• Journal of Multimedia Information System
• /
• 제6권4호
• /
• pp.209-216
• /
• 2019

Over the past decade, researchers were able to solve complex medical problems as well as acquire deeper understanding of entire issue due to the availability of machine learning techniques, particularly predictive algorithms and automatic recognition of patterns in medical imaging. In this study, a technique called transfer learning has been utilized to classify Magnetic Resonance (MR) images by a pre-trained Convolutional Neural Network (CNN). Rather than training an entire model from scratch, transfer learning approach uses the CNN model by fine-tuning them, to classify MR images into Alzheimer's disease (AD), mild cognitive impairment (MCI) and normal control (NC). The performance of this method has been evaluated over Alzheimer's Disease Neuroimaging (ADNI) dataset by changing the learning rate of the model. Moreover, in this study, in order to demonstrate the transfer learning approach we utilize different pre-trained deep learning models such as GoogLeNet, VGG-16, AlexNet and ResNet-18, and compare their efficiency to classify AD. The overall classification accuracy resulted by GoogLeNet for training and testing was 99.84% and 98.25% respectively, which was exceptionally more than other models training and testing accuracies.

• 컴퓨터교육학회논문지
• /
• 제5권4호
• /
• pp.147-154
• /
• 2002

본 연구에서는 경도 정신지체인의 컴퓨터 교육의 효과를 높이기 위해 학습에 참여하고자 하는 학습 동기 유발에 무상토큰에 의한 반응대가 기법이 어느 정도 효과가 있는지 알아보았다. 경도 정신지체인을 대상으로 워드프로세서 프로그램의 표작성 부분을 실험과목으로 설정하고 잘못된 줄 수 입력, 잘못된 칸 수 입력, 잘못된 선 종류, 잘못된 셀 합치기 등 총 4가지의 표적행동을 설정한 후 기초선 기간 I, 처치 기간 I, 기초선 기간 II, 처치 기간 II 총 36회의 실험기간동안 행동관찰 기록카드에 관찰 결과를 기록하였다. 수정된 행동의 유지 여부를 알아보기 위해 2주 후 사후 점검을 6회 실시하였다. 그 결과를 분석해본 결과 무상토큰에 의한 반응대가 기법이 경도 정신지체인의 컴퓨터 교육에 효과가 있는 것을 알 수 있었다.

• International journal of advanced smart convergence
• /
• 제9권1호
• /
• pp.202-208
• /
• 2020

Body balance necessary for ordinary daily activities can be undermined by diverse causes. In this study, as a way to control such a problem, we have produced smart insole as a wearable device in the form of insole and developed analysis software evaluating body balance, which measures ground reaction force applied to each area of sole and Center of Pressure (COP). The software visualized changes in COP positions while a user was moving and average COP positions, and it is also capable of measuring the COP values in the Anterior-Posterior (AP) and Medial-Lateral (ML) areas of feet. Through gait analysis, it can analyze the time of walking, strides, speed, COP trajectory while walking, etc. In addition, we have developed training contents for body balance improvement designed in consideration of Y-Balance Test and Timed Up and Go (TUG) Test. They were established in virtual reality similar to daily living environment so that people can expect more effective training results regardless of places.

• 정보교육학회논문지
• /
• 제13권1호
• /
• pp.23-30
• /
• 2009

이 연구에서 제안한 교육프로그램은 예비교사들을 대상으로 인지심리학의 개념습득 이론 중 원형이론과 본보기 이론의 상호보완을 통하여 정보교육의 필요성과 개념을 습득하도록 하였다. 또한 언플러그드형 수업사례 시연활동을 통하여 컴퓨터과학에 관한 지식이 부족한 학습자들에게 교수-학습 설계능력을 향상시키고, 컴퓨터과학의 개념과 원리를 습득할 수 있도록 하였다. 예비교사들에게 적용해본 결과 효과성이 높은 유의미한 결과를 얻을 수 있었다.

• 한국초전도ㆍ저온공학회논문지
• /
• 제24권3호
• /
• pp.24-29
• /
• 2022

One of the recent proposals with nuclear magnetic resonance (NMR) is a multi-bore NMR which consists of array of magnets which could present possibilities to quickly cope with pandemic virus by multiple inspection of virus samples. Low temperature superconductor (LTS) can be a candidate for mass production of the magnet due to its low price in fabrication as well as operation by applying the helium zero boil-off technology. However, training feature of LTS magnet still hinders the low cost operation due to multiple boil-offs during premature quenches. Thus in this paper, LTS magnet with low mechanical stress is designed targeting the "training-free" LTS magnet for mass production of magnet array for multi-bore NMR. A thorough process of an LTS magnet design is conducted, including the analyses as the followings: electromagnetics, mechanical stress, cryogenics, stability, and protection. The magnet specification was set to 4.7 T in a winding bore of 85 mm, corresponding to the MR frequency of 200 MHz. The stress level is tolerable with respect to the wire yield strength and epoxy crack where mechanical disturbance is less than the minimum quench energy.

