• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.17 no.3
• /
• pp.775-793
• /
• 2023

Human decision-making is a complex behavior. A replication of human decision making offers a potential to enhance the capacity of intelligent systems by providing additional user assistance in decision making. By reducing the effort and task complexity on behalf of the user, such replication would improve the overall user experience, and affect the degree of intelligence exhibited by the system. This paper explores individuals' decision-making processes when using recommender systems, and its related outcomes. In this study, human decision-making (HDM) refers to the selection of an item from a given set of options that are shown as recommendations to a user. The goal of our study was to identify IS constructs that contribute towards such decision-making, thereby contributing towards creating a mental model of HDM. This was achieved through recording Electroencephalographic (EEG) readings of subjects while they performed a decision-making activity. Readings from 16 righthanded healthy avid readers reflect that reward, theory of mind, risk, calculation, task intention, emotion, sense of touch, ambiguity and decision making are the primary constructs that users employ while deciding from a given set of recommendations in an online bookstore. In all 10 distinct brain areas were identified. These brain areas that lead to their respective constructs were found to be cingulate gyrus, precentral gyrus, inferior parietal lobule, posterior cingulate, medial frontal gyrus, anterior cingulate, postcentral gyrus, superior frontal gyrus, inferior frontal gyrus, and middle frontal gyrus (also referred to as dorsolateral prefrontal gyrus (DLPFC)). The identified constructs would help in developing a design theory for enhancing user assistance, especially in the context of recommender systems.

• Asia-pacific Journal of Multimedia Services Convergent with Art, Humanities, and Sociology
• /
• v.7 no.12
• /
• pp.955-963
• /
• 2017

Nowadays, fintech becomes the key technology of the mobile banking and payments. Financial market is moved to fintech-based non-face-to-face trade/payment from traditional face-to-face process in Korea. Core of this transition is the smartphones, which have several sensitive sensors for personal identifications such as fingerprint and iris recognition sensors. But it has some originated security risks by data path attacks, for instance, hacking and pharming. Multi-level certification and security systems are applied to avoid these threats effectively, while these protections can be cause of some inconvenience for non-face-to-face certifications and financing processes. In this paper, I confirmed that it have sensible differences correspond with the data connection paths such as WiFi networks and mobile communication networks of the smartphones, and I propose a gradual certification method which alleviates the inconvenience by risk-level definitions of the data-paths.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2020.06a
• /
• pp.85-85
• /
• 2020

South Korea experiences few large scale erosion and sedimentation problems, however, there are numerous local sedimentation problems. A reliable and consistent approach to modelling and management for sediment processes are desirable in the country. In this study, field measurements of sediment concentration from 34 alluvial river basins in South Korea were used with the Modified Einstein Procedure (MEP) to determine the total sediment load at the sampling locations. And then the Flow Duration-Sediment Rating Curve (FD-SRC) method was used to estimate the specific degradation for all gauging stations. The specific degradation of most rivers were found to be typically 50-300 tons/㎢·yr. A model tree data mining technique was applied to develop a model for the specific degradation based on various watershed characteristics of each watershed from GIS analysis. The meaningful parameters are: 1) elevation at the middle relative area of the hypsometric curve [m], 2) percentage of wetland and water [%], 3) percentage of urbanized area [%], and 4) Main stream length [km]. The Root Mean Square Error (RMSE) of existing models is in excess of 1,250 tons/㎢·yr and the RMSE of the proposed model with 6 additional validations decreased to 65 tons/㎢·yr. Erosion loss maps from the Revised Universal Soil Loss Equation (RUSLE), satellite images, and aerial photographs were used to delineate the geospatial features affecting erosion and sedimentation. The results of the geospatial analysis clearly shows that the high risk erosion area (hill slopes and construction sites at urbanized area) and sedimentation features (wetlands and agricultural reservoirs). The result of physiographical analysis also indicates that the watershed morphometric characteristic well explain the sediment transport. Sustainable management with the data mining methodologies and geospatial analysis could be helpful to solve various erosion and sedimentation problems under different conditions.

