• The Korean Journal of Applied Statistics
• /
• v.23 no.2
• /
• pp.375-382
• /
• 2010

In this study, we propose a robust estimator of the multivariate location parameter by means of the spatial median based on data trimming which extending trimmed mean in the univariate setup. The trimming quantity of this estimator is determined by the bootstrap method, and its covariance matrix is estimated by using the double bootstrap method. This extends the work of Jhun et al. (1993) to the multivariate case. Monte Carlo study shows that the proposed trimmed spatial median estimator yields better efficiency than a spatial median, while its covariance matrix based on double bootstrap overcomes the under-estimating problem occurred on single bootstrap method.

• The Journal of the Acoustical Society of Korea
• /
• v.17 no.5
• /
• pp.51-56
• /
• 1998

문장내 휴지구간의 위치와 길이는 합성음의 자연성을 결정짓는 주요 운율 파라미터 중 하나이다. 본 연구에서는 한국어 음성합성기의 합성음 생성에서 자연성 개선을 위해서 문장내 끊어읽기 위치 및 길이를 추정하기 위한 방법을 제안한다. 먼저 실제 발화에서 끊어 읽기가 발생하는 요인을 검토하였다. 그리고 이들 요인에 부합하여 텍스트에 4단계의 끊어 읽기를 표기함으로써 다량의 데이터를 확보하고 이를 이용한 NN 학습 결과와 HMM 추정 기의 성능을 비교 검토한다. 현재까지의 결과로는 NN 학습의 경우 끊어읽기 없는 경우와 긴 끊어읽기의 추정에서는 우수한 예측능력을 보이지만 짧은 끊어읽기, 중간 끊어읽기의 경 우는 HMM의 성능이 우수한 것으로 판명되었다. 전반적인 성능에서는 HMM이 우수하며 끊어읽기 종류에 따라 추정오차가 10∼25%로서 안정적인 결과를 얻었으며 TTS에의 활용 가능성을 보였다.

• Journal of Korean Society of Transportation
• /
• v.21 no.1
• /
• pp.53-63
• /
• 2003

The Origin-Destination(OD) matrix is very important in describing transport movements in a region. The OD matrix can be estimated using traffic counts on links in the transport network and other available information. This information on the travel is often contained in a target OD matrix and traffic counts in links. To estimate an OD matrix from traffic counts, they are the major input data which obviously affects the accuracy of the OD matrix estimated, Generally, the quality of an estimated OD matrix depends much on the reliability of the input data, and the number and locations of traffic counting points in the network. Any Process regarding the traffic counts such as the amount and their location has to be carefully studied. The objective of this study is to select of the optimal location of traffic counting points for the OD matrix estimation. The model was tested in nationwide network. The network consists of 224 zones, 3,125 nodes and 6,725 links except to inner city road links. The OD matrix applied for selection of traffic counting points was estimated to 3-constrained entropy maximizing model. The results of this study follow that : the selected alternative to the best optimal counting points of six alternatives is the alternative using common links of OD matrix and vehicle-km and traffic density(13.0% of 6,725 links), however the worst alternative is alternative of all available traffic counting points(44.9% of 6,725 links) in the network. Finally, it should be concluded that the accuracy of reproduced OD matrix using traffic counts related much to the number of traffic counting points and locations.

• Journal of the Institute of Electronics Engineers of Korea SC
• /
• v.49 no.4
• /
• pp.45-54
• /
• 2012

Location-based services with GPS positioning technology as a key technology, but recognizing the current location through satellite communication is not possible in an indoor location-aware technology, low-power short-range communication is primarily made of the study. Especially, as Chirp Spread Spectrum(CSS) based location-aware approach for low-power physical layer IEEE802.15.4a is selected as a standard, Ranging distance estimation techniques and data transfer speed enhancements have been more developed. It is known that the distance measured by CSS ranging has quite a lot of noise as well as its bias. However, the noise problem can be adjusted by modeling the non-zero mean noise value by a scaling factor which corresponds to the change of magnitude of a measured distance vector. In this paper, we propose a localization system using the CSS signal to measure distance for a mobile node taken a measurement of the exact coordinates. By applying the extended kalman filter and least mean squares method, the localization system is faster, more stable. Finally, we evaluate the reliability and accuracy of the proposed algorithm's performance by the experiment for the realization of localization system.

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.34 no.5
• /
• pp.74-80
• /
• 2006

GPS, which has been opened to the public since the 1980's, uses the C/A code time of arrival to estimate the position, and measures the carrier doppler frequency to estimate the velocity. In development from the 1990's, DGPS has improved position accuracy by eliminating common errors and CDGPS has achieved cm-level position accuracy using carrier phase. In this paper, a modified LSAST ambiguity resolution method for CDGPS is proposed to improve reliability and computational efficiency. Also the test results of cm level relative positioning of a moving vehicle using single frequency GPS receivers are compared to INS position. This research result can be widely used for the development of high precision INS, unmanned autonomous driving, survey and mapping, etc.

