• Smart Structures and Systems
• /
• v.32 no.5
• /
• pp.319-338
• /
• 2023

The study presents a new hybrid data-driven method by combining radial basis functions neural networks (RBF-NN) with the Jaya algorithm (JA) to provide effective structural health monitoring of arch dams. The novelty of this approach lies in that only one user-defined parameter is required and thus can increase its effectiveness and efficiency, as compared to other machine learning techniques that often require processing a large amount of training and testing model parameters and hyper-parameters, with high time-consuming. This approach seeks rapid damage detection in arch dams under dynamic conditions, to prevent potential disasters, by utilizing the RBF-NNN to seamlessly integrate the dynamic elastic modulus (DEM) and modal parameters (such as natural frequency and mode shape) as damage indicators. To determine the dynamic characteristics of the arch dam, the JA sequentially optimizes an objective function rooted in vibration-based data sets. Two case studies of hyperbolic concrete arch dams were carefully designed using finite element simulation to demonstrate the effectiveness of the RBF-NN model, in conjunction with the Jaya algorithm. The testing results demonstrated that the proposed methods could exhibit significant computational time-savings, while effectively detecting damage in arch dam structures with complex nonlinearities. Furthermore, despite training data contaminated with a high level of noise, the RBF-NN and JA fusion remained the robustness, with high accuracy.

• Journal of Platform Technology
• /
• v.12 no.1
• /
• pp.67-76
• /
• 2024

Small and medium-sized enterprises play a fundamental role in the foundation of our country's industry and economy, and most technological innovations occur in small and medium-sized enterprises rather than large corporations. Technology development and innovation are the only way for small and medium-sized enterprises to survive in a fiercely competitive environment, so they focus on it, but interest and investment in technology protection tend to be stingy. As a result, industrial technology leakage accidents occur frequently, and it is difficult to meet improvement measures. When a leak occurs, digital evidence is required to prove criminal activity, but problems such as digital evidence being damaged or deleted due to management loopholes often occur. Therefore, through this study, we aim to design a digital evidence-based countermeasure depending on the type of technology leak accident. We will classify the types of technology leak incidents that actually occurred and study ways to secure digital evidence in the security environment of small and medium-sized businesses that operate internal information leak prevention solutions.

• Journal of Internet of Things and Convergence
• /
• v.10 no.4
• /
• pp.27-33
• /
• 2024

As of 2023, the number of accident victims in the domestic construction industry is 26,829, ranking second only to other businesses (service industries). The accident types of casualties in all industries were falls (29,229 people), followed by falls (14,357 people). Based on the above data, this study attaches sensors to hard hats and insoles to predict fall accidents that frequently occur at construction sites, and proposes smart safety equipment that applies a random forest algorithm based on the data collected through this. The random forest model can determine fall accidents in real time with high accuracy by generating multiple decision trees and combining the predictions of each tree. This model classifies whether a worker has had a fall accident and the type of behavior through data collected from the MPU-6050 sensor attached to the hard hat. Fall accidents that are primarily determined from hard hats are secondarily predicted through sensors attached to the insole, thereby increasing prediction accuracy. It is expected that this will enable rapid response in the event of an accident, thereby reducing worker deaths and accidents.

• Management & Information Systems Review
• /
• v.34 no.1
• /
• pp.179-190
• /
• 2015

Local governments are commercializing natural environment, one of tourist commodities, to ensure that the proceeds from sale of tourist commodities are returned to local residents(Han Yeong-joo, Lee Moo-yong, 2001). In Songdo beach, Busan, cable car dismantled in 1980s due to the run-down state of the facility is poised for restoration in 26 years and can be said to be of great value as tourist commodity of the region and necessitates the demand forecast. To overcome limitations of demand forecast in existing studies, the analysis was made based on feasibility rate(Gruber index, self-confidence index), the realizable predictive value, for the willingness-to-visit rate when forecasting the demand of visitors. The results of demand forecast suggested that number of visitors would range from approximately 550,684 persons to 1,514,416 persons when the target region for demand forecast was confined to Busan Metropolitan City, and was in the range between 1,013,740 persons and 2,854,340 persons when the target region was expanded to cover Busan, Ulsan, and Gyeongnam. Based on the results of this study, estimation of visitors and demand forecast for Songdo offshore cable car restoration which reflect characteristics of Songdo beach of Busan would provide important basis for proceeding with tourism industry development project.

