• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.60 no.1
• /
• pp.184-192
• /
• 2011

In this study, we introduce a identification methodology for FCM-based fuzzy model. The two underlying design mechanisms of such networks involve Fuzzy C-Means (FCM) clustering method and Particle Swarm Optimization(PSO). The proposed algorithm is based on FCM clustering method for efficient processing of data and the optimization of model was carried out using PSO. The premise part of fuzzy rules does not construct as any fixed membership functions such as triangular, gaussian, ellipsoidal because we build up the premise part of fuzzy rules using FCM. As a result, the proposed model can lead to the compact architecture of network. In this study, as the consequence part of fuzzy rules, we are able to use four types of polynomials such as simplified, linear, quadratic, modified quadratic. In addition, a Weighted Least Square Estimation to estimate the coefficients of polynomials, which are the consequent parts of fuzzy model, can decouple each fuzzy rule from the other fuzzy rules. Therefore, a local learning capability and an interpretability of the proposed fuzzy model are improved. Also, the parameters of the proposed fuzzy model such as a fuzzification coefficient of FCM clustering, the number of clusters of FCM clustering, and the polynomial type of the consequent part of fuzzy rules are adjusted using PSO. The proposed model is illustrated with the use of Automobile Miles per Gallon(MPG) and Boston housing called Machine Learning dataset. A comparative analysis reveals that the proposed FCM-based fuzzy model exhibits higher accuracy and superb predictive capability in comparison to some previous models available in the literature.

• The Korean Journal of Applied Statistics
• /
• v.29 no.4
• /
• pp.581-594
• /
• 2016

We introduce innovations state space exponential smoothing models (ISS-ESM) that can analyze time series with multiple seasonal patterns. Especially, in order to control complex structure existing in the multiple patterns, the model equations use a matrix consisting of seasonal updating parameters. It enables us to group the seasonal parameters according to their similarity. Because of the grouped parameters, we can accomplish the principle of parsimony. Further, the ISS-ESM can potentially accommodate any number of multiple seasonal patterns. The models are applied to predict electricity demand in Korea that is observed on hourly basis, and we compare their performance with that of the traditional exponential smoothing methods. It is observed that the ISS-ESM are superior to the traditional methods in terms of the prediction and the interpretability of seasonal patterns.

• The Journal of Bigdata
• /
• v.3 no.2
• /
• pp.101-112
• /
• 2018

The purpose of the study is to predict the number of police calls using neural network which is one of the machine learning and negative binomial regression, by using the data of 112 police calls received from Chungnam Provincial Police Agency from June 2016 to May 2017. The variables which may affect the police calls have been selected for developing the prediction model : time, holiday, the day before holiday, season, temperature, precipitation, wind speed, jurisdictional area, population, the number of foreigners, single house rate and other house rate. Some variables show positive correlation, and others negative one. The comparison of the methods can be summarized as follows. Neural network has correlation coefficient of 0.7702 between predicted and actual values with RMSE 2.557. Negative binomial regression on the other hand shows correlation coefficient of 0.7158 with RMSE 2.831. Neural network has low interpretability, but an excellent predictability compared with the negative binomial regression. Based on the prediction model, the police agency can do the optimal manpower allocation for given values in the selected variables.

• The Journal of Bigdata
• /
• v.5 no.2
• /
• pp.215-229
• /
• 2020

The interest in machine learning is growing in all industries, but it is difficult to apply it to real-world tasks because of inexplicability. This paper introduces a case of developing a financial customer churn prediction model for a securities company, and introduces the research results on an attempt to develop a machine learning model that can be explained using the SHAP Value methodology and derivation of interpretability. In this study, a total of six customer churn models are compared and analyzed, and the cause of customer churn is inferred through the classification and data analysis of SHAP Value and the type of customer asset change. Based on the results of this study, it would be possible to use it as a basis for comprehensive judgment, such as using the Value of the deviation prediction result that can infer the cause of the marketing manager's actual customer marketing in the future and establishing a target marketing strategy for each customer.

• Nuclear Engineering and Technology
• /
• v.55 no.9
• /
• pp.3409-3416
• /
• 2023

Licensing the next-generation of nuclear reactor designs requires extensive use of Modeling and Simulation (M&S) to investigate system response to many operational conditions, identify possible accidental scenarios and predict their evolution to undesirable consequences that are to be prevented or mitigated via the deployment of adequate safety barriers. Deep Learning (DL) and Artificial Intelligence (AI) can support M&S computationally by providing surrogates of the complex multi-physics high-fidelity models used for design. However, DL and AI are, generally, low-fidelity 'black-box' models that do not assure any structure based on physical laws and constraints, and may, thus, lack interpretability and accuracy of the results. This poses limitations on their credibility and doubts about their adoption for the safety assessment and licensing of novel reactor designs. In this regard, Physics Informed Neural Networks (PINNs) are receiving growing attention for their ability to integrate fundamental physics laws and domain knowledge in the neural networks, thus assuring credible generalization capabilities and credible predictions. This paper presents the use of PINNs as surrogate models for accidental scenarios simulation in Nuclear Power Plants (NPPs). A case study of a Loss of Heat Sink (LOHS) accidental scenario in a Nuclear Battery (NB), a unique class of transportable, plug-and-play microreactors, is considered. A PINN is developed and compared with a Deep Neural Network (DNN). The results show the advantages of PINNs in providing accurate solutions, avoiding overfitting, underfitting and intrinsically ensuring physics-consistent results.

