• 정보처리학회논문지:컴퓨터 및 통신 시스템
• /
• 제4권3호
• /
• pp.85-90
• /
• 2015

본 논문에서는 새로운 병렬 이벤트구동 로직 시뮬레이션 기법을 제안한다. 제안한 예측에 기반한 병렬 이벤트구동 시뮬레이션 기법은 병렬 이벤트구동 시뮬레이션에서 다른 로컬시뮬레이션과의 연동 과정에서 사용되는 입력값과 출력값에 실제값과 예측값을 함께 사용함으로써 성능 향상의 제약 요소인 동기 오버헤드 및 통신 오버헤드를 크게 감소시킬 수 있다. 본 논문에서 제안한 예측기반 병렬 이벤트구동 로직 시뮬레이션의 유용함은 다수의 디자인들에 적용한 실험을 통하여 확인할 수 있었다.

• Advances in nano research
• /
• 제16권3호
• /
• pp.231-249
• /
• 2024

When the amplitude of the vibrations is equivalent to that clearance, the vibrations for small amplitudes will really be significantly nonlinear. Nonlinearities will not be significant for amplitudes that are rather modest. Finally, nonlinearities will become crucial once again for big amplitudes. Therefore, the concrete panel system may experience a big amplitude in this work as a result of the high temperature. Based on the 3D modeling of the shell theory, the current work shows the influences of the von Kármán strain-displacement kinematic nonlinearity on the constitutive laws of the structure. The system's governing Equations in the nonlinear form are solved using Kronecker and Hadamard products, the discretization of Equations on the space domain, and Duffing-type Equations. Thermo-elasticity Equations. are used to represent the system's temperature. The harmonic solution technique for the displacement domain and the multiple-scale approach for the time domain are both covered in the section on solution procedures for solving nonlinear Equations. An effective data-driven solution is often utilized to predict how different systems would behave. The number of hidden layers and the learning rate are two hyperparameters for the network that are often chosen manually when required. Additionally, the data-driven method is offered for addressing the nonlinear vibration issue in order to reduce the computing cost of the current study. The conclusions of the present study may be validated by contrasting them with those of data-driven solutions and other published articles. The findings show that certain physical and geometrical characteristics have a significant effect on the existing concrete panel structure's susceptibility to temperature change and GPL weight fraction. For building construction industries, several useful recommendations for improving the thermo-mechanics' behavior of structural concrete panels are presented.

• 정보교육학회논문지
• /
• 제25권5호
• /
• pp.713-721
• /
• 2021

교육부에서 2022 개정 교육과정에 본격적으로 AI교육을 도입하면서 AI교육과 더불어 데이터 관련 교육의 필요성에 대한 공감도가 높아지고 있다. 인공지능을 제대로 이해하고 활용하는 역량을 기르기 위해서는 데이터에 대한 이해와 활용 역량이 기반되어야 한다. 본 연구에서는 요구분석, 선행연구분석 결과를 종합하여 마이크로비트를 활용한 데이터 기반 문제해결 SW교육 프로그램을 개발하였다. 데이터 기반 문제해결 교육 프로그램은 데이터 과학의 내용 중 초등학생을 대상으로 적용할 수 있는 교육 요소들로 구성하여 개발되었다. 본 연구에서 개발한 프로그램을 통해 실생활 데이터를 바탕으로 다양한 주제와 교과를 융합한 교육을 연계할 수 있다. 더 나아가 데이터에 대한 이해를 바탕으로 보다 내실 있는 AI교육 프로그램의 기반을 갖추게 될 것이다.

• Journal of Smart Tourism
• /
• 제4권2호
• /
• pp.5-14
• /
• 2024

This study explores the transformative potential of machine learning (ML) and ML-driven data analytics in the hospitality industry. It provides a comprehensive overview of this emerging method, from explaining ML's origins to introducing the evolution of ML-driven data analytics in the hospitality industry. The present study emphasizes the shift embodied in ML, moving from explicit programming towards a self-learning, adaptive approach refined over time through big data. Meanwhile, social media analytics has progressed from simplistic metrics deriving nuanced qualitative insights into consumer behavior as an industry-specific example. Additionally, this study explores innovative applications of these innovative technologies in the hospitality sector, whether in demand forecasting, personalized marketing, predictive maintenance, etc. The study also emphasizes the integration of ML and social media analytics, discussing the implications like enhanced customer personalization, real-time decision-making capabilities, optimized marketing campaigns, and improved fraud detection. In conclusion, ML-driven hospitality data analytics have become indispensable in the strategic and operation machinery of contemporary hospitality businesses. It projects these technologies' continued significance in propelling data-centric advancements across the industry.

