• Journal of the Korea Institute of Military Science and Technology
• /
• v.26 no.4
• /
• pp.352-360
• /
• 2023

Recently, AI pilots using reinforcement learning are developing to a level that is more flexible than rule-based methods and can replace human pilots. In this paper, a curriculum was used to help head-on combat with reinforcement learning. It is not easy to learn head-on with a reinforcement learning method without a curriculum, but in this paper, through the two circle-based head-on air combat learning technique, ownship gradually increase the difficulty and become good at head-on combat. On the two-circle, the ATA angle between the ownship and target gradually increased and the AA angle gradually decreased while learning was conducted. By performing reinforcement learning with and w/o curriculum, it was engaged with the rule-based model. And as the win ratio of the curriculum based model increased to close to 100 %, it was confirmed that the performance was superior.

• Journal of KIBIM
• /
• v.6 no.2
• /
• pp.29-38
• /
• 2016

Road bridges are deteriorating gradually, and it is forecasted that the number of road bridges aging over 30 years will increase by more than 3 times of the current number. To maintain road bridges in a safe condition, current safety conditions of the bridges must be estimated for repair or reinforcement. However, budget and professional manpower required to perform in-depth inspections of road bridges are limited. This study proposes an estimation model for safety rating of road bridges by analyzing the data from Facility Management System (FMS) and Yearbook of Road Bridges and Tunnel. These data include basic specifications, year of completion, traffic, safety rating, and others. The distribution of safety rating was imbalanced, indicating 91% of road bridges have safety ratings of A or B. To improve classification performance, five safety ratings were integrated into two classes of G (good, A and B) and P (poor ratings under C). This rearrangement was set because facilities with ratings under C are required to be repaired or reinforced to recover their original functionality. 70% of the original data were used as training data, while the other 30% were used for validation. Data of class P in the training data were oversampled by 3 times, and Repeated Incremental Pruning to Produce Error Reduction (RIPPER) algorithm was used to develop the estimation model. The results of estimation model showed overall accuracy of 84.8%, true positive rate of 67.3%, and 29 classification rule. Year of completion was identified as the most critical factor on affecting lower safety ratings of bridges.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2003.09a
• /
• pp.224-227
• /
• 2003

The Intrsuion Detecion Systems(IDS) are required the accuracy, the adaptability, and the expansion in the information society to be changed quickly. Also, it is required the more structured, and intelligent IDS to protect the resource which is important and maintains a secret in the complicated network environment. The research has the purpose to build the model for the intelligent IDS, which creates the intrusion patterns. The intrusion pattern has extracted from the vast amount of data. To manage the large size of data accurately and efficiently, the link analysis and sequence analysis among the data mining techniqes are used to build the model creating the intrusion patterns. The model is consist of "Time based Traffic Model", "Host based Traffic Model", and "Content Model", which is produced the different intrusion patterns with each model. The model can be created the stable patterns efficiently. That is, we can build the intrusion detection model based on the intelligent systems. The rules prodeuced by the model become the rule to be represented the intrusion data, and classify the normal and abnormal users. The data to be used are KDD audit data.

• Journal of Digital Convergence
• /
• v.16 no.6
• /
• pp.85-93
• /
• 2018

The Latent Growth Modeling(LGM) is known as the arising analysis method of longitudinal data and it could be classified into unconditional model and conditional model. Unconditional model requires estimated value of intercept and slope to complete a model of fitness. However, the existing LGM is in absence of a structured methodology to estimate slope when longitudinal data is neither simple linear function nor the pre-defined function. This study used Sequential Pattern of Association Rule Mining to calculate slope of unconditional model. The applied dataset is 'the Youth Panel 2001-2006' from Korea Employment Information Service. The proposed methodology was able to identify increasing fitness of the model comparing to the existing simple linear function and visualizing process of slope estimation.

• Water Engineering Research
• /
• v.3 no.1
• /
• pp.57-62
• /
• 2002

This research is intended to integrate long-term operation rules and real time operation policy for conservation & flood control in a reservoir. The familiar Yield model has been modified and used to provide long-term rule curves. The model employs linear programming technique under given physical conditions, i.e., total capacity, dead storage, spillways, outlet capacity and their respective elevations to find required and desired minimum storage fur different demands. To investigate the system behavior resulting from the above-mentioned operating policy, i.e., the rule curves, the simulation model was used. Results of the simulation model show that the results of the optimization model are indeed valid. After confirmation of the above mentioned rule curves by the simulation models, gate operation procedure was merged with the long term operation rules to determine the optimum reservoir operating policy. In the gate operation procedure, operating policy in downstream flood plain, i.e., determination of damaging and non-damaging discharges in flood plain, peak floods, which could be routed by reservoir, are determined. Also outflow hydrograph and variations of water surface levels for two known hydrographs are determined. To examine efficiency of the above-mentioned models and their ability in determining the optimum operation policy, Esteghlal reservoir in Iran was analyzed as a case study. A numerical model fur the solution of two-dimensional dam break problems using fractional step method is developed on unstructured grid. The model is based on second-order Weighted Averaged Flux(WAF) scheme with HLLC approximate Riemann solver. To control the nonphysical oscillations associated with second-order accuracy, TVD scheme with SUPERBEE limiter is used. The developed model is verified by comparing the computational solutions with analytic solutions in idealized test cases. Very good agreements have been achieved in the verifications.

