• Journal of the Semiconductor & Display Technology
• /
• v.21 no.4
• /
• pp.121-125
• /
• 2022

This paper deals with the development of a deep-learning-based robot that recognizes various types of stairs and performs a mission to go up to the target floor. The overall motion sequence of the robot is performed based on the ROS robot operating system, and it is possible to detect the shape of the stairs required to implement the motion sequence through rapid object recognition through YOLOv4 and Cuda acceleration calculations. Using the ROS operating system installed in Jetson Nano, a system was built to support communication between Arduino DUE and OpenCM 9.04 with heterogeneous hardware and to control the movement of the robot by aligning the received sensors and data. In addition, the web server for robot control was manufactured as ROS web server, and flow chart and basic ROS communication were designed to enable control through computer and smartphone through message passing.

• Journal of the Korean Operations Research and Management Science Society
• /
• v.29 no.4
• /
• pp.117-134
• /
• 2004

This study suggests a data driven optimization approach, which simulates the models of human learning processes from cognitive sciences. It shows how the human learning processes can be simulated and applied to solving combinatorial optimization problems. The main advantage of using this method is in applying it into problems, which are very difficult to simulate. 'Undecidable' problems are considered as best possible application areas for this suggested approach. The concept of an 'undecidable' problem is redefined. The learning models in human learning and decision-making related to combinatorial optimization in cognitive and neural sciences are designed, simulated, and implemented to solve an optimization problem. We call this approach 'SLO : simulated learning for optimization.' Two different versions of SLO have been designed: SLO with position & link matrix, and SLO with decomposition algorithm. The methods are tested for traveling salespersons problems to show how these approaches derive new solution empirically. The tests show that simulated learning for optimization produces new solutions with better performance empirically. Its performance, compared to other hill-climbing type methods, is relatively good.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.30B no.11
• /
• pp.84-92
• /
• 1993

Calibration of Engine models is a painstaking process but very important for successful application to automotive industry problems. A combined heuristic and machine learning approach has therefore been adopted to improve the efficiency of model calibration. We developed an intelligent calibration program called ICALIB. It has been used on a daily basis for engine model applications, and has reduced the time required for model calibrations from many hours to a few minutes on average. In this paper, we describe the heuristic control strategies employed in ICALIB such as a hill-climbing search based on a state distance estimation function, incremental problem solution refinement by using a dynamic tolerance window, and calibration target parameter ordering for guiding the search. In addition, we present the application of amachine learning program called GID3*for automatic acquisition of heuristic rules for ordering target parameters.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2016.04a
• /
• pp.875-878
• /
• 2016

기존의 스포츠 클라이밍 수업은 지도자가 손과 발의 위치를 일일이 가리키는 방식으로 진행되어 원활한 시연이 이루어지지 못하고 있는 것이 현실이다. 이러한 문제를 해결하기 위해 스포츠 클라이밍 인공 암벽에 올바른 자세로 등반하는 캐릭터 애니메이션을 투사하여 초급자를 위한 등반 자세 학습도구로 활용할 수 있다. 이에 본 연구에서는 이러한 전통적인 클라이밍 등반과 공간증강현실 기반 클라이밍 콘텐츠를 활용한 등반의 근활성도를 측정하고 비교 분석함으로써 그 유용성을 실증적으로 검증하고자 한다.

• Journal of the Korea Society of Computer and Information
• /
• v.21 no.9
• /
• pp.139-147
• /
• 2016

In recent, android application developments have been done widely that intensify smart phone utilization. In this paper, we propose a curriculum that undergraduate students can improve their mobile programming abilities as well as integrate experiences of application development based on android. And also a series of practices to advance their sense of accomplishment are added by offering an opportunity to carry out a real project to use a variety of sensors embedded in smart phone during the course of study. The project is composed of a series of modules for implementing a trekking App that helpful to people who enjoy spending time in outdoors through their favorite activities such as trekking, cycling, and climbing with their own smart phones. Through practical curriculum operation and project implementation, we show that the proposed curriculum is appropriate to a mobile programming education that combine learning and practice.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2019.05a
• /
• pp.423-426
• /
• 2019

본 논문은 진공을 이용한 흡착방식과 바퀴형 이동방식을 사용하는 벽면이동로봇의 구성 및 벽면 균열 검출 알고리즘에 관한 연구로써, 카메라와 함께 임베디드 시스템을 구성하였으며 Convolutional Neural Network를 이용한 머신러닝 알고리즘을 통해 균열을 감지하고 검출된 균열의 영상과 위치정보를 서버(관리자 장치)로 전송하는 통신 환경을 구축하였다. 균열 검출 성능을 검증하기 위해 균열 데이터를 이용하여 실험하고 결과를 제시하였다.

