• 한국지능시스템학회논문지
• /
• 제14권5호
• /
• pp.617-622
• /
• 2004

본 논문에서는 컬러영상에서 Pulse-Coupled Neural Network를 이용한 얼굴 추출 알고리즘의 성능을 향상시키는 방법에 대하여 논의하였다. 색상정보를 이용한 얼굴 추출 알고리즘은 얼굴의 기울어진 정도나 크기 등에 영향을 받지 않으므로, 형태정보를 이용한 얼굴 추출 알고리즘에 비해 비교우위를 가진다. 그러나, 조명의 변화가 심하거나 피부색과 유사한 배경이 포함되어 있을 경우 적절한 성능을 내기 어렵다. 이러한 문제점들을 해결하기 위해 본 논문에서는 실험을 통해 피부색의 평균과 분산 값을 미리 구한 후, 전처리 과정을 거쳐 피부색의 평균값을 갖는 픽셀이 255값을 갖고, 나머지 픽셀 값들이 255를 중심으로 정규분포를 이루도록 하였다. 이러한 전처리 과정을 통해 Pulse-Coupled Neural Network의 linking coefficient를 보다 쉽게 결정하도록 하였다.

• 한국정보기술학회논문지
• /
• 제16권11호
• /
• pp.11-21
• /
• 2018

본 논문에서는 사람을 대신하여 분류, 예측 하는 딥러닝 기술을 활용하여 목소리를 통해 남녀노소를 분류하는 연구를 수행한다. 연구과정은 기존 신경망 기반의 사운드 분류 연구를 살펴보고 목소리 분류를 위한 개선된 신경망을 제안한다. 기존 연구에서는 도시 데이터를 이용해 사운드를 분류하는 연구를 진행하였으나, 얕은 신경망으로 인한 성능 저하가 나타났으며 다른 소리 데이터에 대해서도 좋은 성능을 보이지 못했다. 이에 본 논문에서는 목소리 데이터를 전처리하여 특징값을 추출한 뒤 추출된 특징값을 기존 사운드 분류 신경망과 제안하는 신경망에 입력하여 목소리를 분류하고 두 신경망의 분류 성능을 비교 평가한다. 본 논문의 신경망은 망을 더 깊고 넓게 구성함으로써 보다 개선된 딥러닝 학습이 이루어지도록 하였다. 성능 결과로는 기존 연구와 본 연구의 신경망에서 각각 84.8%, 91.4%로 제안하는 신경망에서 약 6% 더 높은 정확도를 보였다.

• 반도체디스플레이기술학회지
• /
• 제22권3호
• /
• pp.112-118
• /
• 2023

As technology advances, the need for enhanced preparedness against cyber-attacks becomes an increasingly critical problem. Therefore, it is imperative to consider various circumstances and to prepare for cyber-attack strategic technology. This paper proposes a method to solve network security problems by applying reinforcement learning to cyber-security. In general, traditional static cyber-security methods have difficulty effectively responding to modern dynamic attack patterns. To address this, we implement cyber-attack scenarios such as 'Tiny Alpha' and 'Small Alpha' and evaluate the performance of various reinforcement learning methods using Network Attack Simulator, which is a cyber-attack simulation environment based on the gymnasium (formerly Open AI gym) interface. In addition, we experimented with different RL algorithms such as value-based methods (Q-Learning, Deep-Q-Network, and Double Deep-Q-Network) and policy-based methods (Actor-Critic). As a result, we observed that value-based methods with discrete action spaces consistently outperformed policy-based methods with continuous action spaces, demonstrating a performance difference ranging from a minimum of 20.9% to a maximum of 53.2%. This result shows that the scheme not only suggests opportunities for enhancing cybersecurity strategies, but also indicates potential applications in cyber-security education and system validation across a large number of domains such as military, government, and corporate sectors.

• 한국지하수토양환경학회:학술대회논문집
• /
• 한국지하수토양환경학회 2002년도 총회 및 춘계학술발표회
• /
• pp.106-109
• /
• 2002

In order to delineate the flow system of fractured hard rock aquifer, numerical experiments are conducted and the results are analyzed with Mote Carlo simulation. The results show that the percolation threshold and the effective conductivity of a fracture network can be estimated with power law exponent (a) and fracture intensity. But the dependability of the estimated value relies on the percolation threshold, the system scale, and the characterization level.

• 한국소음진동공학회:학술대회논문집
• /
• 한국소음진동공학회 1998년도 춘계학술대회논문집; 용평리조트 타워콘도, 21-22 May 1998
• /
• pp.548-553
• /
• 1998

The specific noise level of 18 rotary compressor mufflers were measured and these data were analyzed by the Taguchi robust design method and the neural network. The optimal design value obtained by the neural network generally showed good agreement with that by the Taguchi method. The effects of eight important design variables on the specific noise level were discussed.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 1989년도 한국자동제어학술회의논문집; Seoul, Korea; 27-28 Oct. 1989
• /
• pp.124-126
• /
• 1989

Inverse kinematic problem is a crucial point for robot manipulator control. In this paper, to implement the Jacobian control technique we used the Hopfield(Tank)'s neural network. The states of neurons represent joint veocities, and the connection weights are determined from the current value of the Jacobian matrix. The network energy function is constructed so that its minimum corresponds to the minimum least square error. At each sampling time, connection weights and neuron states are updated according to current joint position. Inverse kinematic solution to the planar redundant manipulator is solved by computer simulation.

• Journal of the Korean Statistical Society
• /
• 제32권4호
• /
• pp.359-371
• /
• 2003

We consider the probability that the total population of a stable Jackson network reaches a given large value. By using the fluid limit of the reversed network, we derive new upper and lower bounds on this probability, which are sharper than those in Glasserman and Kou (1995). In particular, the improved lower bound is useful for analyzing the performance of an importance sampling estimator for the overflow probability in Jackson tandem networks. Bounds on the expected time to overflow are also obtained.

• 한국시뮬레이션학회논문지
• /
• 제11권4호
• /
• pp.15-23
• /
• 2002

As recently the network environment and application services have been more complex and diverse, there has. In this paper we introduce a scheme the extract useful information for network management by analyzing traffic data in user login file. For this purpose we use classification and association rule based on episode concept in data mining. Since login data has inherently time series characterization, convertible data mining algorithms cannot directly applied. We generate virtual transaction, classify transactions above threshold value in time window, and simulate the classification algorithm.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2002년도 ICCAS
• /
• pp.103.2-103
• /
• 2002

1. Introduction 2. Structure of BNN 3. Decision of weight value and threshold value 4. Principle of Extension in the ETL algorithm 5. Approximation problem of one circular region 6. Problem of synthetic image having four class 7. Conclusion

• 한국전자거래학회:학술대회논문집
• /
• 한국전자거래학회 2001년도 e-Biz World Conference
• /
• pp.445-455
• /
• 2001

it does not matter who (which nation) owns the company.... what matters is where the greatest value is added in the transnational network. Countries will prosper or stagnate by the skills they inject into these value chains. In the economy of the future, knowledge is king, and influence flows from wherever knowledge resides.(omitted)