• Smart Media Journal
• /
• v.10 no.1
• /
• pp.55-62
• /
• 2021

We applied machine learning of semi-supervised learning, transfer learning, and federated learning as examples of AI use cases that can be applied to the three major industries(Automobile industry, Energy industry, and AI/Healthcare industry) of Gwangju Metro-city, and established an ML strategy for AI services for the major industries. Based on the ML strategy of AI service, practical approaches are suggested, the semi-supervised learning approach is used for automobile image recognition technology, and the transfer learning approach is used for diabetic retinopathy detection in the healthcare field. Finally, the case of the federated learning approach is to be used to predict electricity demand. These approaches were tested based on hardware such as single board computer Raspberry Pi, Jaetson Nano, and Intel i-7, and the validity of practical approaches was verified.

• Journal of the Korean Society for information Management
• /
• v.32 no.3
• /
• pp.295-316
• /
• 2015

This study analyzed the policy making process by finding factors of a back-in phenomenon appeared in contracting out of public library using advocacy coalition framework. The coalitions were divided into 'agreement of direct management', 'opposition of direct management' and 'keep the contract out'. Considering their belief and activity, to share core belief could make a change of secondary belief. It suggests that activating public sphere is necessary for enforcement of their strategies throughout the library policy.

• 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 Bigdata
• /
• v.8 no.2
• /
• pp.125-131
• /
• 2023

Globally, drug side effects rank among the top causes of death. To effectively respond to these adverse drug reactions, a shift towards an active real-time monitoring system, along with the standardization and quality improvement of data, is necessary. Integrating individual institutional data and utilizing large-scale data to enhance the accuracy of drug side effect predictions is critical. However, data sharing between institutions poses privacy concerns and involves varying data standards. To address this issue, our research adopts a federated learning approach, where data is not shared directly in compliance with privacy regulations, but rather the results of the model's learning are shared. We employ the Common Data Model (CDM) to standardize different data formats, ensuring accuracy and consistency of data. Additionally, we propose a drug monitoring system that enhances security and scalability management through a cloud-based federated learning environment. This system allows for effective monitoring and prediction of drug side effects while protecting the privacy of data shared between hospitals. The goal is to reduce mortality due to drug side effects and cut medical costs, exploring various technical approaches and methodologies to achieve this.

• 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.