• Proceedings of the KIEE Conference
• /
• 1998.07g
• /
• pp.2189-2192
• /
• 1998

The objective of this paper is, based upon the principles of artificial life, to induce emergent behaviors of multiple autonomous mobile robots which form from simple local rules to complex global intelligence. Here, we propose an architecture of neural network learing with reinforcement signals which perceives the neighborhood information and decides the direction and the velocity of movement as mobile robots navigates in a group. As results of the simulations, the optimum weights are obtained in real time, which not only prevent from the collisions between agents and obstacles in the dynamic environment, but also have the mobile robots move and keep in various patterns.

• Proceedings of the Korean Information Science Society Conference
• /
• 2005.07b
• /
• pp.676-678
• /
• 2005

디지털 비디오에 있어서 멀티미디어 데이터베이스 및 검색 시스템 구축을 하기 위해서는 비디오를 여러개의 장면으로 분할하는 기술이 요구된다. 본 논문에서는 다양한 종류의 장면 전환을 검출하기 위해 기존의 규칙기반이 아닌 신경망 이론을 접목하여 자율학습과 실수값 입력이 가능한 ART2를 이용하였다. 매프레임마다 발생할 수 있는 변동의 폭을 줄이기 위해 MPEG 동영상의 DC에 해당하는 값만을 이용하고, 프레임마다 색상의 분산값을 이용하여 Plateaus 구간을 검출한 다음 Plateaus 구간에 해당하는 프레임들에 대해서만 프레임차이, 히스토그램차이, 상관계수 등의 특징치를 추출하여 ART2에 특징벡터를 입력하여 장면 전환을 검출하였다.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.16 no.3
• /
• pp.259-265
• /
• 2006

Learning and emotions are very important parts to implement intelligent robots. In this paper, we implement intelligent virtual character based on reinforcement learning which interacts with user and have internal emotion model. Virtual character acts autonomously in 3D virtual environment by internal state. And user can learn virtual character specific behaviors by repeated directions. Mouse gesture is used to perceive such directions based on artificial neural network. Emotion-Mood-Personality model is proposed to express emotions. And we examine the change of emotion and learning behaviors when virtual character interact with user.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.13 no.3
• /
• pp.1091-1098
• /
• 2012

From the perspective of risk management, financial organization that have issued ELW require an efficient hedging methodology due to recently increased trade volume of ELW. This study presents an ELW hedging methodology using artificial neural network(ANN) to minimize hedging costs. The performance of the presented methodology in this study is examined by analysis utilizing the prices and volatilities of underlying assets, risk free interest rates, and maturities and computational experiments show that the proposed method is superior to existing dynamic delta hedging(DDH) technique in terms of hedging costs ranged from 25% to 250%.

• Journal of the Korean Institute of Illuminating and Electrical Installation Engineers
• /
• v.23 no.2
• /
• pp.103-107
• /
• 2009

PI controller is widely used as voltage control system of generator. However when a generator system has various characters of continuance, a new PI parameter decision for accurate control is a hard task as method of solving this problem, in this paper, the method to generator voltage control using Neural Network self adaptive control is presented. A property continuous feedback control gain of voltage control system is decided by a rule of delta learning. The function of proposed control method is verified by voltage control experiment results of DC generator.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.12 no.2
• /
• pp.712-717
• /
• 2011

Option issuers generally utilize Dynamic Delta Hedging(DDH) technique to avoid the risk resulting from continuously changing option value. DDH duplicates payoff of option position by adjusting hedge position according to the delta value from Black-Scholes(BS) model in order to maintain risk neutral state. DDH, however, is not able to guarantee optimal hedging performance because of the weaknesses caused by impractical assumptions inherent in BS model. Therefore, this study presents a methodology for dynamic option hedge using artificial neural network(ANN) to enhance hedging performance and show the superiority of the proposed method using various computational experiments.

• Journal of Broadcast Engineering
• /
• v.24 no.4
• /
• pp.573-579
• /
• 2019

To achieve fully autonomous driving, the perceptual skills of the surrounding environment must be superior to those of humans. The $60^{\circ}$ angle, $120^{\circ}$ wide angle cameras, which are used primarily in autonomous driving, have their disadvantages depending on the viewing angle. This paper uses a multi-angle object recognition system to overcome each of the disadvantages of wide and narrow-angle cameras. Also, the aspect ratio of data acquired with wide and narrow-angle cameras was analyzed to modify the SSD(Single Shot Detector) algorithm, and the acquired data was learned to achieve higher performance than when using only monocular cameras.

