• Title/Summary/Keyword: 네트워크 구간

Search Result 505, Processing Time 0.025 seconds

DQN Reinforcement Learning for Mountain-Car in OpenAI Gym Environment (OpenAI Gym 환경의 Mountain-Car에 대한 DQN 강화학습)

  • Myung-Ju Kang
    • Proceedings of the Korean Society of Computer Information Conference
    • /
    • 2024.01a
    • /
    • pp.375-377
    • /
    • 2024
  • 본 논문에서는 OpenAI Gym 환경에서 프로그램으로 간단한 제어가 가능한 Mountain-Car-v0 게임에 대해 DQN(Deep Q-Networks) 강화학습을 진행하였다. 본 논문에서 적용한 DQN 네트워크는 입력층 1개, 은닉층 3개, 출력층 1개로 구성하였고, 입력층과 은닉층에서의 활성화함수는 ReLU를, 출력층에서는 Linear함수를 활성화함수로 적용하였다. 실험은 Mountain-Car-v0에 대해 DQN 강화학습을 진행했을 때 각 에피소드별로 획득한 보상 결과를 살펴보고, 보상구간에 포함된 횟수를 분석하였다. 실험결과 전체 100회의 에피소드 중 보상을 50 이상 획득한 에피소드가 85개로 나타났다.

  • PDF

Modulation Scheme for Network-coded Bi-directional Relaying over an Asymmetric Channel (양방향 비대칭 채널에서 네트워크 부호화를 위한 변조 방식)

  • Ryu, Hyun-Seok;Kang, Chung-G.
    • The Journal of Korean Institute of Communications and Information Sciences
    • /
    • v.37 no.2B
    • /
    • pp.97-109
    • /
    • 2012
  • In this paper, we propose a modulation scheme for a network-coded bi-directional relaying (NBR) system over an asymmetric channel, which means that the qualities of the relay channel (the link between the BS and RS) and access channel (the link between the RS and MS) are not identical. The proposed scheme employs a dual constellation in such a way that the RS broadcasts the network-coded symbols modulated by two different constellations to the MS and BS over two consecutive transmission intervals. We derive an upper bound on the average bit error rate (BER) of the proposed scheme, and compare it with the hybrid constellation-based modulation scheme proposed for the asymmetric bi-directional link. Furthermore, we investigate the channel utilization of the existing bi-directional relaying schemes as well as the NBR system with the proposed dual constellation diversity-based modulation (DCD). From our simulation results, we show that the DCD gives better average BER performance about 3.5~4dB when $E_b/N_0$ is equal to $10^{-2}$, while maintaining the same spectral efficiency as the existing NBR schemes over the asymmetric bi-directional relaying channel.

Analysis of Qualitative Research on Science Education Trend in Korea Using Semantic Network Analysis (네트워크 분석을 통한 국내 과학교육 질적 연구동향 분석)

  • Lee, Sanggyun;Kim, Soonshik;Chae, Donghyun
    • Journal of the Korean Society of Earth Science Education
    • /
    • v.10 no.3
    • /
    • pp.290-307
    • /
    • 2017
  • The purpose of this study is to analyze the research trends related to qualitative research on science education, to provide basic data of qualitative research on science education and to select the direction of follow-up research. The subject of the study is the level of Korean Citation Index (KCI-listed, KCI listing candidates), that can be searched by the key phrase, 'qualitative research', 'science education' in Korean language through the RISS service. In this study, the Descriptive Statistical Analysis Method is utilized to discover the number of research articles, classifying them by year and by journal. Also, the Sementic Network Analysis was conducted to the frequency of key words, Centrality Analysis throughout a variety of research articles using krkwic and Ucinet6.0. The results show that first, 138 research papers were published in 14 journals from 2005 to 2017. Second,, the analysis showed the highest frequency of appearance keyword in each article, 'elementary school teacher', 'gifted student', 'science teacher', 'class' were higher than others. third, according to the results of the whole Network Analysis, 'Analysis', 'elementary school', 'class' were analyzed as a highly influential node. And 'Comparison', 'inquiry', 'recognition', 'gifted students' were not close to the center of network. Fourth, keywords that appear in all sections are analysis, gifted students, and elementary school students, and can be analyzed continuously based on studies, lessons or recognition, and characteristics. Based on the results of this study, we explored the past and present of the study subjects related to the study of science education quality and discussed future direction of study.

