• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제15권5호
• /
• pp.1590-1609
• /
• 2021

Laughter is one of the most important nonverbal sound that human generates. It is a means for expressing his emotions. The acoustic and contextual features of this specific sound are different from those of speech and many difficulties arise during their modeling process. During this work, we propose an audio laughter generation system based on unsupervised generative models: the autoencoder (AE) and its variants. This procedure is the association of three main sub-process, (1) the analysis which consist of extracting the log magnitude spectrogram from the laughter database, (2) the generative models training, (3) the synthesis stage which incorporate the involvement of an intermediate mechanism: the vocoder. To improve the synthesis quality, we suggest two hybrid models (LSTM-VAE, GRU-VAE and CNN-VAE) that combine the representation learning capacity of variational autoencoder (VAE) with the temporal modelling ability of a long short-term memory RNN (LSTM) and the CNN ability to learn invariant features. To figure out the performance of our proposed audio laughter generation process, objective evaluation (RMSE) and a perceptual audio quality test (listening test) were conducted. According to these evaluation metrics, we can show that the GRU-VAE outperforms the other VAE models.

• JSTS:Journal of Semiconductor Technology and Science
• /
• 제17권3호
• /
• pp.411-424
• /
• 2017

An all-digital delay-locked loop (DLL) for a mobile memory interface, which runs at 0.11-2.5 GHz with a phase-shift capability of $180^{\circ}$, has two internal DLLs: a global DLL which uses a time-to-digital converter to assist fast locking, and shuts down after locking to save power; and a local DLL which uses a phase detector with an adaptive phase sampling window (WPD) to reduce jitter accumulation. The WPD in the local DLL adjusts the width of its sampling window adaptively to control the loop bandwidth, thus reducing jitter induced by UP/DN dithering, input clock jitter, and supply/ground noise. Implemented in a 65 nm CMOS process, the DLL operates over 0.11-2.5 GHz. It locks within 6 clock cycles at 0.11 GHz, and within 17 clock cycles at 2.5 GHz. At 2.5 GHz, the integrated jitter is $954fs_{rms}$, and the long-term jitter is $2.33ps_{rms}/23.10ps_{pp}$. The ratio of the RMS jitter at the output to that at the input is about 1.17 at 2.5 GHz, when the sampling window of the WPD is being adjusted adaptively. The DLL consumes 1.77 mW/GHz and occupies $0.075mm^2$.

• 대한임베디드공학회논문지
• /
• 제14권5호
• /
• pp.277-286
• /
• 2019

In this paper, we propose an efficient hyperplane generation technique to classify human activity from combination of events and sequence information obtained from multiple-event sensors. By generating hyperplane efficiently, our machine learning algorithm classify with less memory and run time than the LSVM (Linear Support Vector Machine) for embedded system. Because the fact that light weight and high speed algorithm is one of the most critical issue in the IoT, the study can be applied to smart home to predict human activity and provide related services. Our approach is based on reducing numbers of hyperplanes and utilizing robust string comparing algorithm. The proposed method results in reduction of memory consumption compared to the conventional ML (Machine Learning) algorithms; 252 times to LSVM and 34,033 times to LSTM (Long Short-Term Memory), although accuracy is decreased slightly. Thus our method showed outstanding performance on accuracy per hyperplane; 240 times to LSVM and 30,520 times to LSTM. The binarized image is then divided into groups, where each groups are converted to binary number, in order to reduce the number of comparison done in runtime process. The binary numbers are then converted to string. The test data is evaluated by converting to string and measuring similarity between hyperplanes using Levenshtein algorithm, which is a robust dynamic string comparing algorithm. This technique reduces runtime and enables the proposed algorithm to become 27% faster than LSVM, and 90% faster than LSTM.

