• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.11a
• /
• pp.151-153
• /
• 2023

Federated learning (FL)-based network intrusion detection techniques have enormous potential for securing the Industrial Internet of Things (IIoT) cybersecurity. The openness and connection of systems in smart industrial facilities can be targeted and manipulated by malicious actors, which emphasizes the significance of cybersecurity. The conventional centralized technique's drawbacks, including excessive latency, a congested network, and privacy leaks, are all addressed by the FL method. In addition, the rich data enables the training of models while combining private data from numerous participants. This research aims to create an FL-based architecture to improve cybersecurity and intrusion detection in IoT networks. In order to assess the effectiveness of the suggested approach, we have utilized well-known cybersecurity datasets along with centralized and federated machine learning models.

• International Journal of Precision Engineering and Manufacturing-Green Technology
• /
• v.5 no.5
• /
• pp.659-670
• /
• 2018

The Industrial Internet of Things (IIoT) confronts industrial manufactures with economic, ecological, as well as social benefits and challenges, referring to the Triple Bottom Line of sustainability. So far, research has mainly investigated its dimensions in isolation or economic aspects have not been compared with ecological and social perspectives. Further, research misses studies that are devoted to the special characteristics and requirements of Small and Medium-sized Enterprises (SMEs). This study aims to contribute to close this research gap, providing a research context that encompasses all three dimensions of sustainability. The results are based on data obtained from 329 SMEs, 222 in Germany and 107 in China, therefore allowing for a comparison of the concepts "Industrie 4.0" and "Made in China 2025" in the context of SMEs. In general, German SMEs expect a lower impact through "Industrie 4.0", perceiving the concept as more beneficial for larger enterprises. We further find that Chinese SMEs foremost see social benefits. Challenges whilst introducing "Industrie 4.0"by German SMEs as well as several frame conditions are perceived more relevant than for "Made in China 2025", as seen by Chinese SMEs. The paper closes with implications for research and practice based on these findings.

• Journal of Intelligence and Information Systems
• /
• v.25 no.2
• /
• pp.57-75
• /
• 2019

In this paper, we conducted a study focusing on the innovation direction of the documentary model on the Internet of Things industry, which is the most actively industrialized among the core technologies of the 4th Industrial Revolution. Policy, economic, social, and technical issues were derived using PEST analysis for global trend analysis. It also presented future prospects for the Internet of Things industry of ICT-related global research institutes such as Gartner and International Data Corporation. Global research institutes predicted that competition in network technologies will be an issue for industrial Internet (IIoST) and IoT (Internet of Things) based on infrastructure and platforms. As a result of the PEST analysis, developed countries are pushing policies to respond to the fourth industrial revolution through cooperation of private (business/ research institutes) led by the government. It was also in the process of expanding related R&D budgets and establishing related policies in South Korea. On the economic side, the growth tax of the related industries (based on the aggregate value of the market) and the performance of the entity were reviewed. The growth of industries related to the fourth industrial revolution in advanced countries overseas was found to be faster than other industries, while in Korea, the growth of the "technical hardware and equipment" and "communication service" sectors was relatively low among industries related to the fourth industrial revolution. On the social side, it is expected to cause enormous ripple effects across society, largely due to changes in technology and industrial structure, changes in employment structure, changes in job volume, etc. On the technical side, changes were taking place in each industry, representing the health and medical sectors and manufacturing sectors, which were rapidly changing as they merged with the technology of the Fourth Industrial Revolution. In this paper, various management methodologies for innovation of existing business model were reviewed to cope with rapidly changing industrial environment due to the fourth industrial revolution. In addition, four criteria were established to select a management model to cope with the new business environment: 'Applicability', 'Agility', 'Diversity' and 'Connectivity'. The expert survey results in an AHP analysis showing that Business Model Canvas is best suited for business model innovation methodology. The results showed very high importance, 42.5 percent in terms of "Applicability", 48.1 percent in terms of "Agility", 47.6 percent in terms of "diversity" and 42.9 percent in terms of "connectivity." Thus, it was selected as a model that could be diversely applied according to the industrial ecology and paradigm shift. Business Model Canvas is a relatively recent management strategy that identifies the value of a business model through a nine-block approach as a methodology for business model innovation. It identifies the value of a business model through nine block approaches and covers the four key areas of business: customer, order, infrastructure, and business feasibility analysis. In the paper, the expansion and application direction of the nine blocks were presented from the perspective of the IoT company (ICT). In conclusion, the discussion of which Business Model Canvas models will be applied in the ICT convergence industry is described. Based on the nine blocks, if appropriate applications are carried out to suit the characteristics of the target company, various applications are possible, such as integration and removal of five blocks, seven blocks and so on, and segmentation of blocks that fit the characteristics. Future research needs to develop customized business innovation methodologies for Internet of Things companies, or those that are performing Internet-based services. In addition, in this study, the Business Model Canvas model was derived from expert opinion as a useful tool for innovation. For the expansion and demonstration of the research, a study on the usability of presenting detailed implementation strategies, such as various model application cases and application models for actual companies, is needed.

