• Journal of the Korean Society for Railway
• /
• v.11 no.3
• /
• pp.257-262
• /
• 2008

Design and analysis of road subgrade system, which is exposed to repetitive loading condition, uses resilient modulus. The behavior of railway subgrade system will not be quite different from that of road system. Following this phenomenological feature of the subgrade system, this paper introduces the implementation of the resilient modulus based constitutive model on a commercial finite element software. The implementation of the resilient modulus models such as K-${\theta}$ and Uzan on a FE program has been conducted previously. These model assumes that the material state reaches to the nonlinear elastic condition and with further application of repetitive loads, the response of material is completed in elastic condition. According to the recent test results performed on cohesive subgrade soils, however, permanent deformation occurs with repetitive loads. With aids of previously suggested models the permanent deformation cannot be modeled. To overcome such limitation a plastic potential derived from the test results and simple failure criterion based constitutive model is developed. The comparison between the analysis and test results shows a good correlation.

• Journal of Korea Society of Industrial Information Systems
• /
• v.29 no.4
• /
• pp.25-34
• /
• 2024

This paper presents the development of a mobile application that detects and identifies canine skin diseases by training a deep learning-based U-Net model to infer the presence and location of skin lesions from images. U-Net, primarily used in medical imaging for image segmentation, is effective in distinguishing specific regions of an image in a polygonal form, making it suitable for identifying lesion areas in dogs. In this study, six major canine skin diseases were defined as classes, and the U-Net model was trained to differentiate among them. The model was then implemented in a mobile app, allowing users to perform lesion analysis and prediction through simple camera shots, with the results provided directly to the user. This enables pet owners to monitor the health of their pets and obtain information that aids in early diagnosis. By providing a quick and accurate diagnostic tool for pet health management through deep learning, this study emphasizes the significance of developing an easily accessible service for home use.

• Journal of Biomedical Engineering Research
• /
• v.19 no.1
• /
• pp.59-68
• /
• 1998

Digital hearing aids offer many advantages over conventional analog hearing aids. With the advent of high speed digital signal processing chips, new digital techniques have been introduced to digital hearing aids. In addition, the evaluation of new ideas in hearing aids is necessarily accompanied by intensive subject-based clinical tests which requires much time and cost. In this paper, we present an objective method to evaluate and predict the performance of hearing aid systems without the help of such subject-based tests. In the hearing impairment simulation(HIS) algorithm, a sensorineural hearing impairment medel is established from auditory test data of the impaired subject being simulated. Also, the nonlinear behavior of the loudness recruitment is defined using hearing loss functions generated from the measurements. To transform the natural input sound into the impaired one, a frequency sampling filter is designed. The filter is continuously refreshed with the level-dependent frequency response function provided by the impairment model. To assess the performance, the HIS algorithm was implemented in real-time using a floating-point DSP. Signals processed with the real-time system were presented to normal subjects and their auditory data modified by the system was measured. The sensorineural hearing impairment was simulated and tested. The threshold of hearing and the speech discrimination tests exhibited the efficiency of the system in its use for the hearing impairment simulation. Using the HIS system we evaluated three typical hearing aid algorithms.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.65 no.11
• /
• pp.1868-1878
• /
• 2016

This paper proposes a novel velocity estimator for long-term underwater navigation of autonomous underwater vehicles(AUVs). Provided that an external position fix is not given, a viable goal in designing a underwater navigation algorithm is to reduce the divergence rate of position error only using the sporadic velocity information obtained from Doppler velocity log(DVL). For such case, the performance of underwater navigation eventually depends on accuracy and reliability of external velocity information. This motivates us to devise a velocity estimator which can drastically enhance the navigation performance even when the DVL measurement is unavailable. Incorporating the Gertler-Hagen hydrodynamics model of an AUV with the measurement models of velocity and depth sensors, the velocity estimator design problem is resolved using the extended Kalman filter. Different from the existing methods in which an AUV simulator is regarded as a virtual sensor, our approach is less sensitive to the model uncertainty often encountered in practice. This is because our velocity filter estimates the simulator errors with sensor aids and furthermore compensates these errors based on the indirect feedforward manner. Through the simulations for typical AUV navigation scenarios, the effectiveness of the proposed scheme is demonstrated.

• Journal of the Korea Convergence Society
• /
• v.9 no.5
• /
• pp.1-6
• /
• 2018

In smart grid an accurate load forecasting is crucial in planning resources, which aids in improving its operation efficiency and reducing the dynamic uncertainties of energy systems. Research in this area has included the use of shallow neural networks and other machine learning techniques to solve this problem. Recent researches in the field of computer vision and speech recognition, have shown great promise for Deep Neural Networks (DNN). To improve the performance of daily electric peak load forecasting the paper presents a new deep neural network model which has the architecture of two multi-layer neural networks being serially connected. The proposed network model is progressively pre-learned layer by layer ahead of learning the whole network. For both one day and two day ahead peak load forecasting the proposed models are trained and tested using four years of hourly load data obtained from the Korea Power Exchange (KPX).

