• Journal of the Korean Institute of Rural Architecture
• /
• v.21 no.4
• /
• pp.53-60
• /
• 2019

The purpose of this study is to investigate the change of Hidden gates form with the times. Fortresses position is constructed on the Korea mountain ranges. Hidden gate, one of facilities to construct fortress among various factors, represents as route of supplies way, ask for rescue, or counterattack plan to come in. The shape of hidden gate changes depend on land form, function, and time period. Previous research partially based on archeology or history. This research analyze Namhan mountain Namhansansung, one of the highest hidden gates count in Korea, distributive by main fortress, Bong-am fortress, Hanbong fortress. Nahhan Mountain fortress repeatedly affected by King Injo in Joseon Dynasty. As a result, Nahhan Mountain fortress consist of hidden gates alternation depend on the time of establishment or extension which makes different shape or size.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.17 no.2
• /
• pp.95-104
• /
• 2017

We investigate the God gate olleh of the largest tomb, pyramid, in the world which is scattered in Jeju Island and construct link which is connecting Jeju people's custom to modern science. The three sacred gates and the two tombs are connected to the olegil space. In this space, the principle of complementarity in which coexistence exist between life and death is hidden in Jeju culture. It is a question and wait. Contrarily, the opposite is complementary. (Contraria Sunt Complementa Latin) This refers to the relationship of each other in relation to one another and in a mutually dependent relationship. Seminal vesicles are used as basic logic in DNA codon of human body as well as communication principle.

• Annual Conference on Human and Language Technology
• /
• 2017.10a
• /
• pp.35-40
• /
• 2017

기계 독해(Machine reading comprehension)는 주어진 문맥을 이해하고, 질문에 적합한 답을 문맥 내에서 찾는 문제이다. Simple Recurrent Unit (SRU)은 Gated Recurrent Unit (GRU)등과 같이 neural gate를 이용하여 Recurrent Neural Network (RNN)에서 발생하는 vanishing gradient problem을 해결하고, gate 입력에서 이전 hidden state를 제거하여 GRU보다 속도를 향상시킨 모델이며, Self-matching Network는 R-Net 모델에서 사용된 것으로, 자기 자신의 RNN sequence에 대하여 어텐션 가중치 (attention weight)를 계산하여 비슷한 의미 문맥 정보를 볼 수 있기 때문에 상호참조해결과 유사한 효과를 볼 수 있다. 본 논문에서는 한국어 기계 독해 데이터 셋을 구축하고, 여러 층의 SRU를 이용한 Encoder에 Self-matching layer를 추가한 $S^2$-Net 모델을 제안한다. 실험 결과, 본 논문에서 제안한 $S^2$-Net 모델이 한국어 기계 독해 데이터 셋에서 EM 65.84%, F1 78.98%의 성능을 보였다.

• 한국어정보학회:학술대회논문집
• /
• 2017.10a
• /
• pp.35-40
• /
• 2017

기계 독해(Machine reading comprehension)는 주어진 문맥을 이해하고, 질문에 적합한 답을 문맥 내에서 찾는 문제이다. Simple Recurrent Unit (SRU)은 Gated Recurrent Unit (GRU)등과 같이 neural gate를 이용하여 Recurrent Neural Network (RNN)에서 발생하는 vanishing gradient problem을 해결하고, gate 입력에서 이전 hidden state를 제거하여 GRU보다 속도를 향상시킨 모델이며, Self-matching Network는 R-Net 모델에서 사용된 것으로, 자기 자신의 RNN sequence에 대하여 어텐션 가중치 (attention weight)를 계산하여 비슷한 의미 문맥 정보를 볼 수 있기 때문에 상호참조해결과 유사한 효과를 볼 수 있다. 본 논문에서는 한국어 기계 독해 데이터 셋을 구축하고, 여러 층의 SRU를 이용한 Encoder에 Self-matching layer를 추가한 $S^2$-Net 모델을 제안한다. 실험 결과, 본 논문에서 제안한 $S^2$-Net 모델이 한국어 기계 독해 데이터 셋에서 EM 65.84%, F1 78.98%의 성능을 보였다.

• ETRI Journal
• /
• v.41 no.3
• /
• pp.371-382
• /
• 2019

Machine reading comprehension is the task of understanding a given context and finding the correct response in that context. A simple recurrent unit (SRU) is a model that solves the vanishing gradient problem in a recurrent neural network (RNN) using a neural gate, such as a gated recurrent unit (GRU) and long short-term memory (LSTM); moreover, it removes the previous hidden state from the input gate to improve the speed compared to GRU and LSTM. A self-matching network, used in R-Net, can have a similar effect to coreference resolution because the self-matching network can obtain context information of a similar meaning by calculating the attention weight for its own RNN sequence. In this paper, we construct a dataset for Korean machine reading comprehension and propose an $S^2-Net$ model that adds a self-matching layer to an encoder RNN using multilayer SRU. The experimental results show that the proposed $S^2-Net$ model has performance of single 68.82% EM and 81.25% F1, and ensemble 70.81% EM, 82.48% F1 in the Korean machine reading comprehension test dataset, and has single 71.30% EM and 80.37% F1 and ensemble 73.29% EM and 81.54% F1 performance in the SQuAD dev dataset.

