• 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 Intelligence and Information Systems
• /
• v.15 no.4
• /
• pp.123-140
• /
• 2009

Fuzzy neural network is an integrated model of artificial neural network and fuzzy system and it has been successfully applied in control and forecasting area. Recently ANFIS(Adaptive Network-based Fuzzy Inference System) has been noticed widely among various fuzzy neural network models because of outstanding performance of control and forecasting accuracy. ANFIS has capability to refine its fuzzy rules interactively with human expert. In particular, when we use initial rule structure for machine learning which is generated from human expert, it is highly probable to reach global optimum solution as well as shorten time to convergence. We propose metrics to evaluate interpretability of generated rules as a means of acquiring domain knowledge and compare level of interpretability of ANFIS fuzzy rules to those of C5.0 classification rules. The proposed metrics also can be used to evaluate capability of rule generation for the various machine learning methods.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.33 no.3
• /
• pp.411-425
• /
• 2023

Today, AI (Artificial Intelligence) technology is widely used in various fields, performing classification and regression tasks according to the purpose of use, and research is also actively progressing. Especially in the field of security, unexpected threats need to be detected, and unsupervised learning-based anomaly detection techniques that can detect threats without adding known threat information to the model training process are promising methods. However, most of the preceding studies that provide interpretability for AI judgments are designed for supervised learning, so it is difficult to apply them to unsupervised learning models with fundamentally different learning methods. In addition, previously researched vision-centered AI mechanism interpretation studies are not suitable for application to the security field that is not expressed in images. Therefore, In this paper, we use a technique that provides interpretability for detected anomalies by searching for and comparing optimization references, which are the source of intrusion attacks. In this paper, based on reference, we propose additional logic to search for data closest to real data. Based on real data, it aims to provide a more intuitive interpretation of anomalies and to promote effective use of an anomaly detection model in the security field.

• The Korean Journal of Applied Statistics
• /
• v.24 no.4
• /
• pp.587-595
• /
• 2011

Credit scoring is an objective and automatic system to assess the credit risk of each customer. The logistic regression model is one of the popular methods of credit scoring to predict the default probability; however, it may not detect possible nonlinear features of predictors despite the advantages of interpretability and low computation cost. In this paper, we propose to use a generalized partially linear model as an alternative to logistic regression. We also introduce modern ensemble technologies such as bagging, boosting and random forests. We compare these methods via a simulation study and illustrate them through a German credit dataset.

• Journal of Korean Academy of Nursing
• /
• v.43 no.1
• /
• pp.50-58
• /
• 2013

Purpose: The purpose of this study was to evaluate measurement properties of self-report questionnaires for studies published in Korean nursing journals. Methods: Of 424 Korean nursing articles initially identified, 168 articles met the inclusion criteria. The methodological quality of the measurements used in the studies and interpretability were assessed using the COnsensus-based Standards for the selection of health Measurement INstruments (COSMIN) checklist. It consists of items on internal consistency, reliability, measurement error, content validity, construct validity including structural validity, hypothesis testing, cross-cultural validity, and criterion validity, and responsiveness. For each item of the COSMIN checklist, measurement properties are rated on a four-point scale: excellent, good, fair, and poor. Each measurement property is scored with worst score counts. Results: All articles used the classical test theory for measurement properties. Internal consistency (72.6%), construct validity (56.5%), and content validity (38.2%) were most frequently reported properties being rated as 'excellent' by COSMIN checklist, whereas other measurement properties were rarely reported. Conclusion: A systematic review of measurement properties including interpretability of most instruments warrants further research and nursing-focused checklists assessing measurement properties should be developed to facilitate intervention outcomes across Korean studies.

• Journal of Korean Society for Quality Management
• /
• v.11 no.1
• /
• pp.2-9
• /
• 1983

For the optimal achievement of system goals through a systematic analysis of the complex problems, systems engineering provides us the concepts and methodology that include comprehensive interpretability (or understandability), universal applicability, and feasibility. Under this aspect, the main objective of this study is that it introduces mathematical system theory (MST) as the fundamental tool of SE into the Inventory Control among the related parts with IE, and review it's applicability. Through its work, we can find that it has the alternative aspects with which it can replace other existing methods for problem-solving in understanding and analyzing structurally systems in themselves as well as being considerable of the time evolutionary process of a given system.

• Proceedings of the Korean Society of Near Infrared Spectroscopy Conference
• /
• 2001.06a
• /
• pp.2102-2102
• /
• 2001

Near infrared, diffuse reflectance spectroscopy has shown significant potential for in vitro and in vivo assessment of metabolic status. However, the complexity of living samples can lead to ambiguous results. This presentation will focus on methods that provide controls for scattering and absorption estimation in tissue. For robust estimations, normalization procedures will be shown which can greatly improve interpretability of results. Normalization based on time, location and spectral property will be shown with data from models, tissue phantoms and in vivo measurements. In particular, interpretation of NIR spectra associated with major respiratory constituents will be examined. Measurement of constituents such as hemoglobin, myoglobin, tissue edema, and lactate will be shown. Results suggest that NIR may provide a valuable tool for physiological monitoring in critical care research and practice.

• Journal of Korean Institute of Industrial Engineers
• /
• v.40 no.4
• /
• pp.375-381
• /
• 2014

Data mining is a process of discovering useful patterns or information from large amount of data. Decision tree is one of the data mining algorithms that can be used for both classification and prediction and has been widely used for various applications because of its flexibility and interpretability. Decision trees for classification generally generate a number of rules that belong to one of the predefined category and some rules may belong to the same category. In this case, it is necessary to determine the significance of each rule so as to provide the priority of the rule with users. The purpose of this paper is to propose a rule selection method in classification tree models that accommodate the umber of observation, accuracy, and effectiveness in each rule. Our experiments demonstrate that the proposed method produce better performance compared to other existing rule selection methods.

• The Korean Journal of Applied Statistics
• /
• v.26 no.1
• /
• pp.131-139
• /
• 2013

Support vector machines(SVM) may perform poorly in the presence of noise variables; in addition, it is difficult to identify the importance of each variable in the resulting classifier. A feature selection can improve the interpretability and the accuracy of SVM. Most existing studies concern feature selection in the linear SVM through penalty functions yielding sparse solutions. Note that one usually adopts nonlinear kernels for the accuracy of classification in practice. Hence feature selection is still desirable for nonlinear SVMs. In this paper, we compare the performances of nonlinear feature selection methods such as component selection and smoothing operator(COSSO) and kernel iterative feature extraction(KNIFE) on simulated and real data sets.

• Nuclear Engineering and Technology
• /
• v.54 no.12
• /
• pp.4684-4692
• /
• 2022

Radionuclide identification is an important part of the nuclear material identification system. The development of artificial intelligence and machine learning has made nuclide identification rapid and automatic. However, many methods directly use existing deep learning models to analyze the gamma-ray spectrum, which lacks interpretability for researchers. This study proposes an explainable radionuclide identification algorithm based on the convolutional neural network and class activation mapping. This method shows the area of interest of the neural network on the gamma-ray spectrum by generating a class activation map. We analyzed the class activation map of the gamma-ray spectrum of different types, different gross counts, and different signal-to-noise ratios. The results show that the convolutional neural network attempted to learn the relationship between the input gamma-ray spectrum and the nuclide type, and could identify the nuclide based on the photoelectric peak and Compton edge. Furthermore, the results explain why the neural network could identify gamma-ray spectra with low counts and low signal-to-noise ratios. Thus, the findings improve researchers' confidence in the ability of neural networks to identify nuclides and promote the application of artificial intelligence methods in the field of nuclide identification.