• Journal of Internet Computing and Services
• /
• v.23 no.2
• /
• pp.53-59
• /
• 2022

After the 3rd level autonomous driving vehicle, the 4th and 5th level of autonomous driving technology is trying to maintain the optimal condition of the passengers as well as the perfect driving of the vehicle. However current autonomous driving technology is too dependent on visual information such as LiDAR and front camera, so it is difficult to fully autonomously drive on roads other than designated roads. Therefore this paper proposes a Braking Strength Calculation System (BSCS), in which a vehicle classifies road conditions using data other than visual information and calculates optimal braking strength according to road conditions and driving conditions. The BSCS consists of RCDM (Road Condition Definition Module), which classifies road conditions based on KNN algorithm, and BSCM (Braking Strength Calculation Module), which calculates optimal braking strength while driving based on current driving conditions and road conditions. As a result of the experiment in this paper, it was possible to find the most suitable number of Ks for the KNN algorithm, and it was proved that the RCDM proposed in this paper is more accurate than the unsupervised K-means algorithm. By using not only visual information but also vibration data applied to the suspension, the BSCS of the paper can make the braking of autonomous vehicles smoother in various environments where visual information is limited.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2018.11a
• /
• pp.84-86
• /
• 2018

요즘 자율주행과 같은 최신 기술의 발전과 더불어 촬영된 영상 장면에 대한 깊이있는 이해가 필요하게 되었다. 특히, 기계학습 기술이 발전하면서 카메라로 찍은 영상에 대한 의미론적 분할 기술에 대한 연구도 활발히 진행되고 있다. FuseNet은 인코더-디코더 구조를 이용하여 장면 내에 있는 객체에 대한 의미론적 분할 기술을 적용할 수 있는 신경망 모델이다. FuseNet은 오직 RGB 입력을 받는 기존의 FCN보다 깊이정보까지 활용하여 RGB 정보를 기반으로 추출한 특징지도와의 요소합 연산을 통해 멀티 모달 구조를 구현했다. 의미론적 분할 연구에서는 객체의 전역 컨텍스트가 고려되는 것이 중요한데, 이를 위해 여러 계층을 깊게 쌓으면 연산량이 많아지는 단점이 있다. 이를 극복하기 위해서 기존의 합성곱 방식을 벗어나 새롭게 제안된 팽창 합성곱 연산(Dilated Convolution)을 이용하면 객체의 수용 영역이 효과적으로 넓어지고 연산량이 적어질 수 있다. 본 논문에서는 컨볼루션 연산의 새로운 방법론적 접근 중 하나인 팽창된 합성곱 연산을 이용해 의미론적 분할 연구에서 새로운 멀티 모달 네트워크의 성능 향상 방법을 적용하여 계층을 더 깊게 쌓지 않더라도 파라미터의 증가 없이 해상도를 유지하면서 네트워크의 전체 성능을 향상할 수 있는 최적화된 방법을 제안한다.

• Journal of Internet Computing and Services
• /
• v.22 no.2
• /
• pp.59-68
• /
• 2021

As artificial intelligence(AI) technologies, which have made rapid growth recently, began to be applied to the marine environment such as ships, there have been active researches on the application of CNN-based models specialized for digital videos. In E-Navigation service, which is combined with various technologies to detect floating objects of clash risk to reduce human errors and prevent fires inside ships, real-time processing is of huge importance. More functions added, however, mean a need for high-performance processes, which raises prices and poses a cost burden on shipowners. This study thus set out to propose a method capable of processing information at a high rate while maintaining the accuracy by applying Quantization techniques of a deep learning model. First, videos were pre-processed fit for the detection of floating matters in the sea to ensure the efficient transmission of video data to the deep learning entry. Secondly, the quantization technique, one of lightweight techniques for a deep learning model, was applied to reduce the usage rate of memory and increase the processing speed. Finally, the proposed deep learning model to which video pre-processing and quantization were applied was applied to various embedded boards to measure its accuracy and processing speed and test its performance. The proposed method was able to reduce the usage of memory capacity four times and improve the processing speed about four to five times while maintaining the old accuracy of recognition.