• Journal of Information Technology Services
• /
• v.19 no.5
• /
• pp.33-47
• /
• 2020

In recent years, due to the demand for operating efficiency and cost reduction of industrial facilities, remote access via the Internet is expanding. the control network accelerates from network separation to network connection due to the development of IIoT (Industrial Internet of Things) technology. Transition of control network is a new opportunity, but concerns about cybersecurity are also growing. Therefore, manufacturers must reflect security compliance and standards in consideration of the Internet connection environment, and enterprises must newly recognize the connection area of the control network as a security management target. In this study, the core target of the control system security threat is defined as the network boundary, and issues regarding the security architecture configuration for the boundary and the role & responsibility of the working organization are covered. Enterprises do not integrate the design organization with the operation organization after go-live, and are not consistently reflecting security considerations from design to operation. At this point, the expansion of the control network is a big transition that calls for the establishment of a responsible organization and reinforcement of the role of the network boundary area where there is a concern about lack of management. Thus, through the organization of the facility network and the analysis of the roles between each organization, an static perspective and difference in perception were derived. In addition, standards and guidelines required for reinforcing network boundary security were studied to address essential operational standards that required the Internet connection of the control network. This study will help establish a network boundary management system that should be considered at the enterprise level in the future.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2018.07a
• /
• pp.47-48
• /
• 2018

본 논문에서는 NP-hard 문제로 알려진 잡샵 스케쥴링에 대하여 강화학습적 측면에서 접근하는 방식에 대해 제안한다. 다양한 시간이 소요되는 업무들이 가지는 특징들을 최대한 state space aggregation에 고려하고, 이를 neural network를 통해 최적화 시간을 줄이는 방식이다. 잡샵 스케쥴링에 대한 솔루션은 미래에 대한 예측이 불가능하고 다양한 시간이 소요되는 스케쥴링 문제를 최적화하는 것에 대한 가능성을 제시할 것으로 기대된다.

• Review of KIISC
• /
• v.25 no.3
• /
• pp.5-10
• /
• 2015

스마트그리드(Smartgrid) 시대의 도래 및 제어시스템으로의 IIoT(Industrial Internet of Things) 기술 도입으로 외부 인터넷망과의 접점이 증가하면서 스마트그리드 제어시스템을 대상으로 하는 사이버위협이 증가하고 있는 추세이며, 그에 대한 피해 사례가 지속적으로 보고되고 있다. 또한 스마트그리드 제어시스템에 HCI(Human-Computer Interaction) 기술이 악의적인 내부 공격자는 전문적인 지식이 없더라도 비교적 쉽게 제어시스템을 조작 및 오작동 시킬 수 있게 되었다. 본 논문에서는 HCI가 적용된 스마트그리드 제어시스템에서의 내부자 공격에 대응하기 위해 사용자 및 구성 장비에 대한 인증 기능을 강화하여 제어시스템 사용자와 구성 장비의 신뢰성을 보장할 수 있는 방법을 제시한다.

• Journal of the Korea Society of Computer and Information
• /
• v.27 no.10
• /
• pp.105-113
• /
• 2022

In this paper, we present and analyze 5G system and IEEE time-sensitive networking(TSN) and propose a novel mobility management scheme for time sensitive communications in 5G-TSN to support ultra-low latency networks. Time-sensitive networking(TSN) has a promising future in the Industrial Automation and Industrial Internet of Things(IIoT), as a key technology that is able to provide low-latency, high-reliable and deterministic communications over the Ethernet. When a TSN capable UE moves the TSN service coverage from the non-TSN service coverage, the UE cannot get the TSN service promptly because the related mobility management is not performed appropriately. For the mobility situation with the TSN service coverage, the proposed scheme reports TSN capability to the network and triggers the initial registration in order to be provided the TSN service immediately and ultra-low latency communications compared to existing schemes in 5G mobile networks.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.18 no.2
• /
• pp.348-369
• /
• 2024

With the advancement of Industry 4.0 and Industrial Internet of Things (IIoT), manufacturing increasingly seeks automation and intelligence. Temperature and vibration monitoring are essential for machinery health. Traditional abnormal state detection methodologies often overlook the intricate frequency characteristics inherent in vibration time series and are susceptible to erroneously reconstructing temperature abnormalities due to the highly similar waveforms. To address these limitations, we introduce synergistic, end-to-end, unsupervised Frequency-Time Domain Memory-Enhanced Autoencoders (FTD-MAE) capable of identifying abnormalities in both temperature and vibration datasets. This model is adept at accommodating time series with variable frequency complexities and mitigates the risk of overgeneralization. Initially, the frequency domain encoder processes the spectrogram generated through Short-Time Fourier Transform (STFT), while the time domain encoder interprets the raw time series. This results in two disparate sets of latent representations. Subsequently, these are subjected to a memory mechanism and a limiting function, which numerically constrain each memory term. These processed terms are then amalgamated to create two unified, novel representations that the decoder leverages to produce reconstructed samples. Furthermore, the model employs Spectral Entropy to dynamically assess the frequency complexity of the time series, which, in turn, calibrates the weightage attributed to the loss functions of the individual branches, thereby generating definitive abnormal scores. Through extensive experiments, FTD-MAE achieved an average ACC and F1 of 0.9826 and 0.9808 on the CMHS and CWRU datasets, respectively. Compared to the best representative model, the ACC increased by 0.2114 and the F1 by 0.1876.