• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.20 no.1
• /
• pp.45-51
• /
• 2016

In this paper, we develop an iterative maximum likelihood (ML) receiver for generalized spatial modulation systems. In the proposed ML receiver, to mitigate the deleterious effect of channel information errors on symbol detection, the instantaneous covariance matrix of effective noise is estimated, which is then used to obtain improved ML solutions. The estimated covariance matrix is updated through multiple iterations to enhance the estimation accuracy. The simulation results show that the proposed ML receiver outperforms the conventional ML detection scheme, which does not take the effect of channel information errors into account.

• Proceedings of the IEEK Conference
• /
• 2001.09a
• /
• pp.487-490
• /
• 2001

본 논문에서는 기존의 Caussian Mixture Model을 이용한 실시간문맥독립화자인식시스템의 성능을 향상시키기 위하여 화자검증시스템에서 좋은 결과를 나타내는 유사도정규화 ( Likelihood Normalization )방법을 화자식별시스템에 적용하여 시스템을 구현하였으며, 인식실험한 결과에 대해 보고한다. 시스템은 화자모델생성단과 화자식별단으로 구성하였으며, 화자모델생성단에서는, 화자발성의 음향학적 특징을 잘 표현할 수 있는 GMM(Gaussian Mixture Model)을 이용하여 화자모델을 작성하였으며. GMM의 파라미터를 최적화하기 위하여 MLE(Maximum Likelihood Estimation)방법을 사용하였다. 화자식별단에서는 학습된 데이터와 테스트용 데이터로부터 ML(Maximum Likelihood)을 이용하여 프레임단위로 유사도를 계산하였다. 계산된 유사도는 유사도 정규화 과정을 거쳐 스코어( SC)로 표현하였으며, 가장 높은 스코어를 가지는 화자를 인식화자로 결정한다. 화자인식에서 발성의 종류로는 문맥독립 문장을 사용하였다. 인식실험을 위해서는 ETRI445 DB와 KLE452 DB를 사용하였으며. 특징파라미터로서는 켑스트럼계수 및 회귀계수값만을 사용하였다. 인식실험에서는 등록화자의 수를 달리하여 일반적인 화자식별방법과 프레임단위유사도정규화방법으로 각각 인식실험을 하였다. 인식실험결과, 프레임단위유사도정규화방법이 인식화자수가 많아지는 경우에 일반적인 방법보다 향상된 인식률을 얻을수 있었다.

• Proceedings of the Acoustical Society of Korea Conference
• /
• 1998.08a
• /
• pp.475-478
• /
• 1998

음성에 공존하는 유/무성음 성분을 추정하는 알고리즘을 제안하였다. 유성음 성분은 주기성을 띤 사인곡선의 형태로 표현되며, 무성음 성분은 자동회기의 결과로 표현된다. 두 성분을 각각 차례대로 추정할 경우 한 성분에 대한 추정치의 정확도가 나머지 성분의 추정에도 영향을 주기 때문에 제안된 알고리즘은 두 성분을 공동으로 추정한다. 실제 ML 추정치는 구하기 어려워 이에 근접하는 추정치를 선형 방정식들을 interative 방법으로 풀어 구현하였다. 예비 시험결과 제안한 알고리즘이 정확하고 효율적으로 두 성분을 추정함을 알 수 있었고, 합성된 데이터 뿐만 아니라 실제 음성 데이터를 이용한 실험에서도 좋은 결과를 보여주었다.

• Journal of Electrical Engineering and information Science
• /
• v.1 no.2
• /
• pp.9-14
• /
• 1996

The goal of this research is to provide a practical algorithm for outlining the left ventricular cavity in digital subtraction angiography. The proposed algorithm is based on the elliptic approximation and ML (Maximum Likelihood) estimate, and it produces a good results regarding execution time, robustness against noise, accuracy, and range of position of ROI (Regions Of Interest).

