• Korean Journal of Artificial Intelligence
• /
• v.12 no.1
• /
• pp.17-24
• /
• 2024

This paper introduces a novel approach to time-series estimation for energy load forecasting within Virtual Power Plant (VPP) systems, leveraging advanced artificial intelligence (AI) algorithms, namely Long Short-Term Memory (LSTM) and Seasonal Autoregressive Integrated Moving Average (SARIMA). Virtual power plants, which integrate diverse microgrids managed by Energy Management Systems (EMS), require precise forecasting techniques to balance energy supply and demand efficiently. The paper introduces a hybrid-method forecasting model combining a parametric-based statistical technique and an AI algorithm. The LSTM algorithm is particularly employed to discern pattern correlations over fixed intervals, crucial for predicting accurate future energy loads. SARIMA is applied to generate time-series forecasts, accounting for non-stationary and seasonal variations. The forecasting model incorporates a broad spectrum of distributed energy resources, including renewable energy sources and conventional power plants. Data spanning a decade, sourced from the Korea Power Exchange (KPX) Electrical Power Statistical Information System (EPSIS), were utilized to validate the model. The proposed hybrid LSTM-SARIMA model with parameter sets (1, 1, 1, 12) and (2, 1, 1, 12) demonstrated a high fidelity to the actual observed data. Thus, it is concluded that the optimized system notably surpasses traditional forecasting methods, indicating that this model offers a viable solution for EMS to enhance short-term load forecasting.

• Journal of Korea Water Resources Association
• /
• v.53 no.1
• /
• pp.45-56
• /
• 2020

This study aims to quantify the uncertainty that can be induced by the objective function when calibrating SWAT parameters using SWAT-CUP. SWAT model was constructed to estimate runoff in Naesenong-cheon, which is the one of mid-watershed in Nakdong River basin, and then automatic calibration was performed using eight objective functions (R², bR², NS, MNS, KGE, PBIAS, RSR, and SSQR). The optimum parameter sets obtained from each objective function showed different ranges, and thus the corresponding hydrologic characteristics of simulated data were also derived differently. This is because each objective function is sensitive to specific hydrologic signatures and evaluates model performance in an unique way. In other words, one objective function might be sensitive to the residual of the extreme value, so that well produce the peak value, whereas ignores the average or low flow residuals. Therefore, the hydrological similarity between the simulated and measured values was evaluated in order to select the optimum objective function. The hydrologic signatures, which include not only the magnitude, but also the ratio of the inclining and declining time in hydrograph, were defined to consider the timing of the flow occurrence, the response of watershed, and the increasing and decreasing trend. The results of evaluation were quantified by scoring method, and hence the optimal objective functions for SWAT parameter calibration were determined as MNS (342.48) and SSQR (346.45) with the highest total scores.

• Journal of Intelligence and Information Systems
• /
• v.19 no.2
• /
• pp.39-54
• /
• 2013