• Korean Journal of Radiology
• /
• v.24 no.11
• /
• pp.1061-1080
• /
• 2023

Artificial intelligence (AI) in radiology is a rapidly developing field with several prospective clinical studies demonstrating its benefits in clinical practice. In 2022, the Korean Society of Radiology held a forum to discuss the challenges and drawbacks in AI development and implementation. Various barriers hinder the successful application and widespread adoption of AI in radiology, such as limited annotated data, data privacy and security, data heterogeneity, imbalanced data, model interpretability, overfitting, and integration with clinical workflows. In this review, some of the various possible solutions to these challenges are presented and discussed; these include training with longitudinal and multimodal datasets, dense training with multitask learning and multimodal learning, self-supervised contrastive learning, various image modifications and syntheses using generative models, explainable AI, causal learning, federated learning with large data models, and digital twins.

• Journal of the Korea Society of Computer and Information
• /
• v.29 no.2
• /
• pp.51-59
• /
• 2024

This study examines the relationship between the release of the news and the individual stock returns. Investors utilize a variety of information sources to maximize stock returns when establishing investment strategies. News companies publish their articles based on stock recommendation reports of analysts, enhancing the reliability of the information. Defining release of a stock-recommendation news article as an event, we examine its economic impacts and propose a binary classification model that predicts the stock return 10 days after the event. XGBoost and LightGBM models are applied for the study with accuracy of 75%, 71% respectively. In addition, after categorizing the recommended stocks based on the listed market(KOSPI/KOSDAQ) and market capitalization(Big/Small), this study verifies difference in the accuracy of models across four sub-datasets. Finally, by conducting SHAP(Shapley Additive exPlanations) analysis, we identify the key variables in each model, reinforcing the interpretability of models.

• Korean Journal of Construction Engineering and Management
• /
• v.25 no.3
• /
• pp.58-67
• /
• 2024

In the era of the fourth industrial revolution, data plays a vital role in enhancing the productivity of industries. To advance digitalization in the construction industry, which suffers from a lack of available data, this study proposes a model that classifies construction site photos by work types. Unlike traditional image classification models that solely rely on visual data, the model in this study includes semantic analysis of construction work types. This is achieved by extracting the significance of relationships between objects and work types from the standard construction specification. These relationships are then used to enhance the classification process by correlating them with objects detected in photos. This model improves the interpretability and reliability of classification results, offering convenience to field operators in photo categorization tasks. Additionally, the model's practical utility has been validated through integration into a classification program. As a result, this study is expected to contribute to the digitalization of the construction industry.

• Computers and Concrete
• /
• v.34 no.1
• /
• pp.93-122
• /
• 2024

One well-known reason for using Fiber Reinforced Polymer (FRP) composites is to improve concrete strength and strain capacity via external confinement. Hence, various studies have been undertaken to offer a good illustration of the response of FRP-wrapped concrete for practical design intents. However, in such studies, the strength and strain of the confined concrete were predicted using regression analysis based on a limited number of test data. This study presents an approach based on artificial neural networks (ANNs) to develop models to predict the strength and strain at maximum stress enhancement of circular concrete cross-sections confined with different FRP types (Carbone, Glass, Aramid). To achieve this goal, a large test database comprising 493 axial compression experiments on FRP-confined concrete samples was compiled based on an extensive review of the published literature and used to validate the predicted artificial intelligence techniques. The ANN approach is currently thought to be the preferred learning technique because of its strong prediction effectiveness, interpretability, adaptability, and generalization. The accuracy of the developed ANN model for predicting the behavior of FRP-confined concrete is commensurate with the experimental database compiled from published literature. Statistical measures values, which indicate a better fit, were observed in all of the ANN models. Therefore, compared to existing models, it should be highlighted that the newly developed models based on FRP type are remarkably accurate.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.18 no.3
• /
• pp.345-355
• /
• 2017

The purpose of this study was to examine the validity and reliability of the Communication Skills Attitude Scale, which is used to examine communication learning attitudes for domestic nursing students. Study subjects were 401 nursing students at two nursing college who completed the CSAS scale consisting of 26 items from June 1 to 15. Data were analyzed using exploratory factor analysis, confirmatory factor analysis, internal consistency with IBM Statistics SPSS 21.0, and the IBM Statistics AMOS 21.0 program. To verify the construction factor of the scale, exploratory factor analysis with varimax rotation was performed, resulting in four factors but confirmed positive and negative attitudes two factors with 19 items considering the construct of theory and interpretability. The internal structure of the scale was schematized using confirmatory factor analysis, and goodness of fit of the final research model was very appropriate as shown by ${\chi}^2=446.475$ (df=148, p<0.001), TLI=.90, CFI=.91, RMSEA=.07, SRMR=.05. The final scale consisted of 19 items and two factors based on the confirmatory factor analysis. Cronbach's ${\alpha}$ for final scale was .90, showing internal consistency. The CSAS is expected to be useful to monitor the effectiveness of multiple teaching strategies about communication for domestic nursing students.