• Journal of Intelligence and Information Systems
• /
• v.24 no.4
• /
• pp.155-170
• /
• 2018

Predicting a company's financial bankruptcy is traditionally one of the most crucial forecasting problems in business analytics. In previous studies, prediction models have been proposed by applying or combining statistical and machine learning-based techniques. In this paper, we propose a novel intelligent prediction model based on the simulated annealing which is one of the well-known optimization techniques. The simulated annealing is known to have comparable optimization performance to the genetic algorithms. Nevertheless, since there has been little research on the prediction and classification of business decision-making problems using the simulated annealing, it is meaningful to confirm the usefulness of the proposed model in business analytics. In this study, we use the combined model of simulated annealing and machine learning to select the input features of the bankruptcy prediction model. Typical types of combining optimization and machine learning techniques are feature selection, feature weighting, and instance selection. This study proposes a combining model for feature selection, which has been studied the most. In order to confirm the superiority of the proposed model in this study, we apply the real-world financial data of the Korean companies and analyze the results. The results show that the predictive accuracy of the proposed model is better than that of the naïve model. Notably, the performance is significantly improved as compared with the traditional decision tree, random forests, artificial neural network, SVM, and logistic regression analysis.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.20 no.4
• /
• pp.545-550
• /
• 2019

The frequency of natural disasters and the scale of damage are increasing due to the abnormal weather phenomenon occurring all over the world. As a result, as the hydrological aspect of the urban watershed changes, the increase in impervious area leads to serious domestic flood damage due to increased rainfall. In order to minimize the damage of life and property, domestic flooding prediction system is needed. In this study, we developed a flood nomogram capable of predicting flooding only by rainfall intensity and duration. This study suggests a method to set the internal water immersion alarm criterion by analyzing the characteristics of the flooding damage in the flooded area in the metropolitan area where flooding is highly possible and the risk of flooding is high. In addition, based on the manhole and the pipe, the water level was set as follows under the four conditions. 1) When manhole overflows, 2) when manhole is full, 3) when 70% of the pipe is reached, and 4) when 60% of the pipe is reached. Therefore, it can be used as a criterion and a predictive measure to cope with the pre-preparation before the flooding starts, through the rainfall that causes the flooding and the flooding damage.

• Journal of Digital Convergence
• /
• v.19 no.4
• /
• pp.467-475
• /
• 2021

Purpose: When a patient with acute deterioration occurs in a ward, the decision to transfer to intensive care unit (ICU) is critical to improve the patient's outcomes. However, when available ICU resources limited, it is difficult to determine which of the deteriorating ward patients to transfer to the ICU. Therefore the purpose of this study was to identify risk factors in predicting deteriorating ward patients transferred to intensive care unit (ICU). Methods: We reviewed retrospectively clinical data of 2,945 deteriorating ward patients who referred medical emergency team. Data were analyzed with multivariate logistic regression. Results: The solid cancer that diagnosed at hospitalization (odds ratio[OR] 0.39; 95% confidence interval [CI] 0.32-0.47), when the cause of deterioration was respiratory problem (1.51; 95% CI 1.17-1.95), high MEWS (1.22; 1.17-1.28) and SpO2/FiO2 score (2.41; 2.23-2.60) were predictive of ICU transfer. Conclusion: These findings suggest that early prediction and treatment of patients with high risk of ICU transfer may improve the prognosis of patients.

• Korean Chemical Engineering Research
• /
• v.59 no.2
• /
• pp.209-218
• /
• 2021

First principle-based modeling studies have been performed to improve the heat exchange efficiency of ORV and optimize operation, but the heat transfer coefficient of ORV is an irregular system according to time and location, and it undergoes a complex modeling process. In this study, FNN, LSTM, and AutoML-based modeling were performed to confirm the effectiveness of data-based modeling for complex systems. The prediction accuracy indicated high performance in the order of LSTM > AutoML > FNN in MSE. The performance of AutoML, an automatic design method for machine learning models, was superior to developed FNN, and the total time required for model development was 1/15 compared to LSTM, showing the possibility of using AutoML. The prediction of NG and seawater discharged temperatures using LSTM and AutoML showed an error of less than 0.5K. Using the predictive model, real-time optimization of the amount of LNG vaporized that can be processed using ORV in winter is performed, confirming that up to 23.5% of LNG can be additionally processed, and an ORV optimal operation guideline based on the developed dynamic prediction model was presented.

