• Korean small business review
• /
• v.42 no.4
• /
• pp.285-308
• /
• 2020

This paper analyzes the factors which affect University professors and students on their startup activities, such as (a) University factors: their industrial cooperation organization and systems, their resources for startup support, their knowledge assets, and (b) socioeconomic characteristics in which Universities are located. We used the data and information from the University Information System and the National Statistical Office Publication to analyze 157 4-year Universities in Korea who uploaded their startup-related information on the system. Our analysis shows that Universities' systems, such as the term for Professors' leave of absence for startup activities, and their amount of knowledge assets affect the number of Professor startups significantly positively, while there is no significant effect on their performance, in terms of sales, from those factors, except for the amount of patents that the University has. In the meantime, the number of practical startup courses, the number of startup clubs, and the number of professor startups in the University affect the number of student startups, while the size of industrial cooperation body, the amount of knowledge asset, the area's socioeconomic characteristics didn't affect their performance. The result implies that we need to take different approaches to boost University professor startups and their student startups: better system and more knowledge for the former, more practical courses and programs for the latter. Further study is needed to get a more robust result because this analysis used only one year data, and personal trait data was not included in the analysis. A panel data analysis for several years is recommended for further research.

• KIPS Transactions on Software and Data Engineering
• /
• v.12 no.1
• /
• pp.51-58
• /
• 2023

In this paper, we propose an organ segmentation technique for the automatic extraction of medical diagnostic indicators from X-ray images. In order to calculate diagnostic indicators of heart disease and spinal disease such as VHS(vertebral heart scale) and Cobb angle, it is necessary to accurately segment the thoracic spine, carina, and heart in a chest X-ray image. A deep neural network model in which the high-resolution representation of the image for each layer and the structure converted into a low-resolution feature map are connected in parallel was adopted. This structure enables the relative position information in the image to be effectively reflected in the segmentation process. It is shown that learning performance can be improved by combining the OCR module, in which pixel information and object information are mutually interacted in a multi-step process, and the channel attention module, which allows each channel of the network to be reflected as different weight values. In addition, a method of augmenting learning data is presented in order to provide robust performance against changes in the position, shape, and size of the subject in the X-ray image. The effectiveness of the proposed theory was evaluated through an experiment using 145 human chest X-ray images and 118 animal X-ray images.

• Journal of Intelligence and Information Systems
• /
• v.28 no.3
• /
• pp.119-137
• /
• 2022

Recent recommendation system studies apply various deep learning models to represent user and item interactions better. One of the noteworthy studies is ONCF(Outer product-based Neural Collaborative Filtering) which builds a two-dimensional interaction map via outer product and employs CNN (Convolutional Neural Networks) to learn high-order correlations from the map. However, ONCF has limitations in recommendation performance due to the problems with CNN and the absence of side information. ONCF using CNN has an inductive bias problem that causes poor performances for data with a distribution that does not appear in the training data. This paper proposes to employ a Vision Transformer (ViT) instead of the vanilla CNN used in ONCF. The reason is that ViT showed better results than state-of-the-art CNN in many image classification cases. In addition, we propose a new architecture to reflect side information that ONCF did not consider. Unlike previous studies that reflect side information in a neural network using simple input combination methods, this study uses an independent auxiliary classifier to reflect side information more effectively in the recommender system. ONCF used a single latent vector for user and item, but in this study, a channel is constructed using multiple vectors to enable the model to learn more diverse expressions and to obtain an ensemble effect. The experiments showed our deep learning model improved performance in recommendation compared to ONCF.

