• Journal of Convergence for Information Technology
• /
• v.11 no.3
• /
• pp.7-13
• /
• 2021

This study develops an artificial intelligence prediction system for Fine particulate Matter(PM2.5) based on the deep learning algorithm GAN model. The experimental data are closely related to the changes in temperature, humidity, wind speed, and atmospheric pressure generated by the time series axis and the concentration of air pollutants such as SO2, CO, O3, NO2, and PM10. Due to the characteristics of the data, since the concentration at the current time is affected by the concentration at the previous time, a predictive model for recursive supervised learning was applied. For comparative analysis of the accuracy of the existing models, CNN and LSTM, the difference between observation value and prediction value was analyzed and visualized. As a result of performance analysis, it was confirmed that the proposed GAN improved to 15.8%, 10.9%, and 5.5% in the evaluation items RMSE, MAPE, and IOA compared to LSTM, respectively.

• KNOM Review
• /
• v.24 no.2
• /
• pp.13-23
• /
• 2021

Recently, as networks become more complex due to the activation of IoT devices, research on long-term traffic prediction beyond short-term traffic prediction is being activated to predict and prepare for network congestion in advance. The recursive strategy, which reuses short-term traffic prediction results as an input, has been extended to multi-step traffic prediction, but as the steps progress, errors accumulate and cause deterioration in prediction performance. In this paper, an LSTM-based multi-step traffic prediction method using a multi-output strategy is introduced and its performance is evaluated. As a result of experiments based on actual DNS request traffic, it was confirmed that the proposed LSTM-based multiple output strategy technique can reduce MAPE of traffic prediction performance for non-stationary traffic by 6% than the recursive strategy technique.

• Journal of the Society of Disaster Information
• /
• v.18 no.4
• /
• pp.786-794
• /
• 2022

In construction sites, effective preventive safety management is required beyond post-processing safety management. Purpose: The purpose of this study is to present a model and analyze the relationship between safety management activities, safety culture key elements, safety, unsafe behavior management, and safety for autonomous and preventive safety management. Method: The relationship was analyzed by applying the survey data to the structural equation, and the path to safety outcomes from exogenous variables was explored and major issues were presented by interpreting the part suggested by the hypothesis verified by the analysis results. Result: As a result of analyzing the preliminary model and the path model, the appropriate model fit was confirmed, and the significant effect of exogenous variables on endogenous variables was confirmed. Conclusion: It is judged that it can contribute to continuously improving safety performance before safety accidents occur through safety management activities, safety and unsafe behavior management, and management of key elements of safety culture.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2020.06a
• /
• pp.324-324
• /
• 2020

기후변화에 따른 기상 요소별 추세 변화는 유역유출량의 변동성을 증가시켜 안정적인 수자원 확보 및 홍수 대비에 어려움을 줄 수 있다. 따라서 기후변화에 따른 유역 유출량 변화를 평가하기 위한 많은 연구가 이루어져 왔다. 기존에는 기후변화 자료의 공간적 해상도의 한계로 인해 중대유역을 중심으로 연구가 다수 이루어져 왔으나, 최근 들어, 기후변화 자료의 공간적 상세화 기법이 발달함에 따라 소유역별 유역 유출량 평가에 관한 연구가 증가하고 있다. 특히, 소유역의 경우 유역 특성에 따라 기후변화에 따른 유출량 변화 민감도가 높을 수 있으며, 유출 성분별 변화가 상이할 수 있다. 하지만 기존의 연구에서는 소유역을 대상으로 기후변화에 따른 유출 성분별, 예를 들어 직접유출량과 기저유출량을 구분하여 변화를 평가하는 연구가 부족한 실정이다. 따라서 본 연구에서는 기후변화에 따른 소유역의 유출 성분별 특성을 분석하기 위하여, RCP 4.5, 8.5 시나리오별 기후모델 10개에 대하여 모의한 유출량을 직접유출량과 기저유출량으로 구분하고 결과를 비교 분석하였다. 본 연구의 대상지역은 유역면적이 112.9 ㎢이며, 토지이용이 단순하고, 농경지의 비율(약 50%)이 높은 농업 소유역을 대상으로 하였다. 유출량을 모의하기 위한 모형으로는 농업 소유역 유출량 모의 연구에 다수 사용된 바 있는 SWAT 모형을 이용하였으며, 직접유출량과 기저유출량의 분리는 Recursive Digital Filter 방법을 이용하였다. 기후변화 자료는 기후모델의 연산능력의 한계나 복잡한 자연조건의 불완전한 반영 등의 이유로 지역 기후변화 예측 과정에서 발생하는 불확실성을 지니고 있으므로 RCP 4.5, 8.5 시나리오별 각각 10개 기후모델의 결과를 이용하여 유출 특성 분석에 활용하였다. 본 연구의 결과는 향후 소유역의 미래 유량특성을 파악하기 위한 기초 자료로 활용될 수 있을 것으로 사료된다.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.1 no.1
• /
• pp.85-93
• /
• 1997

