• 대한두경부종양학회지
• /
• 제15권2호
• /
• pp.166-171
• /
• 1999

Background and Objectives: The aim of our study was to describe the appearance of recurrent and residual lesions in the head and neck tumors, and to evaluate the usefullness of CT and MRI. Materials and Methods: CT(n=42) and MRI(n=4) of 44 patients with recurrent head and neck tumors were reviewed retrospectively. Primary tumor sites were larynx/hypopharynx in 15, oral cavity/floor of mouth in 13, base of tongue/tonsil in 5, nasopharynx in 4, palate in 2, and others in 5 patients. Therapeutic modalities included sugery and radiotherapy in 23, radiotherapy in 11, surgery in 5, chemotherapy and radiotherapy in 4, and chemotherapy in 1 patient. Results: The patterns of tumor recurrence were nodal recurrence(n=17), primary tumor bed recurrence combined with nodal recurrence(n=12), primary tumor bed recurrence(n=10) and residual primary tumors(n=5). The most common appearance of residual/recurrent primary tumor on CT was focal or diffuse heterogenous mass with or without surrounding fat or muscle infiltration(25/27). On MRI, the recurrent lesions showed intermediate signal intensity on T1 weighted image and high signal intensity on T2 weighted image with heterogenous enhancement in the most cases(n=3). 38 out of 44 nodal recurrences(86%) which had been pathologically or clinically proved were more than 1 cm in diameter or contained central low density on CT scan. Conclusion: Although CT and MRI findings of recurrent and residual tumors of the head and neck were nonspecific, in the majority the lesions manifested as a mass at primary tumor bed and/or nodal disease including contralateral side of the neck. And CT and MRI are valuable for revealing above lesions.

• 한국컴퓨터정보학회논문지
• /
• 제17권3호
• /
• pp.11-25
• /
• 2012

이 논문은 이진 삼차 재귀 신경망(Binary Third-order Recurrent Neural Networks: BTRNN)에 유전자 알고리즘을 적용하여 문맥-자유 문법을 추론하는 방법을 제안한다. BTRNN은 각 입력심볼에 대응되는 재귀 신경망들의 다층적 구조이고 외부의 스택과 결합된다. BTRNN의 매개변수들은 모두 이진수로 표현되며 상태 전이와 동시에 스택의 한 동작이 실행된다. 염색체로 표현된 BTRNN들에 유전자 알고리즘을 적용하여 긍정과 부정의 입력 패턴들의 문맥-자유 문법을 추론하는 최적의 BTRNN를 얻는다. 이 방법은 기존의 신경망 이용방법보다 적은 학습량과 적은 학습회수로 작거나 같은 상태 수를 갖는 BTRNN을 추론한다. 또한 문법 표현의 염색체 이용방법보다 parsing과정에서 결정적인 상태전이와 스택동작이 실행되므로 입력 패턴에 대한 인식처리 시간복잡도가 우수하다. 문맥-자유 문법의 비단말 심볼의 개수 p, 단말 심볼의 개수 q, 그리고 길이가 k인 문자열이 입력이 될 때, BTRNN의 최대 상태수가 m이라고 하면, BTRNN의 인식처리 병렬처리 시간은 O(k)이고 순차처리 시간은 O(km)이다.

• 반도체디스플레이기술학회지
• /
• 제22권2호
• /
• pp.6-10
• /
• 2023

High-potential data can be predicted and stored in the cache to prevent cache misses, thus reducing the processor's request and wait times. As a result, the processor can work non-stop, hiding memory latency. By utilizing the temporal/spatial locality of memory access, the prefetcher introduced to improve the performance of these computers predicts the following memory address will be accessed. We propose a prefetcher that applies the GRU model, which is advantageous for handling time series data. Display the currently accessed address in binary and use it as training data to train the Gated Recurrent Unit model based on the difference (delta) between consecutive memory accesses. Finally, using a GRU model with learned memory access patterns, the proposed data prefetcher predicts the memory address to be accessed next. We have compared the model with the multi-layer perceptron, but our prefetcher showed better results than the Multi-Layer Perceptron.

