• KIPS Transactions on Computer and Communication Systems
• /
• v.8 no.11
• /
• pp.263-270
• /
• 2019

Vehicular cloud computing is a new emerging technology that can provide drivers with cloud services to enable various vehicular applications. A vehicular cloud is defined as a set of vehicles that share their own resources. Vehicles should collaborate with each other to construct vehicular clouds through vehicle-to-vehicle communications. Since collaborating vehicles to construct the vehicular cloud have different speeds, directions and locations respectively, the vehicular cloud is constructed in multi-hop communication range. Due to intermittent wireless connectivity and low density of vehicles with the limited resources, the construction of vehicular cloud with multi-hop communications has become challenging in vehicular environments in terms of the service success ratio, the service delay, and the transmitted packet number. Thus, we propose a multi-hop vehicular cloud construction protocol that increases the service success ratio and decreases the service delay and the transmitted packet number. The proposed protocol uses a connection time-based intermediate vehicle selection scheme to reduce the cloud failure probability of multi-hop vehicular cloud. Simulation results conducted in various environments verify that the proposed protocol achieves better performance than the existing protocol.

• Journal of the Korea Convergence Society
• /
• v.12 no.9
• /
• pp.11-19
• /
• 2021

A software system is required to change during its life cycle due to various requirements such as adding functionalities, fixing bugs, and adjusting to new computing environments. Such program code modification should be considered as carefully as a new system development becase unexpected software errors could be introduced. In addition, when reusing open source programs, we can expect higher quality software if code changes of the open source program are predicted in advance. This paper proposes a Convolutional Neural Network (CNN)-based deep learning model to predict source code changes. In this paper, the prediction of code changes is considered as a kind of a binary classification problem in deep learning and labeled datasets are used for supervised learning. Java projects and code change logs are collected from GitHub for training and testing datasets. Software metrics are computed from the collected Java source code and they are used as input data for the proposed model to detect code changes. The performance of the proposed model has been measured by using evaluation metrics such as precision, recall, F1-score, and accuracy. The experimental results show the proposed CNN model has achieved 95% in terms of F1-Score and outperformed the multilayer percept-based DNN model whose F1-Score is 92%.

• Journal of Practical Engineering Education
• /
• v.13 no.2
• /
• pp.333-349
• /
• 2021

The fourth industrial revolution based on information and communication technology has increased the need for an environment where contents in new technologies can be learned for the development of lifelong vocational capabilities. To prepare for this, K University's online lifelong education center has established STEP, a smart learning platform. In this study, we conducted a study and other platform case analysis for STEP learner types, a survey of learners, and a comprehensive analysis based on these results to classify characteristics by learner types. It also intended to establish a plan to provide customized services to meet the needs of STEP learners in the future. The derived results are as follows. It is necessary to constantly manage learning content difficulty and learning motivation survey, and also needs to refine the operation of learning content in terms of learning composition. In addition, it is important to secure specialized content, to manage vulnerable learners, to actively introduce a learner support system and various educational methods.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.20 no.3
• /
• pp.216-223
• /
• 2019

This study was conducted to identify the effects of patient safety competency on patient safety management practice by nursing students and provide basic data for the development of the program to improve patient safety management practice. Participants were 293 fourth year nursing students who had clinical practice as student nurses for more than one year. Data were collected from April 26 to May 9, 2018. Collected data were analyzed for frequency, percentage, mean, standard deviation, t-test, ANOVA, Pearson' s correlation coefficient, and multiple regression with SPSS/WIN 24.0 computer program. Nursing students' patient safety competency was an average $2.90{\pm}0.38$ points (patient safety knowledge $2.68{\pm}0.65$; patient safety skills $3.26{\pm}0.56$; patient safety attitudes $2.75{\pm}0.40$). The average core of management practices to patient safety recorded $4.13{\pm}0.57$ points. In terms of the correlation among subjects' patient safety knowledge, skills, attitudes and patient safety management practices, significant correlation existed between skills and management practices (r=.337, p<.001), attitudes and management practices (r=-.150, p =.010), knowledge and management practices (r=.171, p=.003). Regression analysis revealed that 15.7% of the variance in patient safety management practice by nursing students could be explained by patient safety skills (${\beta}=.307$, p<.001), patient safety accident experience of Fire (${\beta}=-.127$, p=.026), patient safety attitudes (${\beta}=-.121$, p=.026), and patient safety accident experience of patient education (${\beta}=-.119$, p=.034). Additional studies to determine the various factors affecting patient safety management practice of nursing students and to develop educational program for increasing patient safety management practice should be conducted.

• KIPS Transactions on Computer and Communication Systems
• /
• v.7 no.12
• /
• pp.301-312
• /
• 2018

In industrial wireless sensor networks, the continuous object detection such as fire or toxic gas detection is one of major applications. A continuous object occurs at a specific point and then diffuses over a wide area. Therefore, many studies have focused on accurately detecting a continuous object and delivering data to a static sink with an energy-efficient way. Recently, some applications such as fire suppression require mobile sinks to provide real-time response. However, the sink mobility support in continuous object detection brings challenging issues. The existing approaches supporting sink mobility are designed for individual object detection, so they establish one-to-one communication between a source and a mobile sink for location update. But these approaches are not appropriate for a continuous object detection since a mobile sink should establish one-to-many communication with all sources. The one-to-many communication increases energy consumption and thus shortens the network lifetime. In this paper, we propose the origin-centric communication scheme to support sink mobility in a continuous object detection. Simulation results verify that the proposed scheme surpasses all the other work in terms of energy consumption.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.36 no.6
• /
• pp.469-481
• /
• 2018

DL (Deep Learning) is getting popular in various fields to implement artificial intelligence that resembles human learning and cognition. DL based on complicate structure of the ANN (Artificial Neural Network) requires computing power and computation cost. Variety of DL models with improved performance have been developed with powerful computer specification. The main purpose of this paper is to detect buildings from aerial images and evaluate performance of Mask R-CNN (Region-based Convolutional Neural Network) developed by FAIR (Facebook AI Research) team recently. Mask R-CNN is a R-CNN that is evaluated to be one of the best ANN models in terms of performance for semantic segmentation with pixel-level accuracy. The performance of the DL models is determined by training ability as well as architecture of the ANN. In this paper, we characteristics of the Mask R-CNN with various types of the images and evaluate possibility of the generalization which is the ultimate goal of the DL. As for future study, it is expected that reliability and generalization of DL will be improved by using a variety of spatial information data for training of the DL models.

