• 디지털콘텐츠학회 논문지
• /
• 제8권4호
• /
• pp.441-449
• /
• 2007

동영상 부호화에서 움직임 추정은 참조 프레임으로부터 현재 프레임의 화소를 추정하는 처리로서 예측 화질과 부호화 시간에 직접적인 영향을 미친다. 본 논문은 고속 움직임 추정을 위해 시공간 움직임 활동도를 이용한 적응형 계층 육각 탐색에 관한 것이다. 제안된 방법은 현재의 매크로블록에 시공간적으로 인접한 매크로블록들의 움직임 벡터를 이용하여 시공간 움직임 활동도를 정의한다. 이렇게 정의한 시공간 움직임 활동도가 낮을 경우 기존의 적응형 육각 탐색을 수행하고, 그렇지 않을 경우, 웨이블렛 변환의 다단계 저주파 부영상들로 구성된 다단계 계층 공간상에서 계층 육각 탐색을 수행한다. 본 논문에서는 서로 다른 움직임 특성을 갖는 복수의 동영상 시퀀스들에 대한 컴퓨터 시뮬레이션 결과를 토대로 예측 화질과 연산 시간 측면에서 제안된 방법의 성능을 분석.평가하였다. 실험 결과는 제안된 방법이 작은 움직임 탐색과 큰 움직임 탐색에 모두 적합함을 보여주고 있다. 제안된 방법은 고속 움직임 탐색이 가능한 적응형 육각 탐색의 장점을 유지하면서도 시공간 움직임 활동도가 높은 비디오 시퀀스에서 야기되는 국부 최소 문제를 적응적으로 경감할 수 있었다.

• BMB Reports
• /
• 제54권7호
• /
• pp.386-391
• /
• 2021

Owing to rapid advancements in NGS (next generation sequencing), genomic alteration is now considered an essential predictive biomarkers that impact the treatment decision in many cases of cancer. Among the various predictive biomarkers, tumor mutation burden (TMB) was identified by NGS and was considered to be useful in predicting a clinical response in cancer cases treated by immunotherapy. In this study, we directly compared the lab-developed-test (LDT) results by target sequencing panel, K-MASTER panel v3.0 and whole-exome sequencing (WES) to evaluate the concordance of TMB. As an initial step, the reference materials (n = 3) with known TMB status were used as an exploratory test. To validate and evaluate TMB, we used one hundred samples that were acquired from surgically resected tissues of non-small cell lung cancer (NSCLC) patients. The TMB of each sample was tested by using both LDT and WES methods, which extracted the DNA from samples at the same time. In addition, we evaluated the impact of capture region, which might lead to different values of TMB; the evaluation of capture region was based on the size of NGS and target sequencing panels. In this pilot study, TMB was evaluated by LDT and WES by using duplicated reference samples; the results of TMB showed high concordance rate (R² = 0.887). This was also reflected in clinical samples (n = 100), which showed R² of 0.71. The difference between the coding sequence ratio (3.49%) and the ratio of mutations (4.8%) indicated that the LDT panel identified a relatively higher number of mutations. It was feasible to calculate TMB with LDT panel, which can be useful in clinical practice. Furthermore, a customized approach must be developed for calculating TMB, which differs according to cancer types and specific clinical settings.

• 한국통신학회논문지
• /
• 제11권4호
• /
• pp.287-295
• /
• 1986

본 논문에서는 디지털 이동 무선통신을 위한 음성신호와 부호화 기법으로 SBC(sub-bnad coding)를 제안하고, SBC의 레일리(Rayleigh) 페이딩 채널에서의 음질의 강인성을 컴퓨터 시뮬레이션을 통해 조사하였다. 먼저 레일리 페이딩 채널, 시뮬레이터 및 16-ary DPSK(differential phase shift key) 수신기 모델을 제시한 후, 모델의 타당성을 이론치와 비교하여 입증하였다. 채널에러에 대한 영향은 SNR, LPC(linear predictive codin) 거리척도 및 주관적인 청각조사를 통해 검토하였다. BER(bit error rate) =$10_{-3}$, $10_{-2}$, 5$ imes$$10_{-2}$에 대한 시뮬레이션결과 BER=$10_{-2}$에서도 음성의 이해도는 확인되었으며, BER=5$ imes$$10_{-2}$에서도 음성통신에 사용하기는 충분하였다. 따라서 SBC는 ECC(error correction code) 사용없이 BER=$10_{-4}$~$10_{-2}$정도의 레일리 페이딩 채널에서 디지탈 이동무선통신에 응용이 가능함을 알 수 있었다.

