• The Journal of the Acoustical Society of Korea
• /
• v.40 no.6
• /
• pp.578-586
• /
• 2021

We propose a semi-supervised learning method based on Variational AutoEncoder (VAE) and Unsupervised Data Augmentation (UDA) to improve the performance of an end-to-end speech recognizer. In the proposed method, first, the VAE-based augmentation model and the baseline end-to-end speech recognizer are trained using the original speech data. Then, the baseline end-to-end speech recognizer is trained again using data augmented from the learned augmentation model. Finally, the learned augmentation model and end-to-end speech recognizer are re-learned using the UDA-based semi-supervised learning method. As a result of the computer simulation, the augmentation model is shown to improve the Word Error Rate (WER) of the baseline end-to-end speech recognizer, and further improve its performance by combining it with the UDA-based learning method.

• Journal of Positioning, Navigation, and Timing
• /
• v.3 no.1
• /
• pp.17-23
• /
• 2014

Satellite Based Augmentation Systems (SBAS) provide ionospheric corrections at geographically five degree-spaced Ionospheric Grid Points (IGPs) and confidence bounds, called Grid Ionospheric Vertical Errors (GIVEs), on the error of those corrections. Since the ionosphere is one of the largest error sources which may threaten the safety of a single frequency Global Navigation Satellite System (GNSS) user, the ionospheric correction and integrity bound algorithm is essential for the development of SBAS. The current single frequency based SBAS, already deployed or being developed, implement the ionospheric correction and error bounding algorithm of the Wide Area Augmentation System (WAAS) developed for use in the United States. However, the ionospheric condition is different for each region and it could greatly degrade the performance of SBAS if its regional characteristics are not properly treated. Therefore, this paper discusses key factors that should be taken into consideration in the development of the ionospheric correction and integrity bound algorithm optimized for the Korean SBAS. The main elements of the conventional GIVE monitor algorithm are firstly reviewed. Then, this paper suggests several areas which should be investigated to improve the availability of the Korean SBAS by decreasing the GIVE value.

• The Journal of Korean Physical Therapy
• /
• v.35 no.6
• /
• pp.213-219
• /
• 2023

Purpose: In this study, based on the error augmentation, we performed walking training with increased rhythmic auditory stimulation speed on the affected side (IRAS) and walking training with decreased rhythmic auditory stimulation speed on the unaffected side (DRAS). The purpose of this study was to verify whether motor learning was effective in improving balance ability. Methods: Twenty-eight subjects with chronic stroke were recruited from a rehabilitation center. The subjects were divided into three groups: an IRAS group (10 subjects), a DRAS group (9 subjects), and control group (9 subjects). They received 30minutes of neuro-developmental therapy and walking training for 30minutes, five times a week for three weeks. Static and functional balance ability were measured before and after the training period. Static balance was measured by balancia software. Functional balance was measured by the timed up and go test (TUG) and the berg balance scale (BBS). Results: After the training periods, the IRAS group showed a significant improvement in TUG, BBS, area 95% COP, and weight distribution on the affected side when compared to both the DRAS group and control group (p<0.05). Conclusion: Based on the results of this study, it is possible to consider error augmentation methods of motor learning if rhythmic auditory stimulation is applied to stroke patients in clinical practice. If the affected side is shorter than the unaffected side, the affected side should be adjusted to the increased rhythmic auditory stimulation speed, which is considered to be an effective intervention to improve balance ability.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.12 no.6
• /
• pp.1045-1050
• /
• 2008

A GNSS augmentation system provides precision information using corrected GNSS pseudorange measurements. Common bias errors are corrected by PRC (Pseudorange Correction) between reference stations and a rover. However non-common errors (ionospheric and tropospheric noise error) are not corrected. Using position error variance this paper analyzes non-common error (noise errors) of ionosphere and troposphere wet vapor.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2008.05a
• /
• pp.197-200
• /
• 2008

A GNSS augmentation system provides precise position information using corrected GNSS pseudorange measurements. Common bias errors are corrected by PRC (Pseudorange Correction) between reference stations and a rover. However non-common errors (Ionospheric and Tropospheric noise error) are not corrected. Using position error variance this paper analyzes non-common errors (noise errors) of ionosphere and troposphere wet vapor.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.4 no.1
• /
• pp.225-233
• /
• 2001

