• KIPS Transactions on Software and Data Engineering
• /
• v.12 no.8
• /
• pp.333-340
• /
• 2023

Efficient prediction of corporate bankruptcy is an important part of making appropriate lending decisions for financial institutions and reducing loan default rates. In many studies, classification models using artificial intelligence technology have been used. In the financial industry, even if the performance of the new predictive models is excellent, it should be accompanied by an intuitive explanation of the basis on which the result was determined. Recently, the US, EU, and South Korea have commonly presented the right to request explanations of algorithms, so transparency in the use of AI in the financial sector must be secured. In this paper, an artificial intelligence-based interpretable classification prediction model was proposed using corporate bankruptcy data that was open to the outside world. First, data preprocessing, 5-fold cross-validation, etc. were performed, and classification performance was compared through optimization of 10 supervised learning classification models such as logistic regression, SVM, XGBoost, and LightGBM. As a result, LightGBM was confirmed as the best performance model, and SHAP, an explainable artificial intelligence technique, was applied to provide a post-explanation of the bankruptcy prediction process.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.41 no.6
• /
• pp.69-80
• /
• 2004

This paper proposes a method to learn action patterns of opponent characters for intelligent characters. For learning action patterns, intelligent characters learn the past actions as well as the current actions of opponent characters. Therefore, intelligent characters react more properly than ones without the knowledge on action patterns. In addition, this paper proposes a method to learn moving actions whose fitness is hard to evaluate. To evaluate the performance of the proposed algorithm, we experiment with four repeated action patterns in a game similar to real games. The results show that intelligent characters learn the optimal actions for action patterns and react properly against to random action opponent characters. The proposed method can be applied to various games in which characters confront each other, e.g. massively multiple of line games.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.59 no.5
• /
• pp.981-989
• /
• 2010

In this study, we introduce a new architecture of fuzzy inference system. In the fuzzy inference system, we use Fuzzy C-Means clustering algorithm to form the premise part of the rules. The membership functions standing in the premise part of fuzzy rules do not assume any explicit functional forms, but for any input the resulting activation levels of such radial basis functions directly depend upon the distance between data points by means of the Fuzzy C-Means clustering. As the consequent part of fuzzy rules of the fuzzy inference system (being the local model representing input output relation in the corresponding sub-space), four types of polynomial are considered, namely constant, linear, quadratic and modified quadratic. This offers a significant level of design flexibility as each rule could come with a different type of the local model in its consequence. Either the Least Square Estimator (LSE) or the weighted Least Square Estimator (WLSE)-based learning is exploited to estimate the coefficients of the consequent polynomial of fuzzy rules. In fuzzy modeling, complexity and interpretability (or simplicity) as well as accuracy of the obtained model are essential design criteria. The performance of the fuzzy inference system is directly affected by some parameters such as e.g., the fuzzification coefficient used in the FCM, the number of rules(clusters) and the order of polynomial in the consequent part of the rules. Accordingly we can obtain preferred model structure through an adjustment of such parameters of the fuzzy inference system. Moreover the comparative experimental study between WLSE and LSE is analyzed according to the change of the number of clusters(rules) as well as polynomial type. The superiority of the proposed model is illustrated and also demonstrated with the use of Automobile Miles per Gallon(MPG), Boston housing called Machine Learning dataset, and Mackey-glass time series dataset.