• Mycobiology
• /
• v.49 no.4
• /
• pp.406-420
• /
• 2021

Gloeostereum incarnatum has edible and medicinal value and was first cultivated and domesticated in China. We sequenced the G. incarnatum monokaryotic strain GiC-126 on an Illumina HiSeq X Ten system and obtained a 34.52-Mb genome assembly sequence that encoded 16,895 predicted genes. We combined the GiC-126 genome with the published genome of G. incarnatum strain CCMJ2665 to construct a genetic linkage map (GiC-126 genome) that had 10 linkage groups (LGs), and the 15 assembly sequences of CCMJ2665 were integrated into 8 LGs. We identified 1912 simple sequence repeat (SSR) loci and detected 700 genes containing 768 SSRs in the genome; 65 and 100 of them were annotated with gene ontology (GO) terms and KEGG pathways, respectively. Carbohydrate-active enzymes (CAZymes) were identified in 20 fungal genomes and annotated; among them, 144 CAZymes were annotated in the GiC-126 genome. The A mating-type locus (MAT-A) of G. incarnatum was located on scaffold885 at 38.9 cM of LG1 and was flanked by two homeodomain (HD1) genes, mip and beta-fg. Fourteen segregation distortion markers were detected in the genetic linkage map, all of which were skewed toward the parent GiC-126. They formed three segregation distortion regions (SDR1-SDR3), and 22 predictive genes were found in scaffold1920 where three segregation distortion markers were located in SDR1. In this study, we corrected and updated the genomic information of G. incarnatum. Our results will provide a theoretical basis for fine gene mapping, functional gene cloning, and genetic breeding the follow-up of G. incarnatum.

• Investigative Magnetic Resonance Imaging
• /
• v.25 no.4
• /
• pp.313-322
• /
• 2021

Purpose: To find diagnostic image features, to compare diagnostic performance of multiphase CT versus gadoxetic acid disodium-enhanced MRI (GAD-MRI), and to evaluate the impact of analyzing Liver Imaging Reporting and Data System (LI-RADS) imaging features, for distinguishing combined hepatocellular-cholangiocarcinoma (CHC) from hepatocellular carcinoma (HCC). Materials and Methods: Ninety-six patients with pathologically proven CHC (n = 48) or HCC (n = 48), diagnosed June 2008 to May 2018 were retrospectively analyzed in random order by three radiologists with different experience levels. In the first analysis, the readers independently determined the probability of CHC based on their own knowledge and experiences. In the second analysis, they evaluated imaging features defined in LI-RADS 2018. Area under the curve (AUC) values for CHC diagnosis were compared between CT and MRI, and between the first and second analyses. Interobserver agreement was assessed using Cohen's weighted κ values. Results: Targetoid LR-M image features showed better specificities and positive predictive values (PPV) than the others. Among them, rim arterial phase hyperenhancement had the highest specificity and PPV. Average sensitivity, specificity, and AUC values were higher for MRI than for CT in both the first (P = 0.008, 0.005, 0.002, respectively) and second (P = 0.017, 0.026, 0.036) analyses. Interobserver agreements were higher for MRI in both analyses (κ = 0.307 for CT, κ = 0.332 for MRI in the first analysis; κ = 0.467 for CT, κ = 0.531 for MRI in the second analysis), with greater agreement in the second analysis for both CT (P = 0.001) and MRI (P < 0.001). Conclusion: Rim arterial phase hyperenhancement on GAD-MRI can be a good indicator suggesting CHC more than HCC. GAD-MRI may provide greater accuracy than CT for distinguishing CHC from HCC. Interobserver agreement can be improved for both CT and MRI by analyzing LI-RADS imaging features.

