• Smart Media Journal
• /
• v.13 no.2
• /
• pp.23-31
• /
• 2024

In precision cattle farm, reliably tracking the identity of each cattle is necessary. Effective tracking of cattle within farm environments presents a unique challenge, particularly with the need to minimize the occurrence of excessive tracking trajectories. To address this, we introduce a trajectory playback decision tree algorithm that reevaluates and cleans tracking results based on spatio-temporal relationships among trajectories. This approach considers trajectory as metadata, resulting in more realistic and accurate tracking outcomes. This algorithm showcases its robustness and capability through extensive comparisons with popular tracking models, consistently demonstrating the promotion of performance across various evaluation metrics that is HOTA, AssA, and IDF1 achieve 68.81%, 79.31%, and 84.81%.

• Smart Media Journal
• /
• v.13 no.6
• /
• pp.90-97
• /
• 2024

This paper focuses on detecting Alzheimer's Disease (AD). The most usual form of dementia is Alzheimer's disease, which causes permanent cause memory cell damage. Alzheimer's disease, a neurodegenerative disease, increases slowly over time. For this matter, early detection of Alzheimer's disease is important. The purpose of this work is using Magnetic Resonance Imaging (MRI) to diagnose AD. A Convolution Neural Network (CNN) model, Reset, and VGG the pre-trained learning models are used. Performing analysis and validation of layers affects the effectiveness of the model. T1-weighted MRI images are taken for preprocessing from ADNI. The Dataset images are taken from the Alzheimer's Disease Neuroimaging Initiative (ADNI). 3D MRI scans into 2D image slices shows the optimization method in the training process while achieving 96% and 94% accuracy in VGG 16 and ResNet 18 respectively. This study aims to classify AD from brain 3D MRI images and obtain better results.

• Informatization Policy
• /
• v.29 no.4
• /
• pp.26-42
• /
• 2022

In order to evaluate the usefulness of metaverse learning from the learner's point of view, this study 1) evaluated whether the expectancy-value of the class was satisfied before and after the learner used the metaverse learning platform and 2) verified factors affecting metaverse learning satisfaction with regard to the self-efficacy and expectancy-value of learners. Expectancy-value was evaluated by the learning effect, communication, class involvement, and learning attitude, whereas self-efficacy was evaluated by preference for task difficulty, self-regulation efficacy, and self-confidence. As a result of a study targeting 70 college students who applied for a few courses using the metaverse platform at a university in the northeastern part of Seoul, learners were found to have high expectations and values for learning before using the metaverse platform, but both were not statistically satisfied after use. In addition, the higher the self-efficacy of the learner, the higher the satisfaction with the metaverse learning, and statistically significant results were found in the task-difficulty preference and self-regulatory efficacy among the sub-factors of self-efficacy. There is a negative causal relationship between expectancy-value factors and satisfaction with metaverse learning. This study implies that it is a learner-centered evaluation of metaverse learning, revealing the expectancy-value effect and factors influencing the satisfaction with metaverse learning.

• ETRI Journal
• /
• v.36 no.5
• /
• pp.704-713
• /
• 2014

Most natural language processing tasks depend on the outputs of some other tasks. Thus, they involve other tasks as subtasks. The main problem of this type of pipelined model is that the optimality of the subtasks that are trained with their own data is not guaranteed in the final target task, since the subtasks are not optimized with respect to the target task. As a solution to this problem, this paper proposes a consolidation of subtasks for a target task ($CST^2$). In $CST^2$, all parameters of a target task and its subtasks are optimized to fulfill the objective of the target task. $CST^2$ finds such optimized parameters through a backpropagation algorithm. In experiments in which text chunking is a target task and part-of-speech tagging is its subtask, $CST^2$ outperforms a traditional pipelined text chunker. The experimental results prove the effectiveness of optimizing subtasks with respect to the target task.

• Journal of Korea Multimedia Society
• /
• v.23 no.7
• /
• pp.803-811
• /
• 2020

This paper proposes an image classification algorithm that transforms the number of convolution layers in the residual block of ResNet, CNN's representative method. The proposed method modified the structure of 34/50 layer of ResNet structure. First, we analyzed the performance of small and many convolution layers for the structure consisting of only shortcut and 3 × 3 convolution layers for 34 and 50 layers. And then the performance was analyzed in the case of small and many cases of convolutional layers for the bottleneck structure of 50 layers. By applying the results, the best classification method in the residual block was applied to construct a 34-layer simple structure and a 50-layer bottleneck image classification model. To evaluate the performance of the proposed image classification model, the results were analyzed by applying to the cifar10 dataset. The proposed 34-layer simple structure and 50-layer bottleneck showed improved performance over the ResNet-110 and Densnet-40 models.