• 전기학회논문지
• /
• 제67권11호
• /
• pp.1536-1541
• /
• 2018

For effective electricity consumption in urban railway station such as peak load shaving, it is important to know each electrical load pattern by various usage. The total electricity consumption in the urban railway substation is already measured in Korea, but the electricity consumption for each usage is not measured. The author proposed the deep learning method to estimate the electrical load pattern for each usage in the urban railway substation with public data such as weather data. GRU (gated recurrent unit), a variation on the LSTM (long short-term memory), was used, which aims to solve the vanishing gradient problem of standard a RNN (recursive neural networks). The optimal model was found and the estimation results with that were assessed.

• Journal of Korean Neurosurgical Society
• /
• 제45권6호
• /
• pp.401-404
• /
• 2009

Arteriovenous malformations (AVM) are generally considered to be cured following angiographically proven complete resection. However, rare instances of AVM recurrence have been reported in both children and adults with negative findings on postoperative angiography. The authors present the case of a 12-year-old boy with recurrent AVM. The AVM was originally fed by the pericallosal arteries on both sides, and it showed changing patterns of supply at recurrence. The authors concluded that a negative postoperative angiogram is not necessarily indicative of a cure. Repeat angiography and regular follow-up examinations should be performed to exclude the possibility of recurrence, especially in children.

• Annals of Clinical Neurophysiology
• /
• 제1권1호
• /
• pp.64-69
• /
• 1999

Background : Syncope was defined as transient loss of consciousness and postural tone. The mechanisms of changes in cerebral hemodynamics during syncope have not been fully evaluated. Transcranial Doppler Ultrasonography can continuously monitor the changes in cerebral hemodynamics during head-up tilt (HUT). TCD could reveal the different patterns of changes in cerebral hemodynamics during syncope. Syncope without hypotension or bradycardia could be detected by TCD. We investigated the changes in cerebral blood flow velocity during HUT using TCD in 33 patients with a history of recurrent syncope or presyncope of unknown origin. Methods & Results : The positive responses were defined as presyncope or syncope with hypotension, bradycardia, or both. During HUT without isoproterenol infusion, there were a $86{\pm}23%$ drop in DV and a $41{\pm}34%$ drop in SV in 5 patients with positive reponses, and mean changes in those were less than 10% in patients with negative reponses (p=.00, p=.00). During HUT with isoproterenol infusion, TCD showed a $80{\pm}18%$ drop in diastolic velocity in 14 patients with positive reponses, and a $47{\pm}10%$ drop in that in patients with negative reponses (p=.00), however the change in systolic velocity did not differ. TCD showed three patterns during positive responses; loss of all flow, loss of end diastolic flow, and a decrease in diastolic velocity. Loss of consciousness occurred in the patients with loss of all flow or end-diastolic flow during positive reponses. Conclusions : TCD shows different patterns of changes in cerebral hemodynamics during HUT. TCD can be used to investigate the pathophysiology of neurocardiogenic syncope.