• Journal of the Korean Society for Library and Information Science
• /
• v.51 no.4
• /
• pp.99-120
• /
• 2017

In order to develop a semiautomatic support system that allows researchers concerned to efficiently analyze the technical trends for the ever-growing industry and market. This paper introduces a couple of Korean sentence generation models that can automatically generate definitional statements as well as descriptions of technical terms and concepts. The proposed models are based on a deep learning model called LSTM (Long Sort-Term Memory) capable of effectively labeling textual sequences by taking into account the contextual relations of each item in the sequences. Our models take technical terms as inputs and can generate a broad range of heterogeneous textual descriptions that explain the concept of the terms. In the experiments using large-scale training collections, we confirmed that more accurate and reasonable sentences can be generated by CHAR-CNN-LSTM model that is a word-based LSTM exploiting character embeddings based on convolutional neural networks (CNN). The results of this study can be a force for developing an extension model that can generate a set of sentences covering the same subjects, and furthermore, we can implement an artificial intelligence model that automatically creates technical literature.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.34 no.3B
• /
• pp.235-246
• /
• 2009

The number of industry wireless networks based on IEEE 802.11 WLAN technology deployed in large outdoor work sites, such as freight container terminal, is increasing these days. Wider service coverage, frequent movements of stations and high requirement on service reliability are main characteristics of these networks compared to the conventional IEEE 802.11 networks used in home, office and school. While the importance of these networks Bets higher, we can hardly find previous studies including concrete analysis on these networks based on actual experiments. We carried out several field experiments at a freight container terminal to analyze its IEEE 802.11 network and found out some problematic situations, such as over 50% retransmission rates and frequent disruption of communication link while a station is moving. We explain why these problematic situations happen and suggest some solutions, such as application of mesh technology, smart handoff based on location and movement pattern and adjustment of signal strength and channel allocation. Methods and tools used in the experiments are also detailed in the paper which may be helpful for similar future studies.

• Asia pacific journal of information systems
• /
• v.18 no.1
• /
• pp.117-144
• /
• 2008

Lots of virtual communities and online businesses presently derive their primary sources of revenues through advertising, but nevertheless are plagued with marginal profitability though they might possess a significant user base. In the light of the need for an efficacious business model, there have been recent insights of an online community in particular reaping profits through an innovative and lucrative revenue generation method that earns by selling digital items. There have been some obvious evidences (e.g., Cyworld, SecondLife, Habo Hotel, etc.) that online communities can be profitable through their unique business model of selling digital items. However, there is lack of understanding about the motivation of purchasing digital items. This study tries to identify the main motivators of digital item purchases based on social/individual identity theory and self-presentation theory. "Digital items", otherwise known as "virtual assets", may include online avatars, accessories for the avatars, decorative ornaments like furniture, digital wallpapers, skins, background music and virtual weapons used for Internet games. These digital items are employed by users for representation and articulation in the online space, especially to create and enhance their online profiles in web pages and games. Prices for digital items typically range from a few cents to a few dollars each. Based on the theoretical framework like social identity theory and self-presentation theory, we developed the research model and proposed seven hypotheses. An analysis of 225 members of Cyworld found that digital item purchase intention in virtual world is affected by both members' need for self-presentation and need for affiliation. We also found that the need for self-presentation is significantly increased by innovativeness of members, community group norm, and community involvement. We concluded that the need for self-presentation could be a key variable for profitable business model in online community service industry. However, neither individual self-efficacy nor the need for affiliation significantly influenced the need for self-presentation which triggers purchase intention of digital items. In term of the theoretical and practical contribution, this study can be a pioneering empirical research that investigates the purchase intention of digital items based on social identity theory and self-presentation theory in the online context. Also, the findings of our study are valuable and practical for practitioners in the market who wish to adopt or improve the business model of selling digital items in an online community. From the findings, it can be seen that innovativeness of users, community group norm, and community involvement are three significant factors that influence need for self-presentation of users which ultimately leads to their intentions to buy digital items. These findings put forth that virtual community providers and online businesses selling digital items should prioritize their efforts and focus on these three factors if they want to increase the sales of these digital items and generate greater revenues. This study provides important implications for academic researchers and practitioners to understand why the community members pay money for their digital items in virtual world and how the practitioners can increase the sales of digital items in an online community. A couple of limitations of the study and future research directions are also discussed.

