• Proceedings of the Korea Water Resources Association Conference
• /
• 2021.06a
• /
• pp.373-373
• /
• 2021

Rainfall forecasting is an important issue that is applied in many areas, such as agriculture, flood warning, and water resources management. In this context, this study proposed a statistical and machine learning-based forecasting model for monthly rainfall. The Bayesian Gaussian process was chosen to optimize the hyperparameters of the Stacked Long Short-term memory (SLSTM) model. The proposed SLSTM model was applied for predicting monthly precipitation of Seoul station, South Korea. Data were retrieved from the Korea Meteorological Administration (KMA) in the period between 1960 and 2019. Four schemes were examined in this study: (i) prediction with only rainfall; (ii) with deseasonalized rainfall; (iii) with rainfall and minimum temperature; (iv) with deseasonalized rainfall and minimum temperature. The error of predicted rainfall based on the root mean squared error (RMSE), 16-17 mm, is relatively small compared with the average monthly rainfall at Seoul station is 117mm. The results showed scheme (iv) gives the best prediction result. Therefore, this approach is more straightforward than the hydrological and hydraulic models, which request much more input data. The result indicated that a deep learning network could be applied successfully in the hydrology field. Overall, the proposed method is promising, given a good solution for rainfall prediction.

• Journal of Korea Water Resources Association
• /
• v.55 no.11
• /
• pp.903-911
• /
• 2022

Groundwater, one of the resources for supplying water, fluctuates in water level due to various natural factors. Recently, research has been conducted to predict fluctuations in groundwater levels using Artificial Neural Network (ANN). Previously, among operators in ANN, Gradient Descent (GD)-based Optimizers were used as Optimizer that affect learning. GD-based Optimizers have disadvantages of initial correlation dependence and absence of solution comparison and storage structure. This study developed Gradient Descent combined with Harmony Search (GDHS), a new Optimizer that combined GD and Harmony Search (HS) to improve the shortcomings of GD-based Optimizers. To evaluate the performance of GDHS, groundwater level at Icheon Yullhyeon observation station were learned and predicted using Multi Layer Perceptron (MLP). Mean Squared Error (MSE) and Mean Absolute Error (MAE) were used to compare the performance of MLP using GD and GDHS. Comparing the learning results, GDHS had lower maximum, minimum, average and Standard Deviation (SD) of MSE than GD. Comparing the prediction results, GDHS was evaluated to have a lower error in all of the evaluation index than GD.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.17 no.10
• /
• pp.2252-2258
• /
• 2013

In this paper, parallel orthogonal matching pursuit (POMP) is proposed to supplement the simultaneous orthogonal matching pursuit (S-OMP) which has been widely used as a greedy algorithm for sparse signal recovery for multiple measurement vector (MMV) problem. The process of POMP is simple but effective: (1) multiple indexes maximally correlated with the observation vector are chosen at the first iteration, (2) the conventional S-OMP process is carried out in parallel for each selected index, (3) the index set which yields the minimum residual is selected for reconstructing the original sparse signal. Empirical simulations show that POMP for MMV outperforms than the conventional S-OMP both in terms of exact recovery ratio (ERR) and mean-squared error (MSE).

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.17 no.8
• /
• pp.1784-1789
• /
• 2013

In this paper, parallel orthogonal matching pursuit (POMP) is proposed to supplement the orthogonal matching pursuit (OMP) which has been widely used as a greedy algorithm for sparse signal recovery. The process of POMP is simple but effective: (1) multiple indexes maximally correlated with the observation vector are chosen at the firest iteration, (2) the conventional OMP process is carried out in parallel for each selected index, (3) the index set which yields the minimum residual is selected for reconstructing the original sparse signal. Empirical simulations show that POMP outperforms than the existing sparse signal recovery algorithms in terms of exact recovery ratio (ERR) for sparse pattern and mean-squared error (MSE) between the estimated signal and the original signal.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 1999.06a
• /
• pp.83-88
• /
• 1999

In this paper, a novel gray-scale lossless image coder combining context-based minimum mean squared error (MMSE) prediction and entropy coding is proposed. To obtain context of prediction, this paper first defines directional difference according to sharpness of edge and gradients of localities of image data. Classification of 4 directional differences forms“geometry context”model which characterizes two-dimensional general image behaviors such as directional edge region, smooth region or texture. Based on this context model, adaptive DPCM prediction coefficients are calculated in MMSE sense and the prediction is performed. The MMSE method on context-by-context basis is more in accord with minimum entropy condition, which is one of the major objectives of the predictive coding. In entropy coding stage, context modeling method also gives useful performance. To reduce the statistical redundancy of the residual image, many contexts are preset to take full advantage of conditional probability in entropy coding and merged into small number of context in efficient way for complexity reduction. The proposed lossless coding scheme slightly outperforms the CALIC, which is the state-of-the-art, in compression ratio.

