• 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.

• Educational Technology International
• /
• 제14권2호
• /
• pp.137-166
• /
• 2013

Problem-based learning (PBL) in engineering education has been implemented in various ways. The wide range of PBL methods sometimes creates difficulties in implementing PBL. The purpose of this study was to identify the major variables that a teacher considers in PBL designs for an engineering course and suggest specific PBL methods according to the PBL design variables. This study was conducted using a review research method involving 21 studies from a range of engineering education fields. The results showed that the major variables that engineering professors need to consider when applying PBL are the authenticity of the PBL problem and the method of providing knowledge or information that the learners must know to solve the given problem. Based on the two variables identified, the following four types of PBL methods for engineering education are suggested: 1) lecture-based problem, 2) guided problem-based learning, 3) problem-based learning and 4) co-op problem-based learning.

• ETRI Journal
• /
• 제44권5호
• /
• pp.733-745
• /
• 2022

In software-defined wireless networking (SDWN), the optimal routing technique is one of the effective solutions to improve its performance. This routing technique is done by many different methods, with the most common using integer linear programming problem (ILP), building optimal routing metrics. These methods often only focus on one routing objective, such as minimizing the packet blocking probability, minimizing end-to-end delay (EED), and maximizing network throughput. It is difficult to consider multiple objectives concurrently in a routing algorithm. In this paper, we investigate the application of machine learning to control routing in the SDWN. An intelligent routing algorithm is then proposed based on the machine learning to improve the network performance. The proposed algorithm can optimize multiple routing objectives. Our idea is to combine supervised learning (SL) and reinforcement learning (RL) methods to discover new routes. The SL is used to predict the performance metrics of the links, including EED quality of transmission (QoT), and packet blocking probability (PBP). The routing is done by the RL method. We use the Q-value in the fundamental equation of the RL to store the PBP, which is used for the aim of route selection. Concurrently, the learning rate coefficient is flexibly changed to determine the constraints of routing during learning. These constraints include QoT and EED. Our performance evaluations based on OMNeT++ have shown that the proposed algorithm has significantly improved the network performance in terms of the QoT, EED, packet delivery ratio, and network throughput compared with other well-known routing algorithms.

• Geomechanics and Engineering
• /
• 제25권1호
• /
• pp.1-16
• /
• 2021

Machine learning models have been widely used for landslide susceptibility assessment (LSA) in recent years. The large number of inputs or conditioning factors for these models, however, can reduce the computation efficiency and increase the difficulty in collecting data. Feature selection is a good tool to address this problem by selecting the most important features among all factors to reduce the size of the input variables. However, two important questions need to be solved: (1) how do feature selection methods affect the performance of machine learning models? and (2) which feature selection method is the most suitable for a given machine learning model? This paper aims to address these two questions by comparing the predictive performance of 13 feature selection-based machine learning (FS-ML) models and 5 ordinary machine learning models on LSA. First, five commonly used machine learning models (i.e., logistic regression, support vector machine, artificial neural network, Gaussian process and random forest) and six typical feature selection methods in the literature are adopted to constitute the proposed models. Then, fifteen conditioning factors are chosen as input variables and 1,017 landslides are used as recorded data. Next, feature selection methods are used to obtain the importance of the conditioning factors to create feature subsets, based on which 13 FS-ML models are constructed. For each of the machine learning models, a best optimized FS-ML model is selected according to the area under curve value. Finally, five optimal FS-ML models are obtained and applied to the LSA of the studied area. The predictive abilities of the FS-ML models on LSA are verified and compared through the receive operating characteristic curve and statistical indicators such as sensitivity, specificity and accuracy. The results showed that different feature selection methods have different effects on the performance of LSA machine learning models. FS-ML models generally outperform the ordinary machine learning models. The best FS-ML model is the recursive feature elimination (RFE) optimized RF, and RFE is an optimal method for feature selection.

• 한국환경교육학회지:환경교육
• /
• 제14권2호
• /
• pp.40-50
• /
• 2001

To meet the objectives of environmental education, teachers especially have to perceive the importance of environmental education, comprehend various characteristics of teaching/learning methods, and be able to conduct classes by choosing proper teaching/leaming methods in accordance with a specific purpose and educational focus about environmental education. Therefore, it Bs necessary to investigate the current status of Korean environmental education and provide teachers with appropriate environmental teaching/leaming methods. To this end this study aims to examine Korean science teachers'perceptions'on environmental education and the kind of teaching/learning methods which can be utilized in environmental education. Teachers who completed the survey were 135 science teachers from middle and high schools in Seoul, and 126 social science teachers from Kyoungki province. The majors of the science teachers were in physics, chemistry, biology, geology, and earth science. Also, there was one teacher who majored in special education. For social science teachers two majors were common, geography and general sociology. After analysis of the data from the surveys the results are as follows. First, science and social science teachers in middle and high school recognized the necessity of environmental education in school education. Second, most teachers had applied environment related topics to their subject of study occasionally, but they mostly concurred that environment related contents should be included in their textbooks. Third, science teachers agreed that field trip, discussion, and the STS approach were the most proper methods for environmental education, and social science teachers agreed that field trips, inquiry, and discussion were the most appropriate methods for a teaching environment. They realized that they should decide good teaching-learning methods appropriate to the objectives and content needed for effective environmental education as they selected different teaching-learning methods according to detailed environmental objectives and contents in their textbooks.

