• The KIPS Transactions:PartB
• /
• v.10B no.4
• /
• pp.381-388
• /
• 2003

This paper presents a method of giving weights to garbage class clustering and Filler model to improve performance of keyword spotting system and a time-saving method of dialogue speech processing system for keyword spotting by calculating keyword transition probability through speech analysis of task domain users. The point of the method is grouping phonemes with phonetic similarities, which is effective in sensing similar phoneme groups rather than individual phonemes, and the paper aims to suggest five groups of phonemes obtained from the analysis of speech sentences in use in Korean morphology and in stock-trading speech processing system. Besides, task-subject Filler model weights are added to the phoneme groups, and keyword transition probability included in consecutive speech sentences is calculated and applied to the system in order to save time for system processing. To evaluate performance of the suggested system, corpus of 4,970 sentences was built to be used in task domains and a test was conducted with subjects of five people in their twenties and thirties. As a result, FOM with the weights on proposed five phoneme groups accounts for 85%, which has better performance than seven phoneme groups of Yapanel [1] with 88.5% and a little bit poorer performance than LVCSR with 89.8%. Even in calculation time, FOM reaches 0.70 seconds than 0.72 of seven phoneme groups. Lastly, it is also confirmed in a time-saving test that time is saved by 0.04 to 0.07 seconds when keyword transition probability is applied.

• Journal of the Institute of Electronics Engineers of Korea TC
• /
• v.45 no.7
• /
• pp.22-31
• /
• 2008

Cognitive radio should imply a proper sensing technique for detecting the presence of licensed users to identify the unused spectrum holes. Besides this, this information should also be used to opportunistically provide communication among secondary users. At the same time the performance of the primary user should not be declined by the secondary users. The detection of licensed users may be significantly difficult for shadowing effect. To prevail over this problem cooperative spectrum sensing, In which the combined observation information gained by multiple secondary users is employed to achieve higher performance of detection, has been inspected. However, the primary challenge of cooperative sensing lays in its ability to detect the presence of licensed user quickly and accurately. In this paper, we have used UltraWideBand (UWB) to detect the presence of licensed users and transmit the sensing information among the nodes of the network. UWB has the capability of transmitting data at a very high rate. It is unique in co-existence capability with narrow band systems. Here, we have shown that the detection probability of licensed user is improved by means of transmitting the spectrum sensing information via UWB. We also have analyzed the throughput of the proposed technique and compared the result with existing sensing method.

• Journal of Korea Society of Industrial Information Systems
• /
• v.19 no.6
• /
• pp.43-51
• /
• 2014

TFT-LCD image includes a defect of various properties. TFT-LCD image have a recognizable defects in the human inspector. On the other hand, it is difficult to detect defects that difference between the background and defect is very low. In this paper, we proposed sequentially detect algorithm from pixels included in the defect region to limited defects. And blob analysis methods using the blob size and gray difference are applied to the defect candidate image. Finally, we detect an accurate defect blob to distinguish the noise. The experimental results show that the proposed method finds the various defects reliably.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.49 no.3
• /
• pp.81-88
• /
• 2012

In this paper, we propose a novel speech enhancement algorithm for effective noise suppression in various noisy environments. In the proposed method, to result in improved decision performance for speech and noise segments, local speech absence probability (LSAP, local SAP) based on Teager energy of noisy speech is used as the feature parameter for voice activity detection (VAD) in each frequency subband instead of conventional LSAP. In addition, The presented method utilizes global SAP (GSAP) derived in each frame as the weighting parameter for the modification of the adopted TE operator to improve the performance of TE operator. Performances of the proposed algorithm are evaluated by objective test under various environments and better results compared with the conventional methods are obtained.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.34 no.1
• /
• pp.11-18
• /
• 2010

Tool condition monitoring (TCM) is crucial for improvement of productivity in manufacturing process. However, TCM techniques have not been applied to monitor tool failure in an industrial gear shaving application. Therefore, this work studied a statistical TCM method for monitoring gear shaving tool condition. The method modeled the vibration signal of the shaving process using beta probability distribution in order to extract the effective features for TCM. Modeling includes rectifying for converting a bi-modal distribution into a unimodal distribution, estimating the parameters of beta probability distribution based on method of moments. The performance of features obtained from the proposed method was evaluated and discussed.