• Journal of the Korea Institute of Building Construction
• /
• v.23 no.4
• /
• pp.405-416
• /
• 2023

Recent seismic activities in countries like China and Turkey have underscored the widespread and severe damages that earthquakes can inflict globally. Being situated in a seismically active zone, South Korea can no longer regard itself as immune to earthquake hazards, necessitating the urgent adoption of proactive measures against such threats. The government has been proactive in evaluating, formulating processes, and methods for the seismic retrofitting of public buildings lacking in earthquake resistance. However, enforcement mechanisms for privately-owned apartment complexes are absent, and in the face of insufficient previous research and guidelines, preemptive measures for public safety remain alarmingly inadequate. With over 48% of residential structures in Korea aged over 30 years, and apartment complexes constituting more than 80% of these, the gravity of the situation is undeniable. This study deduces key factors for seismic retrofitting of apartment buildings like earthquake zones, soil type, building significance, aging degree, vulnerability, etc., based on building seismic design codes. It further proposes an algorithm for a more succinct and efficient determination of the priority of seismic reinforcements for apartment buildings.

• Korean Journal of Exercise Nutrition
• /
• v.23 no.3
• /
• pp.29-38
• /
• 2019

[Purpose] Effective nutritional intervention can help reduce the risk of nutritional problems and improve athletic performance in adolescents. The five A's (assess, advise, agree, assist, and arrange) model is widely used as the theoretical framework for advice on nutrition, smoking, drinking, and physical activity and it recommends that practitioners in primary health care promote behavior change to facilitate positive outcomes. This model has also been useful in understanding the underlying processes of behavior change. This study aimed to develop both a novel evidence-based nutritional intervention protocol, rooted in sound nutritional theory, and a customizable nutritional intervention program to support sustainable healthy eating, enhance nutrient intake, and improve athletic performance in adolescent athletes. [Methods] In this study, we adapted the 5 A's behavioral change model and motivational interview to develop a theoretical framework to help adolescent athletes change their behavior and achieve their goals. [Results] During each step of the 5 A's protocol, a customized nutritional intervention protocol was developed by nutrition experts for each of adolescent athletes. Each plan was developed to improve the eating habits of adolescent athletes through group education and counseling. All nutritional counseling sessions were designed to enable participants to apply nutritional knowledge and practical action plans to their training and competition conditions to enable each of them to achieve individual athletic goals and facilitate self-management. [Conclusion] A theoretical and evidence-based nutritional intervention protocol was developed to identify and address obstacles to healthy dietary habits in adolescent athletes. This could be used as the basis for further studies aimed at improving nutrient intake and athletic performance in adolescent athletes.

• PNF and Movement
• /
• v.21 no.3
• /
• pp.387-401
• /
• 2023

Purpose: The purpose of this study was to develop a Korean version of the Falls Efficacy Scale (K-FES), which is used to measure the fear of falling, that is conceptually equivalent to the original and culturally adaptable to the Korean population. Methods: A five-step translation and adaptation process was employed to create the K-FES, adhering to the established guidelines for cross-cultural rehabilitation outcome measures. The content validity was then evaluated by 22 rehabilitation professionals (15 males and 7 females) with an average clinical experience of 201 months at neurological rehabilitation centers. The content validity ratio and index were used as a basis for judgment. Results: The translation process identified inconsistencies with the terms "objects" and "telephone" in the original Falls Efficacy Scale, which were subsequently resolved in the final K-FES version. The content validity ratios for the original, second, and third versions of the K-FES ranged from -0.27-0.91, -0.27-0.91, and -0.27-0.91, respectively. Correspondingly, the content validity index values for the original, second, and third versions of the K-FES ranged from 0.77-1.00, 0.68-1.00, and 0.63-1.00, respectively. Conclusions: The K-FES was rigorously developed through translation, adaptation, and validation processes, making it a reliable tool for Korean stroke rehabilitation professionals. It is expected to be instrumental in clinical and research settings to assess postural stability and fall risk in patients with strokes and brain injuries.

