• Title/Summary/Keyword: localized process of learning

Search Result 12, Processing Time 0.022 seconds

A Study of Adaptive QoS Routing scheme using Policy-gradient Reinforcement Learning (정책 기울기 값 강화학습을 이용한 적응적인 QoS 라우팅 기법 연구)

  • Han, Jeong-Soo
    • Journal of the Korea Society of Computer and Information
    • /
    • v.16 no.2
    • /
    • pp.93-99
    • /
    • 2011
  • In this paper, we propose a policy-gradient routing scheme under Reinforcement Learning that can be used adaptive QoS routing. A policy-gradient RL routing can provide fast learning of network environments as using optimal policy adapted average estimate rewards gradient values. This technique shows that fast of learning network environments results in high success rate of routing. For prove it, we simulate and compare with three different schemes.

A Localized Adaptive QoS Routing Scheme Using POMDP and Exploration Bonus Techniques (POMDP와 Exploration Bonus를 이용한 지역적이고 적응적인 QoS 라우팅 기법)

  • Han Jeong-Soo
    • The Journal of Korean Institute of Communications and Information Sciences
    • /
    • v.31 no.3B
    • /
    • pp.175-182
    • /
    • 2006
  • In this paper, we propose a Localized Adaptive QoS Routing Scheme using POMDP and Exploration Bonus Techniques. Also, this paper shows that CEA technique using expectation values can be simply POMDP problem, because performing dynamic programming to solve a POMDP is highly computationally expensive. And we use Exploration Bonus to search detour path better than current path. For this, we proposed the algorithm(SEMA) to search multiple path. Expecially, we evaluate performances of service success rate and average hop count with $\phi$ and k performance parameters, which is defined as exploration count and intervals. As result, we knew that the larger $\phi$, the better detour path search. And increasing n increased the amount of exploration.

A Probe for Local Community Centered Lifelong Learning Movement's Course of Action (지역사회 중심 평생학습운동의 추진방향 탐색: 외국의 평생학습운동 사례를 중심으로)

  • Yang Heug-Kweun;Choi Sang-Keun
    • The Korean Journal of Community Living Science
    • /
    • v.17 no.1
    • /
    • pp.109-122
    • /
    • 2006
  • As we encounter the global and localized era, the development operations on a regional level are in active promotion. This manuscript has been completed with the purpose of probing for course of action in lifelong learning movement in terms of activating and developing of local communities. For this, the comparative analysis of practiced cases in America's community school movement, Japan's movement for establishing lifelong learning village and Sweden's study circle movement have been made. For the analytical frame of the comparison, the actual results on background of promotion, themes for practice, details of practice, methods for practice of local community centered lifelong learning movement have been applied. As a result of analysis, the local community centered lifelong learning movement has been promoted to break each country's social and economic crisis and to activate the local community. The promotion of each operation has been accomplished with the support of specific organization and the participants were the citizens of the local community. Also, the details of practice are composed of operating the people-centered lifelong learning program, cooperative learning by local citizens and local community realization activity. The details of education is closely related with the life of learners. Therefore, the lifelong movement for the activation of local community hereafter should be promoted based on the coherence of local community, should be able to contain the actual life of the citizens and should be practiced as a process of forming the lifelong learning group at concerned local community through a democratic learning process.

  • PDF

Development Process of Nuclear Power Industry in a Developing Country : Korean Experience and Implications (개발도상국에 있어서 원자력산업의 기술발전과정 분석 : 한국의 경험과 시사점)

  • 홍사균
    • Proceedings of the Technology Innovation Conference
    • /
    • 1999.06a
    • /
    • pp.176-202
    • /
    • 1999
  • Korea has exerted her efforts to assimilate nuclear power technology, and reportedly localized 95 percent of nuclear power technology by 1995. This paper investigates the evolution of nuclear power program in Korea to exploit the development process of the nuclear power industry and key factors for the technological localization of nuclear power plant. In developing countries, an imitative catching-up process can be shown as a course for developing the absorptive capacity of foreign technology, which depends on prior knowledge base and the intensity of effort. The process of technological learning consists of five stages including preparation, implementation of foreign technology, acquisition of peripheral technology, acquisition of core technology, and improvement f foreign technology. Moreover, this paper discusses six essential factors that have influenced the successful achievement of technological localization of nuclear power plants in Korea. They include the role and strategies of the government, the leading role of utility firm, the development and cooperation of the related organizations, the development of human resources and their efforts, market conditions and the assistance of foreign donors, and social conditions. Finally, this paper discusses about implications offered by the Korean experience for other developing countries.

