• Journal of Korea Multimedia Society
• /
• v.17 no.1
• /
• pp.1-7
• /
• 2014

Hippocampus is an important part of brain which is related with early memory storage and spatial navigation. By observing the anatomy of hippocampus, some brain diseases effecting human memory (e.g. Alzheimer, schizophrenia, etc.) can be diagnosed and predicted earlier. The diagnosis process is highly related with hippocampus segmentation. In this paper, hippocampus segmentation using Active Shape Model, which not only works based on image intensity, but also by using prior knowledge of hippocampus shape and intensity from the training images, is proposed. The results show that ASM is applicable in segmenting hippocampus from whole brain MR image. It also shows that adding more images in the training set results in better accuracy of hippocampus segmentation.

• Proceedings of the IEEK Conference
• /
• 2008.06a
• /
• pp.1193-1194
• /
• 2008

In this paper, we propose application training kit using parallel port circuit of standard architecture in computer system. The proposed training kit is verified through the design of hardware board and a virtual driving test using GUI method in VC++ under window XP operating system.

• Journal of the Korea Society of Computer and Information
• /
• v.22 no.7
• /
• pp.31-37
• /
• 2017

There are lots of combined battlefield elements which complete the war. It looks problematic when collecting and analyzing these elements and then predicting the situation of war. Commander's experience and military power assessment have widely been used to come up with these problems, then simulated combat training program recently supplements the war-game models through recording real-time simulated combat data. Nevertheless, there are challenges to assess winning factors of combat. In this paper, we characterize the combat element (ce) by clustering simulated combat data, and then suggest multi-layered artificial neural network (ANN) model, which can comprehend non-linear, cross-connected effects among ces to assess mission completion degree (MCD). Through our ANN model, we have the chance of analyzing and predicting winning factors. Experimental results show that our ANN model can explain MCDs through networking ces which overperform multiple linear regression model. Moreover, sensitivity analysis of ces will be the basis of predicting combat situation.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2018.07a
• /
• pp.271-272
• /
• 2018

제4차 산업혁명시대에서 강조하는 SW교육은 컴퓨팅 관련 교과 뿐만 아니라 타 교과에서도 그 중요성이 대두되고 있으며, 따라서 정보과 교사가 아닌 비 정보과 교사들에게도 SW 교사 연수의 필요성이 높아지고 있다. 따라서 본 연구에서는 선행 연구들의 고찰을 통하여 비 정보과 교사를 위한 햄스터로봇을 활용한 SW 교사 연수 프로그램을 개발하였다.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2022.07a
• /
• pp.385-386
• /
• 2022

2015 개정 교육과정에서는 미래 사회의 인재를 육성하기 위해 중학교에 정보 교과를 필수화하였다. 이를 지도할 정보·컴퓨터 교사를 확보하기 위해 비 정보과 교사를 대상으로 부전공연수를 실시하여 정보 교육을 할 수 있는 자격을 부여하고 있다. 이들은 일반 학습자와 다르게 교육학적 지식과 역량은 높으나, 내용 지식은 컴퓨터과학의 초보자 수준이다. 이러한 학습자의 특성을 고려하여 마이크로비트를 활용한 연수를 12차시 동안 진행하였고, 이는 비 정보과 교사의 프로그래밍 자아효능감에 긍정적인 영향을 준다는 것을 확인할 수 있었다. 그러나 본 연구는 단일집단에게 실험을 실시하였으므로 그 효과를 일반화하는 데 한계가 있다. 따라서 후속 연구에서는 비교 집단을 설정하는 실험 설계로 교육 효과를 검증할 필요가 있다.

• Journal of Korea Game Society
• /
• v.8 no.4
• /
• pp.65-73
• /
• 2008

In this paper, we designed and implemented edutainment platform that can be effectively applied to developmental disabilities for their education and treatment of sensibility and intelligence training. We developed embedded hardware and contents authoring tool to make multimedia contents operated on the hardware, a management tool to provide result of training, and a real-time monitoring tool for observing the state of study. The hardware is designed by considering the characteristics of developmental disabilities and provides visual, auditory and tactile sense to assist sensibility training for their attention. User-friendly and easy-to-use authoring tool enable teachers and non-specialist to make educational contents. Also the real-time monitoring tool make us to observe user's status even in the outside of classroom. The management tool stores result of training and make us to review the result for further steps. Using this edutainment platform, efficient repetitive training is possible without restriction of time and location. Also when it applied to practical education, we can recognize that our system is effective on improving the ability of attention and studying.