• Economic and Environmental Geology
• /
• v.55 no.4
• /
• pp.353-366
• /
• 2022

Spatial estimation of geoscience data (geo-data) is challenging due to spatial heterogeneity, data scarcity, and high dimensionality. A novel spatial estimation method is needed to consider the characteristics of geo-data. In this study, we proposed the application of Gaussian Mixture Model (GMM) among machine learning algorithms with multivariate data for robust spatial predictions. The performance of the proposed approach was tested through soil chemical concentration data from a former smelting area. The concentrations of As and Pb determined by ex-situ ICP-AES were the primary variables to be interpolated, while the other metal concentrations by ICP-AES and all data determined by in-situ portable X-ray fluorescence (PXRF) were used as auxiliary variables in GMM and ordinary cokriging (OCK). Among the multidimensional auxiliary variables, important variables were selected using a variable selection method based on the random forest. The results of GMM with important multivariate auxiliary data decreased the root mean-squared error (RMSE) down to 0.11 for As and 0.33 for Pb and increased the correlations (r) up to 0.31 for As and 0.46 for Pb compared to those from ordinary kriging and OCK using univariate or bivariate data. The use of GMM improved the performance of spatial interpretation of anthropogenic metals in soil. The multivariate spatial approach can be applied to understand complex and heterogeneous geological and geochemical features.

• Journal of the Korean Geotechnical Society
• /
• v.22 no.9
• /
• pp.45-59
• /
• 2006

The successful performance of any numerical geotechnical simulation depends on the accuracy and efficiency of the numerical implementation of constitutive model used to simulate the stress-strain (constitutive) response of the soil. The corner stone of the numerical implementation of constitutive models is the numerical integration of the incremental form of soil-plasticity constitutive equations over a discrete sequence of time steps. In this paper a well known two-surface soil plasticity model is implemented using a generalized implicit return mapping algorithm to arbitrary convex yield surfaces referred to as the Closest-Point-Projection method (CPPM). The two-surface model describes the nonlinear behavior of coarse-grained materials by incorporating a bounding surface concept together with isotropic and kinematic hardening as well as fabric formulation to account for the effect of fabric formation on the unloading response. In the course of investigating the performance of the CPPM integration method, it is proven that the algorithm is an accurate, robust, and efficient integration technique useful in finite element contexts. It is also shown that the algorithm produces a consistent tangent operator $\frac{d\sigma}{d\varepsilon}$ during the iterative process with quadratic convergence rate of the global iteration process.

• The Journal of the Acoustical Society of Korea
• /
• v.41 no.6
• /
• pp.610-620
• /
• 2022

An acoustic vector sensor can simultaneously receive vector quantities, such as particle velocity and acceleration, as well as acoustic pressure at one location, and thus it can be used as a single input multiple output receiver in underwater acoustic communication systems. On the other hand, vector signals received by a single vector sensor have different channel characteristics due to the azimuth angle between the source and receiver and the difference in propagation angle of multipath in each component, producing different communication performances. In this paper, we propose a channel parameter-based weighting method to improve the performance of an acoustic communication system using a single vector sensor. To verify the proposed method, we used communication data collected from the experiment conducted during the KOREX-17 (Korea Reverberation Experiment). For communication demodulation, block-based time reversal technique which is robust against time-varying channels were utilized. Finally, the communication results showed that the effectiveness of the channel parameter-based weighting method for the underwater communication system using a single vector sensor was verified.

• Membrane Journal
• /
• v.32 no.1
• /
• pp.43-49
• /
• 2022

Solid-state supercapacitors with high safety and robust mechanical properties are attracting global attention as next-generation energy storage devices. As an electrode of a supercapacitor, an economical carbon-based electrode is widely used. However, when an aqueous electrolyte is introduced, the charge transfer resistance increases because the interfacial contact between the hydrophobic electrode surface and aqueous electrolyte is not good. In this regard, we propose a method to obtain higher electrochemical performance based on improved interfacial properties by treating the electrode surface with oxygen plasma. The surface hydrophilization induced by the enriched oxygen functionalities was confirmed by the contact angle measurement. As a result, the degree of hydrophilization was easily adjusted by controlling the power and duration of the oxygen plasma treatment. As the electrolyte of the supercapacitor, PVA/H₃PO₄, which is a typical solid-state aqueous electrolyte, was used. Free-standing membranes of PVA/H₃PO₄ electrolyte were prepared and then pressed onto the electrode. The optimal condition was to perform oxygen plasma treatment for 5 seconds with a low power of 15 W, and the energy density of the supercapacitor increased by about 8%.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.29 no.6D
• /
• pp.745-752
• /
• 2009

