• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.12
• /
• pp.4364-4384
• /
• 2021

The dynamic network state and the mobility of the terminals make the service function chain (SFC) orchestration mechanisms based on static and deterministic assumptions hard to be applied in SDN/NFV mobile edge computing networks. Designing dynamic and online SFC orchestration mechanism can greatly improve the execution efficiency of compute-intensive and resource-hungry applications in mobile edge computing networks. In order to increase the overall profit of service provider and reduce the resource cost, the system running time is divided into a sequence of time slots and a dynamic orchestration scheme based on an improved column generation algorithm is proposed in each slot. Firstly, the SFC dynamic orchestration problem is formulated as an integer linear programming (ILP) model based on layered graph. Then, in order to reduce the computation costs, a column generation model is used to simplify the ILP model. Finally, a two-stage heuristic algorithm based on greedy strategy is proposed. Four metrics are defined and the performance of the proposed algorithm is evaluated based on simulation. The results show that our proposal significantly provides more than 30% reduction of run time and about 12% improvement in service deployment success ratio compared to the Viterbi algorithm based mechanism.

• Smart Structures and Systems
• /
• v.29 no.1
• /
• pp.53-62
• /
• 2022

The deployment of advanced structural health monitoring (SHM) systems in large-scale civil structures collects large amounts of data. Note that these data may contain multiple types of anomalies (e.g., missing, minor, outlier, etc.) caused by harsh environment, sensor faults, transfer omission and other factors. These anomalies seriously affect the evaluation of structural performance. Therefore, the effective analysis and mining of SHM data is an extremely important task. Inspired by the deep learning paradigm, this study develops a novel generative adversarial network (GAN) and convolutional neural network (CNN)-based data anomaly detection approach for SHM. The framework of the proposed approach includes three modules : (a) A three-channel input is established based on fast Fourier transform (FFT) and Gramian angular field (GAF) method; (b) A GANomaly is introduced and trained to extract features from normal samples alone for class-imbalanced problems; (c) Based on the output of GANomaly, a CNN is employed to distinguish the types of anomalies. In addition, a dataset-oriented method (i.e., multistage sampling) is adopted to obtain the optimal sampling ratios between all different samples. The proposed approach is tested with acceleration data from an SHM system of a long-span bridge. The results show that the proposed approach has a higher accuracy in detecting the multi-pattern anomalies of SHM data.

• The Plant Pathology Journal
• /
• v.39 no.5
• /
• pp.504-512
• /
• 2023

After transitioning from periodic to model-based control policy for fire blight blossom infection, it is crucial to provide the timing of field application with easy and accurate information. To assess the risk of blossom infection, Maryblyt was employed in 31 sites across apple-producing regions nationwide, including areas prone to fire blight outbreaks, from 2021 to 2023. In 2021 and 2023, two and seven sites experienced Blossom Infection Risk-Infection warning occurrences among 31 sites, respectively. However, in 2022, most of the sites observed Blossom Infection Risk-Infection from April 25 to 28, highlighting the need for blossom infection control. For the comparison between the two model-based control approaches, we established treatment 1, which involved control measures according to the Blossom Infection Risk-Infection warning and treatment 2, aimed at maintaining the Epiphytic Infection Potential below 100. The analysis of control values between these treatments revealed that treatment 2 was more effective in reducing Blossom Infection Risk-Infection and the number of days with Epiphytic Infection Potential above 100, with respective averages of 95.6% and 93.0% over the three years. Since 2022, the implementation of the K-Maryblyt system and the deployment of Automated Weather Stations capable of measuring orchard weather conditions, with an average of 10 stations per major apple fire blight county nationwide, have taken place. These advancements will enable the provision of more accurate and timely information for farmers based on fire blight models in the future.

• International conference on construction engineering and project management
• /
• 2020.12a
• /
• pp.409-416
• /
• 2020

This paper proposes a study measuring productivity improvement by using a type of technology called "Machine Guidance" through work sampling in earthwork. Earthwork is the activity typically on the critical path, indicating that productivity for the activity is critical for managing schedule on time. Thanks to the development of sensing and information system technologies, productivity for earthwork has been improved. While there have been many studies investigating the application of a certain type of technology to earthwork, few studies have measured the productivity improvement and presented how the technology leads to productivity improvement. Based on the thorough literature review, it is hypothesized that Machine Guidance contributes to improving productivity of earthwork by reducing indirect workhours spent for information waiting and inspection. In addition to the literature review, this paper presents a research model to test the hypothesis by using the work sampling technique. By proving and quantifying the productivity improvement from the technology use, this study can help practitioners justify the investment for technology use, which will contribute to the deployment of technology and more effective execution of earthwork.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.18 no.6
• /
• pp.319-325
• /
• 2023

In this study, we proposed a method for hyperparameter optimization in the building and training of a deep learning model designed to process point cloud data collected by a millimeter-wave radar system. The primary aim of this study is to facilitate the deployment of a baseline model in resource-constrained IoT devices. We evaluated a RadHAR baseline deep learning model trained on a public dataset composed of point clouds representing five distinct human activities. Additionally, we introduced a coarse-to-fine hyperparameter optimization procedure, showing substantial potential to enhance model efficiency without compromising predictive performance. Experimental results show the feasibility of significantly reducing model size without adversely impacting performance. Specifically, the optimized model demonstrated a 3.3% improvement in classification accuracy despite a 16.8% reduction in number of parameters compared th the baseline model. In conclusion, this research offers valuable insights for the development of deep learning models for resource-constrained IoT devices, underscoring the potential of hyperparameter optimization and model size reduction strategies. This work contributes to enhancing the practicality and usability of deep learning models in real-world environments, where high levels of accuracy and efficiency in data processing and classification tasks are required.

