• The Journal of the Acoustical Society of Korea
• /
• v.27 no.1E
• /
• pp.17-24
• /
• 2008

Blind speech separation (BSS) is well-known as a powerful technique for speech enhancement in many real world environments. In this paper, we propose a new application of BSS - acoustic echo cancellation (AEC) in a car environment. For this purpose, we develop a block-online BSS algorithm which provides robust separation than a batch version in changing environments with moving speakers. Simulation results using real world recordings show that the block-online BSS algorithm is very robust to speaker movement. When combined with AEC, simulation results using real audio recording in a car confirm the expectation that BSS improves double talk detection and echo suppression.

• Journal of Information Processing Systems
• /
• v.13 no.4
• /
• pp.1029-1042
• /
• 2017

A joint channel estimation and data detection technique for a multiple input multiple output (MIMO) wireless communication system is proposed. It combines the least square (LS) training based channel estimation (TBCE) scheme with sphere decoding. In this new approach, channel estimation is enhanced with the help of blind symbols, which are selected based on their correctness. The correctness is determined via sphere decoding. The performance of the new scheme is studied through simulation in terms of the bit error rate (BER). The results show that the proposed channel estimation has comparable performance and better computational complexity over the existing semi-blind channel estimation (SBCE) method.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2014.10a
• /
• pp.953-955
• /
• 2014

최근 차량 충돌 방지를 위한 다양한 기술이 상용화되고 있다. FMCW 기반의 레이더 시스템은 구현의 용이성으로 많은 상용차에서 전면 충돌 방지 시스템에 적용되고 있다. 측면 충돌 방지를 위한 BSD(Blind Spot Detection)와 차선변경 보조 시스템(LCA, Lane Change Assistant system)에서는 전방 레이더보다 인식거리가 줄어들고 갱신율이 낮아지므로 고속 FFT 등을 수행하는 신호처리부를 저가격으로 설계가 가능할 것이다. 본 연구에서는 TI사의 MCU인 F28335를 사용하여 근거리를 인식하는 신호처리부를 설계하였다. 이 MCU는 16채널 12bit ADC와 68KB RAM 및 512KB 플래시 메모리를 내장하고, 150MHz 부동소수점 연산을 지원하여 단일 칩으로 신호처리부의 구현이 가능하다. 구현된 시스템은 20m내외의 거리에 있는 장애물에 대하여 10Hz로 갱신이 가능하여 BSD를 위한 기본 기능이 확인되었다. 이러한 구현은 이전의 고가의 DSP나 FPGA를 사용하지 않고 15$이내의 단일 MCU와 간단한 아날로그 회로로 설계되어 저가격의 시스템으로 상용화가 가능할 것이다.

• Proceedings of the IEEK Conference
• /
• 2000.09a
• /
• pp.37-40
• /
• 2000

기존의 신호 공간 추적 방법을 이용한 blind multiuser detector는 nonstationary 환경에서 새로운 환경에 적응하기 위해 비교적 긴 시간을 필요로 한다 본 논문은 가변 망각 인자를 도입한 확장 PASTd (Projection Approximation Subspace Tracking with Deflation) 알고리즘을 이용하여 환경 변화에 좀더 신속히 적응하는 성능 향상을 모의실험을 통해 보이고자 한다.

• Proceedings of the Acoustical Society of Korea Conference
• /
• 1998.06e
• /
• pp.232-235
• /
• 1998

In this paper, we present the modified blind adaptive multiuser detector based on Constant Modulus Algorithm(CMA) for the demodulation of code-division multiple-access(CDMA) signals. Convergence issues are treated, and the performance of three algorithms is compared via computer simulations.

• The Journal of the Convergence on Culture Technology
• /
• v.9 no.5
• /
• pp.605-611
• /
• 2023

Accidents at construction sites have a very high rate of fatalities due to the nature of being prone to severe injury patients. In order to reduce the mortality rate of severely injury patients, quick response is required, and some systems that detect accidents using AI technology and cameras have been devised to respond quickly to accidents. However, since existing accident detection systems use only a single camera, there are blind spots, Thus, they cannot detect all accidents at a construction site. Therefore, in this paper, we present the system that minimizes the detection blind spot by using multiple cameras. Our implemented system extracts feature points from the images of multiple cameras with the YOLO-pose library, and inputs the extracted feature points to a Long Short Term Memory-based recurrent neural network in order to detect accidents. In our experimental result, we confirme that the proposed system shows high accuracy while minimizing detection blind spots by using multiple cameras.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2008.06a
• /
• pp.7-8
• /
• 2008

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.31 no.2C
• /
• pp.184-190
• /
• 2006

In this paper, we propose the blind multiuser detector which is robust against the effects of near-far and multiuser interference. The proposed detector is composed of the partial IC(interference canceller) and the blind MOE(minimum output energy) multiuser detector. The partial IC partially eliminates interference components from the received signal then the output of partial IC is fed into the input of multiuser detector. Simulation results show that the proposed detector has the robust property but the performance of conventional MOE multiuser detector is rapidly degraded in case of existing both near far and multiuser. Thus, the proposed partial IC BMUD(blind multiuser detection) technique has better performance than the conventional MOE.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.54 no.2
• /
• pp.115-122
• /
• 2017

This paper proposes a deep learning algorithm based sign detection and recognition system for the blind. The proposed system is composed of sign detection stage and sign recognition stage. In the sign detection stage, aggregated channel features are extracted and AdaBoost classifier is applied to detect regions of interest of the sign. In the sign recognition stage, convolutional neural network is applied to recognize the regions of interest of the sign. In this paper, the AdaBoost classifier is designed to decrease the number of undetected signs, and deep learning algorithm is used to increase recognition accuracy and which leads to removing false positives which occur in the sign detection stage. Based on our experiments, proposed method efficiently decreases the number of false positives compared with other methods.

• Journal of Communications and Networks
• /
• v.12 no.3
• /
• pp.216-221
• /
• 2010

In this paper, we propose and develop a new algorithm for the principle subspace tracking by orthonormalizing the eigenvectors using an approximation of Gram-Schmidt procedure. We carry out a novel mathematical derivation to show that when this approximated version of Gram-Schmidt procedure is added to a modified form of projection approximation subspace tracking deflation (PASTd) algorithm, the eigenvectors can be orthonormalized within a linear computational complexity. While the PASTd algorithm tries to extracts orthonormalized eigenvectors, the new scheme orthonormalizes the eigenvectors after their extraction, yielding much more tacking efficiency. We apply the new tracking scheme for blind adaptive multiuser detection for non-stationary cellular CDMA environment and use extensive simulation results to demonstrate the performance improvement of the proposed scheme.