Recent explosive increase of electronic commerce provides many advantageous purchase opportunities to customers. In this situation, customers who do not have enough knowledge about their purchases, may accept product recommendations. Product recommender systems automatically reflect user's preference and provide recommendation list to the users. Thus, product recommender system in online shopping store has been known as one of the most popular tools for one-to-one marketing. However, recommender systems which do not properly reflect user's preference cause user's disappointment and waste of time. In this study, we propose a novel recommender system which uses data mining and multi-model ensemble techniques to enhance the recommendation performance through reflecting the precise user's preference. The research data is collected from the real-world online shopping store, which deals products from famous art galleries and museums in Korea. The data initially contain 5759 transaction data, but finally remain 3167 transaction data after deletion of null data. In this study, we transform the categorical variables into dummy variables and exclude outlier data. The proposed model consists of two steps. The first step predicts customers who have high likelihood to purchase products in the online shopping store. In this step, we first use logistic regression, decision trees, and artificial neural networks to predict customers who have high likelihood to purchase products in each product group. We perform above data mining techniques using SAS E-Miner software. In this study, we partition datasets into two sets as modeling and validation sets for the logistic regression and decision trees. We also partition datasets into three sets as training, test, and validation sets for the artificial neural network model. The validation dataset is equal for the all experiments. Then we composite the results of each predictor using the multi-model ensemble techniques such as bagging and bumping. Bagging is the abbreviation of "Bootstrap Aggregation" and it composite outputs from several machine learning techniques for raising the performance and stability of prediction or classification. This technique is special form of the averaging method. Bumping is the abbreviation of "Bootstrap Umbrella of Model Parameter," and it only considers the model which has the lowest error value. The results show that bumping outperforms bagging and the other predictors except for "Poster" product group. For the "Poster" product group, artificial neural network model performs better than the other models. In the second step, we use the market basket analysis to extract association rules for co-purchased products. We can extract thirty one association rules according to values of Lift, Support, and Confidence measure. We set the minimum transaction frequency to support associations as 5%, maximum number of items in an association as 4, and minimum confidence for rule generation as 10%. This study also excludes the extracted association rules below 1 of lift value. We finally get fifteen association rules by excluding duplicate rules. Among the fifteen association rules, eleven rules contain association between products in "Office Supplies" product group, one rules include the association between "Office Supplies" and "Fashion" product groups, and other three rules contain association between "Office Supplies" and "Home Decoration" product groups. Finally, the proposed product recommender systems provides list of recommendations to the proper customers. We test the usability of the proposed system by using prototype and real-world transaction and profile data. For this end, we construct the prototype system by using the ASP, Java Script and Microsoft Access. In addition, we survey about user satisfaction for the recommended product list from the proposed system and the randomly selected product lists. The participants for the survey are 173 persons who use MSN Messenger, Daum Caf$\acute{e}$, and P2P services. We evaluate the user satisfaction using five-scale Likert measure. This study also performs "Paired Sample T-test" for the results of the survey. The results show that the proposed model outperforms the random selection model with 1% statistical significance level. It means that the users satisfied the recommended product list significantly. The results also show that the proposed system may be useful in real-world online shopping store.

• Radiation Oncology Journal
• /
• v.30 no.4
• /
• pp.189-196
• /
• 2012

Purpose: To investigate the safety of high dose hypofractionated radiotherapy (RT) in patients with small hepatocellular carcinoma (HCC) in terms of liver volumetric changes and clinical liver function. Materials and Methods: We retrospectively reviewed 16 patients with small HCC who were treated with high dose hypofractionated RT between 2006 and 2009. The serial changes of the liver volumetric parameter were analyzed from pre-RT and follow-up (FU) computed tomography (CT) scans. We estimated linear time trends of whole liver volume using a linear mixed model. The serial changes of the Child-Pugh (CP) scores were also analyzed in relation to the volumetric changes. Results: Mean pre-RT volume of entire liver was 1,192.2 mL (range, 502.6 to 1,310.2 mL) and mean clinical target volume was 14.7 mL (range, 1.56 to 70.07 mL). Fourteen (87.5%) patients had 4 FU CT sets and 2 (12.5%) patients had 3 FU CT sets. Mean interval between FU CT acquisition was 2.5 months. After considering age, gender and the irradiated liver volume as a fixed effects, the mixed model analysis confirmed that the change in liver volume is not significant throughout the time course of FU periods. Majority of patients had a CP score change less than 2 except in 1 patient who had CP score change more than 3. Conclusion: The high dose hypofractionated RT for small HCC is relatively safe and feasible in terms of liver volumetric changes and clinical liver function.