• Journal of the Ergonomics Society of Korea
• /
• v.31 no.4
• /
• pp.577-583
• /
• 2012

Objective: This paper describes the process and results related to the development of gesture recognition-based natural user interface(NUI) for vehicle maintenance e-Training system. Background: E-Training refers to education training that acquires and improves the necessary capabilities to perform tasks by using information and communication technology(simulation, 3D virtual reality, and augmented reality), device(PC, tablet, smartphone, and HMD), and environment(wired/wireless internet and cloud computing). Method: Palm movement from depth camera is used as a pointing device, where finger movement is extracted by using OpenCV library as a selection protocol. Results: The proposed NUI allows trainees to control objects, such as cars and engines, on a large screen through gesture recognition. In addition, it includes the learning environment to understand the procedure of either assemble or disassemble certain parts. Conclusion: Future works are related to the implementation of gesture recognition technology for a multiple number of trainees. Application: The results of this interface can be applied not only in e-Training system, but also in other systems, such as digital signage, tangible game, controlling 3D contents, etc.

• Journal of the Korean Society for Library and Information Science
• /
• v.50 no.2
• /
• pp.25-45
• /
• 2016

This study investigates how high school students with low academic achievement seek and use information. Participants were seven US students in an American Literature and Composition course of the $11^{th}$ grade Remedial Education Program who completed a class project that required comprehensive information seeking and use. Data were collected through comprehensive observation and individual interviews with each student, the teacher, and two library media specialists. Additionally, we gathered and analyzed the instructions the teacher and the two library media specialists provided and all documents each student produced to complete the class project. The process of data analysis was supported by QSR NVivo. The findings of the study implied that students experienced cognitive and affective challenges for their information seeking and use required for the tasks and suggested that technological and individual conferencing would motivate the students to continue their information seeking and use. We then conclude the study with some important implications that can be used as a basis for designing information literacy instructions for students with low academic achievement.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2014.05a
• /
• pp.890-892
• /
• 2014

최근 스마트기기가 널리 보급되고 소셜네트워크 서비스가 확산되면서, 스마트 기기 및 소셜미디어를 활용함으로서 학습에서 상호작용을 극대화한 교육환경으로 스마트러닝이 크게 부각되고 있다. 그리고 스마트러닝 콘텐츠 및 환경의 확산으로 PC 위주에서 스마트폰 등으로 이러닝 콘텐츠의 사용환경이 확장됨에 따라 콘텐츠 저작의 경제성과 효율성 등을 고려하게 되었으며, 하나의 콘텐츠를 다양한 환경에서 활용 가능하도록 하고 있다. 그러나 기존 PC기반의 콘텐츠를 스마트기기에 적용함에 있어 여러 가지 문제가 발생하는데 이 문제들을 해결하는 방안으로 먼저 콘텐츠에 대한 표준화가 중요한 요소로 작용한다. 따라서 본 논문에서는 전자책 표준화를 활용한 효율적인 스마트러닝 기법을 제시하고자 한다.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2019.07a
• /
• pp.321-324
• /
• 2019

최근 국내에는 실업률 상승, 혼인률 하락 등 청년층 생애주기 변화, 단독거주, 고령층의 증가에 따라 1인 가구가 빠른 속도로 증가하고 있다. 이러한 추세는 지속될 것으로 예상되어 1인 가구를 겨냥한 맞춤형 보안솔루션에 대한 관심이 고조되고 있다. 본 논문에서는 사물 인터넷 기술을 적극적으로 접목할 수 있을 것으로 기대되는 디지털 도어락의 구현에 관한 연구를 수행하였다. 사물 인터넷 기술은 5G 시대의 도래에 따라 다시금 주목받고 있다. 이는 4차 산업혁명 시대의 핵심 기반 기술로 주요 IT 기업들이 상용화 기술 확보를 추진하고 있는 상황이다. 한편 디지털 도어락은 열쇠가 필요하지 않으며 위급상황이나 안전상황에 클릭 한번으로 출동 요원의 출동을 곧바로 요청할 수 있어 고객에게 편의성과 보안성을 제공한다. 하지만 비밀번호 방식의 디지털 도어락은 주기적으로 비밀번호를 교체해주지 않는 이상 지속적으로 같은 자리의 버튼만을 누르게 된다. 이렇게 되면 해당 위치에 지문이 남아서 비밀번호가 노출될 위험이 있다. 그러나 사물 인터넷 기술을 이용한 디지털 도어락을 사용하게 된다면 안전한 도어락 사용으로 주거 보안을 실현할 수 있다. 따라서 1인 가구를 노리는 범죄를 예방하기 위해 라즈베리 파이와 아두이노의 UART 통신, 머신러닝 CV를 이용하여 얼굴 인식으로 동일인임을 판단하는 디지털 도어락을 구현했다.

• ETRI Journal
• /
• v.41 no.4
• /
• pp.415-425
• /
• 2019

Generative adversarial networks (GAN) have been successfully used in many image restoration tasks, including image denoising, super-resolution, and compression artifact reduction. By fully exploiting its characteristics, state-of-the-art image restoration techniques can be used to generate images with photorealistic details. However, there are many applications that require faithful rather than visually appealing image reconstruction, such as medical imaging, surveillance, and video coding. We found that previous GAN-training methods that used a loss function in the form of a weighted sum of fidelity and adversarial loss fails to reduce fidelity loss. This results in non-negligible degradation of the objective image quality, including peak signal-to-noise ratio. Our approach is to alternate between fidelity and adversarial loss in a way that the minimization of adversarial loss does not deteriorate the fidelity. Experimental results on compression-artifact reduction and super-resolution tasks show that the proposed method can perform faithful and photorealistic image restoration.