• Journal of the Korean Institute of Landscape Architecture
• /
• v.41 no.2
• /
• pp.69-82
• /
• 2013

The purpose of this study is to evaluate the effect of Dulegil in Bukhansan National Park in dispersing peak climbing hikers, characterize each section of Dulegil and suggest ideas of improvement. This study was conducted based on the survey completed by visitors in all 21 sections of Dulegil. After the construction of Dulegil, the number of visit to Dulegil grew and it was analyzed that Dulegil attracted new visitors given that the rate of young people(aged 19~30) who visited for the first time was quite high. Regarding the frequency of peak climbing, 7.6% of the respondents said "decreased" and 46.2% said "increased", showing that Dulegil's effect to disperse peak climbing hikers is nominal. Seven qualities were evaluated regarding Dulegil's level of satisfaction. Out of those seven, the quality of recreational place and taking a walk achieved high scores of 3.74 and 3.61 respectively. The quality of culture and history scored the lowest with 3.09. The analysis on the characteristic of each section of Dulegil, reason of visit, and the visitors' level of satisfaction showed that Dulegil is now regarded as a place where they can improve their health through light exercise and walking. In addition, a positive effect can be expected for a long time since there are different ways of utilizing the resources of the National Park, such as getting in touch with nature, preserving ecology, learning history and enjoying beautiful landscapes. If infrastructure and programs specific to each section of Dulegil were improved in a long-term perspective, it would be effective to encourage peak climbers and enjoy the lower parts of the mountain.

• The Transactions of the Korea Information Processing Society
• /
• v.3 no.7
• /
• pp.1773-1780
• /
• 1996

KBANN (knowledge-based artificial neural network) combining the symbolic approach and the numerical approach has been shown to be more effective than other machine learning models. However KBANN doesn't have the theory refinement ability because the topology of network can't be altered dynamically. Although TopGen was proposed to extend the ability of KABNN in this respect, it also had some defects due to the link-ing of hidden nodes to input nodes and the use of beam search. The algorithm which could solve this TopGen's defects, by adding the hidden nodes linked to next layer nodes and using hill-climbing search with backtracking, is designed.

• The Transactions of the Korea Information Processing Society
• /
• v.4 no.11
• /
• pp.2780-2785
• /
• 1997

Although KBANN(knowledge-based artificial neural network) has been shown to be more effective than other machine learning algorithms, KBANN doesn't have the theory refinement capability because the topology of the network can't be altered dynamically. Although TopGen algorithm was proposed to extend the ability of KABNN in this respect, it also had some defects due to the connection of hidden nodes from all input nodes and the use of beam search. An algorithm, which could solve this TopGen's defects by adding the hidden nodes connected from only related input nodes and using hill-climbing search with backtracking, is proposed.

• Journal of Advanced Navigation Technology
• /
• v.25 no.1
• /
• pp.115-123
• /
• 2021

Pine nuts are Korea's representative nut forest products and profitable crops. However, pine nuts are harvested by climbing the trees themselves, thus the risk is high. In order to solve this problem, it is necessary to harvest pine nuts using a robot or an unmanned aerial vehicle(UAV). In this paper, we propose a deep learning based detection method for harvesting pine nut in UAV aerial images. For this, a video was recorded in a real pine forest using UAV, and a data augmentation technique was used to supplement a small number of data. As the data for 3D detection, Unity3D was used to model the virtual pine nut and the virtual environment, and the labeling was acquired using the 3D transformation method of the coordinate system. Deep learning algorithms for detection of pine nuts distribution area and 2D and 3D detection of pine nuts objects were used DeepLabV3+, YOLOv4, and CenterNet, respectively. As a result of the experiment, the detection rate of pine nuts distribution area was 82.15%, the 2D detection rate was 86.93%, and the 3D detection rate was 59.45%.