• The Journal of Korean Institute of Electromagnetic Engineering and Science
• /
• v.28 no.8
• /
• pp.653-660
• /
• 2017

In this paper, the author analyzes direction finding accuracy based on phase comparisons to estimate elevation and azimuth angles of arrival signals. This paper considers the uniform array configurations using four and three elements. In that direction finding structures, I present the analytic expressions for estimated elevation and azimuth angles and then analyze the direction finding errors. And one presents the design guideline of direction finding system in comparison with aspects of accuracy, structure, the number of channels in that structures. The analysis result is similar with simulation one and has difference within $1.2^{\circ}RMS$. From the proposed analysis results, one knows that when SNR is 20 dB and the baseline is half of wavelength, the estimated elevation accuracy of the uniform array using four elements is 1.15 times better than the one of the uniform array using three elements and the estimated azimuth accuracy is same each other. In addition, one knows coning error is eliminated in 2-D direction finding structure.

• The Journal of the Acoustical Society of Korea
• /
• v.40 no.5
• /
• pp.439-451
• /
• 2021

We propose a deep learning-based beamformer combined with spectral subtraction for continuous speech recognition operating in noisy environments. Conventional beamforming systems were mostly evaluated by using pre-segmented audio signals which were typically generated by mixing speech and noise continuously on a computer. However, since speech utterances are sparsely uttered along the time axis in real environments, conventional beamforming systems degrade in case when noise-only signals without speech are input. To alleviate this drawback, we combine online beamforming algorithm and spectral subtraction. We construct a Continuous Speech Enhancement (CSE) evaluation set to evaluate the online beamforming algorithm in noisy environments. The evaluation set is built by mixing sparsely-occurring speech utterances of the CHiME3 evaluation set and continuously-played CHiME3 background noise and background music of MUSDB. Using a Kaldi-based toolkit and Google web speech recognizer as a speech recognition back-end, we confirm that the proposed online beamforming algorithm with spectral subtraction shows better performance than the baseline online algorithm.

• KIPS Transactions on Software and Data Engineering
• /
• v.11 no.4
• /
• pp.179-188
• /
• 2022

There have been many successful researches on a bearing fault diagnosis based on Deep Learning, but there is still a critical issue of the data distribution difference between training data and test data from their different working conditions causing performance degradation in applying those methods to the machines in the field. As a solution, a data adaptation method has been proposed and showed a good result, but each and every approach is strictly limited to a specific applying scenario or presupposition, which makes it still difficult to be used as a real-world application. Therefore, in this study, we have proposed a method that, using a data transformation with MFCCs and a simple CNN architecture, can perform a robust diagnosis on a target domain data without an additional learning or tuning on the model generated from a source domain data and conducted an experiment and analysis on the proposed method with the CWRU bearing dataset, which is one of the representative datasests for bearing fault diagnosis. The experimental results showed that our method achieved an equal performance to those of transfer learning based methods and a better performance by at least 15% compared to that of an input transformation based baseline method.

• The Journal of the Acoustical Society of Korea
• /
• v.40 no.2
• /
• pp.176-182
• /
• 2021

This paper evaluates and compares the performance of the Deep Nerual Network (DNN)-based speech enhancement models according to various loss functions. We used a complex network that can consider the phase information of speech as a baseline model. As the loss function, we consider two types of basic loss functions; the Mean Squared Error (MSE) and the Scale-Invariant Source-to-Noise Ratio (SI-SNR), and two types of perceptual-based loss functions, including the Perceptual Metric for Speech Quality Evaluation (PMSQE) and the Log Mel Spectra (LMS). The performance comparison was performed through objective evaluation and listening tests with outputs obtained using various combinations of the loss functions. Test results show that when a perceptual-based loss function was combined with MSE or SI-SNR, the overall performance is improved, and the perceptual-based loss functions, even exhibiting lower objective scores showed better performance in the listening test.

• Proceedings of the Korean Society of Disaster Information Conference
• /
• 2023.11a
• /
• pp.278-281
• /
• 2023

