• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• 2022.11a
• /
• pp.298-299
• /
• 2022

Digital Transformation in the maritime transportation sector means "by utilizing digital technologies such as artificial intelligence, big data, Internet of Things, block chain, and cloud to create new business models, products, and services for maritime transportation-related companies. It can be defined as a continuous process that adapts to or drives disruptive changes in the market" (Chang, 2021). In a situation where various digital conversion technologies are applied and started to be used in the domestic port logistics field, active acceptance by members can bring about the success of digital conversion. Therefore, in this study, in order to investigate the acceptability of digital transformation in the domestic port logistics sector,

• Journal of Software Assessment and Valuation
• /
• v.15 no.2
• /
• pp.67-72
• /
• 2019

The recent explosion of data traffic, including cloud services, coupled with the Internet penetration has led to a surge in the need for ultra-fast optical networks that can efficiently connect the data center's reconfiguable resources. In this paper, the algorithms for controlling switching cell operation in the optical switch connection structure are proposed, and the resulting performance is compared and analyzed through simulation. Performance analysis results showed that the algorithm proposed in this paper has improved the probability of successful multi-connection setup by about 3 to 7% compared to the existing algorithm.

• Journal of Internet Computing and Services
• /
• v.24 no.6
• /
• pp.1-11
• /
• 2023

Federated learning (FL) is a ground breaking machine learning paradigm that allow smultiple participants to collaboratively train models in a cloud environment, all while maintaining the privacy of their raw data. This approach is in valuable in applications involving sensitive or geographically distributed data. However, one of the challenges in FL is dealing with heterogeneous and non-independent and identically distributed (non-IID) data across participants, which can result in suboptimal model performance compared to traditionalmachine learning methods. To tackle this, we introduce FedGCD, a novel FL algorithm that employs Graph Neural Network (GNN)-based community detection to enhance model convergence in federated settings. In our experiments, FedGCD consistently outperformed existing FL algorithms in various scenarios: for instance, in a non-IID environment, it achieved an accuracy of 0.9113, a precision of 0.8798,and an F1-Score of 0.8972. In a semi-IID setting, it demonstrated the highest accuracy at 0.9315 and an impressive F1-Score of 0.9312. We also introduce a new metric, nonIIDness, to quantitatively measure the degree of data heterogeneity. Our results indicate that FedGCD not only addresses the challenges of data heterogeneity and non-IIDness but also sets new benchmarks for FL algorithms. The community detection approach adopted in FedGCD has broader implications, suggesting that it could be adapted for other distributed machine learning scenarios, thereby improving model performance and convergence across a range of applications.

• Journal of Distribution Science
• /
• v.22 no.2
• /
• pp.21-30
• /
• 2024

Purpose: This study explores the development of zakat distribution studies and the integration of existing studies. This study is expected to complement a systematic literature review in the field of zakat distribution to inspire further research directions. Research design, data, and methodology: This research method uses a systematic literature review assisted by the Nvivo application and the PRISMA system, which selects from 427 articles to 53 articles to be analyzed based on publication and classification of the theme of its findings. This study describes publications, authors, themes, cited articles, and research themes. Results: This study shows the dominance of Malaysian writers and significant developments in 2020. In addition, the study shows the most popular articles based on the most citations and word cloud analysis. The primary topics of zakat distribution publications are management strategy, development, the zakat institution, and the recipient. Conclusions: The study advises that Future research could focus on zakat distribution's asnaf characteristics. Next, a study on administration expenses and scalability concerns in zakat collection and distribution planning can avoid wasting cash. This topic hinders zakat institutions' distribution services.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2024.05a
• /
• pp.774-776
• /
• 2024

The effective implementation of advanced speech recognition (ASR) systems necessitates the deployment of sophisticated keyword spotting models that are both responsive and resource-efficient. The initial local detection of user interactions is crucial as it allows for the selective transmission of audio data to cloud services, thereby reducing operational costs and mitigating privacy risks associated with continuous data streaming. In this paper, we address these needs and propose utilizing the Whisper-Tiny model with fine-tuning process to specifically recognize keywords from google speech dataset which includes 65000 audio clips of keyword commands. By adapting the model's encoder and appending a lightweight classification head, we ensure that it operates within the limited resource constraints of local devices. The proposed model achieves the notable test accuracy of 92.94%. This architecture demonstrates the efficiency as on-device model with stringent resources leading to enhanced accessibility in everyday speech recognition applications.

• The Journal of the Korea Contents Association
• /
• v.20 no.7
• /
• pp.97-106
• /
• 2020

Due to the rapid development and dissemination of 5G communication and IoT technologies, there are increasing demands for big data analysis techniques and service systems. In particular, explosively growing demands on AI technology adoption are also causing high competitions to take advantages of machine/deep-learning models to extract novel values from enormously collected data. In order to adopt AI technology to various research and application domains, it is necessary to prepare high-performance GPU-equipped systems and perform complicated settings to utilze deep learning models. To relieve the efforts and lower the barrier to utilize AI techniques, AIaaS(AI as a service) platform is attracting a great deal of attention as a promising on-line service, where the complexity of preparation and operation can be hidden behind the cloud side and service developers only need to utilize the high-level AI services easily. In this paper, we propose an AIaaS system which can support the creation of AI services based on Docker and OpenFaaS from the registration of models to the on-line operation. We also describe a case study to show how AI services can be easily generated by the proposed system.