• The Journal of the Acoustical Society of Korea
• /
• 제17권2E호
• /
• pp.31-37
• /
• 1998

This paper proposes a feature extraction method using wavelet transform for speech recognition. Speech recognition system generally carries out the recognition task based on speech features which are usually obtained via time-frequency representations such as Short-Time Fourier Transform (STFT) and Linear Predictive Coding(LPC). In some respects these methods may not be suitable for representing highly complex speech characteristics. They map the speech features with same may not frequency resolutions at all frequencies. Wavelet transform overcomes some of these limitations. Wavelet transform captures signal with fine time resolutions at high frequencies and fine frequency resolutions at low frequencies, which may present a significant advantage when analyzing highly localized speech events. Based on this motivation, this paper investigates the effectiveness of wavelet transform for feature extraction of wavelet transform for feature extraction focused on enhancing speech recognition. The proposed method is implemented using Sampled Continuous Wavelet Transform (SCWT) and its performance is tested on a speaker-independent isolated word recognizer that discerns 50 Korean words. In particular, the effect of mother wavelet employed and number of voices per octave on the performance of proposed method is investigated. Also the influence on the size of mother wavelet on the performance of proposed method is discussed. Throughout the experiments, the performance of proposed method is discussed. Throughout the experiments, the performance of proposed method is compared with the most prevalent conventional method, MFCC (Mel0frequency Cepstral Coefficient). The experiments show that the recognition performance of the proposed method is better than that of MFCC. But the improvement is marginal while, due to the dimensionality increase, the computational loads of proposed method is substantially greater than that of MFCC.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2004년도 ICCAS
• /
• pp.1033-1036
• /
• 2004

The study on speech recognition and understanding has been done for many years. In this paper, we propose a new type of recurrent neural network architecture for speech recognition, in which each output unit is connected to itself and is also fully connected to other output units and all hidden units [1]. Besides that, we also proposed the new architecture and the learning algorithm of recurrent neural network such as Backpropagation Through Time (BPTT, which well-suited. The aim of the study was to observe the difference of Arabic's alphabet like "alif" until "ya". The purpose of this research is to upgrade the people's knowledge and understanding on Arabic's alphabet or word by using Recurrent Neural Network (RNN) and Backpropagation Through Time (BPTT) learning algorithm. 4 speakers (a mixture of male and female) are trained in quiet environment. Neural network is well-known as a technique that has the ability to classified nonlinear problem. Today, lots of researches have been done in applying Neural Network towards the solution of speech recognition [2] such as Arabic. The Arabic language offers a number of challenges for speech recognition [3]. Even through positive results have been obtained from the continuous study, research on minimizing the error rate is still gaining lots attention. This research utilizes Recurrent Neural Network, one of Neural Network technique to observe the difference of alphabet "alif" until "ya".

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2004년도 학술대회 논문집 정보 및 제어부문
• /
• pp.310-312
• /
• 2004

The aim of this study was to analyze the characteristics of knee joint sound in frequency domain and classify the knee joint diseases. The spectral analysis of knee joint sounds was performed using LPC(Linear Predictive Coding) and Wigner-Ville distribution. Ten normal subjects and 5 patients with meniscal tearing were enrolled. Each subject was seated on a chair and underwent active knee flexion and extension for 60 seconds. Sampling frequency was 10kHz and electronic stethoscope and electro-goniometer were applied during the knee motion for data collection. The spectral analysis showed 3 peaks in both groups and the difference energy distribution in time-frequency domain. These results suggest that the diagnosis of knee joint pathology using the auscultation could be easier and more correct.

