• Structural Engineering and Mechanics
• /
• v.84 no.5
• /
• pp.605-618
• /
• 2022

Glass fiber reinforced polymer (GFRP) elastic gridshells consist of long continuous GFRP tubes that form elastic deformations. In this paper, a method for the form-finding of gridshell structures is presented based on the interpretable machine learning (ML) approaches. A comparative study is conducted on several ML algorithms, including support vector regression (SVR), K-nearest neighbors (KNN), decision tree (DT), random forest (RF), AdaBoost, XGBoost, category boosting (CatBoost), and light gradient boosting machine (LightGBM). A numerical example is presented using a standard double-hump gridshell considering two characteristics of deformation as objective functions. The combination of the grid search approach and k-fold cross-validation (CV) is implemented for fine-tuning the parameters of ML models. The results of the comparative study indicate that the LightGBM model presents the highest prediction accuracy. Finally, interpretable ML approaches, including Shapely additive explanations (SHAP), partial dependence plot (PDP), and accumulated local effects (ALE), are applied to explain the predictions of the ML model since it is essential to understand the effect of various values of input parameters on objective functions. As a result of interpretability approaches, an optimum gridshell structure is obtained and new opportunities are verified for form-finding investigation of GFRP elastic gridshells during lifting construction.

• Journal of Korean Dental Science
• /
• v.16 no.1
• /
• pp.47-62
• /
• 2023

Purpose: We aimed to investigate the objective cutoff values of unstimulated flow rates (UFR) and stimulated salivary flow rates (SFR) in patients with xerostomia and to present an optimal machine learning model with a classification and regression tree (CART) for all ages. Materials and Methods: A total of 829 patients with oral diseases were enrolled (591 females; mean age, 59.29±16.40 years; 8~95 years old), 199 patients with xerostomia and 630 patients without xerostomia. Salivary and clinical characteristics were collected and analyzed. Result: Patients with xerostomia had significantly lower levels of UFR (0.29±0.22 vs. 0.41±0.24 ml/min) and SFR (1.12±0.55 vs. 1.39±0.94 ml/min) (P<0.001), respectively, compared to those with non-xerostomia. The presence of xerostomia had a significantly negative correlation with UFR (r=-0.603, P=0.002) and SFR (r=-0.301, P=0.017). In the diagnosis of xerostomia based on the CART algorithm, the presence of stomatitis, candidiasis, halitosis, psychiatric disorder, and hyperlipidemia were significant predictors for xerostomia, and the cutoff ranges for xerostomia for UFR and SFR were 0.03~0.18 ml/min and 0.85~1.6 ml/min, respectively. Conclusion: Xerostomia was correlated with decreases in UFR and SFR, and their cutoff values varied depending on the patient's underlying oral and systemic conditions.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.17 no.4
• /
• pp.1080-1099
• /
• 2023

Digital healthcare combined with telemedicine services in the form of convergence with digital technology and AI is developing rapidly. Digital healthcare research is being conducted on many conditions including shock. However, the causes of shock are diverse, and the treatment is very complicated, requiring a high level of medical knowledge. In this paper, we propose a shock detection method based on the correlation between shock and data extracted from hemodynamic monitoring equipment. From the various parameters expressed by this equipment, four parameters closely related to patient shock were used as the input data for a machine learning model in order to detect the shock. Using the four parameters as input data, that is, feature values, a random forest-based ensemble machine learning model was constructed. The value of the mean arterial pressure was used as the correct answer value, the so called label value, to detect the patient's shock state. The performance was then compared with the decision tree and logistic regression model using a confusion matrix. The average accuracy of the random forest model was 92.80%, which shows superior performance compared to other models. We look forward to our work playing a role in helping medical staff by making recommendations for the diagnosis and treatment of complex and difficult cases of shock.

• The Sea:JOURNAL OF THE KOREAN SOCIETY OF OCEANOGRAPHY
• /
• v.27 no.2
• /
• pp.71-86
• /
• 2022

The water quality index (WQI) has been widely used to evaluate marine water quality. The WQI in Korea is categorized into five classes by marine environmental standards. But, the WQI calculation on huge datasets is a very complex and time-consuming process. In this regard, the current study proposed machine learning (ML) based models to predict WQI class by using water quality datasets. Sihwa Lake, one of specially-managed coastal zone, was selected as a modeling site. In this study, adaptive boosting (AdaBoost) and tree-based pipeline optimization (TPOT) algorithms were used to train models and each model performance was evaluated by metrics (accuracy, precision, F1, and Log loss) on classification. Before training, the feature importance and sensitivity analysis were conducted to find out the best input combination for each algorithm. The results proved that the bottom dissolved oxygen (DO_Bot) was the most important variable affecting model performance. Conversely, surface dissolved inorganic nitrogen (DIN_Sur) and dissolved inorganic phosphorus (DIP_Sur) had weaker effects on the prediction of WQI class. In addition, the performance varied over features including stations, seasons, and WQI classes by comparing spatio-temporal and class sensitivities of each best model. In conclusion, the modeling results showed that the TPOT algorithm has better performance rather than the AdaBoost algorithm without considering feature selection. Moreover, the WQI class for unknown water quality datasets could be surely predicted using the TPOT model trained with satisfactory training datasets.

