• 반도체디스플레이기술학회지
• /
• 제16권3호
• /
• pp.127-130
• /
• 2017

In this research, we present a path planning method for an autonomous flight of unmanned aerial vehicles (UAVs) through reinforcement learning under simulated environment. We design the simulator for reinforcement learning of uav. Also we implement interface for compatibility of Deep Q-Network(DQN) and simulator. In this paper, we perform reinforcement learning through the simulator and DQN, and use Q-learning algorithm, which is a kind of reinforcement learning algorithms. Through experimentation, we verify performance of DQN-simulator. Finally, we evaluated the learning results and suggest path planning strategy using reinforcement learning.

• ETRI Journal
• /
• 제46권3호
• /
• pp.379-391
• /
• 2024

To meet increasing traffic requirements in mobile networks, small base stations (SBSs) are densely deployed, overlapping existing network architecture and increasing system capacity. However, densely deployed SBSs increase energy consumption and interference. Although these problems already exist because of densely deployed SBSs, even more SBSs are needed to meet increasing traffic demands. Hence, base station (BS) switching operations have been used to minimize energy consumption while guaranteeing quality-of-service (QoS) for users. In this study, to optimize energy efficiency, we propose the use of deep reinforcement learning (DRL) to create a BS switching operation strategy with a traffic prediction model. First, a federated long short-term memory (LSTM) model is introduced to predict user traffic demands from user trajectory information. Next, the DRL-based BS switching operation scheme determines the switching operations for the SBSs using the predicted traffic demand. Experimental results confirm that the proposed scheme outperforms existing approaches in terms of energy efficiency, signal-to-interference noise ratio, handover metrics, and prediction performance.

• 한국산업정보학회논문지
• /
• 제24권1호
• /
• pp.23-30
• /
• 2019

딥러닝 네트워크 기반의 알고리즘의 발전으로 인공지능은 전세계적으로 빠른 성장세를 보이고 있다. 그 중 금융은 인공지능이 가장 많이 활용될 분야로 예상되고 있으며 최근 많은 연구가 되고 있다. 기존의 딥러닝을 사용한 재무 전략은 단일 종목에 대한 주가 예측에만 치중되어 있어 변동성에 취약하다. 따라서 본 연구는 딥러닝을 이용하여 펀드 구성 종목을 산출하고 종목들을 분산투자하여 ETF 상품을 구성하는 모델을 제안한다. 실험 결과로 제안하는 모델을 통해 코스피 100 지수를 대상으로 하는 성능을 분석하며 수익률 또는 안정성 측면에서 향상된 결과를 확인하였다.

• 한국군사과학기술학회지
• /
• 제23권4호
• /
• pp.399-406
• /
• 2020

In this paper, we propose a time-varying proportional navigation guidance law that determines the proportional navigation gain in real-time according to the operating situation. When intercepting a target, an unidentified evasion strategy causes a loss of optimality. To compensate for this problem, proper proportional navigation gain is derived at every time step by solving an optimal control problem with the inferred evader's strategy. Recently, deep reinforcement learning algorithms are introduced to deal with complex optimal control problem efficiently. We adapt the actor-critic method to build a proportional navigation gain network and the network is trained by the Proximal Policy Optimization(PPO) algorithm to learn an evasion strategy of the target. Numerical experiments show the effectiveness and optimality of the proposed method.

• Nuclear Engineering and Technology
• /
• 제53권7호
• /
• pp.2229-2236
• /
• 2021

In nuclear-related facilities, such as nuclear power plants, research reactors, accelerators, and nuclear waste storage sites, radiation detection, and mapping are required to prevent radiation overexposure. Sensor network systems consisting of radiation sensor interfaces and wxireless communication units have become promising tools that can be used for data collection of radiation detection that can in turn be used to draw a radiation map. During data collection, malfunctions in some of the sensors can occasionally occur due to radiation effects, physical damage, network defects, sensor loss, or other reasons. This paper proposes a reproduction strategy for radiation maps using a U-net model to compensate for the loss of radiation detection data. To perform machine learning and verification, 1,561 simulations and 417 measured data of a sensor network were performed. The reproduction results show an accuracy of over 90%. The proposed strategy can offer an effective method that can be used to resolve the data loss problem for conventional sensor network systems and will specifically contribute to making initial responses with preserved data and without the high cost of radiation leak accidents at nuclear facilities.