• 한국음향학회:학술대회논문집
• /
• 한국음향학회 2004년도 춘계학술발표대회 논문집 제23권 1호
• /
• pp.41-44
• /
• 2004

본 논문에서는 한국어에만 나타나는 경음에 대하여 음운학적, 음향학적 특성을 고찰하고 이를 기반으로 음성인식 실험을 수행한 후 그 결과를 분석하였다. 음성인식 실험을 위하여 입력 음성을 48개의 유사음소단위 (PLU; Phoneme Likely Unit)로 레이블링을 한 후 각각의 음소군에 대하여 LPC (Liner Predictive Coding) 분해능을 증가시키면서 음소인식 및 단어인식 실험을 수행하였다. 그 결과, 음소 인식 실험에서 경음군의 인식률이 가장 낮게 나타나 경음에 대한 분석이 보다 많이 필요함을 알 수 있었다. 또한 PLC의 분해 차원이 23차 일 때 경음과 전체 음소 인식률이 각각 $34.11\%,\;46.1\%$로 나타나 가장 양호함을 알 수 있었으며 단어인식 실험에서도 LPC 23차와 25차 일 때 $81.68\%,\;81.87\%$로 인식률이 가장 좋음을 알 수 있었다. 이상의 실험 결과에서 한국어의 경음은 전체 시스템의 인식 성능과 밀접한 관계가 있음을 알 수 있었다.

• 한국소음진동공학회논문집
• /
• 제21권11호
• /
• pp.1020-1028
• /
• 2011

As rotating machines play an important role in industrial applications such as aeronautical, naval and automotive industries, many researchers have developed various condition monitoring system and fault diagnosis system by applying artificial neural network. Since using obtained signals without preprocessing as inputs of neural network can decrease performance of fault classification, it is very important to extract significant features of captured signals and to apply suitable features into diagnosis system according to the kinds of obtained signals. Therefore, this paper proposes a neural-network-based fault diagnosis system using AR coefficients as feature vectors by LPC(linear predictive coding) and EIV(errors-in variables) analysis. We extracted feature vectors from sound, vibration and current faulty signals and evaluated the suitability of feature vectors depending on the classification results and training error rates by changing AR order and adding noise. From experimental results, we conclude that classification results using feature vectors by EIV analysis indicate more than 90 % stably for less than 10 orders and noise effect comparing to LPC.

• 음성과학
• /
• 제10권2호
• /
• pp.99-109
• /
• 2003

The purpose of this study was to analyze and compare head register with chest register of singers acoustically. Fifteen healthy tenor major students were participated. Fifteen healthy untrained adults were chosen as the control group for this study. Long term average (LTA) power spectrum using the Fast Fourier transform (FFT) algorithm and Linear predictive coding (LPC) filter response were made with /a/ sustained in both head (G4, 392 Hz) and chest registers (C3, 131 Hz). Statistical analysis was performed using the Mann-Whitney test. In the LTA power spectrum, head register of singers increased in the level of energy gain within the frequency of 2.2-3.4 kHz (p<0.01), and 7.5-8.4 kHz (p<0.01, p<0.05). Chest register of singers increased in the frequency of 2.2-3.1 kHz (p<0.01), 7.8-8.4 kHz (p<0.05) and around 9.6 kHz (p<0.01). The LTA power spectrum revealed a peak of acoustic energy around 2,500 Hz, known as the singer's formant and another peak of acoustic energy around 8,000 Hz in the singer's voice.

• 한국멀티미디어학회논문지
• /
• 제20권11호
• /
• pp.1811-1819
• /
• 2017

As the induction motor is the core production equipment of the industry, it is necessary to construct a fault prediction and diagnosis system through continuous monitoring. Many researches have been conducted on motor fault diagnosis algorithm based on signal processing techniques using Fourier transform, neural networks, and fuzzy inference techniques. In this paper, we propose a fault diagnosis method of induction motor using LPC and DNN. To evaluate the performance of the proposed method, the fault diagnosis was carried out using the vibration data of the induction motor in steady state and simulated various fault conditions. Experimental results show that the learning time of our proposed method and the conventional spectrum+DNN method is 139 seconds and 974 seconds each executed on the experimental PC, and our method reduces execution time by 1/8 compared with conventional method. And the success rate of the proposed method is 98.08%, which is similar to 99.54% of the conventional method.