• Journal of the Institute of Electronics Engineers of Korea TC
• /
• v.47 no.8
• /
• pp.32-41
• /
• 2010

We propose the use of multi-preambles using Gold codes and analyze its performance. The multi-preamble is a way of utilizing different codes for preambles according to operation modes or applications in a system. The receiver can be easily implemented using the maximum likelihood algorithm. The performance is robust against noise due to the good correlation characteristic of the Gold codes. We use 128-bit-long multi-preambles generated by 127 bit Gold codes in deriving the detection error probability and in verifying the validity through computer simulation. The results show that the theory and the experiment are in good agreement within the approximation error.

• Journal of the Institute of Electronics Engineers of Korea TC
• /
• v.43 no.10 s.352
• /
• pp.1-7
• /
• 2006

Lattice decoding concept has been proposed for the implementation of the Maximum-Likelihood detection which is the optimal receiver from the viewpoint of the BER (Bit Error Rate) performance for MIMO (Multiple Input Multiple Output) systems. Sphere decoding algorithm and K-best decoding algorithm are based on the lattice decoding concept. A K-best decoding algorithm shows a good BER performance with relatively low complexity. However, with small K value, the error propagation effect severely degrades the performance. In this paper, we propose an adaptive K-best decoding algorithm which has lower average complexity and better BER performance than conventional K-best decoding algorithm.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.34 no.2A
• /
• pp.107-112
• /
• 2009

Spectral efficiency of current two-phase cooperative communications protocols is low since in the second time the relay forwards the same signal received from the source to the destination, the source keeps silent in this time. In this paper, we propose a novel cooperative communications protocol where the signal needed to transmit to the destination is sent in both phases, the source and the relay also transmit different signal to the destination thus no loss of spectral efficiency. This protocol performs signal selection based on log-likelihood ratio (LLR) at relay and maximum likelihood (ML) detection at destination. While existing protocols pay for a worse performance than direct transmission in the low SNR regime which is of special interest in ad hoc networks, ours is better over the whole range of SNR. In addition, the proposal takes advantages of bandwidth efficiency, long delay and interference among many terminals in ad hoc network. Simulation results show that the proposed protocol can significantly save total energy for wireless ad hoc networks.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.10 no.11
• /
• pp.5305-5321
• /
• 2016

In wireless communication, the multiple-input multiple-output (MIMO) system is a well-known approach to improve the reliability as well as the data rate. In MIMO systems, channel state information (CSI) is typically required at the receiver to detect transmitted signals; however, in practical systems, the CSI is imperfect and contains errors, which affect the overall system performance. In this paper, we propose a novel maximum likelihood (ML) scheme for MIMO systems that is robust to the CSI errors. We apply an optimization method to estimate an instantaneous covariance matrix of the CSI errors in order to improve the detection performance. Furthermore, we propose the employment of the list sphere decoding (LSD) scheme to reduce the computational complexity, which is capable of efficiently finding a reduced set of the candidate symbol vectors for the computation of the covariance matrix of the CSI errors. An iterative detection scheme is also proposed to further improve the detection performance.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.27 no.10A
• /
• pp.1000-1010
• /
• 2002

Partial response maximum-likelihood (PRML) and fixed-delay tree search with decision feedback (FDTS/DF) yield a sub-optimum performance in storage systems. However, they suffer from the inevitable complexity problems. this paper focuses on detection schemes to overcome the drawbacks of the sequence detections by exploiting minimum run-length d=2. It is expected that the proposed systems yield substantial reductions of both processing speed and receiver complexity. When combined with a decision feedback equalization (DFE), they prove to keep pace with the FDTS/DF with ${\tau}$=2 and even outperform the PR(1111)ML at normalized density S>5.6.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.42 no.4 s.304
• /
• pp.39-48
• /
• 2005

This paper proposes novel texture segmentation method using Bayesian estimation method and neural networks. We use multi-scale wavelet coefficients and the context information of neighboring wavelets coefficients as the input of networks. The output of neural networks is modeled as a posterior probability. The context information is obtained by HMT(Hidden Markov Tree) model. This proposed segmentation method shows better performance than ML(Maximum Likelihood) segmentation using HMT model. And post-processed texture segmentation results as using multi-scale Bayesian image segmentation technique called HMTseg in each segmentation by HMT and the proposed method also show that the proposed method is superior to the method using HMT.