연구목적: 본 연구는 요양병원 등 재난취약시설에 재난이 발생할 경우 잔류한 요구조자를 정확하게 파악하여 소방 등 대응기관에 제공하는 APC(Auto People Counting)의 인식률 개선에 목적이 있다. 현재 재난 발생 시 건물 내 요구조자의 현황 파악을 위해 대응기관이 재난 현장에 도착하여 건물관계자에게 직접 물어보고 있다. 이는 요구조자에 대한 부정확한 정보일 가능성이 있어 대응기관의 업무범위가 확대되고 이로인해 구조자의 안전에도 위험이 될 수 있다. APC는 건물내 출입하는 인원을 자동으로 집계하여 실시간 잔류인원 정보를 제공함으로써 재난 시 요구조자 현황을 정확히 파악할 수 있다. 본 연구에서는 APC가 보다 정확하게 출입 인원을 집계할 수 있도록 최적의 인공지능 알고리즘을 선정하는데 목적이 있다. 연구방법: 본 연구에서는 실제 재난취약시설에 설치되어 운영 중인 APC를 대상으로 카메라를 통해 출입 인원의 이미지를 인식하는 알고리즘을 개선하기 위해 CNN모델을 활용하여 베이스라인 모델링을 하였다. 다양한 알고리즘의 성능을 분석하여 상위 7개의 후보군을 선정하고 전이학습 모델을 활용하여 성능이 가장 우수한 최적의 알고리즘을 선정하는 방법으로 연구를 수행하였다. 연구결과: 실험결과 시간과 성능이 가장 좋은 Densenet201, Resnet152v2 모델의 정밀도와 재현율을 확인한 결과 모든 라벨에 대해서 정확도 100%를 나타내는 것을 확인할 수 있었다. 이 중 Densenet201 모델이 더 높은 성능을 보여주었다. 결론: 다양한 인공지능 알고리즘 중 APC에 적용할 수 있는 최적의 알고리즘을 선정하였고 이는 APC의 인식률을 개선하여 재난시 요구조자의 정보를 정확하게 파악하여 신속하고 안전한 구조작업이 가능할 것이다. 이는 요구조자의 안전한 구조뿐만 아니라 구조작업을 수행하는 구조자의 안전을 확보하는 데 기여할 것으로 기대된다. 향후 연무 등 다양한 재난상황에서 재난취약시설 내 출입인원을 정확하게 파악할 수 있도록 알고리즘 분석 및 학습에 대한 추가 연구가 요구된다.

• Progress in Medical Physics
• /
• v.26 no.3
• /
• pp.119-126
• /
• 2015

The purpose of this study is to analyze motion-induced dose error generated by each tumor motion parameters of irregular tumor motion in helical tomotherapy. To understand the effect of the irregular tumor motion, a simple analytical model was simulated. Moving cases that has tumor motion were divided into a slightly irregular tumor motion case, a large irregular tumor motion case and a patient case. The slightly irregular tumor motion case was simulated with a variability of 10% in the tumor motion parameters of amplitude (amplitude case), period (period case), and baseline (baseline case), while the large irregular tumor motion case was simulated with a variability of 40%. In the phase case, the initial phase of the tumor motion was divided into end inhale, mid exhale, end exhale, and mid inhale; the simulated dose profiles for each case were compared. The patient case was also investigated to verify the motion-induced dose error in 'clinical-like' conditions. According to the simulation process, the dose profile was calculated. The moving case was compared with the static case that has no tumor motion. In the amplitude, period, baseline cases, the results show that the motion-induced dose error in the large irregular tumor motion case was larger than that in the slightly irregular tumor motion case or regular tumor motion case. Because the offset effect was inversely proportion to irregularity of tumor motion, offset effect was smaller in the large irregular tumor motion case than the slightly irregular tumor motion case or regular tumor motion case. In the phase case, the larger dose discrepancy was observed in the irregular tumor motion case than regular tumor motion case. A larger motion-induced dose error was also observed in the patient case than in the regular tumor motion case. This study analyzed motion-induced dose error as a function of each tumor motion parameters of irregular tumor motion during helical tomotherapy. The analysis showed that variability control of irregular tumor motion is important. We believe that the variability of irregular tumor motion can be reduced by using abdominal compression and respiratory training.

• Economic and Environmental Geology
• /
• v.46 no.6
• /
• pp.485-494
• /
• 2013

$CO_2$ Monitoring, Mitigation and Verification (MMV) is the essential part in the Carbon Capture and Storage (CCS) project in order to assure the storage permanence economically and environmentally. In large-scale CCS projects in the world, the seismic time-lapse survey is a key technology for monitoring the behavior of injected $CO_2$. In this study, we developed a basic process procedure for 3-D seismic baseline data from the Aquistore project, Estevan, Canada. Major target formations of Aquistore CCS project are the Winnipeg and the Deadwood sandstone formations located between 1,800 and 1,900 ms in traveltime. The analysis of trace energy and similarity attributes of seismic data followed by spectral decomposition are carried out for the characterization of $CO_2$ injection zone. High trace energies are concentrated in the northern part of the survey area at 1,800 ms and in the southern part at 1,850 ms in traveltime. The sandstone dominant regions are well recognized with high reflectivity by the trace energy analysis. Similarity attributes show two structural discontinuities trending the NW-SE direction at the target depth. Spectral decomposition of 5, 20 and 40 Hz frequency contents discriminated the successive E-W depositional events at the center of the research area. Additional noise rejection and stratigraphic interpretation on the baseline data followed by applying appropriate imaging technique will be helpful to investigate the differences between baseline data and multi-vintage monitor data.

