• Journal of KIISE:Software and Applications
• /
• v.31 no.2
• /
• pp.101-110
• /
• 2004

In dynamic systems, such as social and economic systems, complex interactions emerge among its members. In that case, their behaviors become adaptive according to Changing environment. In many cases, an individual's behaviors can be modeled by a stimulus-response system in a dynamic environment. In this paper, we use the Iterated Prisoner's Dilemma (IPD) game, which is simple yet capable of dealing with complex problems, to model the dynamic systems. We propose strategic coalition consisting of many agents and simulate their emergence in a co-evolutionary learning environment. Also we introduce the concept of confidence for agents in a coalition and show how such confidences help to improve the generalization ability of the whole coalition. Experimental results are presented to demonstrate that co-evolutionary learning with coalitions and confidence allows better performing strategies that generalize well.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2021.05a
• /
• pp.198-201
• /
• 2021

무인 항공기(UAV, Unmanned Aerial Vehicles)는 높은 기동성을 가지며 설치 비용이 저렴하다는 이점이 있어 홍수, 지진 등의 재난 재해 감시 시스템에 이용되고 있다. 재난 재해 감시 시스템에서 UAV는 지상에 위치한 사물인터넷(IoT, Internet of Things) 기기로부터 데이터를 수집하는 임무를 수행하기 위해 계획된 항로를 따라 비행한다. 이때 UAV가 정상 경로로 비행하기 위해서는 실시간으로 GPS 위치 확인이 가능해야 한다. 만일 UAV가 계산한 현재 위치의 GPS 정보가 잘못될 경우 비행경로에 대한 통제권을 상실하여 임무 수행을 완료하지 못하는 결과가 초래될 수 있다는 취약점이 존재한다. 이러한 취약점으로 인해 UAV는 공격자가 악의적으로 거짓 GPS 위치 신호를 전송하는GPS 스푸핑(Spoofing) 공격에 쉽게 노출된다. 본 논문에서는 신뢰할 수 있는 시스템을 구축하기 위해 지상에 위치한 기기가 송신하는 신호의 세기와 GPS 정보를 이용하여 UAV에 GPS 스푸핑 공격 여부를 탐지하고 공격당한 UAV가 경로를 이탈하지 않도록 대응하기 위해 연합학습(Federated Learning)을 이용하는 방안을 제안한다.

• The Journal of the Korea Contents Association
• /
• v.19 no.11
• /
• pp.144-152
• /
• 2019

Learning styles are the methods of gathering, processing, interpreting, organizing the information. VARK learnig inventory is instructional preference classified according to their visual(V), aural(A), read-write(R), and/or kinesthetic(K) sensory modality preferences(SMP). Learner-centered learning is emphasized, but there are few studies on VARK learning styles in Korean medical school. The purposes of this study were to assess the student' SMPs and compare those with gender, status, and academic achievement. The subjects of study were 394 students at C Medical School and Graduate School of Medicine. For the study style test, 16 questions were used in Korean version of VARK test paper© 7.0 developed by Fleming provided on the VARK website. Academic achievement was converted into a standardized score(t score). Frequency analysis, cross analysis, and variance analysis(t-test, ANOVA) were conducted to identify learning style disposition and differences between groups. The uni-modal type was 87(22.1%) and the multimodal was 307(77.9%). Regardless of gender, quasi-modal VARK was the most preferred. There was no significant difference in learning styles by gender. The first grade in medicine was the lowest in uni-modal type(8.8%) and the highest in quasi-modal VARK type(47.8%), while the fourth grade was the highest in uni-modal type(30.7%) and the lowest in quasi-modal VARK type(19.8%) and tri-modal type(19.8%). There was no difference in academic achievement by all learning types(F=1.09, p=0.37). The knowledge about students' learning styles is helpful for instructors to apply more learner-centered teaching strategies in medical education.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2023.01a
• /
• pp.13-15
• /
• 2023

본 논문에서는 성격, 성향을 근거로 사람의 성향에 따른 직업 및 전공에 대한 만족도를 분류한 데이터셋을 구축하여 사전에 사용자의 성향을 파악하여 직업을 추천하는 알고리즘을 제안한다. 성격유형검사 뿐만이 아닌 최근 게시한 SNS 텍스트를 사전에 학습한 데이터셋에 적용해 성격유형 결과의 정확도를 상승시키고자 한다. 사전에 생성한 데이터셋 외에 대상자가 작성한 정보(직업, 전공, 직엄 및 전공에 대한 만족도)로 연합학습을 진행하여 데이터셋의 정확도를 향상시키고자 한다. 모델의 학습 및 분류의 정확도 향상을 위해 SVM, NB, KNN, SDG 알고리즘들을 비교하였고 각각 67%, 21%, 28%, 69%의 정확도를 도출하였다. 데이터 셋은 캐글에서 제공받았다.

• Journal of KIISE:Software and Applications
• /
• v.27 no.3
• /
• pp.257-265
• /
• 2000

There is much selective confliction in nature where selfish and rational individuals exists. Iterated Prisoner's Dilemma (IPD) game deals with this problem, and has been used to study on the evolution of cooperation in social, economic and biological systems. So far, there has been much work about the relationship of the number of players and cooperation, strategy learning as a machine learning and the effect of payoff functions to cooperation. In this paper, We attempt to investigate the cooperative coalition size according to payoff functions, and observe the relationship of localization and the evolution of cooperation in NIPD (N-player IPD) game. Experimental results indicate that cooperative coalition size increases as the gradient of the payoff function for cooperation becomes steeper than that of defector's payoff function, or as the minimum coalition size gets smaller, Moreover, the smaller the neighborhood of interaction is, the higher the cooperative coalition emerges through the evolution of population.

• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• 2023.05a
• /
• pp.212-213
• /
• 2023

항·포구내에서 주.야간에 걸쳐 미등록 선박을 검출하기 위해, 가시광 및 IR, 라이다 센서를 통해 선박 영상 및 거리정보를 획득하고, 딥러닝 기술을 적용하여 선박의 외관에 대한 특징 분석 및 선박에 표기된 문자열의 인식, 선박의 크기 측정을 통해 선박을 분류하고 특정하는 기술 개발

• Smart Media Journal
• /
• v.13 no.4
• /
• pp.33-48
• /
• 2024

With the advent of 5G, characterized by Enhanced Mobile Broadband (eMBB), Ultra-Reliable Low Latency Communications (URLLC), and Massive Machine Type Communications (mMTC), efficient network management and service provision are becoming increasingly critical. This paper proposes a novel approach to address key challenges of 5G networks, namely ultra-high speed, ultra-low latency, and ultra-reliability, while dynamically optimizing network slicing and resource allocation using machine learning (ML) and deep learning (DL) techniques. The proposed methodology utilizes prediction models for network traffic and resource allocation, and employs Federated Learning (FL) techniques to simultaneously optimize network bandwidth, latency, and enhance privacy and security. Specifically, this paper extensively covers the implementation methods of various algorithms and models such as Random Forest and LSTM, thereby presenting methodologies for the automation and intelligence of 5G network operations. Finally, the performance enhancement effects achievable by applying ML and DL to 5G networks are validated through performance evaluation and analysis, and solutions for network slicing and resource management optimization are proposed for various industrial applications.

• Korean Journal of Cognitive Science
• /
• v.34 no.1
• /
• pp.21-38
• /
• 2023

The present study was designed to investigate the effect of the difficulty level of retrieval practice and the association strength of categories and stimuli within categories on memory inhibition. Most of the studies have investigated whether inhibition was occurred by manipulating the degree of association strength, emotion value or physical characteristics of non-retrieval practice words within the retrieval practice category. Therefore, it was necessary to study how inhibition occurs according to the degree of difficulty of retrieval stimuli during retrieval practice. The difficulty of retrieval was manipulated into three levels: difficult condition, normal condition, and easy condition through the degree of presentation of consonants and vowels of words during retrieval learning. Additionally, the strength of association between categories and words within categories was manipulated. In previous studies, retrieval-induced forgetting occurred under conditions where the association strength between categories and words within the categories was strong. On the other hand, retrieval-induced forgetting did not occur under conditions where the association strength between categories and words within the categories was weak. The present study, if the inhibition process differs according to the difficulty of retrieval, the possibility of different results from previous studies was explored according to the difference in the strength of association with the category. As a result of the study, in the condition of strong association strength, retrieval-induced forgetting was observed under normal and difficult retrieval difficulty conditions. Whereas retrieval-induced forgetting was not observed under conditions of easy retrieval difficulty condition. In the condition of weak association strength, retrieval-induced forgetting tended to occur under difficult retrieval difficulty conditions. Whereas retrieval-induced forgetting was not observed under conditions of normal and easy retrieval difficulty condition. These results suggest that memory inhibition may appear differently depending on the difficulty of retrieval.

• Journal of The Korean Association For Science Education
• /
• v.18 no.4
• /
• pp.589-600
• /
• 1998

The present study tested the hypothesis that adolescent's prefrontal lobe growth plateau and spurt exists and that this plateau and spurt influence students' ability to reason scientifically and to learn theoretical science concepts. In theory, maturation of the prefrontal lobes during early adolescence allows for improvements in students' abilities to inhibit task-irrelevant information and coordinate task-relevant information, which along with both physical and social experience, influences scientific reasoning ability and the ability to reject scientific misconceptions and accept scientific conceptions. Two hundred six students ages 13 to 16 years enrolled in four Korean secondary schools were administered tests of prefrontal lobe functions, scientific reasoning, and theoretical concepts derived from kinetic-molecular theory. A series of 14 lessons designed to teach the concepts were then taught. The concepts test was then re-administered following instruction. As predicted among the 14-year-olds, performance on the measures of prefrontal lobe functions, scientific reasoning, and conceptual change remained similar or regressed. Performance then improved considerably among the 15 and 16-year-olds. Because so few of the present students were able to undergo this apparently necessary conceptual change, the value of introducing theoretical concepts to early adolescent is questioned.

• Electronics and Telecommunications Trends
• /
• v.34 no.6
• /
• pp.71-86
• /
• 2019

The unprecedented demands of mobile communication networks by the rapid rising popularity of mobile applications and services require future networks to support the exploding mobile traffic volumes, the real time extraction of fine-rained analytics, and the agile management of network resources, so as to maximize user experience. To fulfill these needs, research on the use of emerging deep learning techniques in future mobile systems has recently emerged; as such, this study deals with deep learning based mobile communication research activities. A thorough survey of the literature, conference, and workshops on deep learning for mobile communication networks is conducted. Finally, concluding remarks describe the major future research directions in this field.