• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2008.05a
• /
• pp.329-336
• /
• 2008

Nowadays with advancement in technology and aging society, the number of disabled citizens is increasing. The disabled citizens always need a caretaker for daily life routines especially for mobility. In future, the need is considered to increase more. To reduce the burden from the disabled, various devices for healthcare are introduced using computer technology. The power wheelchair is an important and convenient mobility device. The demand of power wheelchair is increasing for assistance in mobility. In this paper we proposed a robotic wheelchair for mobility aid to reduce the burden from the disabled. The main issue in an autonomous wheelchair is the automatic detection and avoidance of obstacles and going to the pre-designated place. The proposed algorithm detects the obstacles and avoids them to drive the wheelchair to the desired place safely. By this way, the disabled will not always have to worry about paying deep attention to the surroundings and his path.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2002.05a
• /
• pp.28-31
• /
• 2002

본 논문에서는 자율 이동 로봇의 학습을 위해 신경망과 진화 알고리즘을 이용한 방법을 제안한다. 이것은 자연계의 생물이 진화와 학습을 통해 환경에 적응해 나가는 방식과 유사하다. 또한 본 논문에서는 행동기반 제어 방법인 포섭구조를 이용해 로봇의 행동을 제어하는 방법을 제안한다 포섭 구조는 행동 규칙을 병렬적으로 모듈화 하여 낮은 레벨에서는 기본적인 행동을 담당하고, 높은 레벨에서는 좀 더 복잡한 행동을 담당하는 구조로 되어있다 따라서 각 행동 레벨이 협조를 함으로써 복잡한 임무를 수행할 수 있다. 포섭 구조에서 각 레벨의 제어기는 신경 망으로 구성하며 각 행동 레벨이 서로 영향을 주고받으며 진화함으로써 주어진 임무를 달성하도록 한다. 제안된 방법은 자율 이동 로봇인 Khepera 로봇을 이용해 실제 환경에서 구현함으로서 그 유효성을 입증한다.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2002.12a
• /
• pp.235-238
• /
• 2002

본 논문에서는 자율 이동 로봇의 학습을 위해 신경망과 진화 알고리즘을 이용한 방법을 제안하고 또한 행동기반 제어 방법인 포섭구조를 이용해 로봇의 행동을 제어하는 방법을 제안한다. 포섭 구조는 기존의 Al방법과는 달리 행동 규칙을 병렬적으로 모듈화 하여 낮은 레벨에서는 기본적인 행동을 담당하고, 높은 레벨에서는 좀 더 복잡한 행동을 담당하는 구조로 되어있다. 따라서 각 행동 레벨이 협조를 함으로써 복잡한 임무를 수행할 수 있다 포섭 구조에서 각 레벨의 제어기는 신경망으로 구성하며 각 행동 레벨이 서로 영향을 주고받으며 진화함으로써 주어진 임무를 달성하도록 한다 제안된 방법은 자율 이동 로봇인 Khepera 로봇의 시뮬레이션을 통해 결과의 효율성을 입증한다.

• Journal of the Korean Institute of Telematics and Electronics T
• /
• v.36T no.1
• /
• pp.58-63
• /
• 1999

In this paper, We present a direction indicator algorithm for a mobile robot which uses VFF and neural networks. The structure of this neural network navigation system is composed of sensor system, backpropagation learning controllers for adjusting weight and the motion control system for real-time execution. The experimental results show that the direction indicator system operates properlv and strongly at any circumstance

• Journal of the Korean Institute of Intelligent Systems
• /
• v.15 no.1
• /
• pp.75-80
• /
• 2005

In this paper, a 3-dimensional analysis of magnetic road and a position sensing system for an autonomous vehicle system is described. Especially, a new position sensing system, end of the important component of an autonomous vehicle, is proposed. In a magnet based autonomous vehicle system, to sense the vehicle position, the sensor measures the field of magnetic road. The field depends on the sensor position of the vehicle on the magnetic road. As the rotation between the magnetic field and the sensor position is highly complex, it is difficult that the relation is stored in memory. Thus, a neural network is used to learn the mapping from th field to the position. The autonomous vehicle system with the proposed position sensing system is tested in experimental setup.