Management of social infrastructure has been advanced from facility management (FM) to asset management (AM), which adopts the aggressive and proactive methods in predicting the deterioration of infrastructure, prevents failures, and eventually saves maintenance cost. Infrastructure asset management is not a simple engineering technique, but it is a new paradigm evolved from facility management practices. To implement the infrastructure asset management successfully, organizational reform is very important. This paper suggests critical success factors and key performance indicators to implement the infrastructure asset management for facility managers of government owned social infrastructures such as roads and bridges. Reorganizing the facility management group requires new vision, objectives, strategies for the paradigm-changing asset management. This paper uses Balanced Score Card (BSC) which is a proven method in measuring and setting new objectives for an organization. Once the performance indicators are reviewed repeatedly by facility managers through experts workshops, developed BSC can be used in practice. This paper discusses the development of robust BSC scoring method through in depth literature reviews and investigation of asset management practices of domestic and international cases.

• Imaging Science in Dentistry
• /
• v.54 no.1
• /
• pp.81-91
• /
• 2024

Purpose: The objective of this study was to propose a deep-learning model for the detection of the mandibular canal on dental panoramic radiographs. Materials and Methods: A total of 2,100 panoramic radiographs (PANs) were collected from 3 different machines: RAYSCAN Alpha (n=700, PAN A), OP-100 (n=700, PAN B), and CS8100 (n=700, PAN C). Initially, an oral and maxillofacial radiologist coarsely annotated the mandibular canals. For deep learning analysis, convolutional neural networks (CNNs) utilizing U-Net architecture were employed for automated canal segmentation. Seven independent networks were trained using training sets representing all possible combinations of the 3 groups. These networks were then assessed using a hold-out test dataset. Results: Among the 7 networks evaluated, the network trained with all 3 available groups achieved an average precision of 90.6%, a recall of 87.4%, and a Dice similarity coefficient (DSC) of 88.9%. The 3 networks trained using each of the 3 possible 2-group combinations also demonstrated reliable performance for mandibular canal segmentation, as follows: 1) PAN A and B exhibited a mean DSC of 87.9%, 2) PAN A and C displayed a mean DSC of 87.8%, and 3) PAN B and C demonstrated a mean DSC of 88.4%. Conclusion: This multi-device study indicated that the examined CNN-based deep learning approach can achieve excellent canal segmentation performance, with a DSC exceeding 88%. Furthermore, the study highlighted the importance of considering the characteristics of panoramic radiographs when developing a robust deep-learning network, rather than depending solely on the size of the dataset.

• Journal of the Microelectronics and Packaging Society
• /
• v.31 no.2
• /
• pp.28-35
• /
• 2024

Corrosion inside electronic packages significantly impacts the system performance and reliability, necessitating non-destructive diagnostic techniques for system health management. This study aims to present a non-destructive method for assessing corrosion in copper interconnects using the Smith chart, a tool that integrates the magnitude and phase of complex impedance for visualization. For the experiment, specimens simulating copper transmission lines were subjected to temperature and humidity cycles according to the MIL-STD-810G standard to induce corrosion. The corrosion level of the specimen was quantitatively assessed and labeled based on color changes in the R channel. S-parameters and Smith charts with progressing corrosion stages showed unique patterns corresponding to five levels of corrosion, confirming the effectiveness of the Smith chart as a tool for corrosion assessment. Furthermore, by employing data augmentation, 4,444 Smith charts representing various corrosion levels were obtained, and artificial intelligence models were trained to output the corrosion stages of copper interconnects based on the input Smith charts. Among image classification-specialized CNN and Transformer models, the ConvNeXt model achieved the highest diagnostic performance with an accuracy of 89.4%. When diagnosing the corrosion using the Smith chart, it is possible to perform a non-destructive evaluation using electronic signals. Additionally, by integrating and visualizing signal magnitude and phase information, it is expected to perform an intuitive and noise-robust diagnosis.