• 한국정보통신학회논문지
• /
• 제25권1호
• /
• pp.50-55
• /
• 2021

다중경로 시스템은 유선망, LTE망, 위성망 등 다양한 망을 동시에 활용하여 데이터를 전송하는 시스템으로, 통신망의 전송속도, 신뢰도, 보안성 등을 높이기 위해 제안되었다. 본 논문에서는 이 시스템에서 각 망의 지연시간을 보상으로 하는 강화학습 기반 경로 선택 방안을 제안하고자 한다. 기존의 강화학습 모델과는 다르게, deep Q 학습을 이용하여 망의 변화하는 환경에 즉각적으로 대응하도록 알고리즘을 설계하였다. 네트워크 환경에서는 보상 정보를 일정 지연시간이 지나야 얻을 수 있으므로 이를 보정하는 방안 또한 함께 제안하였다. 성능을 평가하기 위해, 분산 데이터베이스와 텐서플로우 모듈 등을 포함한 테스트베드 학습 서버를 개발하였다. 시뮬레이션 결과, 제안 알고리즘이 RTT 감소 측면에서 최저 지연시간을 선택하는 방안보다 20% 가량 좋은 성능을 가지는 것을 확인하였다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제14권11호
• /
• pp.4268-4289
• /
• 2020

Advanced traffic signal timing method plays very important role in reducing road congestion and air pollution. Reinforcement learning is considered as superior approach to build traffic light timing scheme by many recent studies. It fulfills real adaptive control by the means of taking real-time traffic information as state, and adjusting traffic light scheme as action. However, existing works behave inefficient in complex intersections and they are lack of feasibility because most of them adopt traffic light scheme whose phase sequence is flexible. To address these issues, a novel adaptive traffic signal timing scheme is proposed. It's based on actor-critic reinforcement learning algorithm, and advanced techniques proximal policy optimization and generalized advantage estimation are integrated. In particular, a new kind of reward function and a simplified form of state representation are carefully defined, and they facilitate to improve the learning efficiency and reduce the computational complexity, respectively. Meanwhile, a fixed phase sequence signal scheme is derived, and constraint on the variations of successive phase durations is introduced, which enhances its feasibility and robustness in field applications. The proposed scheme is verified through field-data-based experiments in both medium and high traffic density scenarios. Simulation results exhibit remarkable improvement in traffic performance as well as the learning efficiency comparing with the existing reinforcement learning-based methods such as 3DQN and DDQN.

• 아태비즈니스연구
• /
• 제10권4호
• /
• pp.223-236
• /
• 2019

Governance can be defined as a concept that encompasses a series of processes including partner selection as well as control and coordination of collaboration to achieve common goals. The study examined efforts to mitigate the risks of opportunistic behaviors into partner selection, partner relationship, control mechanism, and conflict management. For cases that have achieved commercialization outputs with the participation of SMEs, data was collected and analyzed such as interviews with project managers and case records for seven months from October 2016. According to the analysis result, as the complexity increases, such as multilateral cooperation for the development of finished products, cooperation with a trusted partner rather than a partner who can perform a task well was preferred, and the process control was put ahead of the output control. Regarding the partner relationship, the relationship between the owner and the agent differed according to the point of view, and there was a lack of clear allocation of authority and responsibility as well as a reward for the result. In terms of the conflict management, most emphasis was on resolving conflicts or difficulties, and no attempt was made to utilize the positive aspects of the conflict. The structure of most industry-university-institute cooperation organizations is simply composed of the host and participating organizations, and the management regulations should be amended for companies, that put actual funds and use the outputs, to have the authority and responsibility as the owners, and be allowed to use the governance elements appropriately to take the lead as consumers.

