• Proceedings of the Korea Information Processing Society Conference
• /
• 2021.11a
• /
• pp.1128-1131
• /
• 2021

COVID-19로 인한 홈 쿠킹 시장 수요 증가로 사람들은 더 편리한 요리 보조 시스템을 필요로 하고 있다. 기존 요리 시스템은 휴대폰, 책을 통해 레시피를 일방적으로 제공하기 때문에 사용자가 요리과정을 중단하고 반복적으로 열람해야 한다는 한계점을 가진다. '대화형 스마트 쿠킹 서비스' 시스템은 요리 과정 전반에서 필요한 내용을 사용자와 상호작용하며 적절하게 인지하고 알려주는 인공지능 시스템이다. Google의 MediaPipe를 사용해 사용자의 관절을 인식하고 모델을 학습시켜 사용자의 요리 동작을 인식하도록 설계했으며, dialogflow를 이용한 챗봇 기능을 통해 필요한 재료, 다음 단계 등의 내용을 실시간으로 제시한다. 또한 실시간 행동 인식으로 요리과정 중 화재, 베임 사고 등의 위험 상황을 감지하여 사용자에게 정보를 전달해줌으로써 사고를 예방한다. 음성인식을 통해 시스템과 사용자 간의 쌍방향적 소통을 가능하게 했고, 음성으로 화면을 제어함으로써 요리과정에서의 불필요한 디스플레이 터치를 방지해 위생적인 요리 환경을 제공한다.

• KIPS Transactions on Software and Data Engineering
• /
• v.12 no.9
• /
• pp.407-418
• /
• 2023

The Multi-Object Goal Visual Navigation(MultiOn) is a visual navigation task in which an agent must visit to multiple object goals in an unknown indoor environment in a given order. Existing models for the MultiOn task suffer from the limitation that they cannot utilize an integrated view of multimodal context because use only a unimodal context map. To overcome this limitation, in this paper, we propose a novel deep neural network-based agent model for MultiOn task. The proposed model, MCFMO, uses a multimodal context map, containing visual appearance features, semantic features of environmental objects, and goal object features. Moreover, the proposed model effectively fuses these three heterogeneous features into a global multimodal context map by using a point-wise convolutional neural network module. Lastly, the proposed model adopts an auxiliary task learning module to predict the observation status, goal direction and the goal distance, which can guide to learn the navigational policy efficiently. Conducting various quantitative and qualitative experiments using the Habitat-Matterport3D simulation environment and scene dataset, we demonstrate the superiority of the proposed model.

• Journal of the Korea Society for Simulation
• /
• v.18 no.4
• /
• pp.197-206
• /
• 2009

The medical information system is an effective medical diagnosis assistance system which offers an environment in which medial images and diagnosis information can be shared. However, this system can only stored and transmitted information without other functions. To resolve this problem and to enhance the efficiency of diagnostic activities, a medical image classification and retrieval system is necessary. The medical image classification and retrieval system can improve efficiency in a medical diagnosis by providing disease-related images and can be useful in various medical practices by checking diverse cases. However, it is difficult to understand the meanings contained in images because the existing image classification and retrieval system has handled superficial information only. Therefore, a medical image classification system which can classify medical images by analyzing the relation among the elements of the image as well as the superficial information has been required. In this paper, we propose the method for learning and classification of brain MRI, in which the superficial information as well as the spatial information extracted from images are used. The superficial information of images, which is color, shape, etc., is called low-level image information and the logical information of the image is called high-level image information. In extracting both low-level and high-level image information in this paper, the anatomical names and structure of the brain have been used. The low-level information is used to give an anatomical name in brain images and the high-level image information is extracted by analyzing the relation among the anatomical parts. Each information is used in learning and classification. In an experiment, the MRI of the brain including disease have been used.

• Journal of Broadcast Engineering
• /
• v.26 no.2
• /
• pp.155-166
• /
• 2021

Most object detection algorithms are studied based on RGB images. Because the RGB cameras are capturing images based on light, however, the object detection performance is poor when the light condition is not good, e.g., at night or foggy days. On the other hand, high-quality infrared(IR) images regardless of weather condition and light can be acquired because IR images are captured by an IR sensor that makes images with heat information. In this paper, we performed the object detection algorithm based on the compression ratio in RGB and IR images to show the detection capabilities. We selected RGB and IR images that were taken at night from the Free FLIR Thermal dataset for the ADAS(Advanced Driver Assistance Systems) research. We used the pre-trained object detection network for RGB images and a fine-tuned network that is tuned based on night RGB and IR images. Experimental results show that higher object detection performance can be acquired using IR images than using RGB images in both networks.