In this paper, a novel method for obtaining spectra of short pulses is proposed. This method will be well-applied to perform spectral analyses of ultrashort laser pulses which are known to be difficult to evaluate their exact forms in frequency domain because of their narrow-width characteristics in time domain. It must be noted that the method can be represented by a recursive formula derived from the PRS(partial-response signaling) model, and thus more easily available for numerical solutions than the conventional methods such as consecutive differentiations and convolutions. The pulses whose fundamental frames can be exactly determined or approximately represented by truncated Fourier series have well-behaving conditions for applications of this new method. Moreover, the transversal 9-type PRS model can offer various approximations for spectral analyses of ultrashort pulses currently used in transmission systems.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.25 no.4A
• /
• pp.553-557
• /
• 2000

It is known that turbo codes have an error-floor bound according to the effective free distance at high SNR. But the performance for turbo codes in the water-fall area at low SHR has not been studied yet. In this paper, asymmetric turbo codes that consist of RSC(recursive systematic convolutional) codes with different constraint length are proposed and their performance is analysed for SOVA decoding algorithm.

• Journal of Mechanical Science and Technology
• /
• v.14 no.1
• /
• pp.19-29
• /
• 2000

A viscoelastic finite element analysis is presented to investigate residual stresses occurred in a laminated cylindrical shell during cure. An incremental viscoelastic constitutive equation that can describe stress relaxation during the cure is derived as a recursive formula which can be used conveniently for a numerical analysis. The finite element analysis program is developed on the basis of a 3-D degenerated shell element and the first order shear deformation theory, and is verified by comparing with an one dimensional exact solution. Viscoelastic effect on the residual stresses in the laminated shell during the cure is investigated by performing both the viscoelastic and linear elastic analyses considering thermal deformation and chemical shrinkage simultaneously. The results show that there is big difference between viscoelastic stresses and linear elastic stresses. The effect of cooling rates and cooling paths on the residual stresses is also examined.

• International Journal of CAD/CAM
• /
• v.4 no.1
• /
• pp.11-17
• /
• 2004

In this paper, an exponential bound of the distance between a Loop subdivision surface and its control mesh is derived based on the topological structure of the control mesh. The exponential bound is independent of the process of recursive subdivisions and can be evaluated without subdividing the control mesh actually. Using the exponential bound, we can predict the depth of recursion within a user-specified tolerance as well as the error bound after n steps of subdivision. The error-estimating approach can be used in many engineering applications such as surface/surface intersection, mesh generation, NC machining, surface rendering and the like.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2007.11a
• /
• pp.312-315
• /
• 2007

운전자의 변의와 안전을 위한 장치로 센서를 차량에 많이 부착하게 되었다. 레이더도 그런 센서 중의 하나로 다른 센서들 보다 정확하게 주변상황을 인식하게 해 준다. 하지만 그런 레이더 데이터에는 차량의 정보들 뿐만 아니라 주변의 장애물, 건물 동의 원하지 않는 데이터가 같이 들어 오며 이런 물체들은 뒤에 있는 물체들을 가리기 까지 한다. 이 논문에서는 RLS(Recursive Least Square)를 사용하여 이런 가려지는 물체들의 데이터들을 버리지 않고 사용할 수 있는 알고리즘을 제안한다.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2007.11a
• /
• pp.131-137
• /
• 2007

본 연구에서는 RLS(Rescursive Least Square) 추정 알고리즘을 이용하여 정전용량형 센서를 사용한 원격 RF 센서 시스템을 구현하고자 한다. IC 칩 형태의 원격 RF 센서 시스템이 가지는 구성의 복잡성 그리고 전력소모 문제를 해결하기 위해 보다 간단한 유도결합모델이 제안된다. 원격 RF 시스템은 페이저법을 이용하여 수학적으로 모델링되며, 모델기반의 RLS 알고리즘을 적용하기위해 시스템의 파라메타를 재배열한다. 오차 제곱합의 수렴특성을 가진 RLS 알고리즘을 이용하여 정전용량 파라메타를 추정한다. 실제 위상차를 측정하기 위해 Exclusive OR를 이용한 위상차 감지 장치를 제안한다. 센서로는 각종 환경 측정-습도, 압력 등-에 실제 활용되고 있는 정전용량형 센서를 채택한다. 잡음을 내포한 측정 데이터에 대한 추정 성능을 확인함으로써 그 유효성을 검증하고자 한다.