• Journal of Bio-Environment Control
• /
• v.31 no.1
• /
• pp.1-7
• /
• 2022

Strawberry is a stand-out cultivating fruit in Korea. The optimum production of strawberry is highly dependent on growing environment. Smart farm technology, and automatic monitoring and control system maintain a favorable environment for strawberry growth in greenhouses, as well as play an important role to improve production. Moreover, physiological parameters of strawberry plant and it is surrounding environment may allow to give an idea on production of strawberry. Therefore, this study intends to build a machine learning model to predict strawberry's yield, cultivated in greenhouse. The environmental parameter like as temperature, humidity and CO₂ and physiological parameters such as length of leaves, number of flowers and fruits and chlorophyll content of 'Seolhyang' (widely growing strawberry cultivar in Korea) were collected from three strawberry greenhouses located in Sacheon of Gyeongsangnam-do during the period of 2019-2020. A predictive model, Lasso regression was designed and validated through 5-fold cross-validation. The current study found that performance of the Lasso regression model is good to predict the number of flowers and fruits, when the MAPE value are 0.511 and 0.488, respectively during the model validation. Overall, the present study demonstrates that using AI based regression model may be convenient for farms and agricultural companies to predict yield of crops with fewer input attributes.

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.28 no.5
• /
• pp.780-790
• /
• 2022

Quantitative risk levels must be presented by analyzing the causes and consequences of accidents and predicting the occurrence patterns of the accidents. For the analysis of marine accidents related to vessel traffic, research on the traffic such as collision risk analysis and navigational path finding has been mainly conducted. The analysis of the occurrence pattern of marine accidents has been presented according to the traditional statistical analysis. This study intends to present a marine accident prediction model using the statistics on marine accidents related to vessel traffic. Statistical data from 1998 to 2021, which can be accumulated by month and hourly data among the Korean domestic marine accidents, were converted into structured time series data. The predictive model was built using a long short-term memory network, which is a representative artificial intelligence model. As a result of verifying the performance of the proposed model through the validation data, the RMSEs were noted to be 52.5471 and 126.5893 in the initial neural network model, and as a result of the updated model with observed datasets, the RMSEs were improved to 31.3680 and 36.3967, respectively. Based on the proposed model, the occurrence pattern of marine accidents could be predicted by learning the features of various marine accidents. In further research, a quantitative presentation of the risk of marine accidents and the development of region-based hazard maps are required.

• Resources Recycling
• /
• v.31 no.6
• /
• pp.81-91
• /
• 2022

The use of lithium-ion batteries increases significantly with the rapid spread of electronic devices and electric vehicle and thereby an increase in the amount of waste batteries is expected in the near future. Therefore, studies are continuously being conducted to recover various resources of cathode active material (Ni, Co, Mn, Li) from waste battery. In order to recover the cathode active material, black mass is generally recovered from waste battery. The general process of recovering black mass is a waste battery collection - discharge - dismantling - crushing - classification process. This study focus on the crushing/classification process among the processes. Specifically, the particle size distribution of various samples at each crushing/classification step were evaluated, and the particle shape of each particle fraction was analyzed with a microscope and SEM (Scanning Electron Microscopy)-EDS(Energy Dispersive Spectrometer). As a result, among the black mass particle, fine particle less than 74 ㎛ was the mixture of cathode and anode active material which are properly liberated from the current metals. However, coarse particle larger than 100 ㎛ was present in a form in which the current metal and active material were combined. In addition, this study developed a PBM(Population Balance Model) system that can simulate two-species mixture sample with two different crushing properties. Using developed model, the breakage parameters of two species was derived and predictive performance of breakage distribution was verified.

• Journal of the Computational Structural Engineering Institute of Korea
• /
• v.36 no.1
• /
• pp.9-18
• /
• 2023

Predicting the compressive strength of high-performance concrete (HPC) is challenging because of the use of additional cementitious materials; thus, the development of improved predictive models is essential. The purpose of this study was to develop an HPC compressive-strength prediction model using an ensemble machine-learning method of combined bagging and stacking techniques. The result is a new ensemble technique that integrates the existing ensemble methods of bagging and stacking to solve the problems of a single machine-learning model and improve the prediction performance of the model. The nonlinear regression, support vector machine, artificial neural network, and Gaussian process regression approaches were used as single machine-learning methods and bagging and stacking techniques as ensemble machine-learning methods. As a result, the model of the proposed method showed improved accuracy results compared with single machine-learning models, an individual bagging technique model, and a stacking technique model. This was confirmed through a comparison of four representative performance indicators, verifying the effectiveness of the method.