• Proceedings of the Korean Society of Computer Information Conference
• /
• 2021.07a
• /
• pp.539-540
• /
• 2021

본 논문에서는 랜덤 생성 알고리즘을 도입한 디펜스 게임을 제안한다. 기존의 디펜스 게임은 지형물의 변형 및 확장이 불가능하다. 그것에 착안하여 지형물들의 위치가 랜덤으로 생성되는 시스템을 도입하였다. 본 게임은 지형물이 랜덤으로 생성되지만, 난이도에 따라 연속적으로 생성될 수 있는 지형물의 개수를 차별화하고, 사용자가 추가로 설치할 수 있는 지형물의 개수에 제한을 두었다. 또한 조작 가능한 캐릭터를 생성해 적을 공격할 수 있게 구현하여 사용자의 몰입도를 높여줄 것으로 기대한다.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2020.01a
• /
• pp.15-18
• /
• 2020

특정 영화의 스크린 독과점이 꾸준히 논란이 되고 있다. 본 논문에서는 영화 스크린 분배의 불평등성을 지적하고 이에 대한 개선을 요구할 근거로 머신러닝 기법을 활용한 영화 관람객 예측 모델을 제안한다. 이에 따라 KOBIS, 네이버 영화, 트위터, 구글 트렌드에서 수집한 3,143개의 영화 데이터를 이용하여 랜덤포레스트와 그라디언트 부스팅 기법을 활용한 영화 관람객 예측 모델을 구현하였다. 모델 평가 결과, 그라디언트 부스팅 모델의 RMSE는 600,486, 랜덤포레스트 모델의 RMSE는 518,989로 랜덤포레스트 모델의 예측력이 더 높았다. 예측력이 높았던 랜덤포레스트 모델을 활용, 상영관을 크게 확보하지 못 했던 봉준호 감독의 영화 '옥자'의 상영관 수를 조절하여 관람객 수를 예측, 6,345,011명이라는 결과를 제시한다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.05a
• /
• pp.692-693
• /
• 2023

ESG 경영이 중요해짐에 따라 기업의 분식 여부도 중요해졌다. 따라서 본 논문에서는 인공신경망과 랜덤포레스트를 활용하여 기업의 분식회계 여부를 판단 성능을 비교분석하고 그 유용성에 대해 평가하였다. 실제 기업 회계정보를 수집하여 실험을 수행하였고, 실험 결과 F1-Score 기준 랜덤포레스트의 RFECV 기법이 0.81로 분식 기업을, SMOTE 기법을 사용한 모델이 정상 기업을 탐지하였고 Accuracy 기준 랜덤포레스트의 RFECV 기법과 SMOTE 기법을 사용한 모델이 0.77로 가장 효과적인 탐지 성능을 보여주었다.

• Proceedings of the IEEK Conference
• /
• 1998.10a
• /
• pp.939-942
• /
• 1998

본 논문에서는 랜덤 시퀀스와 직교코드를 이용하여 비화성이 강한 디지털 정보은폐 방법을 제시하였다.

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.10 no.4
• /
• pp.349-360
• /
• 2008

In this paper, the modeling procedure of random field with an elasto-plastic finite element algorithm and probability of failure on closely-spaced tunnel were investigated. Local average subdivision (LAS) method which can generate discrete random variables fast and accurately as well as change the resolution in certain region was used. And correlated value allocating and weighted average method were suggested to implement geometrical characteristics of tunnel. After the probability of failure on the test problem was thoroughly investigated using random finite element method, the results were compared with the deterministic strength reduction factor method and single random variable method. Of particular importance in this work, is the conclusion that the probability of failure determined by simplified probabilistic analysis, in which spatial variability is ignored by assuming perfect correlation, can be estimated from the safety factor determined by strength reduction factor method. Also, single random variable method can lead to unconservative estimates of the probability of failure.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.19 no.6
• /
• pp.1313-1320
• /
• 2015

In this paper, we propose a user detection technique based on parallel orthogonal matching pursuit (POMP) for uplink multi-user random access networks (RANs) with a number of users and receiver antennas. In general RANs, it is difficult to estimate the number of users simultaneously transmitting packets at the receiver because users with data send the data without grant of BS. In this paper, therefore, we modify the original POMP for the RAN and evaluate its performances through extensive computer simulations. Simulation results show that the proposed POMP can effectively detect activated users more than about 2%~8% compared with the conventional OMP in RANs.