• 한국IT서비스학회지
• /
• 제19권6호
• /
• pp.131-144
• /
• 2020

As the blockchain technology attracts attention, interest in cryptocurrency that is received as a reward is also increasing. Currently, investments and transactions are continuing with the expectation and increasing value of cryptocurrency. Accordingly, prediction for cryptocurrency price has been attempted through artificial intelligence technology and social sentiment analysis. The purpose of this paper is to develop a deep learning ensemble model for predicting the price fluctuations and one-day lag price of cryptocurrency based on the design science research method. This paper intends to perform predictive modeling on Ethereum among cryptocurrencies to make predictions more efficiently and accurately than existing models. Therefore, it collects data for five years related to Ethereum price and performs pre-processing through customized functions. In the model development stage, four LSTM models, which are efficient for time series data processing, are utilized to build an ensemble model with the optimal combination of hyperparameters found in the experimental process. Then, based on the performance evaluation scale, the superiority of the model is evaluated through comparison with other deep learning models. The results of this paper have a practical contribution that can be used as a model that shows high performance and predictive rate for cryptocurrency price prediction and price fluctuations. Besides, it shows academic contribution in that it improves the quality of research by following scientific design research procedures that solve scientific problems and create and evaluate new and innovative products in the field of information systems.

• Journal of Korean Biological Nursing Science
• /
• 제23권2호
• /
• pp.91-99
• /
• 2021

Purpose: This study aimed to identify occupational stress and health problems as well as turnover reasons among leavers in novice nurses and to estimate factors which might affect turnover by comparing them to stayers. Methods: In this study, secondary analysis of data gathered from the Shift Work Nurse's Health and Turnover studies, was carried out. The data were collected from 204 stayers who have been working for 18 months since 2018 and 48 leavers who left within the same period at two tertiary hospitals in Seoul. The reasons for turnover, occupational stress, and 8 types of health problems were recorded. The data were analyzed using SAS 9.4 to obtain descriptive statistics. In parallel, Pearson's chi-squared test, Fisher's exact test, and independent t-test were also conducted. Results: The main reasons for turnover were job stress and difficult interpersonal relationships in the workplace. Occupational stress of leavers was higher than stayers, especially in the subscales of interpersonal conflict, organizational system, lack of reward, and occupational climate. Among the 8 types of health problems, the depression prevalence of leavers was higher compared to stayers and showed marginal significance. Unexpectedly, the sleep disturbance prevalence of stayers was significantly higher compared to leavers. Conclusion: To reduce the turnover rate of novice nurses, education on how to cope with occupational stress is needed. A customized program for novice nurses to overcome the difficulties of interpersonal relations would be helpful.

• Biomolecules & Therapeutics
• /
• 제30권3호
• /
• pp.238-245
• /
• 2022

Previous reports have demonstrated that genetic mechanisms greatly mediate responses to drugs of abuse, including methamphetamine (METH). The circadian gene Period 2 (Per2) has been previously associated with differential responses towards METH in mice. While the behavioral consequences of eliminating Per2 have been illustrated previously, Per2 overexpression has not yet been comprehensively described; although, Per2-overexpressing (Per2 OE) mice previously showed reduced sensitivity towards METH-induced addiction-like behaviors. To further elucidate this distinct behavior of Per2 OE mice to METH, we identified possible candidate biomarkers by determining striatal differentially expressed genes (DEGs) in both drug-naïve and METH-treated Per2 OE mice relative to wild-type (WT), through RNA sequencing. Of the several DEGs in drug naïve Per2 OE mice, we identified six genes that were altered after repeated METH treatment in WT mice, but not in Per2 OE mice. These results, validated by quantitative real-time polymerase chain reaction, could suggest that the identified DEGs might underlie the previously reported weaker METH-induced responses of Per2 OE mice compared to WT. Gene network analysis also revealed that Asic3, Hba-a1, and Rnf17 are possibly associated with Per2 through physical interactions and predicted correlations, and might potentially participate in addiction. Inhibiting the functional protein of Asic3 prior to METH administration resulted in the partial reduction of METH-induced conditioned place preference in WT mice, supporting a possible involvement of Asic3 in METH-induced reward. Although encouraging further investigations, our findings suggest that these DEGs, including Asic3, may play significant roles in the lower sensitivity of Per2 OE mice to METH.

• 한국엔터테인먼트산업학회논문지
• /
• 제15권2호
• /
• pp.137-148
• /
• 2021

본 연구는 사회재난 대응 업무에 종사하고 있는 소방관들을 대상으로 지역자율방재단의 전문성에 관한 인식도를 조사해 우리나라 지역자율방재단의 방재활동 전반에 대한 현실적인 문제점을 도출하고 개선방안을 모색하고자 하였다. 주요 연구 결과는 다음과 같다. 첫째, 지역자율방재단의 새로운 인적 자원 관리제도와 적극적인 홍보 실시 둘째, 재정적인 지원과 보상제도의 개선이 필요 셋째, 지역자율방재단에 도움이 되는 맞춤식 교육과 훈련이 필요하다. 본 연구 결과는 향후 우리나라 지역자율방재단의 발전을 위한 기초 자료로 활용되기를 기대한다.