• 근관절건강학회지
• /
• 제29권3호
• /
• pp.185-193
• /
• 2022

Purpose: This study aims to provide basic data for future nursing education by identifying the effects of flipped learning-type project-based learning on nursing college students' self-directed learning ability, self-leadership, and academic self-efficacy. Methods: It is a pre-experimental study designed before and after a single group to verify the effect of flipped learning project-based learning on nursing students' self-directed learning ability, self-leadership, and academic self-efficacy in 81 third-grade nursing students. Results: No statistically significant difference in self-efficacy (t=-0.80, p=.545) but self-directed learning ability (t=-3.85, p<.001) and self-leadership (t=-5.18, p<.001) were found to have a statistically significant difference before and after. Conclusion: Flipped learning-type project-based learning was confirmed effective in improving nursing college students' self-directed learning ability and self-leadership. Therefore, instructors will need to develop and apply teaching methods that provide learners with opportunities for pre-learning and carry out learner-centered projects to improve nursing college students' self-directed learning ability and self-leadership.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제15권6호
• /
• pp.2012-2030
• /
• 2021

Named Entity Recognition (NER) is used to identify entity nouns in the corpus such as Location, Person and Organization, etc. NER is also an important basic of research in various natural language fields. The processing of Chinese NER has some unique difficulties, for example, there is no obvious segmentation boundary between each Chinese character in a Chinese sentence. The Chinese NER task is often combined with Chinese word segmentation, and so on. In response to these problems, we summarize the recognition methods of Chinese NER. In this review, we first introduce the sequence labeling system and evaluation metrics of NER. Then, we divide Chinese NER methods into rule-based methods, statistics-based machine learning methods and deep learning-based methods. Subsequently, we analyze in detail the model framework based on deep learning and the typical Chinese NER methods. Finally, we put forward the current challenges and future research directions of Chinese NER technology.

• 한국경영과학회지
• /
• 제29권4호
• /
• pp.117-134
• /
• 2004

This study suggests a data driven optimization approach, which simulates the models of human learning processes from cognitive sciences. It shows how the human learning processes can be simulated and applied to solving combinatorial optimization problems. The main advantage of using this method is in applying it into problems, which are very difficult to simulate. 'Undecidable' problems are considered as best possible application areas for this suggested approach. The concept of an 'undecidable' problem is redefined. The learning models in human learning and decision-making related to combinatorial optimization in cognitive and neural sciences are designed, simulated, and implemented to solve an optimization problem. We call this approach 'SLO : simulated learning for optimization.' Two different versions of SLO have been designed: SLO with position & link matrix, and SLO with decomposition algorithm. The methods are tested for traveling salespersons problems to show how these approaches derive new solution empirically. The tests show that simulated learning for optimization produces new solutions with better performance empirically. Its performance, compared to other hill-climbing type methods, is relatively good.

• 한국임상보건과학회지
• /
• 제8권1호
• /
• pp.1355-1361
• /
• 2020

Purpose: This study was conducted to investigate the effect of flipped-learning method on dental hygiene practice satisfaction. Methods: The study was a patient-group crossover design involving 53 third-year students at D's Department of Dental Hygiene. The study tools used self-questionnair and the analysis program used SPSS Ver 25.0. Results: Class satisfaction increased to 3.85 in the first semester and 4.23 in the second semester (p <0.05). Satisfaction with the flip learning method was 4.26, and most answered yes. In addition, it showed a positive effect on class satisfaction (p <0.01). As a result, it can be seen that the flip-learning learning method has a positive effect on the learners' learning motivation, academic achievement, and class satisfaction. Conclusions: it is considered that the flip learning method for hands-on classes should be expanded for the purpose of fostering job competency and high quality clinical practice experts.

• 한국정보과학회논문지:데이타베이스
• /
• 제37권6호
• /
• pp.285-291
• /
• 2010

본 연구에서는 나이브 베이시안 학습의 환경에서 속성의 가중치를 계산하는 새로운 방식을 제안한다. 기존 방법들이 속성에 가중치를 부여하는 방식인데 반하여 본 연구에서는 한걸음 더 나아가 속성의 값에 가중치를 부여하는 새로운 방식을 연구하였다. 이러한 속성값의 가중치를 계산하기 위하여 Kullback-Leibler 함수를 이용하여 가중치를 계산하는 방식을 제안하였고 이러한 가중치들의 특성을 분석하였다. 제안된 알고리즘은 다수의 데이터를 이용하여 속성 가중치 방식과 비교하였고 대부분의 경우에 더 좋은 성능을 제공함을 알 수 있었다.