• Journal of the Computational Structural Engineering Institute of Korea
• /
• v.32 no.4
• /
• pp.249-256
• /
• 2019

This paper presents an optimization framework of electrical impedance tomography for characterizing electrical conductivity profiles of concrete structures in two dimensions. The framework utilizes a partial-differential-equation(PDE)-constrained optimization approach that can obtain the spatial distribution of electrical conductivity using measured electrical potentials from several electrodes located on the boundary of the concrete domain. The forward problem is formulated based on a complete electrode model(CEM) for the electrical potential of a medium due to current input. The CEM consists of a Laplace equation for electrical potential and boundary conditions to represent the current inputs to the electrodes on the surface. To validate the forward solution, electrical potential calculated by the finite element method is compared with that obtained using TCAD software. The PDE-constrained optimization approach seeks the optimal values of electrical conductivity on the domain of investigation while minimizing the Lagrangian function. The Lagrangian consists of least-squares objective functional and regularization terms augmented by the weak imposition of the governing equation and boundary conditions via Lagrange multipliers. Enforcing the stationarity of the Lagrangian leads to the Karush-Kuhn-Tucker condition to obtain an optimal solution for electrical conductivity within the target medium. Numerical inversion results are reported showing the reconstruction of the electrical conductivity profile of a concrete specimen in two dimensions.

• Journal of Dental Rehabilitation and Applied Science
• /
• v.35 no.1
• /
• pp.11-19
• /
• 2019

Purpose: This study evaluated the usability of and satisfaction with two types of computer-aided design (CAD) software among users who had experience with dental implant CAD software and those who did not. Materials and Methods: Dental technicians (n = 20) who had previous experience with dental implant CAD Software and students from the College of Dentistry (n = 12) who had never designed implant custom abutments were asked to evaluate two types of CAD Software, Exocad and Deltanine. In addition, the participants were asked to fill out a structured questionnaire (Section 1: Entering basic information and retrieving files; Section 2: Setting conditions before abutment design; Section 3: Setting abutment design; and Section 4: Overall satisfaction). For the statistical analysis of the collected data, Mann-Whitney U test was used (${\alpha}=.05$). Results: The ease of design and satisfaction with the implant CAD Software, evaluated with respect to 21 statements divided into four Stages, were significantly higher for Exocad in both groups for Secion 1. For Sections 2 and 3, participants with experience evaluated Deltanine to be significantly better. For Section 4, both groups evaluated Exocad Software to be better. Conclusion: Overall, the Exocad Software was evaluated as having better usability and offering greater satisfaction. However, in terms of performance in the core of the design process, i.e. Sections 2 and 3, Deltanine was rated higher by the experienced users. Thus, if the user interface design parts are supplemented, Deltanine CAD Software could be put to a wider use in clinics.

• Journal of the Korean Society of Radiology
• /
• v.13 no.1
• /
• pp.9-14
• /
• 2019

This study aimed to investigate the performance of the S-detect method in breast ultrasonography and to determine how to reduce unnecessary biopsy by comparing the results of the S-detect method and biopsy. Thirty patients who had undergone breast ultrasonography between August and October 2018 and were scheduled to undergo biopsy because of the presence of breast nodules were retrospectively analyzed. The McNemar test was performed to determine whether detection of a malignant breast mass significantly differed between the S-detect method and biopsy. The following results were obtained from the analysis of the S-detect method: sensitivity, 90.9%; specificity, 84.21%; validity, 86.66%; positive predictive value, 76.92%; and negative predictive value, 94.11%. Analysis of the degree of agreement between the S-detect method and biopsy revealed a kappa value as high as 0.724 (p < 0.05), exhibiting good agreement between the two methods. The S-detect method in breast ultrasonography is diagnostically valuable in terms of distinguishing between malignant and benign breast masses, and if used properly before breast biopsy, unnecessary biopsy can be reduced.

• KIPS Transactions on Computer and Communication Systems
• /
• v.10 no.8
• /
• pp.215-222
• /
• 2021

In order to alleviate the limited resource problem and interference problem in cellular networks, the dual connectivity technology has been introduced with the cooperation of small cell base stations. In this paper, we design a new efficient and fair resource allocation scheme for the dual connectivity technology. Based on two different bargaining solutions - Generalizing Tempered Aspiration bargaining solution and Gupta and Livne bargaining solution, we develop a two-stage radio resource allocation method. At the first stage, radio resource is divided into two groups, such as real-time and non-real-time data services, by using the Generalizing Tempered Aspiration bargaining solution. At the second stage, the minimum request processing speeds for users in both groups are guaranteed by using the Gupta and Livne bargaining solution. These two-step approach can allocate the 5G radio resource sequentially while maximizing the network system performance. Finally, the performance evaluation confirms that the proposed scheme can get a better performance than other existing protocols in terms of overall system throughput, fairness, and communication failure rate according to an increase in service requests.