• 한국정보통신학회논문지
• /
• 제26권8호
• /
• pp.1148-1157
• /
• 2022

2019년 코로나로 인하여 사람들의 많은 생활에 변화를 주었다. 그중 메타버스는 다양한 방식을 통한 비대면 서비스를 지원하여 일상에서 하던 일을 대체하고 있다. 이런 현상은 코로나19의 장기화로 하나의 문화처럼 만들어지고 형성되었다. 본 논문은 메타버스의 재미요인을 알기 위해 기존 게임에서 사용한 재미요소를 정리하여 전문가 5명과 함께 항목, 내용을 메타버스에 맞게 재분류하였다. 분류는 재매개성을 사용하여 분류하였고 감각적 재미[시각(그래픽), 청각, 텍스트, 조작, 감정이입, 유희, 시점], 도전적 재미[몰입, 도전, 성취, 발견, 스릴, 보상, 문제해결], 상상적 재미[새로운 이야기, 사랑, 자유도, 대리자아, 기대감, 변화], 사회적 재미[규칙, 경쟁, 사회적 행위, 지위, 협동, 참여, 교류, 소속, 화폐거래], 상호작용적 재미[의사결정, 커뮤니케이션 공유, 하드웨어, 감정이입, 육성, 자율성], 현실적 재미[현실 일체감, 학습 용이성, 순응, 지적문제해결, 패턴 인식, 실재감, 커뮤니티], 창조적 재미[응용, 창조, 커스텀마이징, 가상세계]로 구분하였다.

• 한국콘텐츠학회논문지
• /
• 제22권6호
• /
• pp.506-517
• /
• 2022

본 연구는 치매환자 가족돌봄자의 돌봄만족감에 대한 개념적 정의와 속성을 확인하기 위해 수행되었다. 연구방법은 혼종모형을 이용하였으며, 이론적 고찰과 7명의 대상자로부터 수집된 현장조사 결과는 최종 단계에서 통합하여 분석하였다. 연구결과로 돌봄만족감은 3개의 차원과 7개의 속성으로 도출되었다. 돌봄만족감의 정의는 가족돌봄자가 경험하는 돌봄에 대한 긍정적인 측면으로서, 관계 차원에서 돌봄의 의무 실천과 상호호혜적 관계로 여기고, 환자와 가족간 관계에서 유대감 강화, 역할수행 차원에서는 성취감, 정서적 보상감, 심리적 안정감을 느끼고, 역할 의미 차원에서 긍정적 의미부여를 하는 것으로 나타났다. 본 연구를 기초로 하여 한국의 치매환자 가족돌봄자의 돌봄만족감 측정도구와 돌봄만족감 증진을 위한 효율적인 간호중재 프로그램 개발을 제언한다.

• 융합정보논문지
• /
• 제11권8호
• /
• pp.194-200
• /
• 2021

뷰티산업은 어려운 사회적 환경에도 지속적으로 발전하였고 과정에 소규모 뷰티업들은 점차 대형화된 뷰티프랜차이즈 상태로 급성장 하였다. 따라서 뷰티산업에 종사하는 종사자들에게 다양한 내부마케팅이 필요하다고 사료되어 본 연구를 진행하였으며 종사자들에게 어떠한 내부마케팅이 직무몰입에 큰영향을 미치는지 알아보기 위해 2021년 2월 1일부터 2021년 3월 31일까지 설문지 250부 중 220부를 수집하여 spss 22.0으로 빈도분석, 신뢰도분석, 요인분석, 상관분석, 다중회기분석한 결과 연구 가설로 세운 4가지 모두 영향을 미치는 것으로 나타났으며, 그중 종사자들이 가장 만족하는 내부마케팅은 보상시스템이 었고 직무몰입에 가장 큰 영향을 미치는 것으로 나타났다. 따라서 내부마케팅은 종사자가 원하는 실질적 내부마케팅이 계획 되어야 한다고 사료된다.