can contribute to a variety of local and regional applications related to soil moisture, such as agriculture, forest, hydrology, and meteorology. Because the ensemble downscaling method can be applied to the other land surface variables such as temperature, humidity, precipitation, and evapotranspiration, it can be a viable option to complement the accuracy and the spatial resolution of satellite images and numerical models.

• The Journal of Korean Institute of Electromagnetic Engineering and Science
• /
• v.24 no.1
• /
• pp.91-97
• /
• 2013

The input parameters of scattering models for computing the backscattering coefficients of earth terrains are mainly soil moisture and surface roughness. The backscattering coefficients of soil surfaces are more sensitive to surface roughness than soil moisture. In this study, we propose a precise measurement method for roughness parameters and analyze measurement errors. We measured surface roughness using a pin-board profiler(1 m, 0.5 cm interval) and a laser profiler(1 m, 0.25 cm interval). The measurement differences between two profilers in an average sense are 0.097 cm for root-mean-square (RMS) height and 1.828 cm for correlation length. The analysis of the correlation functions and relative errors shows that the laser measurements are more stable than the pin-board measurements. The differences of the calculated backscattering coefficients using a surface scattering model between pin-board and laser profiler measurements are less than 1 dB.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.43 no.2
• /
• pp.48-55
• /
• 2020

Recently, a study of prognosis and health management (PHM) was conducted to diagnose failure and predict the life of air craft engine parts using sensor data. PHM is a framework that provides individualized solutions for managing system health. This study predicted the remaining useful life (RUL) of aeroengine using degradation data collected by sensors provided by the IEEE 2008 PHM Conference Challenge. There are 218 engine sensor data that has initial wear and production deviations. It was difficult to determine the characteristics of the engine parts since the system and domain-specific information was not provided. Each engine has a different cycle, making it difficult to use time series models. Therefore, this analysis was performed using machine learning algorithms rather than statistical time series models. The machine learning algorithms used were a random forest, gradient boost tree analysis and XG boost. A sliding window was applied to develop RUL predictions. We compared model performance before and after applying the sliding window, and proposed a data preprocessing method to develop RUL predictions. The model was evaluated by R-square scores and root mean squares error (RMSE). It was shown that the XG boost model of the random split method using the sliding window preprocessing approach has the best predictive performance.

• Journal of Korean Society on Water Environment
• /
• v.35 no.5
• /
• pp.425-431
• /
• 2019

Recently, people have been attracting attention to the good quality of water resources as well as water welfare. to improve the quality of life. This study is a papers on the prediction of benthic macroinvertebrate index (BMI), which is a aquatic ecological health, using the machine learning based CFS (Correlation-based Feature Selection) method and the random forest model to compare the measured and predicted values of the BMI. The data collected from the Han River's branch for 10 years are extracted and utilized in 1312 data. Through the utilized data, Pearson correlation analysis showed a lack of correlation between single factor and BMI. The CFS method for multiple regression analysis was introduced. This study calculated 10 factors(water temperature, DO, electrical conductivity, turbidity, BOD, $NH_3-N$, T-N, $PO_4-P$, T-P, Average flow rate) that are considered to be related to the BMI. The random forest model was used based on the ten factors. In order to prove the validity of the model, $R^2$, %Difference, NSE (Nash-Sutcliffe Efficiency) and RMSE (Root Mean Square Error) were used. Each factor was 0.9438, -0.997, and 0,992, and accuracy rate was 71.6% level. As a result, These results can suggest the future direction of water resource management and Pre-review function for water ecological prediction.