• Journal of Korean Society of Forest Science
• /
• v.98 no.1
• /
• pp.55-65
• /
• 2009

Annex I parties continued its consideration of how to address, the definitions, modalities, rules and guidelines for the treatment of Land Use, Land-use Change and Forestry (LULUCF) in the second commitment period of the Kyoto Protocol by the year of 2009. In the AWG-KP conference held in Accra, Ghana in 2008, four alternatives (gross-net carbon accounting, net-net with base year or base period accounting, net-net with forward looking baseline accounting, and land-based accounting method) for negotiations were decided in order to revise gross-net accounting method applied during the first commitment period of the Kyoto Protocol. In this study, alternative scenarios are set in consideration with reporting system (voluntary or compulsory), discount factors and cap about these three alternatives except for the method of net-net with forward looking baseline accounting, and then estimates the Removal Unit (RMU) among the countries. In the case that article 3.4 activities under the Kyoto Protocol revises from voluntary reporting to mandatory reporting, it is estimated that the loss of RMU would be huge in Russia, Australia, New Zealand, as well as Canada potentially. Net-net with base year or base period carbon accounting and land-based carbon accounting method have big difference of RMU in accordance with the base year or the base period. So the more unfavorable the country with a lot of old-age forests was, the closer the base year or period comes to the commitment period in the context of RMU. If it is getting lowered for the current rate of 85% in discount factors, RMU is getting higher to the whole countries. Therefore in Korea with little potential for afforestation and reforestation, there was the most sensitive response to the change of discount factors. Post-2012 LULUCF hereafter, it is strongly expected for the succession of current carbon accounting system which is voluntary reporting of gross-net carbon accounting and the activity for article 3.4. Other carbon accounting method is hard to accept in aspect that there is big differentiated interests among the countries and it is required enormous cost and time to develop reliable method. Provide for Post-2012 mandatory greenhouse gas reduction, Korea needs to have a competitive negotiation strategies differentiated from Annex I countries. The most reliable alternative would be to lower the discounting factors about the activities for forest management.

• Journal of KIISE:Databases
• /
• v.36 no.6
• /
• pp.476-485
• /
• 2009

In sensor networks, many methods have been proposed to process in-network aggregation effectively. Unlike general aggregation queries, skyline query processing compares multi-dimensional data for the result. Therefore, it is very difficult to process the skyline queries in sensor networks. It is important to filter unnecessary data for energy-efficient skyline query processing. Existing approach like MFTAC restricts unnecessary data transitions by deploying filters to whole sensors. However, network lifetime is reduced by energy consumption for many false positive data and filters transmission. In this paper, we propose a bottom up filtering-based skyline query processing algorithm of in-network for reducing energy consumption by filters transmission and a PBFiltering technique for improving performance of filtering. The proposed algorithm creates the skyline filter table (SFT) in the data gathering process which sends from sensor nodes to the base station and filters out unnecessary transmissions using it. The experimental results show that our algorithm reduces false positives and improves the network lifetime over the existing method.

• Annual Conference on Human and Language Technology
• /
• 1997.10a
• /
• pp.152-159
• /
• 1997

최근 들어 인쇄체 문자 인식 기술의 발전에 힘입어 필기체 한글 인식에 관한 연구가 활발히 진행되고 있다. 인쇄체 문자와는 달리 자연스럽게 필기된 한글 글씨는 동일한 문자라 하더라도 같은 모양을 가지고 있다고 단정하는 것이 불가능할 정도로 필기자의 필기 유형에 따른 다양한 변형을 내포하고 있다. 따라서 효과적인 한글 글씨 인식기를 개발하기 위해서는 다양한 변형을 포함하는 대용량의 한글 글씨 영상 데이터베이스가 필수적이다. 본 논문에서는 시스템공학연구소 주관 국어 정보 베이스 개발 사업의 일환으로 고려대학교에서 구축 중인 오프라인 한글 글씨 영상 데이터베이스, KU-1에 대해 간략히 소개하고자 한다. 본 데이터베이스는 KS C 완성형 한글 사용 빈도순 상위 1,500자에 대하여 다양한 계층, 직업, 연령, 지역 분포를 고려한 1,000명 이상의 필기자가 정서체와 본인의 평소 자유 필체로 필기한 1,000벌의 명도 한글 글씨 영상으로 구성되어 있다.