• The Journal of Korean Institute of Electromagnetic Engineering and Science
• /
• v.28 no.10
• /
• pp.819-824
• /
• 2017

This paper presents a target localization scheme for distributed Multi-input Multi-output(MIMO) radar system using ToA measurements obtained from multiple transmitter and receiver pairs. The proposed method can locate the target from an arbitrary initial point by iteratively finding the Taylor linear approximation equation. The simulation results show that proposed method achieves the better mean square error(MSE) performance than the existing target localization methods, and furthermore, attains Cramer-Rao Lower Bound(CRLB).

• Journal of KIISE:Software and Applications
• /
• v.33 no.12
• /
• pp.1022-1030
• /
• 2006

The location awareness is an important part of many ubiquitous computing systems, but a perfect location system does not exist yet in spite of many researches. Among various location tracking systems, we choose the RFID system due to its wide applications. However, the sensed RSSI signal is too sensitive to the direction of a RFID reader antenna, the orientation of a RFID tag, the human interference, and the propagation media situation. So, the existing location tracking method in spite of using the particle filter is not working well. To overcome this shortcoming, we suggest a robust location tracking method with a double layered structure, where the first layer coarsely estimates a tag's location in the block level using a regression technique or the SVM classifier and the second layer precisely computes the tag's location, velocity and direction using the particle filter technique. Its layered structure improves the location tracking performance by restricting the moving degree of hidden variables. Many extensive experiments show that the proposed location tracking method is so precise and robust to be a good choice for implementing the location estimation of a person or an object in the ubiquitous computing. We also validate the usefulness of the proposed location tracking method by implementing it for a real-time people monitoring system in a noisy and complicate workplace.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• fall
• /
• pp.84-87
• /
• 2021

본 논문에서는 딥러닝을 기반으로 문서영상에서 표 안의 셀 경계선을 히트맵 회귀(heatmap regression)로 추정함으로써 표의 구조를 인식하는 방법을 제안한다. 표는 기본적으로 행과 열로 이루어져 있기 때문에, 제안하는 방법에서는 먼저 1 차원 벡터 형태로 세로/가로 방향의 행/열 경계선 위치를 찾고, 이에 병합된 셀을 처리하기 위해 경계선이 그어져야 할 위치를 2 차원으로 추정한 결과를 적용하여 온전한 표의 경계선을 구한다. 이러한 구조를 통해 제안하는 방법은 표의 행과 열에 대한 정보를 효과적으로 이용함과 동시에, 복잡한 후처리 없이 병합된 셀을 처리할 수 있는 이점을 보인다. 실험은 1 차원의 행/열 경계선 위치를 반영하는 두 가지 방식에 대해 PubTabNet[11]에 대해 진행하여 결과를 보였다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2020.05a
• /
• pp.570-573
• /
• 2020

핀홀 카메라는 그 특성상 전체 공간 중에서 일부분만을 촬영할 수 있으므로 전체 공간을 염두에 두는 3D 재구성에서는 구면 영상에 비해 많은 데이터를 확보해야 한다. 본 논문에서는 다수의 구면 영상에 촬영된 물체의 실제 3차원 위치를 추정하는 방법을 제안한다. 두 카메라의 배치 간격이 가까운 스테레오 비전과는 달리 제안하는 방법에서는 여러 대의 카메라를 넓은 간격으로 배치하여 장애물에 대한 폐색을 극복하도록 한다. 구면 카메라의 화각은 공간 전체를 담을 수 있기 때문에 촬영 간격과 카메라의 회전각이 크더라도 전 영역에 대한 일치 관계를 계산할 수 있다. 실험 결과 구면 영상에 나타난 물체의 실제 위치에 근접한 결과를 얻을 수 있었다.

• Proceedings of the KIEE Conference
• /
• 2015.07a
• /
• pp.75-76
• /
• 2015

본 논문은 실내 이동로봇의 자율주행 방법을 적용한 결과를 기술한다. 구체적으로는 경로 계획, 장애물 회피, 위치 추정에 대해서 설명한다. 위의 기능들은 작성된 지도 정보와 Encoder, IMU, 초음파센서, 비콘 등 여러 센서 데이터를 토대로 구현되었다. 경로계획에는 A* 알고리즘을 활용하여 최단거리 경로를 구했으며, 장애물 회피에는 초음파센서를 활용한 자체 알고리즘을 적용하였다. 또한 비콘을 활용한 삼변 측량법을 활용하여 위치 추정을 하였다. 이러한 방법들을 통합하여 실내 네비게이션 방법을 실제로 구현하여 실험하였으며, 실험을 통하여, 제안한 방법이 로봇을 안전하게 자율주행하게 함을 확인하였다.