• Tunnel and Underground Space
• /
• v.33 no.6
• /
• pp.594-609
• /
• 2023

TBM (Tunnel Boring Machine) method is gaining popularity in urban and underwater tunneling projects due to its ability to ensure excavation face stability and minimize environmental impact. Among the prominent models for predicting disc cutter life, the NTNU model uses the Cutter Life Index(CLI) as a key parameter, but the complexity of testing procedures and rarity of equipment make measurement challenging. In this study, CLI was predicted using multiple linear regression analysis and tree-based machine learning techniques, utilizing rock properties. Through literature review, a database including rock uniaxial compressive strength, Brazilian tensile strength, equivalent quartz content, and Cerchar abrasivity index was built, and derived variables were added. The multiple linear regression analysis selected input variables based on statistical significance and multicollinearity, while the machine learning prediction model chose variables based on their importance. Dividing the data into 80% for training and 20% for testing, a comparative analysis of the predictive performance was conducted, and XGBoost was identified as the optimal model. The validity of the multiple linear regression and XGBoost models derived in this study was confirmed by comparing their predictive performance with prior research.

• Journal of Convergence for Information Technology
• /
• v.7 no.1
• /
• pp.55-60
• /
• 2017

In order to provide intelligent services without human intervention in the Internet of Things environment, it is necessary to analyze the big data generated by the IoT device and learn the normal pattern, and to predict the abnormal symptoms such as faulty or malfunction based on the learned normal pattern. The purpose of this study is to implement a machine learning model that can predict product failure by analyzing big data generated in various devices of product process. The machine learning model uses the big data analysis tool R because it needs to analyze based on existing data with a large volume. The data collected in the product process include the information about product faulty, so supervised learning model is used. As a result of the study, I classify the variables and variable conditions affecting the product failure, and proposed a prediction model for the product failure based on the decision tree. In addition, the predictive power of the model was significantly higher in the conformity and performance evaluation analysis of the model using the ROC curve.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2022.05a
• /
• pp.134-134
• /
• 2022

Streamflow forecasting plays a crucial role in water resource control, especially in highly urbanized areas that are very vulnerable to flooding during heavy rainfall event. In addition to providing the accurate prediction, the evaluation of effects and importance of the input predictors can contribute to water manager. Recently, machine learning techniques have applied their advantages for modeling complex and nonlinear hydrological processes. However, the techniques have not considered properly the importance and uncertainty of the predictor variables. To address these concerns, we applied the GA-BART, that integrates a genetic algorithm (GA) with the Bayesian additive regression tree (BART) model for hourly streamflow forecasting and analyzing input predictors. The Jungrang urban basin was selected as a case study and a database was established based on 39 heavy rainfall events during 2003 and 2020 from the rain gauges and monitoring stations. For the goal of this study, we used a combination of inputs that included the areal rainfall of the subbasins at current time step and previous time steps and water level and streamflow of the stations at time step for multistep-ahead streamflow predictions. An analysis of multiple datasets including different input predictors was performed to define the optimal set for streamflow forecasting. In addition, the GA-BART model could reasonably determine the relative importance of the input variables. The assessment might help water resource managers improve the accuracy of forecasts and early flood warnings in the basin.

• Proceedings of the Korea Inteligent Information System Society Conference
• /
• 2001.01a
• /
• pp.30-33
• /
• 2001

The number of hidden neurons of the feed-forward neural networks is generally decided on the basis of experience. The method usually results in the lack or redundancy of hidden neurons, and causes the shortage of capacity for storing information of learning overmuch. This research proposes a new method for optimizing the number of hidden neurons bases on information entropy, Firstly, an initial neural network with enough hidden neurons should be trained by a set of training samples. Second, the activation values of hidden neurons should be calculated by inputting the training samples that can be identified correctly by the trained neural network. Third, all kinds of partitions should be tried and its information gain should be calculated, and then a decision-tree correctly dividing the whole sample space can be constructed. Finally, the important and related hidden neurons that are included in the tree can be found by searching the whole tree, and other redundant hidden neurons can be deleted. Thus, the number of hidden neurons can be decided. In the case of building a neural network with the best number of hidden units for tea quality evaluation, the proposed method is applied. And the result shows that the method is effective

• Journal of the Korean Association of Geographic Information Studies
• /
• v.7 no.1
• /
• pp.9-19
• /
• 2004

The selection of comparative standard parcels should be objective and reasonable, which is an important task in the individual land price appraisal procedure. However, the current procedure is mainly done manually by government officials. Therefore, the efficiency and objectiveness of this selection procedure is not guaranteed and questionable. In this study, we first defined the problem by analyzing the current comparative standard land parcel selection method. In addition, we devised a decision tree-based method using a machine learning algorithm that is considered to be efficient and objective compared to the current selection procedure. Finally the proposed method is then applied to the study area for evaluating the appropriateness and accuracy.

• Korean Journal of Artificial Intelligence
• /
• v.9 no.1
• /
• pp.9-14
• /
• 2021

This paper predicted a model that indicates whether to buy a car based on primary health insurance customer data. Currently, automobiles are being used to land transportation and living, and the scope of use and equipment is expanding. This rapid increase in automobiles has caused automobile insurance to emerge as an essential business target for insurance companies. Therefore, if the car insurance sales are predicted and sold using the information of existing health insurance customers, it can generate continuous profits in the insurance company's operating performance. Therefore, this paper aims to analyze existing customer characteristics and implement a predictive model to activate advertisements for customers interested in such auto insurance. The goal of this study is to maximize the profits of insurance companies by devising communication strategies that can optimize business models and profits for customers. This study was conducted through the Microsoft Azure program, and an automobile insurance purchase prediction model was implemented using Health Insurance Cross-sell Prediction data. The program algorithm uses Two-Class Logistic Regression and Two-Class Boosted Decision Tree at the same time to compare two models and predict and compare the results. According to the results of this study, when the Threshold is 0.3, the AUC is 0.837, and the accuracy is 0.833, which has high accuracy. Therefore, the result was that customers with health insurance could induce a positive reaction to auto insurance purchases.