• 정보처리학회논문지:소프트웨어 및 데이터공학
• /
• 제6권4호
• /
• pp.203-210
• /
• 2017

본 논문에서는 이미지 캡션 생성과 모델 전이에 효과적인 심층 신경망 모델을 제시한다. 본 모델은 멀티 모달 순환 신경망 모델의 하나로서, 이미지로부터 시각 정보를 추출하는 컨볼루션 신경망 층, 각 단어를 저차원의 특징으로 변환하는 임베딩 층, 캡션 문장 구조를 학습하는 순환 신경망 층, 시각 정보와 언어 정보를 결합하는 멀티 모달 층 등 총 5 개의 계층들로 구성된다. 특히 본 모델에서는 시퀀스 패턴 학습과 모델 전이에 우수한 LSTM 유닛을 이용하여 순환 신경망 층을 구성하며, 캡션 문장 생성을 위한 매 순환 단계마다 이미지의 시각 정보를 이용할 수 있도록 컨볼루션 신경망 층의 출력을 순환 신경망 층의 초기 상태뿐만 아니라 멀티 모달 층의 입력에도 연결하는 구조를 가진다. Flickr8k, Flickr30k, MSCOCO 등의 공개 데이터 집합들을 이용한 다양한 비교 실험들을 통해, 캡션의 정확도와 모델 전이의 효과 면에서 본 논문에서 제시한 멀티 모달 순환 신경망 모델의 높은 성능을 확인할 수 있었다.

• 한국물환경학회지
• /
• 제39권1호
• /
• pp.46-60
• /
• 2023

Climate change causes fluctuations in water quality in the aquatic environment, which can cause changes in water circulation patterns and severe adverse effects on aquatic ecosystems in the future. Therefore, research is needed to predict and respond to water quality changes caused by climate change in advance. In this study, we tried to predict the dissolved oxygen (DO), chlorophyll-a, and turbidity of the Paldang reservoir for about two weeks using long short-term memory (LSTM) and gated recurrent units (GRU), which are deep learning algorithms based on recurrent neural networks. The model was built based on real-time water quality data and meteorological data. The observation period was set from July to September in the summer of 2021 (Period 1) and from March to May in the spring of 2022 (Period 2). We tried to select an algorithm with optimal predictive power for each water quality parameter. In addition, to improve the predictive power of the model, an important variable extraction technique using random forest was used to select only the important variables as input variables. In both Periods 1 and 2, the predictive power after extracting important variables was further improved. Except for DO in Period 2, GRU was selected as the best model in all water quality parameters. This methodology can be useful for preventive water quality management by identifying the variability of water quality in advance and predicting water quality in a short period.

• 한국수학교육학회지시리즈D:수학교육연구
• /
• 제18권3호
• /
• pp.187-208
• /
• 2014

This study engages in the features of interaction in elementary school mathematics lessons as reflected in the class discourse. 28 pre-service teachers documented the discourse during observation of their tutor-teachers' lessons. Mapping the interaction patterns was performed by a unique graphic model developed for that purpose and enabled providing a spatial picture of the discourse conducted in the lesson. The research findings present the known discourse pattern "initiation-response-evaluation / feedback" (IRE/F) which is recurrent in all the lessons and the teacher's exclusive control over the class discourse patterns. Hence, the remaining time of the lesson for the pupils' discourse is short and meaningless.

• 한국음향학회지
• /
• 제36권6호
• /
• pp.407-412
• /
• 2017

본 논문에서는 주목 메커니즘 기반의 심층 신경망을 사용한 음성 감정인식 방법을 제안한다. 제안하는 방식은 CNN(Convolution Neural Networks), GRU(Gated Recurrent Unit), DNN(Deep Neural Networks)의 결합으로 이루어진 심층 신경망 구조와 주목 메커니즘으로 구성된다. 음성의 스펙트로그램에는 감정에 따른 특징적인 패턴이 포함되어 있으므로 제안하는 방식에서는 일반적인 CNN에서 컨벌루션 필터를 tuned Gabor 필터로 사용하는 GCNN(Gabor CNN)을 사용하여 패턴을 효과적으로 모델링한다. 또한 CNN과 FC(Fully-Connected)레이어 기반의 주목 메커니즘을 적용하여 추출된 특징의 맥락 정보를 고려한 주목 가중치를 구해 감정인식에 사용한다. 본 논문에서 제안하는 방식의 검증을 위해 6가지 감정에 대해 인식 실험을 진행하였다. 실험 결과, 제안한 방식이 음성 감정인식에서 기존의 방식보다 더 높은 성능을 보였다.