• ETRI Journal
• /
• 제41권5호
• /
• pp.560-573
• /
• 2019

Two supervised learning algorithms, a basic neural network and a long short-term memory recurrent neural network, are applied to traffic including DDoS attacks. The joint effects of preprocessing methods and hyperparameters for machine learning on performance are investigated. Values representing attack characteristics are extracted from datasets and preprocessed by two methods. Binary classification and two optimizers are used. Some hyperparameters are obtained exhaustively for fast and accurate detection, while others are fixed with constants to account for performance and data characteristics. An experiment is performed via TensorFlow on three traffic datasets. Three scenarios are considered to investigate the effects of learning former traffic on sequential traffic analysis and the effects of learning one dataset on application to another dataset, and determine whether the algorithms can be used for recent attack traffic. Experimental results show that the used preprocessing methods, neural network architectures and hyperparameters, and the optimizers are appropriate for DDoS attack detection. The obtained results provide a criterion for the detection accuracy of attacks.

• Journal of Ginseng Research
• /
• 제39권3호
• /
• pp.250-256
• /
• 2015

Background: It has been known that ginseng can be applied as a potential nutraceutical for memory impairment; however, experiments with animals of old age are few. Methods: To determine the memory enhancing effect of red ginseng, C57BL/6 mice (21 mo old) were given experimental diet pellets containing 0.12% red ginseng extract (approximately 200 mg/kg/d) for 3 mo. Young and old mice (4 mo and 21 mo old, respectively) were used as the control group. The effect of red ginseng, which ameliorated memory impairment in aged mice, was quantified using Y-maze test, novel objective test, and Morris water maze. Red ginseng ameliorated age-related declines in learning and memory in older mice. In addition, red ginseng's effect on the induction of inducible nitric oxide synthase and proinflammatory cytokines was investigated in the hippocampus of aged mice. Results: Red ginseng treatment suppressed the production of age-processed inducible nitric oxide synthase, cyclooxygenase-2, tumor necrosis factor-${\alpha}$, and interleukin-$1{\beta}$ expressions. Moreover, it was observed that red ginseng had an antioxidative effect on aged mice. The suppressed glutathione level in aged mice was restored with red ginseng treatment. The antioxidative-related enzymes Nrf2 and HO-1 were increased with red ginseng treatment. Conclusion: The results revealed that when red ginseng is administered over long periods, age-related decline of learning and memory is ameliorated through anti-inflammatory activity.

• 전기전자학회논문지
• /
• 제21권2호
• /
• pp.136-141
• /
• 2017

본 논문에서는 딥러닝을 PC에 적용하기 위한 메모리 최적화에 관한 알고리즘을 제안한다. 제안된 알고리즘은 일반 PC에서 기존의 딥러닝 구조에서 요구되는 연산처리 과정과 데이터 량을 감소시켜 메모리 및 연산처리 시간을 최소화한다. 본 논문에서 제안하는 알고리즘은 분별력이 있는 랜덤 필터를 이용한 컨볼루션 층 구성 과정, PCA를 이용한 데이터 축소 과정, SVM을 사용한 CNN 구조 생성 등의 3과정으로 이루어진다. 분별력이 있는 랜덤 필터를 이용한 컨볼루션 층 구성 과정에서는 학습과정이 필요치 않아서 전체적인 딥러닝의 학습시간을 단축시킨다. PCA를 이용한 데이터 축소 과정에서는 메모리량과 연산처리량을 감소시킨다. SVM을 사용한 CNN 구조 생성에서는 필요로 하는 메모리량과 연산 처리량의 감소 효과를 극대화 시킨다. 제안된 알고리즘의 성능을 평가하기 위하여 예일 대학교의 Extended Yale B 얼굴 데이터베이스를 사용하여 실험한 결과, 본 논문에서 제안하는 알고리즘이 기존의 CNN 알고리즘과 비교하여 비슷한 성능의 인식률을 보이면서 연산 소요시간과 메모리 점유율에 있어 우수함이 확인되었다. 본 논문에서 제안한 알고리즘을 바탕으로 하여 일반 PC에서도 많은 데이터와 연산처리를 가진 딥러닝 알고리즘을 구현할 수 있으리라 기대된다.

• 시스템엔지니어링학술지
• /
• 제19권2호
• /
• pp.18-31
• /
• 2023

Exploring artificial intelligence and machine learning for nuclear safety has witnessed increased interest in recent years. To contribute to this area of research, a machine learning model capable of accurately predicting nuclear power plant response with minimal computational cost is proposed. To develop a robust machine learning model, the Best Estimate Plus Uncertainty (BEPU) approach was used to generate a database to train three models and select the best of the three. The BEPU analysis was performed by coupling Dakota platform with the best estimate thermal hydraulics code RELAP/SCDAPSIM/MOD 3.4. The Code Scaling Applicability and Uncertainty approach was adopted, along with Wilks' theorem to obtain a statistically representative sample that satisfies the USNRC 95/95 rule with 95% probability and 95% confidence level. The generated database was used to train three models based on Recurrent Neural Networks; specifically, Long Short-Term Memory, Gated Recurrent Unit, and a hybrid model with Long Short-Term Memory coupled to Convolutional Neural Network. In this paper, the System Engineering approach was utilized to identify requirements, stakeholders, and functional and physical architecture to develop this project and ensure success in verification and validation activities necessary to ensure the efficient development of ML meta-models capable of predicting of the nuclear power plant response.