• 정보화정책
• /
• 제24권4호
• /
• pp.79-92
• /
• 2017

도시 기능이 복합적으로 발전함에 따라 스마트 시티에 대한 관심이 높아지고 있다. 스마트 시티란 정보통신기술을 활용하여 교통, 안전, 복지, 생활 등 도시 문제를 효과적으로 해결하는 것을 말한다. 최근 세계 각국은 빅데이터, 사물인터넷, 인공지능 기술을 스마트 시티에 도입하는 시도를 하고 있으나 종합적인 도시 서비스로는 발전하지 못하고 있다. 본 논문에서는 국내외 스마트 시티 추진 현황을 살펴보고 핵심 문제로 부각된, 데이터 공유문제, 서비스 호환성 문제를 해결하는 방안을 제시하였다. 이를 위해 딥러닝 기술을 스마트 시티 서비스에 접목한 "딥러닝 시티 프레임워크"를 제안하고 도시 여러 영역의 시공간 데이터를 안전하게 공유하고 여러 도시의 학습 데이터를 융합하는 새로운 스마트 시티 추진 전략을 제시하였다.

• 공학교육연구
• /
• 제21권5호
• /
• pp.20-31
• /
• 2018

The purpose of this study was to investigate the relationship between instructional strategies applied to engineering courses and students' learning strategies. As a result, students perceived that the application principle was the most applied and then the problem-centered principle was applied to engineering courses. In addition, the students showed that rehearsal strategies are the most used in courses. The most important instructional principle in this study was the problem-centered principle, and the higher the degree of application of problem-centered principle in engineering course, the students were likely to use more deep learning strategies such as elaboration and organization strategy, critical thinking strategy, and metacognitive strategy.

• 한국컴퓨터정보학회논문지
• /
• 제24권2호
• /
• pp.17-24
• /
• 2019

In this paper, we propose a new model for predicting effective Win/Loss in professional baseball game in Korea using machine learning technique. we used basic baseball data and Sabermetrics data, which are highly correlated with score to predict and we used the deep learning technique to learn based on supervised learning. The Drop-Out algorithm and the ReLu activation function In the trained neural network, the expected odds was calculated using the predictions of the team's expected scores and expected loss. The team with the higher expected rate of victory was predicted as the winning team. In order to verify the effectiveness of the proposed model, we compared the actual percentage of win, pythagorean expectation, and win percentage of the proposed model.

• 한국정보통신학회논문지
• /
• 제25권9호
• /
• pp.1267-1270
• /
• 2021

In this paper, we propose a distributed routing algorithm for mobile ad hoc networks (MANET) where mobile devices can be utilized as relays for communication between remote source-destination nodes. The objective of the proposed algorithm is to minimize the end-to-end communication delay caused by transmission failure with deep channel fading. In each hop, the node needs to select the next relaying node by considering a tradeoff relationship between the link stability and forward link distance. Based on such feature, we formulate the problem with partially observable Markov decision process (MDP) and apply deep reinforcement learning to derive effective routing strategy for the formulated MDP. Simulation results show that the proposed algorithm outperforms other baseline schemes in terms of the average end-to-end delay.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제14권11호
• /
• pp.4557-4572
• /
• 2020

The Alaska competition provides an opportunity to study the practical problems of real-world steganalysis. Participants are required to solve steganalysis involving various embedding schemes, inconsistency JPEG Quality Factor and various processing pipelines. In this paper, we propose a method to ensemble multiple deep learning steganalyzers. We select SRNet and RESDET as our base models. Then we design a three-layers model ensemble network to fuse these base models and output the final prediction. By separating the three colors channels for base model training and feature replacement strategy instead of simply merging features, the performance of the model ensemble is greatly improved. The proposed method won second place in the Alaska 1 competition in the end.