• Food Science of Animal Resources
• /
• v.40 no.2
• /
• pp.183-196
• /
• 2020

The protective effect of pig skin gelatin water extracts (PSW) and the low molecular weight hydrolysates of PSW generated via enzymatic hydrolysis with Flavourzyme® 1000L (LPSW) against scopolamine-induced impairment of cognitive function in mice was determined. Seventy male ICR mice weighing 20-25 g were randomly assigned to seven groups: Control (CON); scopolamine (SCO, 1 mg/kg B.W., intraperitoneally (i.p.); tetrahydroaminoacridine 10 [THA 10, tacrine; 10 mg/kg B.W. per oral (p.o.) with SCO (i.p.)]; PSW 10 (10 mg/kg B.W. (p.o.) with SCO (i.p.); PSW 40 (40 mg/kg B.W. (p.o.) with SCO (i.p.); LPSW 100 (100 mg/kg B.W. (p.o.) with SCO (i.p.); LPSW 400 (400 mg/kg B.W. (p.o.) with SCO (i.p.). All treatment groups, except CON, received scopolamine on the day of the experiment. The oxygen radical absorbance capacity of LPSW 400 at 1 mg/mL was 154.14 μM Trolox equivalent. Administration of PSW and LPSW for 15 weeks did not significantly affect on physical performance of mice. LPSW 400 significantly increased spontaneous alternation, reaching the level observed for THA and CON. The latency time of animals receiving LPSW 400 was higher than that of mice treated with SCO alone in the passive avoidance test, whereas it was shorter in the water maze test. LPSW 400 increased acetylcholine (ACh) content and decreased ACh esterase activity (p<0.05). LPSW 100 and LPSW 400 reduced monoamine oxidase-B activity. These results indicated that LPSW at 400 mg/kg B.W. is a potentially strong antioxidant and contains novel components for the functional food industry.

• Journal of Gastric Cancer
• /
• v.19 no.4
• /
• pp.438-450
• /
• 2019

Purpose: Although linear-shaped gastroduodenostomy (LSGD) was reported to be a feasible and reliable method of Billroth I anastomosis in patients undergoing totally laparoscopic distal gastrectomy (TLDG), the feasibility of LSGD for patients undergoing totally robotic distal gastrectomy (TRDG) has not been determined. This study compared the feasibility of LSGD in patients undergoing TRDG and TLDG. Materials and Methods: All c: onsecutive patients who underwent LSGD after distal gastrectomy for gastric cancer between January 2009 and December 2017 were analyzed retrospectively. Propensity score matching (PSM) analysis was performed to reduce the selection bias between TRDG and TLDG. Short-term outcomes, functional outcomes, learning curve, and risk factors for postoperative complications were analyzed. Results: This analysis included 414 patients, of whom 275 underwent laparoscopy and 139 underwent robotic surgery. PSM analysis showed that operation time was significantly longer (163.5 vs. 132.1 minutes, P<0.001) and postoperative hospital stay significantly shorter (6.2 vs. 7.5 days, P<0.003) in patients who underwent TRDG than in patients who underwent TLDG. Operation time was the independent risk factor for LSGD after intracorporeal gastroduodenostomy. Cumulative sum analysis showed no definitive turning point in the TRDG learning curve. Long-term endoscopic findings revealed similar results in the two groups, but bile reflux at 5 years showed significantly better improvement in the TLDG group than in the TRDG group (P=0.016). Conclusions: LSGD is feasible in TRDG, with short-term and long-term outcomes comparable to that in TLDG. LSGD may be a good option for intracorporeal Billroth I anastomosis in patients undergoing TRDG.

• School Mathematics
• /
• v.5 no.3
• /
• pp.361-384
• /
• 2003

The purpose of this study was to investigate students' problem solving process based on the model of IDEAL if they learn to solve word problems of simultaneous linear equations through structure-representation instruction. The problem solving model of IDEAL is followed by stages; identifying problems(I), defining problems(D), exploring alternative approaches(E), acting on a plan(A). 160 second-grade students of middle schools participated in a study was classified into those of (a) a control group receiving no explicit instruction of structure-representation in word problem solving, and (b) a group receiving structure-representation instruction followed by IDEAL. As a result of this study, a structure-representation instruction improved word-problem solving performance and the students taught by the structure-representation approach discriminate more sharply equivalent problem, isomorphic problem and similar problem than the students of a control group. Also, students of the group instructed by structure-representation approach have less errors in understanding contexts and using data, in transferring mathematical symbol from internal learning relation of word problem and in setting up an equation than the students of a control group. Especially, this study shows that the model of direct transformation and the model of structure-schema in students' problem solving process of I and D stages.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.11 no.8
• /
• pp.3984-4005
• /
• 2017

