• Journal of Korea Multimedia Society
• /
• v.24 no.11
• /
• pp.1481-1491
• /
• 2021

Since most biosignals rely on contact-based measurement, there is still a problem in that it is hard to provide convenience to users by applying them to daily life. In this paper, we present a mobile application for estimating heart rate based on a deep learning model. The proposed application measures heart rate by capturing real-time face images in a non-contact manner. We trained a three-dimensional convolutional neural network to predict photoplethysmography (PPG) from face images. The face images used for training were taken in various movements and situations. To evaluate the performance of the proposed system, we used a pulse oximeter to measure a ground truth PPG. As a result, the deviation of the calculated root means square error between the heart rate from remote PPG measured by the proposed system and the heart rate from the ground truth was about 1.14, showing no significant difference. Our findings suggest that heart rate measurement by mobile applications is accurate enough to help manage health during daily life.

• Journal of The Korean Association of Information Education
• /
• v.9 no.3
• /
• pp.407-416
• /
• 2005

Considering teaching methods for computer education is a must for effectively instructing students of knowledge and skills on computers. In this paper, we adopts STAD Cooperative Learning method, among many others, in order to reduce any burden teachers and learners may have. As a result, it finds out that practical training based on STAD Cooperative Learning is very effective in enhancing students' abilities for ICT data collection and manipulation. The teaching model driven out as a result of this study, will be a good example for teaching models in many computer-related departments. In the future, more studies on teaching models will have to take place for more effective teaching of computer courses.

• The Journal of the Korea Contents Association
• /
• v.15 no.3
• /
• pp.40-47
• /
• 2015

VR(virtual reality) which already is used commonly in diverse areas including entertainment, design, and simulation training is most important area in ICT. VR already has various uses within the tourism sector. As VR technology continues to evolve, there is little reason to doubt that it will become more prevalent throughout society and the tourism sector in particular. In this paper, we plan to improve the VR content to the market possibility and competitiveness of VR content in the culture industry. Out of focus, lens dust, motion blur, blur effect were minimized to improve the simulation sickness which caused by the cognitive dissonance in the HMD. And also, the content was considered UI design for user's immersion.

• Journal of Practical Engineering Education
• /
• v.11 no.2
• /
• pp.269-282
• /
• 2019

The purpose of this study is to identify the level of development of major technologies used in smart manufacturing in Korea and to use it as an objective basis for establishing smart manufacturing R & D personnel training policies. We select 25 key technologies to build and operate smart factories for the US, Germany, Japan, EU, Korea, and China, and examine the level (%) and gap (year) by smart manufacturing technology in each country. Based on the results, it is expected to contribute to reinforcing the global market competitiveness of the Korea manufacturing industry by checking the current status of R & D personnel training and suggesting policy suggestions for nurturing R & D personnel.

• The Journal of Korea Robotics Society
• /
• v.18 no.3
• /
• pp.293-298
• /
• 2023

The military is facing a continuous decrease in personnel, and in order to cope with potential accidents and challenges in operations, efforts are being made to reduce the direct involvement of personnel by utilizing the latest technologies. Recently, the use of various sensors related to Manned-Unmanned Teaming and artificial intelligence technologies has gained attention, emphasizing the need for flexible utilization methods. In this paper, we propose four dataset construction methods that can be used for effective training of robots that can be deployed in military operations, utilizing not only RGB image data but also data acquired from IR image sensors. Since there is no publicly available dataset that combines RGB and IR image data, we directly acquired the dataset within buildings. The input values were constructed by combining RGB and IR image sensor data, taking into account the field of view, resolution, and channel values of both sensors. We compared the proposed method with conventional RGB image data classification training using the same learning model. By employing the proposed image data fusion method, we observed improved stability in training loss and approximately 3% higher accuracy.

• Journal of Platform Technology
• /
• v.6 no.1
• /
• pp.3-8
• /
• 2018

This paper proposes a technique for recognizing online handwritten cursive data obtained by tracing a motion trajectory while a user is in the 3D space based on a convolution neural network (CNN) algorithm. There is a difficulty in recognizing the virtual character input by the user in the 3D space because it includes both the character stroke and the movement stroke. In this paper, we divide syllable into consonant and vowel units by using labeling technique in addition to the result of localizing letter stroke and movement stroke in the previous study. The coordinate information of the separated consonants and vowels are converted into image data, and Korean handwriting recognition was performed using a convolutional neural network. After learning the neural network using 1,680 syllables written by five hand writers, the accuracy is calculated by using the new hand writers who did not participate in the writing of training data. The accuracy of phoneme-based recognition is 98.9% based on convolutional neural network. The proposed method has the advantage of drastically reducing learning data compared to syllable-based learning.

• International Journal of Safety
• /
• v.9 no.2
• /
• pp.11-15
• /
• 2010

Infrastructures in Japan constructed mostly in high economic growth period become elder & elder, and the troubles & accidents caused by the aging increase. Though investment for the renewal is necessary, the shortage of public fund delays the action. Besides, we expect the decrease of the population that means the decrease of the engineers who take care of social infrastructures. Thus, it is necessary for us to develop Advanced Management system of social Infrastructures (AMI) to realize the efficient and economical operation. Our concept of AMI consists of using ICT, PI (Public Involvement) and establishment of O&M diagnosis system. We expect AMI will support to realize the appropriate repairing, preventive maintenance based on the actual performance, accidents & dangerous experience and education & training of the workers. In this paper, development of AMI for the waste disposal facility as a first example of infrastructures will be shown.

• Smart Media Journal
• /
• v.12 no.9
• /
• pp.45-59
• /
• 2023

Weakly supervised object localization (WSOL) is a task of localizing an object in an image using only image-level labels. Previous studies have followed the conventional class activation mapping (CAM) pipeline. However, we reveal the current CAM approach suffers from problems which cause original CAM could not capture the complete defects features. This work utilizes a convolutional neural network (CNN) pretrained on image-level labels to generate class activation maps in a multi-scale manner to highlight discriminative regions. Additionally, a vision transformer (ViT) pretrained was treated to produce multi-head attention maps as an auxiliary detector. By integrating the CNN-based CAMs and attention maps, our approach localizes defective regions without requiring bounding box or pixel-level supervision during training. We evaluate our approach on a dataset of apple images with only image-level labels of defect categories. Experiments demonstrate our proposed method aligns with several Object Detection models performance, hold a promise for improving localization.

• International Journal of Advanced Culture Technology
• /
• v.8 no.4
• /
• pp.235-241
• /
• 2020

Artificial intelligence and machine learning are used in many parts of our daily lives, but the basic processes and concepts are barely exposed to most people. Understanding these basic concepts is becoming increasingly important as kids don't have the opportunity to explore AI processes and improve their understanding of basic machine learning concepts and their essential components. Machine learning educational tools can help children easily understand artificial intelligence and machine learning. In this paper, we examine machine learning education tools and compare their features.

• Journal of Advanced Navigation Technology
• /
• v.25 no.1
• /
• pp.96-101
• /
• 2021

This paper presents a machine learning model that predicts stroke risks in atrial fibrillation patients using public big data. As the training data, 68 independent variables including demographic, medical history, health examination were collected from the Korean National Health Insurance Service. To predict stroke incidence in patients with atrial fibrillation, we applied deep neural network. We firstly verify the performance of conventional statistical models (CHADS2, CHA2DS2-VASc). Then we compared proposed model with the statistical models for various hyperparameters. Accuracy and area under the receiver operating characteristic (AUROC) were mainly used as indicators for performance evaluation. As a result, the model using batch normalization showed the highest performance, which recorded better performance than the statistical model.