• Journal of the Korean Applied Science and Technology
• /
• v.35 no.2
• /
• pp.445-453
• /
• 2018

The purpose of this study was to analyze the effect of acute respiratory training feedback upon a change on HRV-Autonomic nervous system in middle-aged women. The research subjects were totally 24 middle-aged women(40-60 years old), were randomly allocated 12 people to the respiratory training group and 12 people to the control group, and then were carried out the acute respiratory training. The feedback exercise in the respiratory training group was conducted for totally 15 minutes. Following the 10-minute breath awareness training according to the expert's guidance, the 5-minute autonomous breathing exercise was implemented. The data analysis was carried out Repeated Measures ANOVA with SPSS WIN 20.0. The conclusions that were obtained through this are as follows. The middle-aged women got significantly higher in SDNN, RMSSD, LF, HF after the acute respiratory training. Compared to the control group. the respiratory training group was indicated to have gotten higher significantly in SDNN, RMSSD, LF, HF. Mean HR and LF/HF were not shown a significant difference in both the main effect of group & period and the interaction effect of group & period. Above of a result the acute respiratory training feedback is effective for SDNN, RMSSD, sympathetic activity, parasympathetic activity in the middle-aged women. Thereby, the respiratory training program improves autonomic nervous system, being considered to be possibly expected the effective value of exercise intervention available for relieving stress and recovering autonomic dysfunction in the middle-aged women.

• Journal of the Korean Institute of Illuminating and Electrical Installation Engineers
• /
• v.21 no.7
• /
• pp.103-108
• /
• 2007

Neural network is used in many fields of control systems currently. However, It is not easy to obtain input-output pattern when neural network is used for the system of a single feedback controller and it is difficult to get satisfied performance with neural network when load changes rapidly or disturbance is applied. To resolve these problems, this paper proposes a new mode to implement a neural network controller by installing a real object in place of activation function of Neural Network output node. As the Neural Network self adaptive control system is designed in simple structure neural network input-output pattern problem is solved naturally and real tin Loaming becomes possible through general back propagation algorithm. The effect of the proposed Neural Network self adaptive control algorithm was verified in a test of controlling the speed of a A.C. servo motor equipped with a high speed computing capable DSP (TMS320C32) on which the proposed algorithm was loaded.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2017.11a
• /
• pp.839-841
• /
• 2017

일반적으로 자율 주행에 딥러닝을 적용하기 위해서 실제 차량에 관련 장비를 설치하고 테스트 한다. 본 논문에서는 The Open Racing Car Simulator(TORCS)에서 다양한 신경망 구조를 적용하도록 Convolutional Neural Network(CNN)을 통하여 학습 및 테스트할 수 있는 시스템을 제안한다. 가상 환경에서 테스트함으로써 하드웨어를 구매하거나 제작하지 않아도 되며 신경망 구조를 선택후 학습함으로써 다양한 데이터에 적합한 신경망 구조를 적용할 수 있다.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.17 no.1
• /
• pp.105-110
• /
• 2022

Traffic sign recognition plays an important role in solving traffic-related problems. Traffic sign recognition and classification systems are key components for traffic safety, traffic monitoring, autonomous driving services, and autonomous vehicles. A lightweight model, applicable to portable devices, is an essential aspect of the design agenda. We suggest a lightweight convolutional neural network model with residual blocks for traffic sign recognition systems. The proposed model shows very competitive results on publicly available benchmark data.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2000.05a
• /
• pp.245-248
• /
• 2000

In this paper we improve the performance of autonomous mobile robot by induction of reinforcement learning concept. Generally, the system used in this paper is divided into two part. Namely, one is neural-fuzzy and the other is dynamic recurrent neural networks. Neural-fuzzy determines the next action of robot. Also, the neural-fuzzy is determined to optimal action internal reinforcement from dynamic recurrent neural network. Dynamic recurrent neural network evaluated to determine action of neural-fuzzy by external reinforcement signal from environment, Besides, dynamic recurrent neural network weight determined to internal reinforcement signal value is evolved by genetic algorithms. The architecture of propose system is applied to the computer simulations on controlling autonomous mobile robot.