• Journal of Korea Spatial Information System Society
• /
• v.7 no.2 s.14
• /
• pp.39-45
• /
• 2005

Nowadays, the demand of the output analyzed from the grid data have been sharply increased as the remote sensing technologies and GIS related industry have been developed. Therefore, a metadata access system which fits the requirements of the users should be developed for better managing and utilizing gridded data. In this background, this study defined a common application schema through the analysis of the metadata built by numerous institutes based on the draft metadata standards. The draft metadata standards has been proposed from the study supported by ETRI at 2003 which mainly concentrated on establishing the standards of distributing metadata for the grid data. Also, XML based integrated system was developed to access metadata maintained by SaTReC as well as SIMC to facilitate more convenient data access for the grid data users. The results of the pilot system developed from this study can be expected to contribute to build more efficient and enlarged integrated access system of metadata for grid data.

• Korean journal of communication and information
• /
• v.33
• /
• pp.169-191
• /
• 2006

Changing our monopoly broadcasting advertising system into free competition system may give rise to serious troubles that intensify commercialism of broadcasting and reduce diversity of public opinion. In the boundaries of public interest out of danger, korean broadcasting system should adopt a system that partially adopts the principle of free market. Broadcasting advertising sale system affect the whole broadcasting system because it functions as an effective capital-resource provider. Thus, it affects the broadcasting policies' righteousness and efficiency. Due to the non-elastic nature of the total advertising market, broadcasting advertising's size affects other media's capital allocation process. Therefore, broadcasting advertising sales system not only affects broadcast's social duty and public interest, but also affects the whole media industry. First, provide fair and open-competitive measures to support broadcast sales policy so that the market-based system can be run smoothly. Second, block any un-due influence from advertisers by separating production/programming and advertising sales. Third, sustain public broadcast system, not based on the advertising sales but based on the subscription fee. Fourth, social intervention of the advertising market. Fifth, provide policies that can set up multiple media channels/outlets and public opinion. By providing the minimum capital resources to the public broadcasting system, the broadcasting system can act on its public-interest duty and support the people's right-to-know rights.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.9 no.3
• /
• pp.257-265
• /
• 2016

In this study, an optimal design for motor-driven track type traveling system applied into high clearance working machineries in orchard is proposed. Tractive performance and hill climbing ability were predicted and evaluated for the optimal motor traveling system by taking into account of soil characteristics in orchard utilizing the high clearance working machineries. Design criteria for tractive performance were based on the traction force calculated from tractive effort subtracted by motion resistance, while hill climbing ability had its design criteria that fulfill the climbing 20% slope ground at a speed of 3km/h. Based on the evaluation results of traction and climbing ability, two DC48V, 4500rpm, 1.6kW AC motors were independently applied to both left and right side of orbits; each motor is designed to transmit power on driving sprocket of track type traveling system via 50:1 reduction gear ratio. The motor-driven track type traveling system developed in the study found to have 396 kgf of tractive force, which is 12.5% higher than climbing resistance at orchard soil having 20% slope ground (352 kgf), demonstrating sufficient tractive performance and hill climbing ability.