• KIPS Transactions on Software and Data Engineering
• /
• v.10 no.5
• /
• pp.179-186
• /
• 2021

Manipulation of complex objects with an anthropomorphic robot hand like a human hand is a challenge in the human-centric environment. In order to train the anthropomorphic robot hand which has a high degree of freedom (DoF), human demonstration augmented deep reinforcement learning policy optimization methods have been proposed. In this work, we first demonstrate augmentation of human demonstration in deep reinforcement learning (DRL) is effective for object manipulation by comparing the performance of the augmentation-free Natural Policy Gradient (NPG) and Demonstration Augmented NPG (DA-NPG). Then three DRL policy optimization methods, namely NPG, Trust Region Policy Optimization (TRPO), and Proximal Policy Optimization (PPO), have been evaluated with DA (i.e., DA-NPG, DA-TRPO, and DA-PPO) and without DA by manipulating six objects such as apple, banana, bottle, light bulb, camera, and hammer. The results show that DA-NPG achieved the average success rate of 99.33% whereas NPG only achieved 60%. In addition, DA-NPG succeeded grasping all six objects while DA-TRPO and DA-PPO failed to grasp some objects and showed unstable performances.

• Journal of Korea Game Society
• /
• v.20 no.2
• /
• pp.183-192
• /
• 2020

Due to the problem of matching between virtual world space and real-world space, the reality of augmented reality content is rather low. There are many reasons for this result, firstly virtual object is rendered without considering relation between real-world space and virtual world space. Secondly, virtual objects rely too much on the marker to reduce reality. We propose two schemes to improve the reality of augmented reality, one is people occlusion, the other is to reduce the dependence of virtual objects on the marker.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.18 no.6
• /
• pp.285-292
• /
• 2023

With the wide spread of smart farms and the advancements in IoT technology, it is easy to obtain additional data in addition to crop images. Consequently, deep learning-based crop disease diagnosis research utilizing multimodal data has become important. This study proposes a crop disease diagnosis method using multimodal supervised contrastive learning by expanding upon the multimodal self-supervised learning. RandAugment method was used to augment crop image and time series of environment data. These augmented data passed through encoder and projection head for each modality, yielding low-dimensional features. Subsequently, the proposed multimodal supervised contrastive loss helped features from the same class get closer while pushing apart those from different classes. Following this, the pretrained model was fine-tuned for crop disease diagnosis. The visualization of t-SNE result and comparative assessments of crop disease diagnosis performance substantiate that the proposed method has superior performance than multimodal self-supervised learning.

• The Journal of the Korea Contents Association
• /
• v.15 no.6
• /
• pp.616-631
• /
• 2015

This study proposes a mobile Augmented Reality (AR)-based "word card" learning tool for children aged 3 to 5. First, this study suggests a learning structure to improve motivation and immersion of learning, Secondly, it designs and implements the user interface applying the proposed learning structure. Also, it designs a content management tool supporting the production of the content so that instructors can easily manage the contents for various learners. This study is conducted by four steps - reference research, design of "word card" learning content for the learner, design of content management tool for the instructor and the effectiveness verification of the proposed content. The proposed content was designed based on an education content architecture for enhancement of immersion and motivation to study. Moreover, it includes an 'AR content management tool for instructor' designed to easily update AR education content. The class for six children aged 3 to 5 was given to validate the enhancement of immersion to study. Experiment results showed that the proposed content enhanced the study immersion and that special interaction design for early children was necessary.

• Journal of the Institute of Electronics Engineers of Korea SC
• /
• v.48 no.5
• /
• pp.7-12
• /
• 2011

In this papwer, we propose a new feature extraction method, named as Class-augmented Kernel Principal Component Analysis (CA-KPCA), which can extract nonlinear features for classification. Among the subspace method that was being widely used for feature extraction, Class-augmented Principal Component Analysis (CA-PCA) is a recently one that can extract features for a accurate classification without computational difficulties of other methods such as Linear Discriminant Analysis (LDA). However, the features extracted by CA-PCA is still restricted to be in a linear subspace of the original data space, which limites the use of this method for various problems requiring nonlinear features. To resolve this limitation, we apply a kernel trick to develop a new version of CA-PCA to extract nonlinear features, and evaluate its performance by experiments using data sets in the UCI Machine Learning Repository.