Image recognition has become an increasingly important topic for its wide application. It is highly challenging when facing to large-scale database with large variance. The recognition systems rely on a key component, i.e. the low-level feature or the learned mid-level feature. The recognition performance can be potentially improved if the data distribution information is exploited using a more sophisticated way, which usually a function over hidden variable, model parameter and observed data. These methods are called generative score space. In this paper, we propose a discriminative extension for the existing generative score space methods, which exploits class label when deriving score functions for image recognition task. Specifically, we first extend the regular generative models to class conditional models over both observed variable and class label. Then, we derive the mid-level feature mapping from the extended models. At last, the derived feature mapping is embedded into a discriminative classifier for image recognition. The advantages of our proposed approach are two folds. First, the resulted methods take simple and intuitive forms which are weighted versions of existing methods, benefitting from the Bayesian inference of class label. Second, the probabilistic generative modeling allows us to exploit hidden information and is well adapt to data distribution. To validate the effectiveness of the proposed method, we cooperate our discriminative extension with three generative models for image recognition task. The experimental results validate the effectiveness of our proposed approach.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.18 no.3
• /
• pp.360-366
• /
• 2008

The initial fuzzy partitions in fuzzy rule-based classification systems are determined by considering the domain region of each attribute with the given data, and the optimal classification boundaries within the fuzzy partitions can be discovered by tuning their parameters using various learning processes such as neural network, genetic algorithm, and so on. In this paper, we propose a selection method for fuzzy partition based on statistical information to maximize the performance of pattern classification without learning processes where statistical information is used to extract the uncertainty regions (i.e., the regions which the classification boundaries in pattern classification problems are determined) in each input attribute from the numerical data. Moreover the methods for extracting the candidate rules which are associated with the partition intervals generated by statistical information and for minimizing the coupling problem between the candidate rules are additionally discussed. In order to show the effectiveness of the proposed method, we compared the classification accuracy of the proposed with those of conventional methods on the IRIS and New Thyroid Cancer data. From experimental results, we can confirm the fact that the proposed method only considering statistical information of the numerical patterns provides equal to or better classification accuracy than that of the conventional methods.

• Journal of Digital Convergence
• /
• v.17 no.3
• /
• pp.227-234
• /
• 2019

The purpose of this study is to present a block type smart classroom model for comprehensive supply of educational contents, classroom environment and ICT technology in African countries where educational infrastructure is weak. It will provide a contextual solution that integrates learning management, power management, and classroom environment management systems, and will be a convergence model that can optimize economic and non-economic conditions for different African countries. It can be expected to enhance utilization as it is a differentiated model from existing classrooms with a single container, as well as independent research and development centered on services, content, and solutions. Through this integrated research process, we can overcome the spatial and functional limitations appearing in single container classrooms and build a flexible space for advanced e-learning technology. The depth and scope of the follow-up study can be carried by investigating the performance and models that are in line with the educational and infrastructure conditions of the various regions.

• Composite Materials and Engineering
• /
• v.3 no.3
• /
• pp.201-220
• /
• 2021

In this study, potential of three machine learning techniques i.e., M5P, Support vector machines and Gaussian processes were evaluated to find the best algorithm for the prediction of flexural strength of concrete mix with steel fibre. The study comprises the comparison of results obtained from above-said techniques for given dataset. The dataset consists of 124 observations from past research studies and this dataset is randomly divided into two subsets namely training and testing datasets with (70-30)% proportion by weight. Cement, fine aggregates, coarse aggregates, water, super plasticizer/ high-range water reducer, steel fibre, fibre length and curing days were taken as input parameters whereas flexural strength of the concrete mix was taken as the output parameter. Performance of the techniques was checked by statistic evaluation parameters. Results show that the Gaussian process technique works better than other techniques with its minimum error bandwidth. Statistical analysis shows that the Gaussian process predicts better results with higher coefficient of correlation value (0.9138) and minimum mean absolute error (1.2954) and Root mean square error value (1.9672). Sensitivity analysis proves that steel fibre is the significant parameter among other parameters to predict the flexural strength of concrete mix. According to the shape of the fibre, the mixed type performs better for this data than the hooked shape of the steel fibre, which has a higher CC of 0.9649, which shows that the shape of fibers do effect the flexural strength of the concrete. However, the intricacy of the mixed fibres needs further investigations. For future mixes, the most favorable range for the increase in flexural strength of concrete mix found to be (1-3)%.