This paper deals with the transfer alignment problem of SDINS(StrapDown Inertial Navigation System) subjected to roll and pitch motions of the ship. Specifically, to reduce alignment errors induced by measurement time-delay and ship body flexure, an error compensation method is suggested based on delay state augmentation and DCM(Direction Cosine Matrix) partial matching. A linearized error model for the velocity and attitude matching transfer alignment system is first derived by linearizing the nonlinear measurement equation with respect to its time delay and augmenting the delay state into the conventional linear state equations. And then DCM partial matching is properly combined to reduce effects of a ship's Y axis flexure. The simulation results show that the suggested method is effective enough resulting in considerably less azimuth alignment errors.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.26 no.5
• /
• pp.493-504
• /
• 2008

Space-Based Augmentation System (SBAS), which is one of the GPS augmentation systems, is a Wide-Area Differential GPS that provides differential GPS corrections and integrity data. In this study, we did performance analysis of kinematic SBAS surveying by conducting Real-Time Kinematic (RTK), DGPS, standalone, and SBAS surveys. Considering static survey results as truth, 2-D Root Mean Square (RMS) error and 3-D RMS error were computed to evaluate the positioning accuracy of each survey method. As a result, the 3-D positioning error of RTK was 13.1cm, DGPS 126.0cm, standalone (L1/L2) 135.7cm, standalone (C/A) 428.9cm, and SBAS 109.2cm. The results showed that the positioning accuracy of SBAS was comparable to that of DGPS.

• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• v.1
• /
• pp.361-365
• /
• 2006

High ionospheric spatial gradient during ionospheric storm is most concern for the landing approach with GNSS (Global Navigation Satellite System) augmentation systems. In case of the GBAS (Ground-Based Augmentation System), the ionospheric storm causes sudden increase of the ionospheric delay difference between a ground facility and a user (aircraft), and the aircraft position error increases significantly. Since the ionosphere behavior and the storm effect depend on geographic location, understanding the ionospheric storm behavior at specific regional area is crucial for the GNSS augmentation system development and implementation. Korea Aerospace Research Institute and collaborating universities have been developing an integrity monitoring test bed for GBAS research and for future regional augmentation system development. By using the dense GPS (Global Positioning System) networks in Korea, a regional ionosphere map is constructed for finding detailed aspect of the ionosphere variation. Preliminary analysis on the ionospheric gradient variation during a recent storm period is performed and the results are discussed.

• Journal of Korean Society for Quality Management
• /
• v.50 no.4
• /
• pp.701-716
• /
• 2022

Purpose: This study aims to predict the dry cargo transportation market economy. The subject of this study is the BDI (Baltic Dry Index) time-series, an index representing the dry cargo transport market. Methods: In order to increase the accuracy of the BDI time-series, we have pre-processed the original time-series via time-series decomposition and data augmentation techniques and have used them for ANN learning. The ANN algorithms used are Multi-Layer Perceptron (MLP), Recurrent Neural Network (RNN), and Long Short-Term Memory (LSTM) to compare and analyze the case of learning and predicting by applying time-series decomposition and data augmentation techniques. The forecast period aims to make short-term predictions at the time of t+1. The period to be studied is from '22. 01. 07 to '22. 08. 26. Results: Only for the case of the MAPE (Mean Absolute Percentage Error) indicator, all ANN models used in the research has resulted in higher accuracy (1.422% on average) in multivariate prediction. Although it is not a remarkable improvement in prediction accuracy compared to uni-variate prediction results, it can be said that the improvement in ANN prediction performance has been achieved by utilizing time-series decomposition and data augmentation techniques that were significant and targeted throughout this study. Conclusion: Nevertheless, due to the nature of ANN, additional performance improvements can be expected according to the adjustment of the hyper-parameter. Therefore, it is necessary to try various applications of multiple learning algorithms and ANN optimization techniques. Such an approach would help solve problems with a small number of available data, such as the rapidly changing business environment or the current shipping market.

• Journal of Advanced Navigation Technology
• /
• v.22 no.5
• /
• pp.384-390
• /
• 2018

This paper introduces a MATLAB graphical user interface (GUI) based software for analysis of korea augmentation satellite system (KASS) availability performance. This software uses minimum variance (MV) estimator and Kriging algorithm to generate integrity information such as user differential range error (UDRE) and grid ionospheric vertical error (GIVE). The information is offered to ground and aviation users in Korean region. The software also gives accuracy data, protection level data and availability map about each user position by using the integrity information. In particular the software calculates the protection level along a path of aircraft. We verified the result of protection level of aviation user by comparing them with the results of SBASimulator#2, which is a simulation tool of european geostationary navigation overlay service (EGNOS). As a result, the protection level error between the result of our software and the SBASimulator#2 was about 2% which means that the result of our software is accurate.