• Journal of the Korea Computer Graphics Society
• /
• v.25 no.3
• /
• pp.11-20
• /
• 2019

In this study, a novel virtual reality (VR) experience environment is proposed for enabling walking adaptation of visually impaired people. The core of proposed VR environment is based on immersive walking interactions and deep learning based braille blocks recognition. To provide a realistic walking experience from the perspective of visually impaired people, a tracker-based walking process is designed for determining the walking state by detecting marching in place, and a controller-based VR white cane is developed that serves as the walking assistance tool for visually impaired people. Additionally, a learning model is developed for conducting comprehensive decision-making by recognizing and responding to braille blocks situated on roads that are followed during the course of directions provided by the VR white cane. Based on the same, a VR application comprising an outdoor urban environment is designed for analyzing the VR walking environment experience. An experimental survey and performance analysis were also conducted for the participants. Obtained results corroborate that the proposed VR walking environment provides a presence of high-level walking experience from the perspective of visually impaired people. Furthermore, the results verify that the proposed learning algorithm and process can recognize braille blocks situated on sidewalks and roadways with high accuracy.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.5 no.1
• /
• pp.66-73
• /
• 2010

The curriculum of programming education including algorithm has been recognized as a very important subject to many students majoring in natural sciences and engineering including electronic engineering and computer related departments. However, many students have had difficulties with it due to its characteristics; as a consequence, they have been in trouble taking upper-level subjects. Flow chart is a diagram that expresses logical stages necessary to solve certain problems and has been widely used to have an understanding of the flow of algorithm. The practice-oriented education of algorithm and programming would be very important to assist the understanding of operation processes. Furthermore, it has been desperately required to the necessity of auxiliary programs that could enhance an understanding of the concept of algorithm and program execution process. This study was aimed to design and embody the learning system of programming languages using basic algorithms so as for students to easily learn basic algorithm among the entire programming curriculum.

• Journal of The Korean Association For Science Education
• /
• v.22 no.3
• /
• pp.595-603
• /
• 2002

The influences of the characteristics of anomalous data on cognitive conflict and conceptual change in learning density were investigated. The subjects were 416 seventh graders. First, the Group Assessment of Logical Thinking and a preconception test were administered. A questionnaire on the responses to anomalous data was then administered. In the questionnaire, four types of anomalous data varying presentation type (movie/text) and authority level (high/low) were randomly presented. After a computer-assisted instruction on density, a conception test was administered. The results indicated that anomalous data presented in movie type significantly induced more cognitive conflict than that in text type. Students presented with anomalous data of high authority scored higher in the conception test than those of low authority. There were no significant interactions between the characteristics of anomalous data and students' logical thinking ability in the scores of both the cognitive conflict and the conception test.

• Journal of KIISE:Software and Applications
• /
• v.30 no.11
• /
• pp.1044-1053
• /
• 2003

A virtual science experience space(VSES) using virtual reality technology including haptic device is proposed to overcome limits which the existing science education has and to improve the effect of it. Four example scientific worlds such as Micro World, Friction World, Electromechanical World and Macro World are demonstrated by the developed VSES. Van der Waals forces in Micro World and Stick-Slip friction in Friction World, the principle of induction motor and power generator in Electromechanical World and Coriolis acceleration that is brought about by relative motion on the rotating coordinate are modeled mathematically based on physical principles. Emulation methods for haptic interface are suggested. The proposed VSES consists of haptic device, HMD or Crystal Eyes and a digital computer with stereoscopic graphics and GUI. The proposed system is believed to increase the realism and immersion for user.

• Journal of The Korean Association of Information Education
• /
• v.24 no.6
• /
• pp.643-652
• /
• 2020

Since the 21st century knowledge and information society 20 years ago, online education has been emphasized. Online courses at online universities or universities have been activated in developed countries. But to this day, online lectures have not been activated at education colleges and have been used as supplementary educational materials. Since February 2020, the company has been forced to provide online education due to external factors of the coronavirus. In this study, the results of the results of the first semester of 2020 by organizing the online lectures in the same way as the offline lectures for the 2019 prospective teachers are as follows. Online education can be seen as effective in terms of understanding the achievement criteria, in terms of developing teaching materials, in terms of evaluation data development and evaluation methods, and in terms of students' ability to provide software education.

• KIPS Transactions on Computer and Communication Systems
• /
• v.12 no.8
• /
• pp.235-242
• /
• 2023

In recent years, as online counseling for infants and adolescents has increased, CNN-based deep learning models are widely used as assistance tools for emotion recognition. However, since most emotion recognition models are trained on mainly adult data, there are performance restrictions to apply the model to infants and adolescents. In this paper, in order to analyze the performance constraints, the characteristics of facial expressions for emotional recognition of infants and adolescents compared to adults are analyzed through LIME method, one of the XAI techniques. In addition, the experiments are performed on the male and female groups to analyze the characteristics of gender-specific facial expressions. As a result, we describe age-specific and gender-specific experimental results based on the data distribution of the pre-training dataset of CNN models and highlight the importance of balanced learning data.