• 전기전자학회논문지
• /
• 제22권3호
• /
• pp.816-821
• /
• 2018

최근 감정 분석 및 질병 진단을 위한 뇌파 연구 분야에서 인공 신경망을 기반으로 한 기계학습 알고리즘이 분류기로 널리 사용되기 시작했다. 뇌파 데이터 분류를 위해 기계학습 모델을 사용하는 경우 유사한 특성을 가지는 데이터만으로 학습데이터가 구성되면 다른 그룹의 데이터에 적용했을 때 분류 성능이 떨어질 수 있다. 본 논문에서는 이러한 문제점을 개선하기 위해 준 지도학습 알고리즘을 사용해 여러 그룹의 데이터를 선택하여 학습데이터 세트를 구성하는 방법을 제안한다. 이후 제안하는 방법을 사용하여 구성한 학습데이터 세트와 유사한 특성을 가지는 데이터로 구성된 학습데이터 세트로 모델을 학습하여 두 모델의 성능을 비교하였다.

• 한국컴퓨터정보학회논문지
• /
• 제21권9호
• /
• pp.107-112
• /
• 2016

In this paper, we propose the effects of military cardiopulmonary resuscitation(CPR) on the quality of debriefing and feedback device training. The key idea of combination debriefing and feedback device training is to maximize effects of CPR. The participants of the research were non-medic soldiers in ROK army, and had not undergone any professional CPR training before. Each group of soldier was randomized to perform of military CPR by using training method in each group. After 5 minutes of performing CPR, each D, F, DF group showed significant improvement in CPR performance. When comparing each group, the rate of success in CPR performance in DF group was significantly higher than that of F group with the average difference of 11.160(p<.01) points. In summation, the training programs that DF received seemed to be more efficient and effective than that of D and F. The fatigue level was evaluated by comparing the lactate concentration in blood after performing CPR. Through this experiment, we show that the training programs that DF received is more efficient and effective than that of D and F.

• International Journal of Computer Science & Network Security
• /
• 제21권3호
• /
• pp.120-126
• /
• 2021

The article analyzes the possibility of using information and innovation experience in training public administration specialists, and also explores the system of training public administration and management specialists abroad. It was determined that in the European Union, Japan and other developed countries, three concepts of qualified personnel training will be developed: the concept of specialized training is focused on the present or near future and is relevant for the respective workplace; the concept of multidisciplinary training is effective from an economic point of view, as it increases intra-production and non-production mobility of an employee; the concept of learner-centered learning with the aim of developing human qualities.

• International Journal of Computer Science & Network Security
• /
• 제22권7호
• /
• pp.171-180
• /
• 2022

In the knowledge development of online assessment in learning management systems (LMSs), many assessments are evaluated weekly in the summer training course for undergraduate students in the Faculty of Computing and Information Technology at King Abdul-Aziz University in Saudi Arabia. The number of performance assessments in the summer training course reaches 15 weeks. Many of them, however, are sent or done informally or through unreliable ways and cannot be verified by third parties. Therefore, applying the concept of digital transformation is essential. This research study reported herein used the action design research (ADR) method to build a new information technology system that could assist in the digital transformation. An electronic platform was designed, developed, implemented, and evaluated using the ADR method so that the main people involved in the summer training process (i.e., students, academic supervisors, and administrators) would have a high level of satisfaction with it. The study was conducted on 452 students, 105 academic supervisors, and 15 administrative staff and was conducted during the summer semester of 2020. All the training processes were digitally transformed and automated to control and raise the level and reliability of the training. All involved people were satisfied, thus, shifting the process to be in a digital form assist in achieving the high-level goal.

• 방송공학회논문지
• /
• 제26권7호
• /
• pp.855-861
• /
• 2021

Neural Architecture Search (NAS) is cutting-edge technology in the machine learning community. NAS Without Training (NASWOT) recently has been proposed to tackle the high demand of computational resources in NAS by leveraging some indicators to predict the performance of architectures before training. The advantage of these indicators is that they do not require any training. Thus, NASWOT reduces the searching time and computational cost significantly. However, NASWOT only considers high-performing networks which does not guarantee a fast inference speed on hardware devices. In this paper, we propose a multi objectives reward function, which considers the network's latency and the predicted performance, and incorporate it into the Reinforcement Learning approach to search for the best networks with low latency. Unlike other methods, which use FLOPs to measure the latency that does not reflect the actual latency, we obtain the network's latency from the hardware NAS bench. We conduct extensive experiments on NAS-Bench-201 using CIFAR-10, CIFAR-100, and ImageNet-16-120 datasets, and show that the proposed method is capable of generating the best network under latency constrained without training subnetworks.