• Proceedings of the Korean Society of Computer Information Conference
• /
• 2021.07a
• /
• pp.477-480
• /
• 2021

본 논문에서는 딥러닝 기술을 활용한 객체 검출(object detection) 모델인 YOLO를 기반으로 하는 감정에 따른 표정 인식 시스템을 활용하여 상담 시 보조 도구로 사용하는 방법을 제공한다. 또한, 머신러닝 기술 기반의 툴킷인 dlib 라이브러리를 사용하여 마스크 착용자의 눈 형태 관측을 통한 표정 인식 및 감정 분석의 정확도 상승을 도모하였다. 이 기술은 코로나19의 장기화로 온라인 수업이나 화상회의를 지원하는 플랫폼들이 전성기를 누리고 있는 현시점에서 다양한 분야로 확장할 수 있을 것으로 기대한다.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2021.01a
• /
• pp.171-172
• /
• 2021

현재까지 항공기에 적용되는 기술들은 수많이 발전해왔다. 조종사의 편의성을 위한 기술들 또한 많이 발전해왔다. 자동운항 등 많은 기술들이 조종사를 보조하며 편의성을 위해 사용되고 있다. 하지만 비행기가 처음 만들어 졌을 때부터 바뀌지 않은 조종의 방식과 항공기의 국제성이 가지는 장시간의 비행은 여전히 조종사에게는 큰 피로를 안겨주고 있다. 본 논문은 조종사들의 피로를 경감 시켜 피로로 인해 발생 할 수 있는 사고들을 예방하기 위해 음성인식을 적용하여 새로운 조종의 방식인 '음성인식을 통한 항공기 조종면의 제어' 기술을 제안한다. 기존의 손을 사용한 조종방식이 아닌 컴퓨터와 조종사의 대화를 통해 데이터를 처리하고 즉각적인 피드백을 받으며 조종사의 편의성을 증가시켜 나아가 피로를 경감 시킬 수 있다.

• Korean Journal of Child Studies
• /
• v.32 no.4
• /
• pp.1-14
• /
• 2011

The purpose of this study was to investigate young children's perceptions of a teacher assistant robot, IrobiQ. in a kindergarten classroom. The subjects of this study were 23 6-year-olds attending to G kindergarten located in E city, Korea, where the teacher assistant robot had been in operation since Oct. 2008. Each child responded to questions assessing the child's perceptions of IrobiQ's identity regarding four domains : it's biological, intellectual, emotional and social identity. Some questions asked the child to affirm or deny some characteristics pertaining to the robot and the other questions asked the reasons for the answer given. The results indicated that while majority of children considered an IrobiQ not as a biological entity, but as a machine, they thought it could have an emotion and be their playmate. The implications of these results are two folds : firstly, they force us to reconsider the traditional ontological categories regarding intelligent service robots to understand human-robot interaction and secondly, they open up an ecological perspective on the design of teacher assistant robots for use with young children in early childhood education settings.

• Journal of IKEEE
• /
• v.19 no.2
• /
• pp.148-154
• /
• 2015

Automotive electronics system must alarm accurately in every moment. In order to apply vehicle's image recognition algorithms, it is necessary to preprocess the system quickly. In this paper, blurred image correction method that utilizes histogram equalization and bilateral filter using deviation for driver assist system's image processing is proposed. It forms 5-stage processes namely scaler, equalization, modified noise filter, blur decision and edge detector. Using the extracted proper, values in bilateral filter for driving environment occurred driver assist system, the proposed algorithm is much faster processing time compare to the previous methods in blurred within 10 pixel. Results of experiment which are run time and experimental PSNR results using MATLAB is obtained and verified that our proposed algorithm is more faster performance compare with the existing methods.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.17 no.1
• /
• pp.49-58
• /
• 2022

With the recent start of the 4th Industrial Revolution, markets related to autonomous driving are rapidly developing. In order to understand the rapidly developed technology trend of autonomous driving technology, we would like to investigate the characteristics and differences of level 0 to level 5 of autonomous driving. The overall configuration, recognition technology, and auxiliary technologies of autonomous vehicles are analyzed, and through this, the structure and algorithm of autonomous driving technology are identified. In addition, by manufacturing a simulated autonomous RC car using an ultrasonic sensor and a camera, the necessity of recognition technology and auxiliary technology is identified.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2022.01a
• /
• pp.39-40
• /
• 2022

최근 전동 킥보드, 전동휠, 전기 자전거 등 개인형 이동수단(Personal Mobility)의 보급이 늘면서 관련 인명 교통사고가 급증하고 있다. 본 논문에서는 개인형 이동수단의 사용위험 및 사고 감소를 목적으로, 딥러닝 객체탐지 기술을 적용하여 다양한 위험요소를 증강현실 기술을 기반으로 한 HMD(Helmet mounted display)에 표시하는 '딥러닝 객체 인식과 증강현실을 적용한 개인 이동장치를 위한 HMD(Helmet Mounted Display) 어플리케이션'을 설계한다. 제시하는 방법은 실시간으로 수집된 전방의 실시간 영상 정보를 객체 탐지 알고리즘을 통해 위험요소 및 안전한 주행을 보조하는 객체를 감지하고 증강현실을 적용해 사용자에게 적절한 운전 보조장치 및 기능을 제공한다.

