• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.31 no.1B
• /
• pp.21-27
• /
• 2011

When execute runoff forecasting, can not remove perfectly uncertainty of forecasting results. But, reduce uncertainty by various techniques analysis. This study applied various forecasting techniques for runoff prediction's accuracy elevation in Gongju basin. statics techniques is ESP, Period Average & Moving average, Exponential Smoothing, Winters, Auto regressive moving average process. Authoritativeness estimation with results of runoff forecasting by each techniques used MAE (Mean Absolute Error), RMSE (Root Mean Squared Error), RRMSE (Relative Root Mean Squared Error), Mean Absolute Percentage Error (MAPE), TIC (Theil Inequality Coefficient). Result that use MAE, RMSE, RRMSE, MAPE, TIC and confirm improvement effect of runoff forecasting, ESP techniques than the others displayed the best result.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2018.10a
• /
• pp.626-628
• /
• 2018

In this paper, we compare the performances of SVM (Support Vector Machine) and ANN (Artificial Neural Network) machine learning models for predicting solar energy by using meteorological data. Two machine learning models were built by using fifteen kinds of weather data such as long and short wave radiation average, precipitation and temperature. Then the RBF (Radial Basis Function) parameters in the SVM model and the number of hidden layers/nodes and the regularization parameter in the ANN model were found by experimental studies. MAPE (Mean Absolute Percentage Error) and MAE (Mean Absolute Error) were considered as metrics for evaluating the performances of the SVM and ANN models. Sjoem Simulation results showed that the SVM model achieved the performances of MAPE=21.11 and MAE=2281417.65, and the ANN model did the performances of MAPE=19.54 and MAE=2155345.10776.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.25 no.1B
• /
• pp.128-140
• /
• 2000

In this paper, we propose a fast block matching algorithm using the mean absolute error (MAE) of neighbor search point and search region reduction. The proposed algorithm is composed of two stages. At the first stage,the search region is divided into nonoverlapped 3$\times$3 areas and MAE of the center point of each area iscalculated. The minimum MAE value of all the calculated MAE's is determined as reference MAE. At thesecond stage, because the possibility that final motion vector exist near the position of reference MAE is veryhigh, we use smaller search region than first stage, And, using the MAE of center point of each area, the lowerbound of rest search point of each area is calculated and block matching process is performed only at the searchpoints that the lower bound is smaller than reference MAE. By doing so, we can significantly reduce thecomputational complexity while keep the increasement of motion estimation error small.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.37 no.3
• /
• pp.41-56
• /
• 2000

In this paper, we propose a two-stage fast block matching algorithm using the mean absolute error (MAE) of neighbor search point that can reduce the computational complexity to estimate motion vector while the motion estimation error performance is nearly the same as full search algorithm (FSA) In the proposed method, the lower bound of MAE 6at current search point IS calculated using the MAE of neighbor search point And we reduce the computational complexity by performing the block matching process only at the search point that has to be block matched using the lower bound of MAE The proposed algorithm is composed of two stages The experimental results show that the proposed method drastically reduces the computational complexity while the motion compensated error performance is nearly kept same as that of FSA.

• Journal of Auto-vehicle Safety Association
• /
• v.15 no.1
• /
• pp.55-62
• /
• 2023

In this study, a chest deflection is predicted by introducing a deep learning technique with the results of the frontal impact of the USNCAP conducted for 110 car models from MY2018 to MY2020. The 120 data are divided into training data and test data, and the training data is divided into training data and validation data to determine the hyperparameters. In this process, the deceleration data of each vehicle is averaged in units of 10 ms from crash pulses measured up to 100 ms. The performance of the deep learning model is measured by the indices of the mean squared error and the mean absolute error on the test data. A DNN (Deep Neural Network) model can give different predictions for the same hyperparameter values at every run. Considering this, the mean and standard deviation of the MSE (Mean Squared Error) and the MAE (Mean Absolute Error) are calculated. In addition, the deep learning model performance according to the inclusion of CVW (Curb Vehicle Weight) is also reviewed.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2018.05a
• /
• pp.457-459
• /
• 2018

