• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.22 no.5
• /
• pp.29-35
• /
• 2022

This paper proposes a fuel cell education framework installed on a Metaverse environment, which is to reduce the burden of education costs and improve the effect of education or learning. This Meta-Fuel cell platform utilizes the Unity 3D Web and enables not only theoretical education but also hands-on training. The platform was designed and developed to accommodate a variety of unit education contents, such as ppt documents, videos, etc. The platform, therdore, integrates ppt and video demonstrations for theoretical education, as well as software content "STACK-Up" for hands-on training. Theoretical education section provides specialized liberal arts knowledge on hydrogen, including renewable energy, hydrogen economy, and fuel cells. The software "STACK-Up" provides a hands-on practice on assembling the stack parts. Stack is the very core component of fuel cells. The Meta-Fuelcell platform improves the limitations of face-to-face education. It provides educators with the opportunities of non-face-to-face education without restrictions such as educational place, time, and occupancy. On the other hand, learners can choose educational themes, order, etc. It provides educators and learners with interesting experiences to be active in the metaverse space. This platform is being applied experimentally to a education project which is to develop advanced manpower in the fuel cell industry. Its improvement is in progress.

• Journal of Internet of Things and Convergence
• /
• v.10 no.1
• /
• pp.69-75
• /
• 2024

This paper proposes an innovative cognitive IoT framework specifically designed for fog computing (FC) in the context of industrial Internet of Things (IIoT). The discourse in this paper is centered on the intricate design and functional architecture of the Cognitive IoT platform. A crucial feature of this platform is the integration of machine learning (ML) and artificial intelligence (AI), which enhances its operational flexibility and compatibility with a wide range of industrial applications. An exemplary application of this platform is highlighted through the Predictive Maintenance-as-a-Service (PdM-as-a-Service) model, which focuses on real-time monitoring of machine conditions. This model transcends traditional maintenance approaches by leveraging real-time data analytics for maintenance and management operations. Empirical results substantiate the platform's effectiveness within a fog computing milieu, thereby illustrating its transformative potential in the domain of industrial IoT applications. Furthermore, the paper delineates the inherent challenges and prospective research trajectories in the spheres of Cognitive IoT and Fog Computing within the ambit of Industrial Internet of Things (IIoT).

• The Transactions of the Korea Information Processing Society
• /
• v.13 no.6
• /
• pp.260-268
• /
• 2024

Cervical cancer is the fourth most common cancer in women worldwide, and more than 604,000 new cases were reported in 2020 alone, resulting in approximately 341,831 deaths. The Cox regression model is a major model widely adopted in cancer research, but considering the existence of nonlinear associations, it faces limitations due to linear assumptions. To address this problem, this paper proposes ResSurvNet, a new model that improves the accuracy of cervical cancer mortality prediction using ResNet's residual learning framework. This model showed accuracy that outperforms the DNN, CPH, CoxLasso, Cox Gradient Boost, and RSF models compared in this study. As this model showed accuracy that outperformed the DNN, CPH, CoxLasso, Cox Gradient Boost, and RSF models compared in this study, this excellent predictive performance demonstrates great value in early diagnosis and treatment strategy establishment in the management of cervical cancer patients and represents significant progress in the field of survival analysis.

• Journal of Digital Contents Society
• /
• v.17 no.6
• /
• pp.565-579
• /
• 2016

In this paper a novel cancer subtype's classifier based on Hybrid Samples Balanced Genetic Algorithm with Extreme Learning Machine (hSBGA-ELM) is presented. Proposed cancer subtype's classifier uses genes' expression data of 16063 genes from open Global Cancer Map (GCM) data base for accurate cancer subtype's classification. Proposed method efficiently classifies 14 subtypes of cancer (breast, prostate, lung, colorectal, lymphoma, bladder, melanoma, uterus, leukemia, renal, pancreas, ovary, mesothelioma and CNS). Proposed hSBGA-ELM unifies genes' selection procedure and cancer subtype's classification into one framework. Proposed Hybrid Samples Balanced Genetic Algorithm searches a reduced robust set of genes responsible for cancer subtype's classification from 16063 genes available in GCM data base. Selected reduced set of genes is used to build cancer subtype's classifier using Extreme Learning Machine (ELM). As a result, reduced set of robust genes guarantees stable generalization performance of the proposed cancer subtype's classifier. Proposed hSBGA-ELM discovers 95 genes probably responsible for cancer. Comparison with existing cancer subtype's classifiers clear indicates efficiency of the proposed method.

• Management & Information Systems Review
• /
• v.36 no.3
• /
• pp.131-150
• /
• 2017

The purpose of this study is to observe the spread pattern of open source software (OSS) while establishing relations with surrounding actors during its operation period. In order to investigate the change pattern of participants in the OSS, we use a netnography on the basis of online data, which can trace the change patterns of the OSS depending on the passage of time. For this, the cases of three OSSs (e.g. jQuery, MooTools, and YUI), which are JavaScript frameworks, were compared, and the corresponding data were collected from the open application programming interface (API) of GitHub as well as blog and web searches. This research utilizes the translation process of the actor-network theory to categorize the stages of the change patterns on the OSS translation process. In the project commencement stage, we identified the type of three different OSS-related actors and defined associated relationships among them. The period, when a master commences a project at first, is refined through the course for the maintenance of source codes with persons concerned (i.e. project growth stage). Thereafter, the period when the users have gone through the observation and learning period by being exposed to promotion activities and codes usage respectively, and becoming to active participants, is regarded as the 'leap of participants' stage. Our results emphasize the importance of promotion processes in participants' selection of the OSS for participation and confirm the crowding-out effect that the rapid speed of OSS development retarded the emergence of participants.

