• Journal of the Korea Society of Computer and Information
• /
• v.28 no.12
• /
• pp.23-32
• /
• 2023

E-sports, a burgeoning facet of modern sports culture, has achieved global prominence. Particularly, Aeon of Strife (AOS) games, emblematic of E-sports, blend individual player prowess with team dynamics to significantly influence outcomes. This study aggregates and analyzes real user gameplay data using statistical techniques. Furthermore, it develops and tests win-loss prediction models through machine learning, leveraging a substantial dataset of 1,149,950 individual data points and 230,234 team data points. These models, employing five machine learning algorithms, demonstrate an average accuracy of 80% for individual and 95% for team predictions. The findings not only provide insights beneficial to game developers for enhancing game operations but also offer strategic guidance to general users. Notably, the team-based model outperformed the individual-based model, suggesting its superior predictive capability.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2017.11a
• /
• pp.873-876
• /
• 2017

최근 딥러닝(Deep-learning)을 활용한 기상 예측, 심리 예측, 교통상황 예측 등 다양한 분야에 걸쳐 여러 모델의 인공신경망이 활용되고 있다. 본 논문에서는 여러 분야 중 스포츠라는 분야에 접근했으며, 딥러닝 모델을 통해 승부를 예측하는 실험을 진행하였다. 야구의 승부는 선수의 능력치, 기상의 변화, 험/어웨이 여부, 교체 여부 등 가늠할 수 없이 수많은 데이터들에 의존하고 있다. 그러나 본 논문에서는 이러한 수많은 데이터 중 경기 외적인 데이터를 제외한 데이터를 활용하여 그 다음 경기의 승부를 예측할 수 있을 지를 연구한다. 날짜 별 경기들이 훈련데이터가 되고 목표는 이전 경기들의 영향으로 예측된 다음 경기의 승/패를 예측한다. 즉 순차적인 데이터의 활용에 적합한 모델, Recurrent Neural-Network을 이용하였다. 이를 위하여 KBreport에서 데이터를 수집하였고, 수집된 데이터를 훈련 데이터 세트로 만들어 Recurrent Neural Network를 통해 훈련시켜 다음 경기의 승패를 예측하였다.

• 한국지구과학회:학술대회논문집
• /
• 2005.09a
• /
• pp.112-123
• /
• 2005

자기지전류 탐사의 적용에 있어 인공잡음의 영향은 탐사의 승패를 좌우하는 중요한 요소이며 인공잡음의 영향을 최소화할 수 있는 탐사의 설계와 자료처리가 요구되고 있다. 본 연구에서는 수치공간자료를 이용한 공간모델링을 통해 MT 주파수 대역에서의 잡음을 예측하고 실제 탐사 자료와 비교분석하여 MT 잡음 모델링을 가능성을 살펴보았다. 수치지도로부터 추출된 잡음원일 가능성이 높은 건물, 도로, 고압 송전선에 의해 발생하는 전자기장의 강도를 지하매질의 전기전도도에 따른 전자기파의 전파 특성을 고려하여 예측하는 잡음모델을 제안하였다. 제안된 잡음모델로부터 예측된 잡음 파워와 실제 탐사를 통해 측정된 MT 자료와의 상관도 분석을 수행한 결과, 전반적으로 전기장에서는 넓은 주파수 대역에서 높은 상관관계를 보이는 반면 자기장은 60 Hz 부근의 대역에서만 상관관계를 가진다. 본 연구에서 제안된 공간모델링을 통한 잡음 예측은 특히 고도로 산업화되어가는 도시 주변지역에서의 MT 탐사를 수행하는데 있어 유용한 정보를 제공할 수 있을 것이다.

• The Journal of the Korea Contents Association
• /
• v.22 no.5
• /
• pp.48-56
• /
• 2022

The importance of data analysis in baseball has been increasing after the success of MLB's Oakland which applied Billy Beane's money ball theory, and the 2020 KBO winner NC Dinos. Various studies using data in baseball has been conducted not only in the United States but also in Korea, In particular, the models using deep learning and machine learning has been suggested. However, in the previous studies using deep learning and machine learning, the focus is only on predicting the win or loss of the game, and there is a limitation in that it is difficult to interpret the results of which factors have an important influence on the game. In this paper, to investigate which factors is important by position, the prediction model for the Golden Glove award which is given for the best player by position is developed. To develop the prediction model, XGBoost which is one of boosting method is used, which also provide the feature importance which can be used to interpret the factors for prediction results. From the analysis, the important factors by position are identified.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2018.01a
• /
• pp.241-242
• /
• 2018

야구 관람객들은 주로 자기가 선호하는 팀의 경기나 이길 가능성이 높은 경기를 관람하고자 한다. 때문에 시중에 지난 경기, 당일의 경기, 미래 경기에 대한 정보를 얻을 수 있는 KBO 사이트와 경기 승/패를 예측하기 위한 정보를 얻을 수 있는 사이트에서 경기 기록에 대한 정보를 얻어 관람 일을 결정하는데 도움을 얻는다. 따라서 본 연구에서는 데이터마이닝을 통하여 프로야구 팬들이 특정 팀의 승/패를 예측하는데 사용할 수 있는 유용한 규칙과 패턴을 도출해보고자 한다.

