• 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.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2013.06a
• /
• pp.14-15
• /
• 2013

본 논문에서는 공간 계층 분해를 이용한 3 차원 메쉬 시퀀스 압축 기법을 제안한다. 제안하는 기법은 우선 각 점에 대한 시간적 궤적을 공분산 행렬로 표현하고, PCA(Principal component analysis)를 적용하여 시간 궤적에 대한 고유 벡터와 PCA 계수를 획득한다. 공간적인 예측을 통해 PCA 계수에 대한 벡터 차를 추출하고, 벡터 차와 그것에 대한 고유 벡터를 전송한다. 제안하는 방법은 PCA 계수 예측의 성능을 높이기 위해 점진적 압축에서 사용하는 공간 계층 분해 기법을 적용하여, 계수 예측에 효과적인 이웃 점을 지정하도록 한다. 또한, 이웃 점 개수를 사용자가 임의로 지정할 수 있도록 하여, 성능과 복잡도간의 트레이드 오프를 제어할 수 있도록 한다. 다양한 모델에 대한 실험 결과를 통해 제안하는 방법의 성능을 확인한다.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.35 no.5C
• /
• pp.464-471
• /
• 2010

The demand for high quality of multimedia applications, which far surpasses the rapid evolution of transmission and storage technologies, makes better compression coding capabilities ever increasingly more important. In order to provide enhanced video coding performance, this paper proposes an efficient competition-based motion vector coding scheme. The proposed algorithm adaptively forms the motion vector predictors based on the contexts of scene characteristics such as camera motion and nearby motion vectors, providing more efficient candidate predictors than the previous competition-based motion vector coding schemes which resort to the fixed candidates optimized by extensive simulations. Up to 200% of compression gain was observed in the experimental results for the proposed scheme applied to the motion vector selection for skip mode processing.

• Journal of Korea Water Resources Association
• /
• v.56 no.9
• /
• pp.563-574
• /
• 2023

Recently, climate change has affected functional responses of river basins to meteorological variables, emphasizing the importance of rainfall-runoff simulation research. Simultaneously, the growing interest in machine learning has led to its increased application in hydrological studies. However, it is not yet clear whether machine learning models are more advantageous than the conventional conceptual models. In this study, we compared the performance of the conventional GR6J model with the machine learning-based Random Forest model across 38 basins in Korea using both gauged and ungauged basin prediction methods. For gauged basin predictions, each model was calibrated or trained using observed daily runoff data, and their performance was evaluted over a separate validation period. Subsequently, ungauged basin simulations were evaluated using proximity-based parameter regionalization with Leave-One-Out Cross-Validation (LOOCV). In gauged basins, the Random Forest consistently outperformed the GR6J, exhibiting superiority across basins regardless of whether they had strong or weak rainfall-runoff correlations. This suggest that the inherent data-driven training structures of machine learning models, in contrast to the conceptual models, offer distinct advantages in data-rich scenarios. However, the advantages of the machine-learning algorithm were not replicated in ungauged basin predictions, resulting in a lower performance than that of the GR6J. In conclusion, this study suggests that while the Random Forest model showed enhanced performance in trained locations, the existing GR6J model may be a better choice for prediction in ungagued basins.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.22 no.4
• /
• pp.111-117
• /
• 2022

Many studies have been conducted on software fault prediction models for decades, and the models using machine learning techniques showed the best performance. Deep learning techniques have become the most popular in the field of machine learning, but few studies have used them as classifiers for fault prediction models. Some studies have used deep learning to obtain semantic information from the model input source code or syntactic data. In this paper, we produced several models by changing the model structure and hyperparameters using MLP with three or more hidden layers. As a result of the model evaluation experiment, the MLP-based deep learning models showed similar performance to the existing models in terms of Accuracy, but significantly better in AUC. It also outperformed another deep learning model, the CNN model.