  • PDF

An Exploratory Case Study on the Localization Activities of Automotive Components SMEs: Transplants of Hyundai/Kia suppliers in the US (자동차 부품 중소기업의 해외 현지화 활동에 대한 탐색적 사례연구: - 미국진출 현대차/기아차 협력업체를 중심으로 -)

  • Ha, Seongwook;Lee, Sang Kon
    • Knowledge Management Research
    • /
    • v.13 no.2
    • /
    • pp.19-35
    • /
    • 2012
  • This study empirically investigates the differences of dominant management problems (hereafter, DMPs) among transplants in different degree of localization, based on the exploratory case study on the nine transplants of Hyundai/Kia suppliers in US using AHP(Analytic Hierarchy Process) technique. On the results of the literature review, this study divides the DMPs of transplants into three main categories such as building human infrastructure, stabilizing manufacturing processes, and building learning network. Each categories is also divided into four subcategories. The degree of localization includes two variables such as the localization stage and the employee size of transplant. Main findings are as follows. First, 'Communication among Korean and local employees' is important DMP in all transplants examined. Second, 'Local adaptation of Korean manufacturing technology' and 'Education on the Korean culture and management practices' are more important DMPs for less-localized transplants than more-localized ones. On the contrary, 'Motivating local employees' is more important DMP for more-localized transplants than less-localized ones. Third, 'Education on the technology and quality' is more important DMP for transplants in post-production stage than in stabilization stage. On the contrary, 'Staffing local employees' is more important DMP for transplants in stabilization stage than in post-production stage. Fourth, 'Acquiring test and measurement equipments' is more important DMP for small-sized transplants than large-sized ones. On the contrary, 'adopting new technology' and 'Building local suppliers network' are more important DMPs for large-sized transplants than small-sized ones.

  • PDF

Sparse Matrix Compression Technique and Hardware Design for Lightweight Deep Learning Accelerators (경량 딥러닝 가속기를 위한 희소 행렬 압축 기법 및 하드웨어 설계)

  • Kim, Sunhee;Shin, Dongyeob;Lim, Yong-Seok
    • Journal of Korea Society of Digital Industry and Information Management
    • /
    • v.17 no.4
    • /
    • pp.53-62
    • /
    • 2021
  • Deep learning models such as convolutional neural networks and recurrent neual networks process a huge amounts of data, so they require a lot of storage and consume a lot of time and power due to memory access. Recently, research is being conducted to reduce memory usage and access by compressing data using the feature that many of deep learning data are highly sparse and localized. In this paper, we propose a compression-decompression method of storing only the non-zero data and the location information of the non-zero data excluding zero data. In order to make the location information of non-zero data, the matrix data is divided into sections uniformly. And whether there is non-zero data in the corresponding section is indicated. In this case, section division is not executed only once, but repeatedly executed, and location information is stored in each step. Therefore, it can be properly compressed according to the ratio and distribution of zero data. In addition, we propose a hardware structure that enables compression and decompression without complex operations. It was designed and verified with Verilog, and it was confirmed that it can be used in hardware deep learning accelerators.

Supervised learning and frequency domain averaging-based adaptive channel estimation scheme for filterbank multicarrier with offset quadrature amplitude modulation

  • Singh, Vibhutesh Kumar;Upadhyay, Nidhi;Flanagan, Mark;Cardiff, Barry
    • ETRI Journal
    • /
    • v.43 no.6
    • /
    • pp.966-977
    • /
    • 2021
  • Filterbank multicarrier with offset quadrature amplitude modulation (FBMC-OQAM) is an attractive alternative to the orthogonal frequency division multiplexing (OFDM) modulation technique. In comparison with OFDM, the FBMC-OQAM signal has better spectral confinement and higher spectral efficiency and tolerance to synchronization errors, primarily due to per-subcarrier filtering using a frequency-time localized prototype filter. However, the filtering process introduces intrinsic interference among the symbols and complicates channel estimation (CE). An efficient way to improve the CE in FBMC-OQAM is using a technique known as windowed frequency domain averaging (FDA); however, it requires a priori knowledge of the window length parameter which is set based on the channel's frequency selectivity (FS). As the channel's FS is not fixed and not a priori known, we propose a k-nearest neighbor-based machine learning algorithm to classify the FS and decide on the FDA's window length. A comparative theoretical analysis of the mean-squared error (MSE) is performed to prove the proposed CE scheme's effectiveness, validated through extensive simulations. The adaptive CE scheme is shown to yield a reduction in CE-MSE and improved bit error rates compared with the popular preamble-based CE schemes for FBMC-OQAM, without a priori knowledge of channel's frequency selectivity.