• The Journal of Bigdata
• /
• v.5 no.2
• /
• pp.231-240
• /
• 2020

With the development in the IT industry and the growth in the game industry, user's game data is recorded in seconds according to various plays and options, and a vast amount of game data can be analyzed based on Bigdata. Combined with business, Bigdata is used to discover new values for profit creation in various fields, but it is utilized in the game industry in insufficient ways. In this study, considering the characteristics of the subdivided lines, we constructed a win-loss prediction model for each line using the game data of League of Legends, and derived the importance of variables. This study can contribute to planning of strategies for general game users to get information about team members in advance and increase the win rate by using the record search sites.

• KIPS Transactions on Software and Data Engineering
• /
• v.9 no.5
• /
• pp.161-168
• /
• 2020

Predicting outcome of the sports enables teams to establish their strategy by analyzing variables that affect overall game flow and wins and losses. Many studies have been conducted on the prediction of the outcome of sports events through statistical techniques and machine learning techniques. Predictive performance is the most important in a game prediction model. However, statistical and machine learning models show different optimal performance depending on the characteristics of the data used for learning. In this paper, we propose a new ensemble model to predict English Premier League soccer games using statistical models and the machine learning models which showed good performance in predicting the results of the soccer games and this model is possible to select a model that performs best when predicting the data even if the data are different. The proposed ensemble model predicts game results by learning the final prediction model with the game prediction results of each single model and the actual game results. Experimental results for the proposed model show higher performance than the single models.

• Geophysics and Geophysical Exploration
• /
• v.8 no.4
• /
• pp.251-261
• /
• 2005

The quality of MT (magnetotellurics) data highly depends on the level of artificial noise form industrial sources. We have conducted the feasibility study of MT noise modelling using digital spatial data and spatial modelling through the comparison between the predicted and the measured MT noises. A simple noise model predicting the intensity of electromagnetic field radiated from the latent noise sources, that is, the electric facilities in the building, road and high-voltage powerline, is developed in consideration of the propagation property of electromagnetic waves. From the analysis of correlation between the predicted and the measured noise power, the correlation coefficients of electric field are higher than those of magnetic field in whole frequency band. The magnetic field component has the high correlation in the narrow band near 60 Hz only. The spatial noise modelling proposed in this study would provide some useful informations for the MT surveys in the noisy environment like urban area.

• Korean Journal of Construction Engineering and Management
• /
• v.20 no.5
• /
• pp.104-114
• /
• 2019

This study explored to analyze the winning determinants of the lawsuit cases on the urban and housing redevelopment project based on jurimetric methods. Based on affirm-rate and staircase matrix tables, 441 lawsuit judgments are analyzed. Research findings in affirm-rate analysis indicate that past legal relation, no own defect of accreditation, no ownership or association member status, lapse of period of litigation, and no legal interest are identified as higher rate in order for the reason for plea on the merit. And so are defect on calculation of consent rate, defect in relation with written consent, approval before zoning designation, defect in relation with general meeting, and defect on zoning designation for the issue on the merit. It is noteworthy from the staircase matrix table analysis that the criteria for affecting the lawsuit outcome is determined based on key forecasting variables such as past legal relation and no ownership or association member status. This study intends to provide the implication that the unnecessary disputes can be reduced in the urban and housing redevelopment project by the implementation of jurimetric quantitative analysis methodology from the perspective of empirical law.

• Composites Research
• /
• v.19 no.1
• /
• pp.29-35
• /
• 2006

The avoidance of enemy's radar detection is very important issue in the modem electronic weapon system. Researchers have studied to minimize reflected signals of radar. In this research, two types of radar absorbing structure (RAS), 'C'-type shell and 'U'-type shell, were fabricated using fiber-reinforced composite materials and their radar cross section (RCS) were evaluated. The absorption layer was composed of glass fiber reinforced epoxy and nano size carbon-black, and the reflection layer was fabricated with carbon fiber reinforced epoxy. During their manufacturing process, undesired thermal deformation (so called spring-back) was observed. In order to reduce spring-back, the bending angle of mold was controlled by a series of experiments. The spring-back of parts fabricated by using compensated mold was predicted by finite element analysis (ANSYS). The RCS of RAS shells were measured by compact range and predicted by physical optics method. The measured RCS data was well matched with the predicted data.