• Proceedings of the IEEK Conference
• /
• 2001.06b
• /
• pp.309-312
• /
• 2001

A primitive gas classification system which can classify limited species of gas was designed and simulated. The 'electronic nose' consists of an array of 4 metal oxide gas sensors with different selectivity patterns, signal collecting unit and a signal pattern recognition and decision Part in PLD(programmable logic device) chip. Sensor array consists of four commercial, tin oxide based, semiconductor type gas sensors. BP(back propagation) neutral networks with MLP(Multilayer Perceptron) structure was designed and implemented on CPLD of fifty thousand gate level chip by VHDL language for processing the input signals from 4 gas sensors and qualification of gases in air. The network contained four input units, one hidden layer with 4 neurons and output with 4 regular neurons. The 'electronic nose' system was successfully classified 4 kinds of industrial gases in computer simulation.

• Nuclear Engineering and Technology
• /
• v.56 no.9
• /
• pp.3740-3749
• /
• 2024

To reduce the losses caused by aging failure of insulation gate bipolar transistor (IGBT), which is the core components of nuclear power plant rod position indicating and rod control (RPC) system. It is necessary to conduct studies on its life prediction. The selection of IGBT failure characteristic parameters in existing research relies heavily on failure principles and expert experience. Moreover, the analysis and learning of time-domain degradation data have not been fully conducted, resulting in low prediction efficiency as the monotonicity, time correlation, and poor anti-interference ability of extracted degradation features. This paper utilizes the advantages of the stacked denoising autoencoder(SDAE) network in adaptive feature extraction and denoising capabilities to perform adaptive feature extraction on IGBT time-domain degradation data; establishes a long-short-term memory (LSTM) prediction model, and optimizes the learning rate, number of nodes in the hidden layer, and number of hidden layers using the Gray Wolf Optimization (GWO) algorithm; conducts verification experiments on the IGBT accelerated aging dataset provided by NASA PCoE Research Center, and selects performance evaluation indicators to compare and analyze the prediction results of the SDAE-LSTM model, PSOLSTM model, and BP model. The results show that the SDAE-LSTM model can achieve more accurate and stable IGBT life prediction.

• The Journal of the Acoustical Society of Korea
• /
• v.13 no.2E
• /
• pp.58-67
• /
• 1994

Hidden Markov Model (HMM)-based algorithms have been used successfully in many speech recognition systems, especially large vocabulary systems. Although general purpose processors can be employed for the system, they inevitably suffer from the computational complexity and enormous data. Therefore, it is essential for real-time speech recognition to develop specialized hardware to accelerate the recognition steps. This paper concerns with a real-time implementation of an isolated word recognition system based on HMM. The speech recognition system consists of a host computer (PC), a DSP board, and a prototype Viterbi scoring board. The DSP board extracts feature vectors of speech signal. The Viterbi scoring board has been implemented using three field-programmable gate array chips. It employs a hardware-efficient Viterbi scoring architecture and performs the Viterbi algorithm for HMM-based speech recognition. At the clock rate of 10 MHz, the system can update about 100,000 states within a single frame of 10ms.

• Journal of Physiology & Pathology in Korean Medicine
• /
• v.21 no.4
• /
• pp.795-802
• /
• 2007

The fire not to back to its origin(火不歸原) is said that source yang(元陽) of sea of qi(氣海) rises because fire(火) of lower energizer(下焦) can't return to its origin. Successive medical men regarded the cause of it as yang deficiency(陽虛) or yin deficiency(陰虛) generally, but Jangseoksun(張錫純) presented eight kinds of cause, they are syndrome of upcast yang(戴陽證), deficiency of qi(氣虛), yin deficiency, yin and yang deficiency(陰陽虛), thoroughfare qi ascending counterflow(衝氣上衝), heart fire(心火), yang deficiency with cold fluid retention(寒飮) in middle energizer(中焦寒飮), yang deficiency with sunken cold locked in(沈寒錮冷). The method of conducting fire back to its origin may be the treatment of fire not to back to its origin as an interpretation of the phrase in a broad sense, but it is limited to yang deficiency with sunken cold locked in besides syndrome of upcast yang as the treatment based on pathological conditions. By this standpoint Eunsuryong(殷壽龍) used conducting fire back to its origin to remove hidden cold(伏寒) and make rising false fire(假火) settle. The meaning of conducting fire back to its origin is not just raise yang qi(陽氣) but break sunken cold locked in by using the drugs like Buja(附子), Yukgye(肉桂). Jakyak(芍藥) can concentrate yang qi on the life gate(命門) by converging it, Sukjihwang(熟地黃) can supply yin essence(陰精) and check the intense nature of tonifing yang(補陽) drugs. So if we want to use the method of conducting fire back to its origin, we should confirm the symptoms of sunken cold locked in and yang deficiency not to misdiagnose yin deficiency.

• The Transactions of the Korean Institute of Electrical Engineers D
• /
• v.52 no.5
• /
• pp.290-294
• /
• 2003

Using a backpropagation neural network (BPNN), a high power semiconductor device was empirically modeled. The device modeled is a n-LDMOSFET and its electrical characteristics were measured with a HP4156A and a Tektronix curve tracer 370A. The drain-source current $(I_{DS})$ was measured over the drain-source voltage $(V_{DS})$ ranging between 1 V to 200 V at each gate-source voltage $(V_{GS}).$ For each $V_{GS},$ the BPNN was trained with 100 training data, and the trained model was tested with another 100 test data not pertaining to the training data. The prediction accuracy of each $V_{GS}$ model was optimized as a function of training factors, including training tolerance, number of hidden neurons, initial weight distribution, and two gradients of activation functions. Predictions from optimized models were highly consistent with actual measurements.