• 대한원격탐사학회:학술대회논문집
• /
• 대한원격탐사학회 2007년도 Proceedings of ISRS 2007
• /
• pp.418-421
• /
• 2007

Using gridded wind-stress products constructed by satellite scatterometers (ERS-1, 2 and QSCAT) data and those by numerical weather prediction(NWP) model(NCEP-reanalysis), we estimate wind-driven transports of the North Pacific subtropical gyre, and compare them in the central portion of the gyre (around 300 N) with geostrophic transports calculated from historical hydrographic data (World Ocean Database 2005). Even if there are some discrepancies between the wind-driven transports by the QSCAT and NCEP products, they are both in good agreement with the geostrophic transports within reasonable errors, except for the regional difference in the eastern part of the zone. The difference in the eastern part is characterized by an anticyclonic deviation of the geostrophic transport resulting from an anti-cyclonic anomalous flow in the surface layer, suggesting that it is related to the Eastern Gyral produced by the thermohaline process associated with the formation of the Eastern Subtropical Mode Water. We also examine the consistency of the Sverdrup transports estimated from these products by comparing them with the transports of the western boundary current, namely the Kuroshio regions, in previous studies. The net southward transport, based on the sum of the Sverdrup transports by QSCAT and NCEP products and the thermohaline transport, agrees well with the net northward transport of the western boundary current, namely the Kuroshio transport. From these results, it is concluded that the Sverdrup balance can hold in the North Pacific subtropical gyre.

• 음성과학
• /
• 제9권1호
• /
• pp.39-47
• /
• 2002

This paper proposes an effective method to remedy the acoustic modeling problem inherent in the usual log-normal Parallel Model Composition intended for achieving robust speech recognition. In particular, the Gaussian kernels under the prescribed log-normal PMC cannot sufficiently express the corrupted speech distributions. The proposed scheme corrects this deficiency by judiciously selecting the 'fairly' corrupted component and by re-estimating it as a mixture of two distributions using data-driven PMC. As a result, some components become merged while equal number of components split. The determination for splitting or merging is achieved by means of measuring the similarity of the corrupted speech model to those of the clean model and the noise model. The experimental results indicate that the suggested algorithm is effective in representing the corrupted speech distributions and attains consistent improvement over various SNR and noise cases.

• 한국시뮬레이션학회논문지
• /
• 제5권1호
• /
• pp.1-12
• /
• 1996

We propose a new approach to classifying a time series data into one of the autoregressive moving-average (ARMA) models. It is bases on two pattern recognition concepts for solving time series identification. The one is an extended sample autocorrelation function (ESACF). The other is a neural network-driven decision tree classifier(NNDTC) in which two pattern recognition techniques are tightly coupled : neural network and decision tree classfier. NNDTc consists of a set of nodes at which neural network-driven decision making is made whether the connecting subtrees should be pruned or not. Therefore, time series identification problem can be stated as solving a set of local decisions at nodes. The decision values of the nodes are provided by neural network functions attached to the corresponding nodes. Experimental results with a set of test data and real time series data show that the proposed approach can efficiently identify the time seires patterns with high precision compared to the previous approaches.

• International journal of advanced smart convergence
• /
• 제9권2호
• /
• pp.58-67
• /
• 2020

In this paper, we propose a data-driven-based beam selection scheme for massive multiple-input and multiple-output (MIMO) systems in ultra-dense networks (UDN), which is capable of addressing the problem of high computational cost of conventional coordinated beamforming approaches. We consider highly dense small-cell scenarios with more small cells than mobile stations, in the millimetre-wave band. The analog beam selection for hybrid beamforming is a key issue in realizing millimetre-wave UDN MIMO systems. To reduce the computation complexity for the analog beam selection, in this paper, two deep neural network models are used. The channel samples, channel gains, and radio frequency beamforming vectors between the access points and mobile stations are collected at the central/cloud unit that is connected to all the small-cell access points, and are used to train the networks. The proposed machine-learning-based scheme provides an approach for the effective implementation of massive MIMO system in UDN environment.

• Journal of Communications and Networks
• /
• 제14권6호
• /
• pp.597-605
• /
• 2012

With the smart grid coming near, wide-area supervisory control and data acquisition (SCADA) becomes more and more important. However, traditional SCADA systems are not suitable for the openness and distribution requirements of smart grid. Distributed SCADA services should be openly composable and secure. Event-driven methodology makes service collaborations more real-time and flexible because of the space, time and control decoupling of event producer and consumer, which gives us an appropriate foundation. Our SCADA services are constructed and integrated based on distributed events in this paper. Unfortunately, an event-driven SCADA service does not know who consumes its events, and consumers do not know who produces the events either. In this environment, a SCADA service cannot directly control access because of anonymous and multicast interactions. In this paper, a distributed security framework is proposed to protect not only service operations but also data contents in smart grid environments. Finally, a security implementation scheme is given for SCADA services.

• 아시아태평양코퍼스연구
• /
• 제4권1호
• /
• pp.25-42
• /
• 2023

The number of studies on data-driven learning (DDL) has increased in recent years, and DDL's overall effectiveness as an L2 (second language) teaching methodology has been reported to be high. However, the degree of its effectiveness in grammar instruction, particularly for the goal of correcting errors in L2 writing, is still unclear. To provide guidelines for focused grammar instruction with DDL in the Japanese classroom setting, we aimed to identify the typical grammatical errors made by Japanese learners in the Cambridge Learner Corpus First Certificate in English (CLC FCE) dataset. The results revealed that three error types (nouns, articles, and prepositions) should be addressed in DDL grammar instruction for Japanese English as a foreign language (EFL) learners. In light of the findings, pedagogical implications and suggestions for future DDL research and practice are discussed.