A Shortest Path Algorithm Considering Directional Delays at Signalized Intersection (신호교차로에서 방향별 지체를 고려한 최적경로탐색 연구)

  • Min, Keun-Hong;Jo, Mi-Jeong;Kho, Seung-Young
    • The Journal of The Korea Institute of Intelligent Transport Systems
    • /
    • v.9 no.3
    • /
    • pp.12-19
    • /
    • 2010
  • In road network, especially in urban area, inefficiency of travel time is caused by signal control and turn maneuver at intersection and this inefficiency has substantial effects on travel time. When searching for the shortest path, this inefficiency which is caused by turn maneuver must be considered. Therefore, travel time, vehicle volume and delay for each link were calculated by using simulation package, PARAMICS V5.2 for adaptation of turn penalty at 16 intersections of Gangnam-gu. Turn penalty was calculated respectively for each intersection. Within the same intersection, turn penalty differs by each approaching road and turn direction so the delay was calculated for each approaching road and turn direction. Shortest path dealing with 16 intersections searched by Dijkstra algorithm using travel time as cost, considering random turn penalty, and algorithm considering calculated turn penalty was compared and analyzed. The result shows that by considering turn penalty searching the shortest path can decrease the travel time can be decreased. Also, searching the shortest path which considers turn penalty can represent reality appropriately and the shortest path considering turn penalty can be utilized as an alternative.

A Proxy Mobile IP based Fast Layer-3 Handover scheme for Mobile WiMAX based Wireless Mesh Networks (Mobile WiMAX 기반의 무선 메쉬 네트워크를 위한 Proxy Mobile IP 기반의 고속 3계층 핸드오버 방안)

  • Kim, Min;Kim, Jong-Min;Kim, Hwa-Sung
    • The Journal of Korean Institute of Communications and Information Sciences
    • /
    • v.35 no.8B
    • /
    • pp.1129-1140
    • /
    • 2010
  • Wireless mesh networks have been widely studied as the next generation technology to solve the problems of conventional wireless networks. Particularly, Mobile WiMAX based wireless mesh networks are noticed due to many advantages. Mobile WiMAX standard provides two kinds of layer-3 handover schemes: Mobile IP and Proxy Mobile IP based handover schemes. MIP based handover scheme has a problem in that it incurs the long handover latency because mobile nodes generate a lot of handover messages. On the other hand, PMIP based handover scheme decreases the handover latency by reducing the number of handover messages, because mobile nodes do not participate in handover procedure. Therefore, layer-3 handover for Mobile WiMAX should be designed based on PMIP. However, conventional PMIP based handover still has latency overhead, because of many message exchanges between PBU and PBA after completing the layer-2 handover. Hence, in this paper, we propose a fast layer-3 handover scheme that achieves the lower handover latency for Mobile WiMAX based wireless mesh networks. Proposed scheme has advantages in terms of handover latency. Simulation results show that proposed scheme achieves low handover latency during the layer-3 handover.

An Efficient Transmission Plan for Adaptable Bandwidth Allocation Technique (적응형 대역폭 할당 방법을 위한 효율적인 전송 계획)

  • Lee, Myoun-Jae;Park, Do-Soon
    • The KIPS Transactions:PartC
    • /
    • v.14C no.3 s.113
    • /
    • pp.285-292
    • /
    • 2007
  • In the adaptable bandwidth allocation technique, a transmission plan for variable rate video data is made by the CBA algorithm and the data is transmitted by considering network traffic. But the CBA algorithm produces a transmission plan where the size of the increasing interval of transmission rate is generally larger than the size of the decreasing interval. And the transmission rate in CBA algorithm is changed in overflow curve during the increasing interval of transmission rate. This ぉy cause many frames to be discarded when available transmission rate is small. In this paper, a smoothing algorithm is proposed, where transmission rate is changed in the middle of underflow curve and overflow curve, but the transmission rate increases at the minimum. In order to show the performance, the proposed algorithm and a CBA algorithm were applied to a transmission plan in the adaptable bandwidth allocation technique, and the minimum frame rates, the average frame rates, the variation of frame rates, and the numbers of discarded frames were compared in both algorithms.