• Journal of Industrial Convergence
• /
• v.17 no.4
• /
• pp.15-20
• /
• 2019

Augmented reality is used in various fields such as culture, education, military, medical. This is a method of recognizing information of an augmented object on the camera. Exhibitions and educational contents for children are already produced in various ways. This research showed the developed contents deliver cultural property information using augmented reality. 'Galgibi AR' and 'Jang Young-sil's Invention AR' allow you to experience cultural assets up close. 'Galgibi AR' is the experience content in the form of 3D blocks. It makes to understand the structure of the zeolite, Galgibi. 'Jang Young-sil's Invention AR' make you to watch out four objects in detail by zooming in, zooming out and rotating. It can also take pictures with the inventions. Both contents implement what we want to deliver accurately through simple content. They increase the enjoyment of cultural heritage through experience contents. This research addressed to help the cultural property information spread to the public by using Augmented Reality.

• Journal of the Korea Computer Graphics Society
• /
• v.28 no.3
• /
• pp.125-134
• /
• 2022

This paper implements an AR manual for a vehicle that can be used even in the vehicle interior space where it is difficult to apply the augmentation method of AR content, which is mainly used, and applies a deep learning model to improve the augmentation matching between real space and virtual objects. Through deep learning, the logo of the steering wheel is recognized regardless of the position, angle, and inclination, and 3D interior space coordinates are generated based on this, and the virtual button is precisely augmented on the actual vehicle parts. Based on the same learning model, the function to recognize the main warning light symbols of the vehicle is also implemented to increase the functionality and usability as an AR manual for vehicles.

• International Journal of Internet, Broadcasting and Communication
• /
• v.10 no.2
• /
• pp.19-24
• /
• 2018

This study investigated the academic stress and the immersion in learning in relation to AR and VR assisted instructions compared to traditional approaches. To that end, 78 $8^{th}$ graders in T and S city in Gangwondo were assigned to experimental and control groups. The experimental group received the VR and AR lessons. The academic stress was measured with the pre- and post-test scores, while the immersion in learning was measured with the post-test scores. In brief, AR and VR assisted lessons made statistically significant differences in the academic stress and immersion in learning in comparison to the traditional approaches.

• ETRI Journal
• /
• v.46 no.2
• /
• pp.263-276
• /
• 2024

Different diseases occur in the brain. For instance, hereditary and progressive diseases affect and degenerate the white matter. Although addressing, diagnosing, and treating complex abnormalities in the brain is challenging, different strategies have been presented with significant advances in medical research. With state-of-art developments in artificial intelligence, new techniques are being applied to brain magnetic resonance images. Deep learning has been recently used for the segmentation and classification of brain images. In this study, we classified normal and pathological brain images using pretrained deep models through transfer learning. The EfficientNet-B5 model reached the highest accuracy of 98.39% on real data, 91.96% on augmented data, and 100% on pathological data. To verify the reliability of the model, fivefold cross-validation and a two-tier cross-test were applied. The results suggest that the proposed method performs reasonably on the classification of brain magnetic resonance images.

• Convergence Security Journal
• /
• v.5 no.4
• /
• pp.33-40
• /
• 2005

As e-learning studying is activated, learner's requirement increased. Therefore, need correct e-learning model augmented requirement of learner and new ubiquitous surrounding. In this treatise when, proposed to supplement studying contents relationship conversion service and cooperation studying service function to LMS that analyze existing e-learning model's limitation for ubiquitous environment e-learning model that can study regardless of, ubiquitously some contents and do based on SCORM ubiquitous-network and next generation sensor technology etc. Learning form conversion service senses a learner's surrounding situations and recognize his/her body condition using smart sensor technology and provides the learner with contents in the optimal form. Using sensing projects like Orestia and SOB, users can more effective collaborative learning service.