• International journal of advanced smart convergence
• /
• 제10권2호
• /
• pp.73-78
• /
• 2021

Recently, the number of people who visit the hospital due to diabetes is increasing. According to the Korean Diabetes Association, it is statistically indicated that one in seven adults aged 30 years or older in Korea suffers from diabetes, and it is expected to be more if the pre-diabetes, fasting blood sugar disorders, are combined. In the last study, the validity of Triglyceride and Cholesterol associated with diabetes was confirmed and analyzed using Random Forest. Random Forest has a disadvantage that as the amount of data increases, it uses more memory and slows down the speed. Therefore, in this paper, we compared and analyzed Random Forest and XGBoost, focusing on improvement of learning speed and prevention of memory waste, which are mainly dealt with in machine learning. Using XGBoost, the problem of slowing down and wasting memory was solved, and the accuracy of the diabetes recognition factor was further increased.

• 인지과학
• /
• 제13권1호
• /
• pp.53-59
• /
• 2002

본 논문은 퍼지 인지 맵과 퍼지 연상 메모리를 사용하여 열과 온도에 관한 학생들의 과학개념 이해에서 발생되는 오인을 진단할 수 있는 오인 진단 모델을 제시한다. 오인 진단 모델에서 퍼지 인지 맵은 과학현상에 대한 학생들이 가지는 선입개념들과 오인들을 인과관계로 표현할 수 있다. 또한 개념간의 인과관계를 기억할 수 있는 퍼지 연상 메모리를 통하여 오인의 원인들을 진단한다. 본 연구는 기존의 학습 오인을 진단하는 규칙기반 전문가 시스템의 한계성을 극복할 수 있는 새로운 방법을 제공하며, 교육분야의 다양한 영역에서 학습자들의 학습 진단을 위한 지능형 개인교수 시스템으로 적용될 수 있을 것이다.

• 지식경영연구
• /
• 제6권2호
• /
• pp.67-90
• /
• 2005

Attention has been focused recently on the concept of shared cognition which encompasses the notion that effective team members hold knowledge that is overlapping and complementary with teammates. This shared cognition is expected to improve team effectiveness. In contrast to the continued efforts in developing theoretical approach of shared cognition, empirical studies are meager. Thus, we conducted an empirical study to investigate the role of shared cognition on team effectiveness. This study classifies shared cognition into two types, team mental model and transactive memory system, by shared meaning. A total of 121 new product development teams in the IT industry were surveyed for the data collection. The results of analysis can be summarized as follows: first, team mental model has a positive influence on team performance, team innovative behavior and team learning effect. And the relation with team mental model and team performance is moderated by the similarity of knowledge structure among the expert. Second, transactive memory system has a positive influence on team performance, team innovative behavior and team learning effect.

• 대한약침학회지
• /
• 제4권1호
• /
• pp.49-53
• /
• 2001

This experiment has investigated the influence of Yamen (Du. 15) point injection on learning and memory dysfunction caused by cerebral ischemia and reprofusion in bilateral cervical general artery combined with bleeding on mouse tail to mimic vascular dementia in human beings. By dividing 40 mice into 4 groups (group1false operation group, group2model group, group3point injection with Cerebrolysin group4point injection with saline.) According to random dividing principles, we observed the influence of Yamen(Du. 15) point injection on the time of swimming the whole course used by model mice which had received treatment for different days in different groups, and the influence of those mice on wrong times they entered blind end. The result showed that point injection with Cerebrolysin and saline could improve learning and memory dysfunction of the mice caused by cerebral ischemia.

• 컴퓨터교육학회논문지
• /
• 제14권5호
• /
• pp.39-46
• /
• 2011

기능성 게임은 게임적 요소인 재미에 교육과 훈련, 치료 등의 특별한 목적을 부가하여 개발한 게임을 말한다. 최근 국내외 기능성 게임 시장은 급성장하고 있으며, 차세대 플랫폼으로 떠오르고 있는 스마트폰의 보급으로 인해 기능성 게임 시장은 더욱 다양한 목적과 사용자를 대상으로 확대될 것으로 예견된다. 본 연구에서는 스마트폰을 이용하여 일반인의 기억력 향상을 위한 기능성 게임 'QUICK REMEMBER 20'을 설계 및 구현하고, 게임 이용자에 대한 사회통계학적 분류에 따른 분석과 게임의 학습 효과에 대한 분석 연구를 수행하였다.

• 스마트미디어저널
• /
• 제12권11호
• /
• pp.134-144
• /
• 2023

Nowadays, Deep Learning (DL) technology is being used in several government departments. South Korea imports a lot of seafood. If the demand for fishery products is not accurately predicted, then there will be a shortage of fishery products and the price of the fishery product may rise sharply. So, South Korea's Ministry of Ocean and Fisheries is attempting to accurately predict seafood imports using deep learning. This paper introduces the solution for the fish import prediction in South Korea using the Long Short-Term Memory (LSTM) method. It was found that there was a huge gap between the sum of consumption and export against the sum of production especially in the case of two species that are Hairtail and Pollock. An import prediction is suggested in this research to fill the gap with some advanced Deep Learning methods. This research focuses on import prediction using Machine Learning (ML) and Deep Learning methods to predict the import amount more precisely. For the prediction, two Deep Learning methods were chosen which are Artificial Neural Network (ANN) and Long Short-Term Memory (LSTM). Moreover, the Machine Learning method was also selected for the comparison between the DL and ML. Root Mean Square Error (RMSE) was selected for the error measurement which shows the difference between the predicted and actual values. The results obtained were compared with the average RMSE scores and in terms of percentage. It was found that the LSTM has the lowest RMSE score which showed the prediction with higher accuracy. Meanwhile, ML's RMSE score was higher which shows lower accuracy in prediction. Moreover, Google Trend Search data was used as a new feature to find its impact on prediction outcomes. It was found that it had a positive impact on results as the RMSE values were lowered, increasing the accuracy of the prediction.