Calculation of a Diesel Vehicle's Carbon Dioxide Emissions during Haulage Operations in an Underground Mine using GIS (GIS를 이용한 지하광산 디젤 차량의 운반작업 시 탄소배출량 산정)

  • Park, Boyoung;Park, Sebeom;Choi, Yosoon;Park, Han-Su
    • Tunnel and Underground Space
    • /
    • v.25 no.4
    • /
    • pp.373-382
    • /
    • 2015
  • This study presents a method to calculate carbon dioxide emissions of diesel vehicles operated in an underground mine using Geographic Information Systems (GIS). An underground limestone mine in Korea was selected as the study area. A GIS database was constructed to represent the haulage roads as a 3D vector network. The speed of dump trucks at each haulage road was investigated to determine the carbon dioxide emission factor. The amount of carbon dioxide emissions related to the truck's haulage work could be calculated by considering the carbon dioxide emission factor at each haulage road and the haulage distance determined by GIS-based optimal route analysis. Because diesel vehicles are widely utilized in the mining industry, the method proposed in this study can be used and further improved to calculate the amount of carbon dioxide emissions in mining sites.

Real-time Error Detection Based on Time Series Prediction for Embedded Sensors (임베디드 센서를 위한 시계열 예측 기반 실시간 오류 검출 기법)

  • Kim, Hyung-Il
    • Journal of the Korea Society of Computer and Information
    • /
    • v.16 no.12
    • /
    • pp.11-21
    • /
    • 2011
  • An embedded sensor is significantly influenced by its spatial environment, such as barriers or distance, through low power and signal strength. Due to these causes, noise data frequently occur in an embedded sensor. Because the information acquired from the embedded sensor exists in a time series, it is hard to detect an error which continuously takes place in the time series information on a realtime basis. In this paper, we proposes an error detection method based on time-series prediction that detects error signals of embedded sensors in real time in consideration of the physical characteristics of embedded devices. The error detection method based on time-series prediction proposed in this paper determines errors in generated embedded device signals using a stable distance function. When detecting errors by monitoring signals from an embedded device, the stable distance function can detect error signals effectively by applying error weight to the latest signals. When detecting errors by monitoring signals from an embedded device, the stable distance function can detect error signals effectively by applying error weight to the latest signals.

Performance Evaluation of WUSB over WBAN Communication Structure for Wireless Wearable Computers (무선 웨어러블 컴퓨터를 위한 WUSB over WBAN 통신 구조의 성능 분석)

  • Hur, Kyeong
    • Journal of the Korea Institute of Information and Communication Engineering
    • /
    • v.18 no.4
    • /
    • pp.839-847
    • /
    • 2014
  • A recent major development in computer technology is the advent of the wearable computer system that is based on human-centric interface technology trends and ubiquitous computing environments. Wearable computer systems can use the wireless universal serial bus (WUSB) that refers to USB technology that is merged with WiMedia PHY/MAC technical specifications. In this paper, we focus on an integrated system of the wireless USB over the wireless body area networks (WBAN) for wireless wearable computer systems supporting U-health services. To construct the WUSB over WBAN communication systems, we propose a WBAN beaconing structure to assign WUSB communication periods. In the proposed structure, WUSB uses private periods of WBAN. In our performance evaluations, we compare theoretical results and simulation results about throughputs of WUSB under various WBAN channel occupations to evaluate the effectiveness of proposed structure in WUSB over WBAN communications.

A New Energy Saving Transport Protocol in Wireless Environments (무선 환경에서 새로운 에너지 절약형 전송 프로토콜)

  • Hwang, Sae-Joon;Lee, Jung-Min;Chung, Kwang-Sue
    • Journal of KIISE:Computer Systems and Theory
    • /
    • v.32 no.11_12
    • /
    • pp.654-662
    • /
    • 2005
  • Mobile portable devices for wireless network solely depend on a limited battery power. Therefore, we need to design for wireless communication protocols with an energy efficiency. TCP-Westwood is one of the most important approaches on TCP performance improvement in wireless environments that estimates the available bandwidth by using the sampling mechanism. The advantage is that data can be transmitted efficiently using the estimation of available bandwidth. However, when the sender with TCP-Westwood is in a wireless environment, it does not consider of the sampling mechanism operation. In this thesis, a new energy saving transport protocol, called E2TP(Energy Efficient Transport Protocol), is proposed to solve problems which occur when the sender with TCP-Westwood is in a wireless environment. Also, when there are packet loss while doing frequent link error in a wireless environment, E2TP provides the instantaneous segment size adjustment for a more efficient data retransmission. The simulation result proves that the proposed E2TP has better performance in energy efficiency and throughput than both TCP and TCP-Westwood.