• International Journal of Computer Science & Network Security
• /
• v.24 no.6
• /
• pp.153-160
• /
• 2024

Information technology plays an important role in healthcare. The cloud has several applications in the fields of education, social media and medicine. But the advantage of the cloud for medical reasons is very appropriate, especially given the large volume of data generated by healthcare organizations. As in increasingly health organizations adopting towards electronic health records in the cloud which can be accessed around the world for various health issues regarding references, healthcare educational research and etc. Cloud computing has many advantages, such as "flexibility, cost and energy savings, resource sharing and rapid deployment". However, despite the significant benefits of using the cloud computing for health IT, data security, privacy, reliability, integration and portability are some of the main challenges and obstacles for its implementation. Health data are highly confidential records that should not be made available to unauthorized persons to protect the security of patient information. In this paper, we discuss the privacy and security requirement of EHS as well as privacy and security issues of EHS and also focus on a comprehensive review of the current and existing literature on Electronic health that uses a variety of approaches and procedures to handle security and privacy issues. The strengths and weaknesses of some of these methods were mentioned. The significance of security issues in the cloud computing environment is a challenge.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.36 no.12B
• /
• pp.1744-1751
• /
• 2011

The concept of the advanced concept technology demonstration (ACTD) has previously been introduced in USA in order to make it possible to rapidly transfer advanced technologies developed in commercial sectors to develop weapon systems in the defense area. Since then in Korea several ACTD programs have been developed and being carried out However, there are few program management methods suitable for the characteristics of the ACTD programs, which requires stringent management of the program requirements and risks due to the radically shortened development time. In this paper such a problem has been addressed and as a solution approach the quality function deployment (QFD) method has been adopted, which is being served as a successful model in various areas such as manufacturing. The QFD method is used in our study to improve communication between various stakeholders involved in the ACTD programs and also to reduce risks related to requirements. Specifically we have developed the ACTD standard templates based on the QFD method and discussed how to use the developed templates. Finally, the application of the study result is demonstrated through the ACTD program of flight information demonstration system and also specific ways are suggested to use the standard templates, to manage requirements, and to reduce risks.

• Journal of Advanced Marine Engineering and Technology
• /
• v.40 no.9
• /
• pp.836-841
• /
• 2016

An indoor positioning system using Wi-Fi is essential to produce a radio map that combines the indoor space of two or more dimensions, the information of node positions, and etc. in processing for constructing the radio map, the measurement of the received signal strength indicator(RSSI) and the confirmation of node placement information counsume substantial time. Especially, when the installed wireless environment is changed or a new space is created, easy installation of the node and fast indoor radio mapping are needed to provide indoor location-based services. In this paper, to reduce the time consumption, we propose an algorithm to distinguish the straight and curve lines of a corridor section by RSSI visualization and Sobel filter-based edge detection that enable accurate node deployment and space analysis using cable-type Wi-Fi node installed at a 3 m interval. Because the cable type Wi-Fi is connected by a same power line, it has an advantage that the installation order of nodes at regular intervals could be confirmed accurately. To be able to analyze specific sections in space based on this advantage, the distribution of the signal was confirmed and analyzed by Sobel filter based edge detection and total RSSI distribution(TRD) computation through a visualization process based on the measured RSSI. As a result to compare the raw data with the performance of the proposed algorithm, the signal intensity of proposed algorithm is improved by 13.73 % in the curve section. Besides, the characteristics of the straight and the curve line were enhanced as the signal intensity of the straight line decreased by an average of 34.16 %.

• Journal of the Institute of Electronics Engineers of Korea TC
• /
• v.43 no.7 s.349
• /
• pp.93-103
• /
• 2006

Network solutions for protecting against worm attacks that complement partial end system patch deployment is a pressing problem. In the content-based worm filtering, the challenges focus on the detection accuracy and its performance enhancement problem. We present a worm filter architecture using the bloom filter for deployment at high-speed transit points on the Internet, including firewalls and gateways. Content-based packet filtering at multi-gigabit line rates, in general, is a challenging problem due to the signature explosion problem that curtails performance. We show that for worm malware, in particular, buffer overflow worms which comprise a large segment of recent outbreaks, scalable -- accurate, cut-through, and extensible -- filtering performance is feasible. We demonstrate the efficacy of the design by implementing it on an Intel IXP network processor platform with gigabit interfaces. We benchmark the worm filter network appliance on a suite of current/past worms, showing multi-gigabit line speed filtering prowess with minimal footprint on end-to-end network performance.

• Journal of Nuclear Fuel Cycle and Waste Technology(JNFCWT)
• /
• v.16 no.2
• /
• pp.261-270
• /
• 2018

In this study, to replace the 'J-slot joint', a joint device between a disposal canister and an emplacement jig in Deep Borehole Disposal process, a novel joint device was designed and tested. The novel joint device was composed of a wedge on top of a disposal canister and a hook box at the end of a winch system. The designed joint device had merits in that it can recombine an emplaced canister freely without the replacement of the joint component. Moreover, it can be applied to various emplacement jigs such as drill pipes, wire-lines, and coiled tubing. To demonstrate the designed joint device, the joint device (${\Phi}110mm$, H 148 mm), a twin canister string (${\Phi}140mm$, H 1,105 mm), and a water tube (${\Phi}150mm$, H 1,500 mm) as a borehole model were manufactured at 1/3 scale. As deployment muds, Na-type bentonite (MX-80) and Ca-type (GJ II) bentonite muds were prepared at solid contents of 7wt% and 28wt%, respectively. The manufactured joint device showed good performance in pure water and viscous muds, with an operation speed of $10m{\cdot}min^{-1}$. It was concluded that the newly developed joint device can be used for the emplacement and retrieval of a deep disposal canister, below 3~5 km, in the future.