• Journal of Embryo Transfer
• /
• v.29 no.3
• /
• pp.289-296
• /
• 2014

The pedigree information and race records of 1,000 m finishing time of Jeju race horses at KRA were used to study the effect of amount of pedigree information and parental misidentification on the estimates of genetic parameters. The modified data sets were made at the range of 2.5 to 25% parental misidentifications or loss of parental information of individuals with an increment of 2.5 percent. For each incremental level, 20 randomly replicated data sets were obtained and analyzed by single-trait analysis with a DF-REML(AI) algorithm. As the rate of misidentification increased or the amount of pedigree information decreased, the estimates of fraction of additive genetics variance component gradually decreased almost linearly (p<0.05), while the estimated fractions of error variance and permanent environmental variance components gradually increased for the finishing time. Regression coefficients of the percentage amount of both parents' information loss and incorrect pedigree information on additive genetic variances were -0.079 and -0.114, respectively (p<0.01). The estimate of heritability decreased by 0.92% for one percent loss of both parents' information and 1.39% for one percent increase of both parental misidentifications of progeny (p<0.01). For the consideration of probable incorrect and missing parent information of progeny in this early population of Jeju horses, the estimates of additive genetic parameters would be biased downward about ten percent. This results indicate that the amount of pedigree information loss and misidentification of progeny would severely affect estimates of genetic parameters and would reduce genetic gains for selection in Jeju horse population.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.28 no.5A
• /
• pp.673-683
• /
• 2008

This study improved the existing method of using the longitudinal strain and concept of influence line to develop Bridge Weigh-in-Motion system without axle detector using the dynamic strain of the bridge girders and concrete slab. This paper first describes the considered algorithms of extracting passing vehicle information from the dynamic strain signal measured at the bridge slab, girders, and cross beams. Two different analysis methods of 1) influence line method, and 2) neural network method are considered, and parameter study of measurement locations is also performed. Then the procedures and the results of field tests are described. The field tests are performed to acquire training sets and test sets for neural networks, and also to verify and compare performances of the considered algorithms. Finally, comparison between the results of different algorithms and discussions are followed. For a PSC I-girder bridge, vehicle weight can be calculated within a reasonable error range using the dynamic strain gauge installed on the girders. The passing lane and passing speed of the vehicle can be accurately estimated using the strain signal from the concrete slab. The passing speed and peak duration were added to the input variables to reflect the influence of the dynamic interaction between the bridge and vehicles, and impact of the distance between axles, respectively; thus improving the accuracy of the weight calculation.

• Korean Journal of Radiology
• /
• v.23 no.11
• /
• pp.1078-1088
• /
• 2022

Objective: To develop and validate a model using radiomics features from apparent diffusion coefficient (ADC) map to diagnose local tumor recurrence in head and neck squamous cell carcinoma (HNSCC). Materials and Methods: This retrospective study included 285 patients (mean age ± standard deviation, 62 ± 12 years; 220 male, 77.2%), including 215 for training (n = 161) and internal validation (n = 54) and 70 others for external validation, with newly developed contrast-enhancing lesions at the primary cancer site on the surveillance MRI following definitive treatment of HNSCC between January 2014 and October 2019. Of the 215 and 70 patients, 127 and 34, respectively, had local tumor recurrence. Radiomics models using radiomics scores were created separately for T2-weighted imaging (T2WI), contrast-enhanced T1-weighted imaging (CE-T1WI), and ADC maps using non-zero coefficients from the least absolute shrinkage and selection operator in the training set. Receiver operating characteristic (ROC) analysis was used to evaluate the diagnostic performance of each radiomics score and known clinical parameter (age, sex, and clinical stage) in the internal and external validation sets. Results: Five radiomics features from T2WI, six from CE-T1WI, and nine from ADC maps were selected and used to develop the respective radiomics models. The area under ROC curve (AUROC) of ADC radiomics score was 0.76 (95% confidence interval [CI], 0.62-0.89) and 0.77 (95% CI, 0.65-0.88) in the internal and external validation sets, respectively. These were significantly higher than the AUROC values of T2WI (0.53 [95% CI, 0.40-0.67], p = 0.006), CE-T1WI (0.53 [95% CI, 0.40-0.67], p = 0.012), and clinical parameters (0.53 [95% CI, 0.39-0.67], p = 0.021) in the external validation set. Conclusion: The radiomics model using ADC maps exhibited higher diagnostic performance than those of the radiomics models using T2WI or CE-T1WI and clinical parameters in the diagnosis of local tumor recurrence in HNSCC following definitive treatment.