• Journal of rehabilitation welfare engineering & assistive technology
• /
• v.5 no.1
• /
• pp.17-25
• /
• 2011

This paper aims to find the optimal control gain for enhancing the convenience of electric walking frames and design a control algorithm. With the recent advances in medical technology, there has been a rapid increase in the aging population and a variety of mobile walking frames have been developed for improvement of the quality of life. However, the manual walking frames of such mobile aids don't have any electric motor which helps facilitate elderly users' walking and thus are not efficient enough for the old people of weak strength to use especially when moving on uneven surfaces such as slopes or thresholds. The types of electric walking frames have been developed to overcome such inefficiency. Electric walking frames require users' control operations for motor driving unlike manual frames. Therefore, when they are not properly handled, it causes considerable inconvenience to their users. The present study compared the electric walking frames with manual ones in terms of operational convenience and attempted to improve the user convenience of walking frames varying the control value for user convenience based on certain standards. This paper presented a haptic sensor designed to recognize the will to walk and measure the degree of convenience and proposed a control algorithm for improvement of convenience. For user convenience, this paper evaluated the relative convenience of walking frames in view of changing differences between the center of vehicle (COV) and the center of position (COP). With the employment of an electric walking frame and a new measuring method, all the processes were experimentally tested and validated.

• The Journal of Korean Association of Computer Education
• /
• v.9 no.2
• /
• pp.79-88
• /
• 2006

This study investigated the effects of computer-assisted instruction adapting to the level of students' conceptual understanding upon students' conceptual understanding, retention of conceptions, learning motivation, and perception about computer-assisted instruction in concept learning. 94 seventh grade students from a coed middle school in Seoul were randomly assigned to control, CAI, adaptive CAI groups, and were taught about 'motion of molecules' for 7 class periods. Two-way ANCOVA results revealed that the scores of a conception test and a learning motivation test for the adaptive CAI group were significantly higher than those for the control group. The scores of a retention test of conceptions for the adaptive CAI group were significantly higher than those for other two groups. There were no significant interactions between the instruction and the level of previous achievement in the scores of the conception test, the learning motivation test, and the retention test of conceptions. The perception about computer-assisted instruction for the students of the adaptive CAI group were more positive than those for the students of the CAI group.

• Journal of the Institute of Electronics Engineers of Korea TC
• /
• v.42 no.6 s.336
• /
• pp.23-32
• /
• 2005

This paper proposes a new algorithm for the energy constraint ad-hoc network which efficiently spread the energy usage over the network through the backup route scheme in order to increase the network lifetime. Recently, the various energy-efficient routing algorithms based on On-demanding method are proposed. Among them, PSR(Power-aware Source Routing) increased the network lifetime through the periodical route alternation depended on the use of the battery while DSR(Dynamice Source Routing) uses only the route selected during the route discovery phase. But PSR has a problem that it increases the route overhead because of the frequent flooding for the route alternation. For solving this problem, we propose HPSR(Hierarchical Power-aware Source Routing) which uses the backup route set during the route discovery in order to alternation the route without the flooding. HPSR increases the network lifetime due to the frequent route alternation using backup route while it decreases the routing overhead due to the reduced flooding. In this paper, we also prove the performance of HPSR through the simulation using OPNET.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.16 no.6
• /
• pp.1355-1362
• /
• 2021

Recently, not only congenital hearing impairment, but also the number of people with hearing impairment due to acquired factors is increasing. The environment in which sign language can be learned is poor. Therefore, this study intends to present a sign language (sign language number/sign language text) evaluation system as a sign language learning assistance tool for sign language learners. Therefore, in this paper, sign language is captured as an image using OpenCV and Convolutional Neural Network (CNN). In addition, we study a system that recognizes sign language behavior using MediaPipe, converts the meaning of sign language into text-type data, and provides it to users. Through this, self-directed learning is possible so that learners who learn sign language can judge whether they are correct dez. Therefore, we develop a sign language learning assistance system that helps us learn sign language. The purpose is to propose a sign language learning assistance system as a way to support sign language learning, the main language of communication for the hearing impaired.