• The Journal of the Acoustical Society of Korea
• /
• v.39 no.5
• /
• pp.497-504
• /
• 2020

Constructing speaker embeddings in speaker verification is an important issue. In general, a self-attention mechanism has been applied for speaker embedding encoding. Previous studies focused on training the self-attention in a high-level layer, such as the last pooling layer. In this case, the effect of low-level layers is not well represented in the speaker embedding encoding. In this study, we propose Masked Cross Self-Attentive Encoding (MCSAE) using ResNet. It focuses on training the features of both high-level and low-level layers. Based on multi-layer aggregation, the output features of each residual layer are used for the MCSAE. In the MCSAE, the interdependence of each input features is trained by cross self-attention module. A random masking regularization module is also applied to prevent overfitting problem. The MCSAE enhances the weight of frames representing the speaker information. Then, the output features are concatenated and encoded in the speaker embedding. Therefore, a more informative speaker embedding is encoded by using the MCSAE. The experimental results showed an equal error rate of 2.63 % using the VoxCeleb1 evaluation dataset. It improved performance compared with the previous self-attentive encoding and state-of-the-art methods.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.21 no.4
• /
• pp.525-537
• /
• 2020

This study aimed to determine the current state and characteristics of simulation-based operating processes in nursing education based on the Jeffries theoretical framework in South Korea by taking an integrated look at study findings in order to provide a scientific basis for future simulation-based operating processes. We searched eight databases, including the Korea Education and Research Information Service, National Library, Korean Studies Information Service System, National Digital Science Library, Korea Institute of Science and Technology Information, KOREAMED, and Korean Medical Database, using terms "simulation" and "nursing" as keywords in November 2017 in the Korean language. Sixteen studies were identified, reviewed, and appraised in this integrative review. The literature was categorized into these themes: general study characteristics, operation method, teaching and learning methods, subject characteristics, outcome variables, and theoretical framework. The simulation processes in nursing education in South Korea that were analyzed in this study did not fully reflect the main concepts suggested in the NLN Jeffries simulation framework. Thus, simulation program developers need to consider and incorporate a variety of strategies, based on the identification of essential components, to improve simulation effectiveness.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.21 no.1
• /
• pp.93-98
• /
• 2021

Due to the development of deep learning and AI, the scale of the model has grown, and it has been integrated into other fields to blend into our lives. However, in environments with limited resources such as embedded devices, it is exist difficult to apply the model and problems such as power shortages. To solve this, lightweight methods such as clouding or offloading technologies, reducing the number of parameters in the model, or optimising calculations are proposed. In this paper, quantization of learned models is applied to ONNX models used in various framework interchange formats, neural network structure and inference performance are compared with existing models, and various module methods for quantization are analyzed. Experiments show that the size of weight parameter is compressed and the inference time is more optimized than before compared to the original model.

• Journal of the Korea Society of Computer and Information
• /
• v.27 no.4
• /
• pp.231-239
• /
• 2022

In this paper, I analyze the difficulties of web service development education for non-IT majors through the Q&A of students posted in the k-mooc lecture, and propose methods to improve them. Through Q&A analysis, it was confirmed that non-majors mainly had difficulties in using unfamiliar tools, cost of cloud service, setting up server environment, and writing code while taking web service development courses. To solve this problem, I propose a method to reduce the server cost problem and the complexity of the server environment by using BaaS(Backend as a Service), which is one of the cloud service models. It also shows that it is possible to reduce the length of code that needs to be written at once by using the React library to modularize long code into smaller units. Finally, I propose an improvement plan that even non-IT majors can easily learn by implementing a web application that works by using the design output obtained by using Figma.

• Journal of KIISE:Software and Applications
• /
• v.35 no.3
• /
• pp.197-206
• /
• 2008

In the mobile Internet environment, frequent communications between a mobile device and a content server are required for searching or downloading learning materials. In this paper, we propose an efficient prefetching technique to reduce the network cost and to improve the communication efficiency in the mobile dictionary. Our prefetching-based approach can be explained as follows. First, we propose an overall framework for the prefetching-based mobile dictionary. Second, we present a systematic way of determining the amount of prefetching data for each of packet-based and flat-rate billing cases. Third, by focusing on the English-Korean mobile dictionary for middle or high school students, we propose an intuitive method of determining the words to be prefetched in advance. Fourth, based on these determination methods, we propose an efficient prefetching algorithm. Fifth, through experiments, we show the superiority of our prefetching-based method. From this approach, we can summarize major contributions as follows. First, to our best knowledge, this is the first attempt to exploit prefetching techniques in mobile applications. Second, we propose a systematic way of applying prefetching techniques to a mobile dictionary. Third, using prefetching techniques we improve the overall performance of a network-based mobile dictionary. Experimental results show that, compared with the traditional on-demand approach, our prefetching based approach improves the average performance by $9.8%{\sim}33.2%$. These results indicate that our framework can be widely used not only in the mobile dictionary but also in other mobile Internet applications that require the prefetching technique.