• Geophysics and Geophysical Exploration
• /
• v.10 no.1
• /
• pp.1-18
• /
• 2007

Non-linear elastic wavefield inversion is a powerful method for estimating elastic parameters for physical constraints that determine subsurface rock and properties. Here, I introduce six elastic-wave velocity models by reconstructing elastic-wave velocity variations from real data and a 2D elastic-wave velocity model. Reflection seismic data information is often decoupled into short and long wavelength components. The local search method has difficulty in estimating the longer wavelength velocity if the starting model is far from the true model, and source frequencies are then changed from lower to higher bands (as in the 'frequency-cascade scheme') to estimate model elastic parameters. Elastic parameters are inverted at each inversion step ('simultaneous mode') with a starting model of linear P- and S-wave velocity trends with depth. Elastic parameters are also derived by inversion in three other modes - using a P- and S-wave velocity basis $('V_P\;V_S\;mode')$; P-impedance and Poisson's ratio basis $('I_P\;Poisson\;mode')$; and P- and S-impedance $('I_P\;I_S\;mode')$. Density values are updated at each elastic inversion step under three assumptions in each mode. By evaluating the accuracy of the inversion for each parameter set for elastic models, it can be concluded that there is no specific difference between the inversion results for the $V_P\;V_S$ mode and the $I_P$ Poisson mode. The same conclusion is expected for the $I_P\;I_S$ mode, too. This gives us a sound basis for full wavelength elastic wavefield inversion.

• Korean Journal of Microbiology
• /
• v.39 no.4
• /
• pp.207-215
• /
• 2003

Gene structure prediction, which is to predict protein coding regions in a given nucleotide sequence, is the most important process in annotating genes and greatly affects gene analysis and genome annotation. As eukaryotic genes have more complicated stuructures in DNA sequences than those of prokaryotic genes, analysis programs for eukaryotic gene structure prediction have more diverse and more complicated computational models. We have developed EGSP, a eukaryotic gene structure program, using duration hidden markov model. The program consists of two major processes, one of which is a training process to produce parameter values from training data sets and the other of which is to predict protein coding regions based on the parameter values. The program predicts multiple genes rather than a single gene from a DNA sequence. A few computational models were implemented to detect signal pattern and their scanning efficiency was tested. Prediction performance was calculated and was compared with those of a few commonly used programs, GenScan, GeneID and Morgan based on a few criteria. The results show that the program can be practically used as a stand-alone program and a module in a system. For gene prediction of eukaryotic microbial genomes, training and prediction analysis was done with Saccharomyces chromosomes and the result shows the program is currently practically applicable to real eukaryotic microbial genomes.

• Journal of Korean Society of Forest Science
• /
• v.90 no.5
• /
• pp.650-662
• /
• 2001

The growth and yield models for five different kinds of natural forest types were systemically developed in the natural Broadleaved-Korean pine Forests in Northeast China. The data were collected from 359 temporary plots and 58 permanent plots with area ranged from 0.06 ha to 1.0 ha, ranging in stand age from 43 to 364 years. The Site Class Index (SCI) was introduced to evaluate site quality and the Crown Competition Factor (CCF) was selected as a measure of stand density for the mixed natural forest. The Chapman-Richards function was adopted to develop SCI equation and height-diameter curve. The Schumacher growth function was selected as base model to develop the DBH, basal area, and stand volume growth models by using re-parameterized method. In modeling mean DBH and basal area growth, it was found that the asymptotic parameter A of Schumacher function was exponentially related to site quality (SCI) and stand density (CCF). The rate parameter k was related to stand density and it was independent of SCI. Several validation measures for predicted stand variables were evaluated in the growth and yield models using independent data sets. The results indicated that relative mean errors (RME) in predicted stand attributes were less than ${\pm}5%$ and the estimated precision values of the stand variables were all greater than 95%.