• Proceedings of the Korea Institute of Convergence Signal Processing
• /
• 2001.06a
• /
• pp.213-216
• /
• 2001

The H.263 Annex I method for the intraframe coding is based on the prediction in DCT domain, unlike JPEG, MPEG-1, and MPEG-2 where the intraframe coding uses block DCT, independent of the neighboring blocks. In this paper, we show the ineffectiveness of H.263 Annex I prediction method by mathematically deriving the spatial domain meaning of H.263 Annex I prediction method. Based on the derivation, we propose a prediction method which is based on the spatial correlation property of image signals. From the experiment and derivation, we verified the proposed method.

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.30 no.5
• /
• pp.62-70
• /
• 2002

Methodology of predicting steady performance of gas turbine engine from transient test data was explored to develop an economic performance test technique. Discrepancy of transient performance from steady performance was categorized as dynamic, thermal and aerodynamic transient effects. Each effect was mathematically modeled and quantified to provide correction factors for calculating steady performance. Engine performance tests were conducted at Altitude Engine Test Facility of KARI. The influence of engine inlet/outlet condition change on engine performance was corrected firstly, and then steady performance was predicted from the correction factors. The result was compared with steady performance test data. This correction method showed an acceptable level of precision, 3.68% difference of fuel flow.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.29 no.5A
• /
• pp.492-501
• /
• 2004

The performance of mobile communication systems depends on the state of the time-varying multi-path fading channel. To effectively prevent the corruption of video stream and its propagation in spatial and temporal domain, proactive error controls are widely being deployed. Among possible candidates, the rate compatible punctured convolutional (RCPC) code has been widely used for multimedia data, since its rate can be determined flexibly. In this paper, the adaptive channel estimation and the adaptive error correction techniques over the time-varying mobile channel have been proposed. Extensive computer simulations show that the proposed techniques yield the superior performance than the fixed rate system.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.19 no.4
• /
• pp.161-167
• /
• 2019

Recently, demand forecasting techniques have been actively studied due to interest in stable power supply with surging power demand, and increase in spread of smart meters that enable real-time power measurement. In this study, we proceeded the deep learning prediction model experiments which learns actual measured power usage data of home and outputs the forecasting result. And we proceeded pre-processing with moving average method. The predicted value made by the model is evaluated with the actual measured data. Through this forecasting, it is possible to lower the power supply reserve ratio and reduce the waste of the unused power. In this paper, we conducted experiments on three types of networks: Multi Layer Perceptron (MLP), Recurrent Neural Network (RNN), and Long Short Term Memory (LSTM) and we evaluate the results of each scheme. Evaluation is conducted with following method: MSE(Mean Squared Error) method and MAE(Mean Absolute Error).

• Proceedings of the Korea Information Processing Society Conference
• /
• 2016.04a
• /
• pp.571-574
• /
• 2016

최근 에너지 효율을 최적화하는 차세대 지능형 전력망인 스마트 그리드 시스템(Smart Grid System)이 국내외에 널리 보급되고 있다. 그로 인해 그리드 시스템의 효율적인 운영을 위해 적용되는 EMS(Energy Management System) 기술의 중요성이 커지고 있다. EMS는 에너지 사용량 예측의 높은 정확성이 요구되며, 예측이 정확하게 수행될수록 에너지의 활용성이 높아진다. 본 논문은 전력 사용량 예측의 정확성 향상을 위한 새로운 기법을 제안한다. 구체적으로, 먼저 사용량에 영향을 미치는 환경적인 요인들을 분석한다. 분석된 요인들을 적용하여 유사한 환경을 가지는 전력 사용량 데이터의 사전 군집화를 수행한다. 그리고 예측 일에 관련된 환경 정보와 가장 유사한 군집의 전력 사용량 데이터를 기반으로 전력 사용량을 예측한다. 제안하는 기법의 성능을 평가하기 위해, 다양한 실험을 통하여 일간 전력 사용량을 예측하고 그 정확성을 측정하였다. 결과적으로, 기존의 기법들과 비교했을 때, 최대 52.88% 향상된 전력 사용량 예측 정확성을 보였다.