• The Transactions of the Korea Information Processing Society
• /
• v.7 no.8
• /
• pp.2473-2483
• /
• 2000

In this paper, The turbo code is used to effectively remove noise which is generated on the image communication channel. Turbo code had excellent decoding performance. However, it had limitations for real time communication because of the system complexity and time delay in decoding procedure. To overcome this problem, this paper proposed a new SRI(Semi Random Interleaved algorithm, which decrease the time delay, when the image data, which reduced the interleaver size of turbo code encoder and decoder, transmitted. The SRI algorithm was composed of 0.5 interleaver size from input frame sequence. When the data inputs in interleaver, the data recorded by row such as block interleaver. But, When the data read in interleaver, the data was read by randomly and the next data located by the just address simultaneously. Therefore, the SRI reduced half-complexity when it was compared with pre-existing method such as block, helical, random interleaver. The image data could be the real time processing when the SRI applied to turbo code.

• Journal of the Computational Structural Engineering Institute of Korea
• /
• v.30 no.1
• /
• pp.23-30
• /
• 2017

Since shape, size and distribution of particles in particulate composites have spreaded characteristics, properties of particulate composites have variation and also system behavior using particulate composites have variation. However, it is difficult to consider spreaded characteristic of particles so that a system behavior is analysed using homogeneous techniques or using microstructure in local areas. In this study, for considering random variation of particles, RMDFs(random morphology description functions) are used to generate random microstructure and relationship between the number of gaussian functions and spreaded characteristic of particles was analysed using the geometrical moment of area. Also, multi-scale analysis was carried out for cantilever beam with full-random microstructure to study behavior of particulate composites structure. As a result, it is defined that spreaded characteristic of particles and the variation of deflections of cantilever beam are decreased as the number of Gaussian functions(N) is increased and converges at N=200.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.22 no.1
• /
• pp.175-182
• /
• 2018

As Internet of things with a large number of nodes emerges, wireless-power communication networks (WPCN) based on a random access protocol needs to be investigated. In the random access-based WPCN, a terminal accessing later in given random access (RA) slots can harvest more energy before transmission and thus can transmit data with higher power and achieve higher throughput if the access is successful. On the basis of this property, the proposed random access control protocol gives the terminals priority and distinguishes the RA slots according to the priority level, so that a near terminal with access point allows to access preferentially other than a remote terminal. This operation decreases the throughput of near terminal and increases the throughput of remote terminal, and then, the doubly near-far problem in WPCN is resolved and the user fairness is improved. Results show that the proposed random access control improves both channel throughput and user fairness according to the priority level.

• Journal of the Korea Society for Simulation
• /
• v.20 no.3
• /
• pp.19-28
• /
• 2011

Adaptive Random Testing (ART) aims to enhance the performance of pure random testing by detecting failure region in a software. The ART algorithm generates effective test cases which requires less number of test cases than that of pure random testing. However, all ART algorithms currently proposed are designed for the tests of monolithic system or unit level. In case of integrated system tests, ART approaches do not achieve same performances as those of ARTs applied to the unit or monolithic system. In this paper, we propose an extended ART algorithm which can be applied to the integrated system testing environment without degradation of performance. The proposed approach investigates an input distribution of the unit under a test with limited number of seed input data and generates information to be used to resizing input domain partitions. The simulation results show that our approach in an integration environment could achieve similar level of performance as an ART is applied to a unit testing. Results also show resilient effectiveness for various failure rates.