• 사물인터넷융복합논문지
• /
• 제10권2호
• /
• pp.125-130
• /
• 2024

모빌리티 기술의 급격한 성장으로 산업 분야의 수요는 차량 내에 다양한 장비와 센서의 데이터를 안정적으로 처리할 수 있는 저장장치를 요구하고 있다. NAND 플래시 메모리는 외부에 강한 충격뿐만 아니라 저전력, 빠른 데이터 처리 속도의 장점이 있기 때문에 모빌리티 환경의 저장장치로 활용되고 있다. 그러나 플래시 메모리는 고온에 장기 노출될 경우 데이터 손상이 발생할 수 있는 특징이 있다. 따라서 태양 복사열 등 날씨나 외부 열원에 의한 고온 노출이 빈번한 모빌리티 환경에서는 온도를 관리하기 위한 전용 시스템이 필요하다. 본 논문은 모빌리티 환경에서 저장장치 온도 관리하기 위한 전용 온도 관리 시스템을 설계한다. 설계한 온도 관리 시스템은 전통적인 공기 냉각 방식과 수 냉각방식의 기술을 하이브리드로 적용하였다. 냉각 방식은 저장장치의 온도에 따라 적응형으로 동작하도록 설계하였으며, 온도 단계가 낮을 경우 동작하지 않도록 설계하여 에너지 효율을 높였다. 마지막으로 실험을 통해 각 냉각방식과 방열재질의 차이 따른 온도 차이를 분석하였고, 온도 관리 정책이 성능을 유지하는데 효과가 있음을 증명하였다.

• Journal of Ginseng Research
• /
• 제38권1호
• /
• pp.1-7
• /
• 2014

Background: Although ginsenosides such as Rg1, Rb1 and Rg3 have shown promise as potential nutraceuticals for cognitive impairment, their use has been limited due to high production cost and low potency. In particular, the process of extracting pure Rg3 from ginseng is laborious and expensive. Methods: We described the methods in preparing ginseol k-g3, an Rg3-enriched fraction, and evaluated its effects on scopolamine-induced memory impairment in mice. Results: Ginseol k-g3 (25-200 mg/kg) significantly reversed scopolamine-induced cognitive impairment in the passive avoidance, but not in Y-maze testing. Ginseol k-g3 (50 and 200 mg/kg) improved escape latency in training trials and increased swimming times within the target zone of the Morris water maze. The effect of ginseol k-g3 on the water maze task was more potent than that of Rg3 or Red ginseng. Acute or subchronic (6 d) treatment of ginseol k-g3 did not alter normal locomotor activity of mice in an open field. Ginseol k-g3 did not inhibit acetylcholinesterase activity, unlike donezepil, an acetylcholinesterase inhibitor. Rg3 enrichment through the ginseol k-g3 fraction enhanced the efficacy of Rg3 in scopolamine-induced memory impairment in mice as demonstrated in the Morris water maze task. Conclusion: The effects of ginseol k-g3 in ameliorating scopolamine-induced memory impairment in the passive avoidance and Morris water maze tests indicate its specific influence on reference or long-term memory. The mechanism underlying the reversal of scopolamine-induced amnesia by ginseol k-g3 is not yet known, but is not related to anticholinesterase-like activity.

• 디지털콘텐츠학회 논문지
• /
• 제13권2호
• /
• pp.213-224
• /
• 2012

창작과정은 인간의 총체적 경험을 담고 있는 기억으로부터 출발한다. 오늘날 디지털 기술의 발달로 인해 인간의 전유물로 여겨졌던 창작과정을 모방한 디지털 서사 창작도구의 개발이 이루어지고 있다. 본 논문은 CBR 모델을 통해 인간의 장기기억이 창작에 개입하는 과정을 모방하고자 한 두 서사 창작도구인 <민스트럴>과 <스토리헬퍼>를 비교분석하였다. <민스트럴>은 인물의 목표를 사례의 구축과 도출, 재사용의 중심에 두고 개연성 있는 이야기의 생성을 시도하였다. 한편 <스토리헬퍼>는 위반성을 지닌 모티프를 사례의 구축과 도출, 재사용의 중심에 둠으로써 이야기에 잠재해있는 우발성의 부각하고, 이를 통해 작가의 창작 발상을 지원하고자 하였다. 향후에는 다양한 서사물의 창작에 디지털 매체의 활용의 가속화될 전망이다. 이 같은 전망 속에서 본 연구가 앞으로의 서사 창작 지원도구 도움이 될 수 있을 것으로 기대해본다.