• Explosives and Blasting
• /
• v.41 no.3
• /
• pp.73-92
• /
• 2023

With the increase of risk of gas explosion, various methods for indirectly estimating the explosion paramaters, which are required for the prediction of gas explosion scale and impact. In this study, the characteristics of the most frequently used methods such as TNT equivalent method, TNO multi-energy method, and BST method and the processes for determining the parameters of the methods were compared. In the case of TNT equivalent method, an adequate selection of the efficiency factor for various conditions such as the type of vapor cloud explosion and explosion material is needed. There is no objective guidelines for the selection of class number in TNO multi-energy method and it is not possible to estimate negative overpressure. It was found that there were some mistakes in the reported parameter values and suggested corrected values. BST method provides more detailed guidelines for the estimation of the explosion parameters including negative overpressure, but the graphs used in this methods are not clear. In order to overcome the problem, the graphs were redrawn. A more convenient estimation of explosion parameters with the numerical expression of the redrawn graphs will be available in the future.

• 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.

• Convergence Security Journal
• /
• v.24 no.2
• /
• pp.3-8
• /
• 2024

Recently, in order to build a cyber threats have increased in number and complexity. These threats increase the risk of using personally owned devices for work. This research addresses how to utilize an AI-enabled breach analysis tool. To this end, we developed and proposed the feasibility of using an AI-based breach analysis tool that reduces the workload of analysts and improves analysis efficiency through automated analysis processes. This allows analysts to focus on more important tasks. The purpose of this research is to propose the development and utilization of an AI-based breach analysis tool. We propose a new research direction in the field of breach analysis and suggest that automated tools should be improved in performance, coverage, and ease of use to enable organizations to respond to cyberattacks more effectively. As a research method, we developed a breach analysis tool using A.I. technology and studied various use cases. We also evaluated the performance, coverage, and ease of use of automated tools, and conducted research on predicting and preventing breaches and automatically responding to them. As a result, this research will serve as a foundation for the development and utilization of AI-based breach analysis tools, which can be used to respond to cyberattacks more effectively through experiments.

• Journal of the Korean Society of Safety
• /
• v.39 no.1
• /
• pp.55-61
• /
• 2024

In response to the COVID-19 pandemic, the logistics industry in Korea has rapidly been expanding, with offline demand concentrating on online platforms owing to the development of digital infrastructure. This has increased the workload of courier drivers considerably, along with labor intensity. A delivery driver died recently from overwork due to the continuous increase in delivery volume, which raises social concerns. Delivery drivers work long hours, (over 12 hours) and are greatly affected by weather conditions, such as snow, rain, heat waves, and cold waves. In addition, they lack a fixed workplace; perform atypical work handling workpieces of various sizes, weights, and shapes; and spend a large amount of time driving as part of their work. This work involves a high level of tension and requires attention and concentration. Despite the frequency of industrial accidents in the courier industry, studies on safety and health to quantitatively analyze and systematize the work of courier workers are very scarce. Therefore, to define the work process necessary for investigating the harmful factors in delivery service and the work analysis, this study conducted interviews and on-site surveys to analyze the unit work of the delivery service by targeting delivery workers. In other words, a framework of unit work for work analysis was presented to enable research and analysis by considering the aforementioned characteristics of the courier industry. The process was broadly divided into work, transport, storage, delay, and inspection. Work was divided into loading, sorting, unloading, and door subcategories, and transportation was divided into vehicle, cart, and walking subcategories as well as 10 small processes. Moreover, 22 unit works were again drawn by conducting field surveys and interviews. The risk of unit work derived from this study was ergonomically evaluated, and the ergonomic analysis revealed that uploading and transportation were the most dangerous. The results of this study could be used as basic data for preventing industrial accidents among courier workers, whose work has increased with the logistics volume and the development of the logistics industry.