• Journal of Internet Computing and Services
• /
• v.19 no.4
• /
• pp.1-6
• /
• 2018

In smart cities, data from various kinds of sensors are collected and processed to provide smart services to the citizens. Noise information services with noise maps using the collected sensor data from various kinds of ubiquitous sensor networks is one of them. This paper presents a research result which generates three dimensional (3D) noise maps in real-time for smart cities. To make a noise map, we have to converge many informal data which include big image data of geographical Information and massive sensor data. Making such a 3D noise map in real-time requires the processing of the stream data from the ubiquitous sensor networks in real-time and the convergence operation in real-time. They are very challenging works. We developed our own methodology for real-time distributed and parallel processing for it and present it in this paper. Further, we developed our own real-time 3D noise map generation system, with the methodology. The system uses open source softwares for it. Here in this paper, we do introduce one of our systems which uses Apache Storm. We did performance evaluation using the developed system. Cloud computing was used for the performance evaluation experiments. It was confirmed that our system was working properly with good performance and the system can produce the 3D noise maps in real-time. The performance evaluation results are given in this paper, as well.

• Journal of Service Research and Studies
• /
• v.5 no.2
• /
• pp.15-24
• /
• 2015

The trade balance for the information and communications technology (ICT) industries in 2014 have reached 863 hundred million dollars as the main export products such as smart phone and semi-conductor increase, since the ICT industries have played an important role in economic growth in Korea. Until now, the consistent supporting of government and investment of company have been doing with the growth of ICT industries, as a result, Korea marked as the first in the UN electronic government preparing index, and rank 12 in the network preparing index through the policy of national information and basic plan of inter-industry convergence. However, as the unstable international economic circumstances, ICT industries is faced with the stagnation, and then preemptive development of products and services for ICT convergence industries is needed to continually get definite ICT Korea image. In this paper, the ICT convergence industry is analyzed and forecasted. In specific, the international and domestic market for cloud, 3D convergence, and internet of things is diagnosed. The market for ICT convergence industries is predicted to be 3.6 trillion dollar in the world, and 110 trillion won in domestic. From the analytical results for technology and services development, the preemptive supporting of the technology development and policy for the internet of things and 3D convergence industries is required. In addition to, through the future forecasting by socio-tech matrix method, the policy supporting for the ICT convergence area of healthcare, fintech, artificial intelligence, body platform, and human security is needed.

• Journal of the Korea Society for Simulation
• /
• v.32 no.1
• /
• pp.35-44
• /
• 2023

In recent, there are many research cases that analyze trends or research trends with text analysis. When collecting documents by searching for keywords in abbreviations for data analysis, it is necessary to disambiguate abbreviations. In many studies, documents are classified by hand-work reading the data one by one to find the data necessary for the study. Most of the studies to disambiguate abbreviations are studies that clarify the meaning of words and use supervised learning. The previous method to disambiguate abbreviation is not suitable for classification studies of documents looking for research data from abbreviation search documents, and related studies are also insufficient. This paper proposes a method of semi-automatically classifying documents collected by abbreviations by going topic modeling with Non-Negative Matrix Factorization, an unsupervised learning method, in the data pre-processing step. To verify the proposed method, papers were collected from academic DB with the abbreviation 'MSA'. The proposed method found 316 papers related to Micro Services Architecture in 1,401 papers. The document classification accuracy of the proposed method was measured at 92.36%. It is expected that the proposed method can reduce the researcher's time and cost due to hand work.

• Journal of Intelligence and Information Systems
• /
• v.28 no.1
• /
• pp.29-43
• /
• 2022

With the advent of the Internet and the development of mobile digital devices such as smartphones and tablet PCs, the communication service paradigm began to shift from existing voice services to data services. Recently, as social network services (SNS) are activated and 4th industrial revolution technologies centered on ICT (Information and Communication Technologies) such as Big Data, Blockchain, Cloud, and 5G/6G are rapidly developed, the amount of shared data type and the amount of data are increasing rapidly. As the transition to a digital society begins actively, the importance of using data information, as well as the economic and social values of personal information are becoming increasingly important. As a result, they are actively discussing policies to revitalize the data information industry around the world and ways to efficiently obtain, analyze, and utilize increasingly diverse and vast data, as well as to protect/guarantee the rights of information subjects (providers) in various fields such as society, culture, economy, and politics.. In this paper, in order to improve the self-determination right of personal information on data produced by information subjects, and further expand the use of safe data and the data economy, a differentiated data trusts system was considered and suggested. In addition, the components and data trusts procedures necessary to efficiently operate the data trusts system in Korea were considered, and the non-profit data trusts system and the for-profit data trusts system were considered as a way to flexibly operate the data trusts system. Furthermore, the legal items necessary for the implementation of the data trusts system were investigated and considered. In this paper, in order to propose a domestic data trusts system, cases related to existing data trusts systems such as the United States, Japan, and Korea were reviewed and analyzed. In addition, in order to prepare legislation necessary for the data trusts system, data-related laws in major countries and domestic legal and policy trends were reviewed to study the rights that conflict or overlap with existing laws, and differences were investigated and considered. The Data trusts system proposed in this paper is a reasonable system that is expected to recognize the asset value of data in the capitalist market economy system, to provide legitimate compensation for data produced by data subjects, and further to contribute greatly to the use of safe data and creation of a new service market.