• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.24 no.9A
• /
• pp.1392-1400
• /
• 1999

In this paper, we propose a two-stage fast full search algorithm for block motion estimation that produces the same performance to that of full search algorithm (FSA) but with remarkable computation reduction. The proposed algorithm uses the search region subsampling and the difference of adjacent pixels in the current block. In the first stage, we subsample the search region by a factor of 9, and then calculate mean absolute error (MAE) at the subsampled search points. And in the second stage, we reduce the search points that need block matching process by using the lower bound of MAE value at each search Point. We Set the lower bound of MAE value for each search point from the MAE values which are calculated at the first stage and the difference of adjacent pixels in the current block. The experimental results show that we can reduce the computational complexity considerably without any degradation of picture quality.

• Journal of Navigation and Port Research
• /
• v.28 no.6
• /
• pp.509-515
• /
• 2004

The aim of this paper is to forecast passenger numbers and freight volumes in 2005 and it is proposed optimal tonnage of passenger ship. The forecasting of passenger numbers and freight volumes is important problem in order to determine optimal tonnage of passenger ship, port plan and development. In this paper, the forecasting of passenger numbers and freight volumes are performed by the method of neural network using back-propagation learning algorithm. And this paper compares the forecasting performance of neural networks with moving average method and exponential smooth method As the result of analysis. The forecasting of passenger numbers and freight volumes is that the neural networks performed better than moving average method and exponential smoothing method on the basis of MSE(mean square error) and MAE(mean absolute error).

• Journal of IKEEE
• /
• v.23 no.1
• /
• pp.120-126
• /
• 2019

Recently, accurate prediction of power consumption based on machine learning techniques in Internet of Energy (IoE) has been actively studied using the large amount of electricity data acquired from advanced metering infrastructure (AMI). In this paper, we propose a deep learning model based on Gated Recurrent Unit (GRU) as an artificial intelligence (AI) network that can effectively perform pattern recognition of time series data such as the power consumption, and analyze performance of the prediction based on real household power usage data. In the performance analysis, performance comparison between the proposed GRU-based learning model and the conventional learning model of Long Short Term Memory (LSTM) is described. In the simulation results, mean squared error (MSE), mean absolute error (MAE), forecast skill score, normalized root mean square error (RMSE), and normalized mean bias error (NMBE) are used as performance evaluation indexes, and we confirm that the performance of the prediction of the proposed GRU-based learning model is greatly improved.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.37 no.2
• /
• pp.21-27
• /
• 2000

In Fast motion estimaion algorithms, they reduce the computational complexity using the assumption that the matching error increases monotonically as the search moves away from the global minimum error In this paper, we first investigate the statistical characteristics of motion vector that the motion vector mostly occures on the side of small MAE (mean absolute error) between the reference search points when the MAE difference of them is large Therefore, we propose a fast motion estimation algorithm using this property and can reduce the number of search points The computer simulation result shows that the proposed method reduces computational complexity compared with conventional fast algorithms.

• Journal of Broadcast Engineering
• /
• v.27 no.3
• /
• pp.361-368
• /
• 2022

Quaternary tree plus multi-type tree (QT+MTT) structure was adopted in the Versatile Video Coding (VVC) standard as a block partitioning tool. QT+MTT provides excellent coding gain; however, it has huge encoding complexity due to the flexibility of the binary tree (BT) and ternary tree (TT) splits. This paper proposes a fast inter coding unit (CU) partitioning algorithm for BT and TT split types based on prediction accuracy functions using the mean of the absolute error (MAE). The MAE-based decision model was established to achieve a consistent time-saving encoding with stable coding loss for a practical low complexity VVC encoder. Experimental results under random access test configuration showed that the proposed algorithm achieved the encoding time saving from 24.0% to 31.7% with increasing luminance Bjontegaard delta (BD) rate from 1.0% to 2.1%.

• The Korean Journal of Applied Statistics
• /
• v.30 no.5
• /
• pp.733-745
• /
• 2017

Local composite quantile regression is a useful non-parametric regression method widely used for its high efficiency. Data smoothing methods using kernel are typically used in the estimation process with performances that rely largely on the smoothing parameter rather than the kernel. However, $L_2$-norm is generally used as criterion to estimate the performance of the regression function. In addition, many studies have been conducted on the selection of smoothing parameters that minimize mean square error (MSE) or mean integrated square error (MISE). In this paper, we explored the optimality of selecting smoothing parameters that determine the performance of non-parametric regression models using local linear composite quantile regression. As evaluation criteria for the choice of smoothing parameter, we used mean absolute error (MAE) and mean integrated absolute error (MIAE), which have not been researched extensively due to mathematical difficulties. We proved the uniqueness of the optimal smoothing parameter based on MAE and MIAE. Furthermore, we compared the optimal smoothing parameter based on the proposed criteria (MAE and MIAE) with existing criteria (MSE and MISE). In this process, the properties of the proposed method were investigated through simulation studies in various situations.