Machine Learning-based landslide susceptibility mapping - Inje area, South Korea

  • Chanul Choi;Le Xuan Hien;Seongcheon Kwon;Giha Lee
    • Proceedings of the Korea Water Resources Association Conference
    • /
    • 2023.05a
    • /
    • pp.248-248
    • /
    • 2023
  • In recent years, the number of landslides in Korea has been increasing due to extreme weather events such as localized heavy rainfall and typhoons. Landslides often occur with debris flows, land subsidence, and earthquakes. They cause significant damage to life and property. 64% of Korea's land area is made up of mountains, the government wanted to predict landslides to reduce damage. In response, the Korea Forest Service has established a 'Landslide Information System' to predict the likelihood of landslides. This system selects a total of 13 landslide factors based on past landslide events. Using the LR technique (Logistic Regression) to predict the possibility of a landslide occurrence and the accuracy is known to be 0.75. However, most of the data used for learning in the current system is on landslides that occurred from 2005 to 2011, and it does not reflect recent typhoons or heavy rain. Therefore, in this study, we will apply a total of six machine learning techniques (KNN, LR, SVM, XGB, RF, GNB) to predict the occurrence of landslides based on the data of Inje, Gangwon-do, which was recently produced by the National Institute of Forest. To predict the occurrence of landslides, it is necessary to process converting landslide events and factors data into a suitable form for machine learning techniques through ArcGIS and Python. In addition, there is a large difference in the number of data between areas where landslides occurred or not. Therefore, the prediction was performed after correcting the unbalanced data using Tomek Links and Near Miss techniques. Moreover, to control unbalanced data, a model that reflects soil properties will use to remove absolute safe areas.

  • PDF

Conceptualizing the Engagement of Universities in Regional Development in a Knowledge-based Society (지식기반사회에서 대학과 지역발전의 관계: 진화론적 관점)

  • Nam, Jae-Geol;Lee, Jong-Ho
    • Journal of the Economic Geographical Society of Korea
    • /
    • v.13 no.1
    • /
    • pp.19-38
    • /
    • 2010
  • Following the emergence of a knowledge-based economy, the role of universities in regional development has been re-evaluated through considering localized interactive learning processes. This paper tries to identify the role of universities for regional development and the variables effecting on their localized engagement in regional development. We argues that universities cannot be viewed as a single angle, because the behaviors of a university are influenced by the degree of their independence from regional and national governments. Likewise, the contributions of universities to their regional development can be differential depending on the organizational characteristics of individual universities, the social, political, and economical contexts of a given region and nation, and complex relations between and within universities and other regional stakeholders. These variables can be both the drivers and barriers when each university responds to regional needs. Based on the literature review, we suggest that the explanatory factors of shaping the engagement of universities in regional development can be classified into four categories: the characteristics of individual universities, the national context, the local and regional context, and the policy context.

  • PDF

An Improvement Study on the Hydrological Quantitative Precipitation Forecast (HQPF) for Rainfall Impact Forecasting (호우 영향예보를 위한 수문학적 정량강우예측(HQPF) 개선 연구)

  • Yoon Hu Shin;Sung Min Kim;Yong Keun Jee;Young-Mi Lee;Byung-Sik Kim
    • Journal of Korean Society of Disaster and Security
    • /
    • v.15 no.4
    • /
    • pp.87-98
    • /
    • 2022
  • In recent years, frequent localized heavy rainfalls, which have a lot of rainfall in a short period of time, have been increasingly causing flooding damages. To prevent damage caused by localized heavy rainfalls, Hydrological Quantitative Precipitation Forecast (HQPF) was developed using the Local ENsemble prediction System (LENS) provided by the Korea Meteorological Administration (KMA) and Machine Learning and Probability Matching (PM) techniques using Digital forecast data. HQPF is produced as information on the impact of heavy rainfall to prepare for flooding damage caused by localized heavy rainfalls, but there is a tendency to overestimate the low rainfall intensity. In this study, we improved HQPF by expanding the period of machine learning data, analyzing ensemble techniques, and changing the process of Probability Matching (PM) techniques to improve predictive accuracy and over-predictive propensity of HQPF. In order to evaluate the predictive performance of the improved HQPF, we performed the predictive performance verification on heavy rainfall cases caused by the Changma front from August 27, 2021 to September 3, 2021. We found that the improved HQPF showed a significantly improved prediction accuracy for rainfall below 10 mm, as well as the over-prediction tendency, such as predicting the likelihood of occurrence and rainfall area similar to observation.