• Economic and Environmental Geology
• /
• v.56 no.3
• /
• pp.331-341
• /
• 2023

When creating a soil contamination map using geostatistical techniques, there are various sources that can affect prediction errors. In this study, a grid-based soil contamination map was created from the sampling data of heavy metal concentrations in soil in abandoned mine areas using Ordinary Kriging. Five factors that were judged to affect the prediction error of the soil contamination map were selected, and the variation of the root mean squared error (RMSE) between the predicted value and the actual value was analyzed based on the Leave-one-out technique. Then, using a machine learning algorithm, derived the top three factors affecting the RMSE. As a result, it was analyzed that Variogram Model, Minimum Neighbors, and Anisotropy factors have the largest impact on RMSE in the Standard interpolation. For the variogram models, the Spherical model showed the lowest RMSE, while the Minimum Neighbors had the lowest value at 3 and then increased as the value increased. In the case of Anisotropy, it was found to be more appropriate not to consider anisotropy. In this study, through the combined use of geostatistics and machine learning, it was possible to create a highly reliable soil contamination map at the local scale, and to identify which factors have a significant impact when interpolating a small amount of soil heavy metal data.

• The Journal of Advanced Prosthodontics
• /
• v.15 no.2
• /
• pp.55-62
• /
• 2023

PURPOSE. The aim of this study is to evaluate the accuracy of removable partial denture (RPD) frameworks produced using different digital protocols. MATERIALS AND METHODS. 80 frameworks for RPDs were produced using CAD-CAM technology and divided into four groups of twenty (n = 20): Group 1, Titanium frameworks manufactured by digital metal laser sintering (DMLS); Group 2, Co-Cr frameworks manufactured by DMLS; Group 3, Polyamide PA12 castable resin manufactured by multi-jet fusion (MJF); and Group 4, Metal (Co-Cr) casting by using lost-wax technique. After the digital acquisition, eight specific areas were selected in order to measure the Δ-error value at the intaglio surface of RPD. The minimum value required for point sampling density (0.4 mm) was derived from the sensitivity analysis. The obtained Δ-error mean value was used for comparisons: 1. between different manufacturing processes; 2. between different manufacturing techniques in the same area of interest (AOI); and 3. between different AOI of the same group. RESULTS. The Δ-error mean value of each group ranged between -0.002 (Ti) and 0.041 (Co-Cr) mm. The Pearson's Chi-squared test revealed significant differences considering all groups paired two by two, except for group 3 and 4. The multiple comparison test documented a significant difference for each AOI among group 1, 3, and 4. The multiple comparison test showed significant differences among almost all different AOIs of each group. CONCLUSION. All Δ-mean error values of all digital protocols for manufacturing RPD frameworks optimally fit within the clinical tolerance limit of trueness and precision.

• Journal of Communications and Networks
• /
• v.12 no.5
• /
• pp.442-448
• /
• 2010

Cooperative relaying methods have attracted a lot of interest in the past few years. A conventional cooperative relaying scheme has a source, a destination, and a single relay. This cooperative scheme can support one symbol transmission per time slot, and is caned full rate transmission. However, existing fun rate cooperative relay approaches provide asymmetrical gain for different transmitted symbols. In this paper, we propose a cooperative relaying scheme that is assisted with dual relays and provides full transmission rate with the same macro-diversity to each symbol. We also address equalization for the dual relay transmission system in addition to addressing the issues concerning the improvement of system performance in terms of optimal power allocations.

• Journal of the Korean Institute of Telematics and Electronics
• /
• v.26 no.10
• /
• pp.1561-1570
• /
• 1989

In this paper, we propose an image coding scheme which combines the Laplacian pyramid structure and a hierarchical finite state classified vector quantizer in the DCT domain, namely FSDCT-CTQ. First, an optimal bit allocation problem for fixed rates DCT-CVQ on the Laplacian pyramid structure is described. In an asymptotic case, with an optimal bit allocation, a coding gain over scalar quantization of each Laplacian plane is derived. Second, it is experimentallhy shown that the Laplacian pyramid structure provides a considerable codng gain in the sense of total MMSE (minimum mean squared error). Finally, we propose an FS-DCT-CVQ which exploits the hierarchicla correlation between the Laplacian planes. Simulation results on real images show that the proposed coding scheme can reconstruct an image with 30.33 dB at 0.192 bpp, 32.45 dB at 0.385 bpp, respectively.

• Journal of the Optical Society of Korea
• /
• v.13 no.3
• /
• pp.367-372
• /
• 2009

In this paper we propose an electronic domain timing phase selection scheme for the optical communication systems suffering from inter-symbol-interference (ISI) distortion due to chromatic dispersion (CD) or polarization mode dispersion (PMD). In the presence of CD/PMD a proper timing phase selection is important for discrete time domain equalizers, since different timing phases produce different nonlinear ISI channels of different severity. The proposed timing phase recovery scheme based on dispersion minimization (DM) practically approximates the optimal minimum mean squared error (MMSE) timing phase without training signals which reduces overall throughput substantially, especially in time-varying channels such as PMD. The simulation results show that the proposed DM timing agrees with MMSE timing phase, under proper normalization of the received signals, for various dispersion and OSNR.