• 사물인터넷융복합논문지
• /
• 제8권2호
• /
• pp.79-84
• /
• 2022

본 논문은 문서의 보안과 손실 및 오염에 대하여 복원능력을 향상시키는 방안을 제안한다. 이를 위해서 암호화로 DnCNN(DeNoise Convolution Neural Network)을 제시한다. 암호화 방법을 구현하기 위하여 2D이미지정보를 광학에 사용되는 공간주파수 전달함수(Spatial Frequency Transfer Function)의 수학적 모델을 적용한다. 공간 주파수 전달함수를 사용하여 광학적 간섭 패턴을 암호화로 사용하고 공간 주파수 전달함수의 수학적 변수를 복호화하는 암호로 사용하는 방법을 제안하였다. 또한, 딥러닝을 적용한 DnCNN 방법을 적용하여 노이즈 제거하여 복원 성능을 개선한다. 실험결과, 65%의 정보 손실이 있는 경우에도 Pre-Training DnCNN Deep Learning을 적용한 결과 공간 주파수 전달함수만을 활용한 복원 결과 와 비교하여 PSNR(Peak Signal-to-noise ratio)을 11% 이상 우수한 성능을 확인할 수 있다. 또한, CC(Correlation Coefficient)의 특성도 16% 이상 우수한 결과를 보이고 있다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제15권10호
• /
• pp.3668-3684
• /
• 2021

Video action recognition is widely used in video surveillance, behavior detection, human-computer interaction, medically assisted diagnosis and motion analysis. However, video action recognition can be disturbed by many factors, such as background, illumination and so on. Two-stream convolutional neural network uses the video spatial and temporal models to train separately, and performs fusion at the output end. The multi segment Two-Stream convolutional neural network model trains temporal and spatial information from the video to extract their feature and fuse them, then determine the category of video action. Google Xception model and the transfer learning is adopted in this paper, and the Xception model which trained on ImageNet is used as the initial weight. It greatly overcomes the problem of model underfitting caused by insufficient video behavior dataset, and it can effectively reduce the influence of various factors in the video. This way also greatly improves the accuracy and reduces the training time. What's more, to make up for the shortage of dataset, the kinetics400 dataset was used for pre-training, which greatly improved the accuracy of the model. In this applied research, through continuous efforts, the expected goal is basically achieved, and according to the study and research, the design of the original dual-flow model is improved.

• 수산해양교육연구
• /
• 제19권3호
• /
• pp.403-414
• /
• 2007

The study aims at analyzing practices of vocational life of human resources in Busan. This study adopted a questionnaire method in research of university(14), college(12) and public & private vocational training institute(10) in Busan areas for empirical analysis. Analyzing items are consist of two parts. The one is employment life and job-seeking activity, the other is career development and future plan in career. The major findings of this study are summarized as follows. First, employees have had a 2-3 times job transfer experiences. Second, difficulties of job-seeking activity are lack of information and experience. Third, the best wanted region for job transfer is Seoul etc.

• 대한원격탐사학회지
• /
• 제39권4호
• /
• pp.395-407
• /
• 2023

Super-resolution (SR) has great significance in image processing because it enables downstream vision tasks with high spatial resolution. Recently, SR studies have adopted deep learning networks and achieved remarkable SR performance compared to conventional example-based methods. Deep-learning-based SR models generally require low-resolution (LR) images and the corresponding high-resolution (HR) images as training dataset. Due to the difficulties in obtaining real-world LR-HR datasets, most SR models have used only HR images and generated LR images with predefined degradation such as bicubic downsampling. However, SR models trained on simple image degradation do not reflect the properties of the images and often result in deteriorated SR qualities when applied to real-world images. In this study, we propose an image degradation model for HR satellite images based on the modulation transfer function (MTF) of an imaging sensor. Because the proposed method determines the image degradation based on the sensor properties, it is more suitable for training SR models on remote sensing images. Experimental results on HR satellite image datasets demonstrated the effectiveness of applying MTF-based filters to construct a more realistic LR-HR training dataset.

• 전자공학회논문지
• /
• 제54권5호
• /
• pp.35-41
• /
• 2017

본 논문에서는 지식추출(knowledge distillation) 및 지식전달(knowledge transfer)을 위하여 최근에 소개된 선생-학생 프레임워크 기반의 힌트(Hint)-knowledge distillation(KD) 학습기법에 대한 성능을 분석한다. 본 논문에서 고려하는 선생-학생 프레임워크는 현재 최신 딥러닝 모델로 각광받고 있는 딥 residual 네트워크를 이용한다. 따라서, 전 세계적으로 널리 사용되고 있는 오픈 딥러닝 프레임워크인 Caffe를 이용하여 학생모델의 인식 정확도 관점에서 힌트-KD 학습 시 선생모델의 완화상수기반의 KD 정보 비중에 대한 영향을 살펴본다. 본 논문의 연구결과에 따르면 KD 정보 비중을 단조감소하는 경우보다 초기에 설정된 고정된 값으로 유지하는 것이 학생모델의 인식 정확도가 더 향상된다는 것을 알 수 있었다.