• 대한공간정보학회지
• /
• 제5권2호
• /
• pp.193-205
• /
• 1997

대용량의 매핑 자료를 다수의 사용자들이 효율적으로 공유하는데는 클라이언트-서버 환경에서 복제 일관성을 위한 분산 모델 개발이 요구된다. 기존의 분산 모델은 각 사이트들의 사본간의 일관성을 강조했으나 GUI를 이용한 화면과 사본간의 일관성이 고려되지 못하여 매핑 시스템과 같은 장기 트랜잭션에는 적합하지 않다. 매핑자료의 특성상 분산 환경에서 트랜잭션들의 일관성을 유지하는데는 시간 지연이 많으므로 병행효율이 중요하다. 본 연구에서는 디스플레이 록을 이용하여 GUI 화면과 사본들 사이의 일관성을 지원한다. 매핑자료의 특성을 이용하여 낙관적 병행제어 기법과 일관성 모델을 개선하여, 처리효율을 향상하는 일관성 모델을 제시한다.

• 산업공학
• /
• 제23권3호
• /
• pp.229-238
• /
• 2010

Virtual metrology (VM), a critical component of semiconductor manufacturing, is an efficient way of assessing the quality of wafers not actually measured. This is done based on a model between equipment sensor data (obtained for all wafers) and the quality characteristics of wafers actually measured. This paper considers principal component regression (PCR), partial least squares regression (PLSR), kernel PCR (KPCR), and kernel PLSR (KPLSR) as VM models. For each regression model, two cases are considered. One utilizes all explanatory variables in developing a model, and the other selects significant variables using the genetic algorithm (GA). The prediction performances of 8 regression models are compared for the short- and long-term etch process data. It is found among others that the GA-KPLSR model performs best for both types of data. Especially, its prediction ability is within the requirement for the short-term data implying that it can be used to implement VM for real etch processes.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2001년도 하계종합학술대회 논문집(5)
• /
• pp.25-28
• /
• 2001

This paper introduce a millimeter-wave radar system. As Fig 1 shows, This system consists of millimeter-wave radar front-end and digital signal processing parts through receive waves regarding up-coming obstacles. The system works as follow process; (1) Generate regular tripodal waves using the FMCW pulse generator (2) Transmit/Receive waves regarding up-coming obstacles (3) Analog filtering (4) FIFO memory interface (5) FFT(Fast Fourier Transform) (6) Calculation of distance / speed between cars (7) Object display and calibration. We have progress to solve the problem like as increase of traffic accidents causing damage and injuries due to the increased number of motor vehicles and long distance driving, and Need for a device to help drivers who are in trouble due to bad weather conditions. We are expect to Take the lead as a core technology in the ITS industry and to develop circuit and signal processing technologies related to millimeter-wave bandwidth.

• International Journal of Computer Science & Network Security
• /
• 제21권7호
• /
• pp.159-168
• /
• 2021

Detecting cyber-attacks using machine learning or deep learning is being studied and applied widely in network intrusion detection systems. We noticed that the application of deep learning algorithms yielded many good results. However, because each deep learning model has different architecture and characteristics with certain advantages and disadvantages, so those deep learning models are only suitable for specific datasets or features. In this paper, in order to optimize the process of detecting cyber-attacks, we propose the idea of building a new deep learning network model based on the association and combination of individual deep learning models. In particular, based on the architecture of 2 deep learning models: Convolutional Neural Network (CNN) and Long Short Term Memory (LSTM), we combine them into a combined deep learning network for detecting cyber-attacks based on network traffic. The experimental results in Section IV.D have demonstrated that our proposal using the CNN-LSTM deep learning model for detecting cyber-attacks based on network traffic is completely correct because the results of this model are much better than some individual deep learning models on all measures.