• Journal of the Korea Society of Computer and Information
• /
• v.27 no.1
• /
• pp.69-75
• /
• 2022

This paper proposes a method of identifying the moment when a student with developmental disabilities needs assistance intervention in performing barista vocational training using virtual reality-based realistic contents. To this end, 21 students enrolled in a vocational training center for persons with disabilities were selected as study subjects. These students were trained to recognize the barista tools in a virtual reality environment. During the training, if students experienced difficulties and were unable to proceed further, they were asked to raise their hands or verbally request assistance. Using the collected data, two hypotheses were established based on the distance between the hand of the student and each barista tool in the virtual reality space in order to derive a criterion for judging the moment when an intervention is required. As a result of verifying the hypotheses, this study found that the cumulative distance from the hand of a student, who successfully finished the training without requiring an intervention, to the target barista tool as well as adjacent tools was significantly shorter than the cumulative distance to other barista tools.

• Journal of the Korea Society of Computer and Information
• /
• v.28 no.7
• /
• pp.19-27
• /
• 2023

In the process of collecting social reviews, a number of noise reviews irrelevant to a given search keyword can be included in the search results. To filter out such reviews, machine learning can be used. However, if the number of reviews is insufficient for a target place to be analyzed, filtering accuracy can be degraded due to the lack of training data. To resolve this issue, we propose a supervised learning method to improve accuracy of the noise review filtering for the places with insufficient reviews. In the proposed method, training is not performed by an individual place, but by a group including several places with similar characteristics. The classifier obtained through the training can be used for the noise review filtering of an arbitrary place belonging to the group, so the problem of insufficient training data can be resolved. To verify the proposed method, a noise review filtering model was implemented using LSTM and BERT, and filtering accuracy was checked through experiments using real data collected online. The experimental results show that the accuracy of the proposed method was 92.4% on the average, and it provided 87.5% accuracy when targeting places with less than 100 reviews.

• Journal of Korea Multimedia Society
• /
• v.22 no.1
• /
• pp.44-54
• /
• 2019

Recently, image-based object detection has made great progress with the introduction of Convolutional Neural Network (CNN). Many trials such as Region-based CNN, Fast R-CNN, and Faster R-CNN, have been proposed for achieving better performance in object detection. YOLO has showed the best performance under consideration of both accuracy and computational complexity. However, these data-driven detection methods including YOLO have the fundamental problem is that they can not guarantee the good performance without a large number of training database. In this paper, we propose a data sampling method using CycleGAN to solve this problem, which can convert styles while retaining the characteristics of a given input image. We will generate the insufficient data samples for training more robust object detection without efforts of collecting more database. We make extensive experimental results using the day-time and night-time road images and we validate the proposed method can improve the object detection accuracy of the night-time without training night-time object databases, because we converts the day-time training images into the synthesized night-time images and we train the detection model with the real day-time images and the synthesized night-time images.

• Journal of the Korea Society of Computer and Information
• /
• v.29 no.3
• /
• pp.11-20
• /
• 2024

Among the generative models in Artificial Intelligence (AI), especially Generative Adversarial Network (GAN) has been successful in various applications such as image processing, density estimation, and style transfer. While the GAN models including Conditional GAN (CGAN), CycleGAN, BigGAN, have been extended and improved, researchers face challenges in real-world applications in specific domains such as disaster simulation, healthcare, and urban planning due to data scarcity and unstable learning causing Image distortion. This paper proposes a new progressive learning methodology called Progressive Step Training (PST) based on the Auxiliary Classifier GAN (ACGAN) that discriminates class labels, leveraging the progressive learning approach of the Progressive Growing of GAN (PGGAN). The PST model achieves 70.82% faster stabilization, 51.3% lower standard deviation, stable convergence of loss values in the later high resolution stages, and a 94.6% faster loss reduction compared to conventional methods.