Solar power generation system is a energy generation technology that produces electricity from solar power, and it is growing fastest among renewable energy technologies. It is of utmost importance that the solar power system supply energy to the load stably. However, due to unstable energy production due to weather and weather conditions, accurate prediction of energy production is needed. In this paper, an Artificial Neural Network(ANN) that predicts solar energy using 15 kinds of meteorological data such as precipitation, long and short wave radiation averages and temperature is implemented and its performance is evaluated. The ANN is constructed by adjusting hidden parameters and parameters such as penalty for preventing overfitting. In order to verify the accuracy and validity of the prediction model, we use Mean Absolute Percentage Error (MAPE) and Mean Absolute Error (MAE) as performance indices. The experimental results show that MAPE = 19.54 and MAE = 2155345.10776 when Hidden Layer $Sizes=^{\prime}16{\times}10^{\prime}$.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.19 no.5
• /
• pp.79-85
• /
• 2019

In this paper, we propose a short-term power forecasting method by applying Long Short Term Memory (LSTM) and Gated Recurrent Unit (GRU) neural network to Internet of Things (IoT) power meter. We analyze performance based on real power consumption data of households. Mean absolute error (MAE), mean absolute percentage error (MAPE), mean percentage error (MPE), mean squared error (MSE), and root mean squared error (RMSE) are used as performance evaluation indexes. The experimental results show that the GRU-based model improves the performance by 4.52% in the MAPE and 5.59% in the MPE compared to the LSTM-based model.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.16 no.4
• /
• pp.625-632
• /
• 2021

This paper studies the effect of the number of filters in the CNN (Convolutional Neural Network) layer on the performance of a noise attenuator. Speech is estimated from a noised speech signal using a 64-neuron, 16-kernel CNN filter and an error back-propagation algorithm. In this study, in order to verify the performance of the noise attenuator with respect to the number of filters, a program using Keras library was written and simulation was performed. As a result of simulation, it can be seen that this system has the smallest MSE (Mean Squared Error) and MAE (Mean Absolute Error) values when the number of filters is 16, and the performance is the lowest when there are 4 filters. And when there are more than 8 filters, it was shown that the MSE and MAE values do not differ significantly depending on the number of filters. From these results, it can be seen that about 8 or more filters must be used to express the characteristics of the speech signal.

• Journal of the Korean Data and Information Science Society
• /
• v.26 no.3
• /
• pp.561-568
• /
• 2015

In this study we predict apartment prices per unit in Daegu-Gyeongbuk areas by spatial lag and spatial error models, both of which belong to so-called spatial regression model. A spatial weight matrix is constructed by k-nearest neighbours method and then the models for the apartment prices in March, 2012 are fitted using the weight matrix. The apartment prices in March, 2013 are predicted by the fitted spatial regression models and then performances of two spatial regression models are compared by RMSE (root mean squared error), RRMSE (root relative mean squared error), MAE (mean absolute error).

• Tunnel and Underground Space
• /
• v.31 no.6
• /
• pp.508-519
• /
• 2021

In this study, a model was developed to predict the peak particle velocity (PPV) that affects people and the surrounding environment during blasting. Four machine learning models using the k-nearest neighbors (kNN), classification and regression tree (CART), support vector regression (SVR), and particle swarm optimization (PSO)-SVR algorithms were developed and compared with each other to predict the PPV. Mt. Yogmang located in Changwon-si, Gyeongsangnam-do was selected as a study area, and 1048 blasting data were acquired to train the machine learning models. The blasting data consisted of hole length, burden, spacing, maximum charge per delay, powder factor, number of holes, ratio of emulsion, monitoring distance and PPV. To evaluate the performance of the trained models, the mean absolute error (MAE), mean square error (MSE), and root mean square error (RMSE) were used. The PSO-SVR model showed superior performance with MAE, MSE and RMSE of 0.0348, 0.0021 and 0.0458, respectively. Finally, a method was proposed to predict the degree of influence on the surrounding environment using the developed machine learning models.