• Information Systems Review
• /
• v.24 no.1
• /
• pp.105-123
• /
• 2022

Thanks to the remarkable success of Artificial Intelligence (A.I.) techniques, a new possibility for its application on the real-world problem has begun. One of the prominent applications is the bankruptcy prediction model as it is often used as a basic knowledge base for credit scoring models in the financial industry. As a result, there has been extensive research on how to improve the prediction accuracy of the model. However, despite its impressive performance, it is difficult to implement machine learning (ML)-based models due to its intrinsic trait of obscurity, especially when the field requires or values an explanation about the result obtained by the model. The financial domain is one of the areas where explanation matters to stakeholders such as domain experts and customers. In this paper, we propose a novel approach to incorporate financial domain knowledge into local rule generation to provide explanations for the bankruptcy prediction model at instance level. The result shows the proposed method successfully selects and classifies the extracted rules based on the feasibility and information they convey to the users.

• Journal of Korea Game Society
• /
• v.9 no.5
• /
• pp.25-41
• /
• 2009

The objective of this study is to develop an analytic framework to code systematically the gamer's behaviour in MMO(Massively Multi-player Online) gameplay experience, to explore their gameplay as a problem solving procedure empirically. Previous studies about model human processor, content based protocol, and procedure based protocol are reviewed in order to build the outline of the analytic framework related to MMO gameplay. The specific gameplay actions and contents were derived by using concurrent protocol analysis method through the empirical experiment executed in MMORPG gameplay. Consequently, gameplay are divided into six actions : kinematics, perception, function, representation, simulation, and rule (heuristics, following, and transcedence). The analytic framework suitable for MMO gameplay was built. As a result of this study, we found three rule spaces in the problem solving domain of gameplay that are an heuristics, a following of the rule, and a transcendence of the rule. 'Heuristics' denotes the rule action that discovers the rule of game through trial-and-error. 'Following' indicates the rule action that follows the rule of game embedded in game by game designers. 'Transcendence' presents the rule action that transcends that. The new discovered rule spaces where 'Following' and 'Transcendence' actions occur and the gameplay pattern in them is provided with the key basis to determine the level design elements of MMO game, such as terrain feature, monster attribute, item, and skill et cetera. Therefore, this study is concludes with key implications to support game design to improve the quality of MMO game product.

• Journal of the Korean Geotechnical Society
• /
• v.16 no.1
• /
• pp.65-73
• /
• 2000

An elasto-plastic constitutive model was proposed, in which the behavior at small-to-large strain level can be modeled. The proposed model is based on the anisotropic hardening description with the generalization of isotropic hardening rule and the total stress concept. From a mathematical approach it was proved that the model includes the previous successful models. The model was verified by a series of resonant column tests, torsional shear tests and triaxial tests, and the proposed model predicted small-to-large strain behavior more consistently and accurately than the hyperbolic model and the Ramberg-Osgood model for a weathered granitic soil. In addition, the nonlinearity under small strain condition was predicted appropriately for the torsional shear test results.

• Journal of the Korea Society of Computer and Information
• /
• v.26 no.4
• /
• pp.93-103
• /
• 2021

Despite the efforts of financial authorities in conducting the direct management and supervision of collection agents and bond-collecting guideline, the illegal and unfair collection of debts still exist. To effectively prevent such illegal and unfair debt collection activities, we need a method for strengthening the monitoring of illegal collection activities even with little manpower using technologies such as unstructured data machine learning. In this study, we propose a classification model for illegal debt collection that combine machine learning such as Support Vector Machine (SVM) with a rule-based technique that obtains the collection transcript of loan companies and converts them into text data to identify illegal activities. Moreover, the study also compares how accurate identification was made in accordance with the machine learning algorithm. The study shows that a case of using the combination of the rule-based illegal rules and machine learning for classification has higher accuracy than the classification model of the previous study that applied only machine learning. This study is the first attempt to classify illegalities by combining rule-based illegal detection rules with machine learning. If further research will be conducted to improve the model's completeness, it will greatly contribute in preventing consumer damage from illegal debt collection activities.

• International Journal of Quality Innovation
• /
• v.8 no.2
• /
• pp.132-146
• /
• 2007

Constructing an effective production control policy is the most important issue in wafer fabrication factories. Most of researches focus on the input regulations of wafer fabrication. Although many of these policies have been proven to be effective for wafer fabrication manufacturing, in practical, there is a need to help operators decide which lots should be pulled in the right time and to develop a systematic way to alleviate the long queues at the bottleneck workstation. The purpose of this study is to construct a photolithography workstation dispatching rule (PADR). This dispatching rule considers several characteristics of wafer fabrication and influential factors. Then utilize the weights and threshold values to design a hierarchical priority rule. A simulation model is also constructed to demonstrate the effect of the PADR dispatching rule. The PADR performs better in throughput, yield rate, and mean cycle time than FIFO (First-In-First-Out) and SPT (Shortest Process Time).