• Computers and Concrete
• /
• v.31 no.5
• /
• pp.457-468
• /
• 2023

Buildings, bridges, and dams are examples of civil infrastructure that play an important role in public life. These structures are prone to structural variations over time as a result of external forces that might disrupt the operation of the structures, cause structural integrity issues, and raise safety concerns for the occupants. Therefore, monitoring the state of a structure, also known as structural health monitoring (SHM), is essential. Owing to the emergence of the fourth industrial revolution, next-generation sensors, such as wireless sensors, UAVs, and video cameras, have recently been utilized to improve the quality and efficiency of building forensics. This study presents a method that uses a target-based system to estimate the dynamic displacement and its corresponding dynamic properties of structures using UAV-based video. A laboratory experiment was performed to verify the tracking technique using a shaking table to excite an SDOF specimen and comparing the results between a laser distance sensor, accelerometer, and fixed camera. Then a field test was conducted to validate the proposed framework. One target marker is placed on the specimen, and another marker is attached to the ground, which serves as a stationary reference to account for the undesired UAV movement. The results from the UAV and stationary camera displayed a root mean square (RMS) error of 2.02% for the displacement, and after post-processing the displacement data using an OMA method, the identified natural frequency and damping ratio showed significant accuracy and similarities. The findings illustrate the capabilities and reliabilities of the methodology using UAV to evaluate the dynamic properties of structures.

• Journal of The Korean Society of Agricultural Engineers
• /
• v.59 no.6
• /
• pp.61-71
• /
• 2017

The tracer gas method has an advantage that can estimate total and local ventilation rate by tracing air flow. However, the field measurement using tracer gas has disadvantages such as danger, inefficiency, and high cost. Therefore, the aim of this study was to evaluate ventilation rate in pig house by using the thermal distribution data rather than tracer gas. Especially, LMA (Local Mean Age), which is an index based on the age of air theory, was used to evaluate the ventilation rate in pig house. Firstly, the field experiment was conducted to measure micro-climate inside pig house, such as the air temperature, $CO_2$ concentration and wind velocity. And then, LMA was calculated based on the decay of $CO_2$ concentration and air temperature, respectively. This study compared between LMA determined by $CO_2$ concentration and air temperature; the average error and root mean square error were 3.76 s and 5.34 s. From these results, it was determined that thermal distribution data could be used for estimation of LMA. Finally, CFD (Computational fluid dynamic) model was validated using LMA and wind velocity. The mesh size was designed to be 0.1 m based on the grid independence test, and the Standard $k-{\omega}$ model was eventually chosen as the proper turbulence model. The developed CFD model was highly appropriate for evaluating the ventilation rate in pig house.

• The Journal of Korean Society for Radiation Therapy
• /
• v.19 no.1
• /
• pp.19-26
• /
• 2007

Purpose: To compare of the accuracy among various measurement procedures of HDR Brachytherapy, and to evaluate the clinical suitability and usefulness of alternative PMMA (polymethylmethacrylateplastics: $C_5H_8O_2$) plate phantom without any additional cost due to the purchase of measuring apparatus. Materials and Methods: We made a comparative study on three types of measuring systems: well type chamber, source calibration jig, and PMMA plate phantom. Farmer type chamber was used for source calibration jig method and PMMA plate phantom method. Measurement was done 5 times each in comparison with the measurement values from manufacturer. Measurement results from experiment were compared with that from the manufacturer which is offered with the source whenever a source is substituted by a new one and evaluate the accuracy of source activity. Results: As a consequence of Ir-192 source measurement using well type chamber, source calibration jig and PMMA plate phantom, RMS (Root Mean Square) values for the relative error are 0.6%, 1.57%, 2.1%, respectively, compared with the data from manufacturer. And the mean errors with standard deviation are given $-0.2{\pm}0.5%$, $0.97{\pm}1.23%$, $-0.89{\pm}1.87%$ respectively. Conclusion: From the results shown by the three types of measurement system (well type chamber, source calibration jig, and PMMA plate phantom), the measurement with well type chamber produced the best accuracy. It turns out that we can also use the alternative system of PMMA plate phantom clinically without purchasing any additional particular apparatus since the system does not exceed the recommendation of AAPM (American Association of Physicists in Medicine), which requires the error range of within ${\pm}5%$.