• Journal of the Korea Society of Computer and Information
• /
• v.27 no.4
• /
• pp.27-36
• /
• 2022

In this paper, to improve the conditions of the fish processing site, we propose a method to predict the cutting point of fish according to the target weight using AI machine vision. The proposed method performs image-based preprocessing by first photographing the top and front views of the input fish. Then, RANSAC(RANdom SAmple Consensus) is used to extract the fish contour line, and then 3D external information of the fish is obtained using 3D modeling. Next, machine learning is performed on the extracted three-dimensional feature information and measured weight information to generate a neural network model. Subsequently, the fish is cut at the cutting point predicted by the proposed technique, and then the weight of the cut piece is measured. We compared the measured weight with the target weight and evaluated the performance using evaluation methods such as MAE(Mean Absolute Error) and MRE(Mean Relative Error). The obtained results indicate that an average error rate of less than 3% was achieved in comparison to the target weight. The proposed technique is expected to contribute greatly to the development of the fishery industry in the future by being linked to the automation system.

• Journal of the Korea Society of Computer and Information
• /
• v.17 no.4
• /
• pp.83-90
• /
• 2012

In e-commerce systems that deal with a large number of items, the function of personalized recommendation is essential. Collaborative filtering that is a successful recommendation algorithm, suffers from the sparsity, cold-start, and scalability restrictions. Additionally, this work raises a new flaw of the algorithm, inconsistent performance of recommendation. This is also not measurable by the current MAE-based evaluation that does not consider the deviation of prediction error, and furthermore is performed independently of precision and recall measurement. To evaluate the collaborative filtering comprehensively, this work proposes an extended evaluation model that includes the current criteria such as MAE, Precision, Recall, deviation, and applies it to cluster-based combined collaborative filtering.

• Journal of radiological science and technology
• /
• v.46 no.2
• /
• pp.131-139
• /
• 2023

High-dose I-131 used for the treatment of thyroid cancer causes localized exposure among radiology technologists handling it. There is a delay between the calibration date and when the dose of I-131 is administered to a patient. Therefore, it is necessary to directly measure the radioactivity of the administered dose using a dose calibrator. In this study, we attempted to apply machine learning modeling to measured external dose rates from shielded I-131 in order to predict their radioactivity. External dose rates were measured at 1 m, 0.3 m, and 0.1 m distances from a shielded container with the I-131, with a total of 868 sets of measurements taken. For the modeling process, we utilized the hold-out method to partition the data with a 7:3 ratio (609 for the training set:259 for the test set). For the machine learning algorithms, we chose linear regression, decision tree, random forest and XGBoost. To evaluate the models, we calculated root mean square error (RMSE), mean square error (MSE), and mean absolute error (MAE) to evaluate accuracy and R² to evaluate explanatory power. Evaluation results are as follows. Linear regression (RMSE 268.15, MSE 71901.87, MAE 231.68, R² 0.92), decision tree (RMSE 108.89, MSE 11856.92, MAE 19.24, R² 0.99), random forest (RMSE 8.89, MSE 79.10, MAE 6.55, R² 0.99), XGBoost (RMSE 10.21, MSE 104.22, MAE 7.68, R² 0.99). The random forest model achieved the highest predictive ability. Improving the model's performance in the future is expected to contribute to lowering exposure among radiology technologists.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.18 no.3
• /
• pp.528-550
• /
• 2024

Warehousing demand prediction is an essential part of the supply chain, providing a fundamental basis for product manufacturing, replenishment, warehouse planning, etc. Existing forecasting methods cannot produce accurate forecasts since warehouse demand is affected by external factors such as holidays and seasons. Some aspects, such as consumer psychology and producer reputation, are challenging to quantify. The data can fluctuate widely or do not show obvious trend cycles. We introduce a new model for warehouse demand prediction called MAGRU, which stands for Multi-layer Attention with GRU. In the model, firstly, we perform the embedding operation on the input sequence to quantify the external influences; after that, we implement an encoder using GRU and the attention mechanism. The hidden state of GRU captures essential time series. In the decoder, we use attention again to select the key hidden states among all-time slices as the data to be fed into the GRU network. Experimental results show that this model has higher accuracy than RNN, LSTM, GRU, Prophet, XGboost, and DARNN. Using mean absolute error (MAE) and symmetric mean absolute percentage error(SMAPE) to evaluate the experimental results, MAGRU's MAE, RMSE, and SMAPE decreased by 7.65%, 10.03%, and 8.87% over GRU-LSTM, the current best model for solving this type of problem.