• 한국수자원학회:학술대회논문집
• /
• 한국수자원학회 2005년도 학술발표회 논문집
• /
• pp.44-51
• /
• 2005

Water flow in rivers during flood season can be 10 to 100 fold higher than normal seasons (low precipitation) in Japan and predicting flood runoff is essential for operating reservoirs with discharging gates. Abundant experiences and knowledge are requisites for operators to be able to make efficient decisions at work. This research investigated a method to transfer technical knowledge by acquiring skills and knowledge from actual dam operators and by using the information to construct an educational training system. The purpose of the research was to enable the execution of a secure and rational reservoir operation during flood period. The educational training system for reservoir operation was developed with the focuses on acquiring knowledge on hydraulics and hydrology and learning about decision making related to the reservoir operation as well as the timing of control. The system is capable of conducting education that corresponds to individual levels in each location. Of the educational training methods, a lecture method that uses textbooks is effective for the understanding of basic knowledge and concepts while a training method that uses a simulation device is essential for the practice of advanced and specialized procedures in specific fields. Simulation devices are used in operational training for airplane flight and driving cars and trains. The educational system presented here was designed to provide further assistance to those who have acquired basic knowledge and concepts through textbooks and also to at low them to perform the satisfactory operation of dam equipment. Our research proposes a method which can realize a system to acquire technical skills-the skills which are the foundation of technical knowledge and operation.

• 동력기계공학회지
• /
• 제22권6호
• /
• pp.11-19
• /
• 2018

In this study, the authors examine the propulsion shafting of the training ship SAEDONGBAEK and perform modeling to analyze the torsional free vibration of the shafting. In this paper, the computational algorithm for analyzing the torsional free vibration of the shafting with a reduction gear is formulated by the sylvester-transfer stiffness coefficient method (S-TSCM) that is a recently developed and a powerful method in free vibration analysis. According to the state of the controllable pitch propeller of the shafting and the temperature of the elastic coupling, the torsional free vibration of the shafting is performed by the S-TSCM. The authors examine the changes of the natural frequencies and natural modes which are the results of the torsional free vibration analysis of the shafting.

• 한국응급구조학회지
• /
• 제15권2호
• /
• pp.67-84
• /
• 2011

Purpose: The aim of this study is to present the basic data for qualitative improvement of emergency care for emergency patient by paramedic in fire station by understanding the level of awareness and practice in prehospital and transfer step, and understanding the level of emergency care and improvement of clinical knowledge through hospital clinical training. Methods: The researchers explained the objective for 143 persons who completed hospital clinical training from June 2nd, 2006 to October 23rd, 2009 among paramedic in fire station. The questionnaire in this research consisted of 80 questions. In the reliability for the awareness of emergency patient assessment, cronbach's $\alpha$ was 0.95, and in the reliability for emergency care fulfillment, cronbach's $\alpha$ was 0.93. reliability for clinical knowledge improvement is cronbach's $\alpha=.95$, and reliability for emergency care fulfillment is cronbach's $\alpha=.82$. Collected data was analyzed through SPSS 18.0 statistics program for frequency, percentage, average, standard deviation, Paired t-test, t-test, Correlation Coefficient, and internal consistency reliability was analyzed by cronbach's $\alpha$. Results: 1) The paramedic awareness and practice difference for emergency patient is statistically signification for general patient assessment(t=14.159, p=.000), trauma patient assessment(t=11.288, p=.000), internal medicine patient assessment(t=10.898, p=.000), and it shows the level of practice is lower than the level of awareness. 2) The paramedic difference between the level of awareness and practice according to whether or not they have clinical career is not signification on awareness(t=3.119, p=.125), and is high on practice(t=3.119, p=.002). 3) The correlation between paramedic awareness and the level of practice shows positive correlation(r=.61, p=.000). The higher the awareness of emergency patient assessment is, the higher the level of practice is. 4) The difference between paramedic clinical knowledge improvement and the level of emergency care practice is statistically significant(t=3.351, p=.001). 5) 89.6%(128 persons) of paramedic replied hospital clinical training experiences are helpful for field activity. 92.3%(133 persons) replied they apply well for clinical knowledge learned during hospital clinical training and emergency care skills in the field. Conclusion: Paramedic in fire station must evaluate the patient's initial assessment and activate the transfer system to the emergency department. It is necessary to develop and implement the effective education program continuously. The education program should systemize currently operated hospital clinical training. emergency disease and symptoms emergency care method, and practice mainly skill education should be progressed. In the prehospital and transfer management, high quality of medical assessment is required to the emergency medical service system. Medical direction from the doctors can feedback the paramedic continuously and continuing education must be provided to the paramedic in fire station.

• 한국음향학회지
• /
• 제40권5호
• /
• pp.515-522
• /
• 2021

음성감정인식을 위한 훈련 데이터는 감정 레이블링의 어려움으로 인해 충분히 확보하기 어렵다. 본 논문에서는 음성감정인식의 성능 개선을 위해 트랜스포머 기반 모델에 대규모 음성인식용 훈련 데이터를 통한 전이학습을 적용한다. 또한 음성인식과의 다중작업학습을 통해 별도의 디코딩 없이 문맥 정보를 활용하는 방법을 제안한다. IEMOCAP 데이터 셋을 이용한 음성감정인식 실험을 통해, 가중정확도 70.6 % 및 비가중정확도 71.6 %를 달성하여, 제안된 방법이 음성감정인식 성능 향상에 효과가 있음을 보여준다.

• 대한기계학회논문집B
• /
• 제30권7호
• /
• pp.700-706
• /
• 2006

This study presents a numerical procedure to optimize the shape of dimple surface to enhance turbulent heat transfer in a rectangular channel. The response surface based optimization method is used as an optimization technique with Reynolds-averaged Wavier-Stokes analysis of fluid flow and heat transfer with shear stress transport (SST) turbulence model. The dimple depth-to-dimple print diameter ratio, channel height-to-dimple print diameter ratio, and dimple print diameter-to-pitch ratio are chosen as design variables. The objective function is defined as a linear combination of heat transfer related term and friction loss related term with a weighting factor. full factorial method is used to determine the training points as a mean of design of experiment. The optimum shape shows remarkable performance in comparison with a reference shape.