• Journal of the Institute of Electronics Engineers of Korea TC
• /
• v.46 no.1
• /
• pp.89-93
• /
• 2009

In this paper, we investigated effect of sensing time on the performance of enhanced spectrum sensing method, which is the energy detector with multiples of verification using time delay, under Suzuki channel. We assumed that SNR is 1dB, $P_{FA}=0.1$ and various mobile speed such as 3, 60, 110 km/h. The performance is investigated by simulation and compared to that of conventional energy detector.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.4 no.3
• /
• pp.189-196
• /
• 2011

In this paper, we analyze the error performance of SIC-based signal detection methods in MIMO systems. Considered detection methods are SIC signal detection and LR-SIC signal detection. We derive BLER performance of the methods and the performance is confirmed by computer simulations.

• Journal of Korea Multimedia Society
• /
• v.17 no.3
• /
• pp.294-299
• /
• 2014

In this paper, we propose a novel algorithm to improve the performance of a voice activity detection(VAD) which is based on the generalized normal-Laplace(GNL) distribution. In our algorithm, the probability density function(PDF) of the noisy speech signal is represented by the GNL distribution and the variance of the speech and noise of GNL distribution are estimated using higher order moments. Experimental results show that the proposed algorithm yields better results compared to the conventional VAD algorithms.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.26 no.10A
• /
• pp.1746-1755
• /
• 2001

본 논문에서는 인터넷 트래픽의 자기 유사성 특성을 이용한 큐 관리 기법을 제안한다. 제안 기법은 LRD 프로세스의 특성을 이용하여 큰 타임 스케일에서 다음 혼잡 검출 주기 동안 평균 트래픽 입력율을 예측하고 이를 통해 혼잡 발생 여부를 미리 검출한다. 혼잡 검출시 입력 패킷을 확률적으로 폐기함으로써 망 내부에서 혼잡 발생을 사전에 방지한다. 제안 기법은 종단 시스템의 혼잡 제어 기법이나 각 플로우의 통신 환경에 무관하게 라우터의 평균 큐 길이와 큐 길이 변이를 작게 유지할 수 있으므로 지연과 지연 변이에 민감한 멀티미디어 서비스 제어에 적합하다. 또한 제안 기법은 입력율 예측을 통해 혼잡을 사전에 검출하기 때문에 종단간 혼잡 제어 기법을 사용하지 않는 플로우들에 의해 발생된 패킷들이 망 자원을 불평등하게 많이 사용하는 현상을 방지한다. 제안 기법은 각 플로우별 상태 정보를 관리하지 않으므로 확장성이 뛰어나며 이로 인해 소수의 PHB에 따라 각 홉별로 차등화된 서비스를 제공하는 Diffserv 구조에 적합하다. 또한 제안 기법은 기존 인터넷 구조에 변화를 주지 않고 라우터의 소프트웨어 업그레이드만으로 서비스가 가능하며, 필요한 버퍼의 양도 크지 않다는 장점을 가진다.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2004.05b
• /
• pp.463-467
• /
• 2004

본 논문에서는 컬러정보를 이용하여 외부 조명의 영향에 대응하면서 얼굴 후보영역을 추출하고, 추출된 후보 영역으로부터 다채널 스킨컬러 모델로 특정 정보를 추출하는 검출 기법을 제시한다. 외부 조명에 민감한 스킨컬러 특성을 고려해 색상정보와 광도를 분리할 수 있는 Y $C_{r}$ , $C_{b}$ 색상모델을 이용하며, Green, Blue 채널의 정보를 Gaussian 확률밀도 모델로부터 $C_{b-}$ $C_{g}$ 의 좁은 범위에 분포되어 있는 스킨컬러 영역 밀도를 모델링한다. 또한 얼굴영역에 Region Restricting과 임계값 반복 알고리즘을 사용하여 눈 영역 검출 과정을 보이고, 실시간 복합 얼굴 검출 시스템 조명방식에 의해 결과를 나타낸다.다.