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.12 no.7
• /
• pp.2939-2944
• /
• 2011

The performance and efficiency of a Molten Carbonate Fuel Cell system will improve with the aids of numerical simulations such as finite element analysis. For best simulation results, the virtual model must accurately reflect the actual model including the material properties. It is very difficult, however, to make a detailed numerical model of the stack that consists of hundreds of layers of unit cells composed of various materials like metal, ceramics, polymer, etc. Instead, a practical approach is to find a homogenized material property of the stack as a whole as an approximate replacement. In this paper, the compression ratio of a unit cell is introduced, and a new method is proposed to estimate the homogeneous material properties for both the active and the manifold regions of the stack under the assumption that the compressive deformation occurs only at the separators and matrices in the unit cells. The estimated properties are applied successfully to simulating an actual stack.

• Journal of Convergence for Information Technology
• /
• v.12 no.4
• /
• pp.143-157
• /
• 2022

The aim of this study is to design Spudsville, an immersive game environment in Minecraft that can effectively help learners acquire the English language. To create a successful learning experience using Minecraft, the researchers adopted the Agile Model and the Design Thinking approach. The researchers first conducted an analysis through an extensive literature review in order to assess the learners' needs. Afterwards, they designed and developed a Minecraft world based on the data collected during the analysis phase. The researchers learned that implementing constructivist and behaviorist approaches has benefits, even though applying a cognitivist-learning model to Spudsville could have provided the researchers with more insight on how learner processes information. Making these adjustments could improve Spudsville's effectiveness and could potentially help the ways in which gamified learning aids with language acquisition.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.18 no.3
• /
• pp.570-590
• /
• 2024

Breast cancer ranks among the most prevalent forms of malignancy and foremost cause of death by cancer worldwide. It is not preventable. Early and precise detection is the only remedy for lowering the rate of mortality and improving the probability of survival for victims. In contrast to present procedures, thermography aids in the early diagnosis of cancer and thereby saves lives. But the accuracy experiences detrimental impact by low sensitivity for small and deep tumours and the subjectivity by physicians in interpreting the images. Employing deep learning approaches for cancer detection can enhance the efficacy. This study explored the utilization of thermography in early identification of breast cancer with the use of a publicly released dataset known as the DMR-IR dataset. For this purpose, we employed a novel approach that entails the utilization of a pre-trained MobileNetV2 model and fine tuning it through transfer learning techniques. We created three models using MobileNetV2: one was a baseline transfer learning model with weights trained from ImageNet dataset, the second was a fine-tuned model with an adaptive learning rate, and the third utilized early stopping with callbacks during fine-tuning. The results showed that the proposed methods achieved average accuracy rates of 85.15%, 95.19%, and 98.69%, respectively, with various performance indicators such as precision, sensitivity and specificity also being investigated.

• Cartoon and Animation Studies
• /
• s.40
• /
• pp.337-365
• /
• 2015

The objective of this study proposes the new user's addiction model in 'Social Network Games' (SNGs). Research model is derived from the separation of two characteristics. First one is logical characteristics that includes 'Functional' (F), 'Keystroke' (K), and 'Goal' (G). Second one is feeling characteristics that consists a few factors such as 'Emotion' (E), 'Social' (S), and 'Affection' (A). For the pre-test, a total of 30 participants responded to survey in order to inspect the fitness of research questionnaire, roughly validity of the proposed model, and the direction of this reseach. After that for the main test, a total 300 users participated in this research. The final number of effective participants were 261 because 39 were insincere respondents and without playing SNGs who were excluded. Then we examined the measurement model by performing 'Partial Least Squares - Structural Equation Modeling' (PLS-SEM) analysis to test the research hypothesis empirically. The results of the measurement and structural model test lend support to the proposed research model by providing a good fit to the construct data. Interestingly, the model showed the significant effects of the interaction between eleven hypothesis(H1,H2,H3,H4,H5,H6,H7,H8,H9,H10, H12). Only one hypothesis decision t-value not supported that is involved the relationship between SNGs Addiction and Keystroke, H11(1.193). This research expect to contributes to an exploratory SNGs research to clarify the base of addition and will aids understanding of users' behavior associated with SNGs development.

• Genomics & Informatics
• /
• v.12 no.1
• /
• pp.35-41
• /
• 2014

Single-nucleotide polymorphisms (SNPs) have been emerging out of the efforts to research human diseases and ethnic disparities. A semantic network is needed for in-depth understanding of the impacts of SNPs, because phenotypes are modulated by complex networks, including biochemical and physiological pathways. We identified ethnicity-specific SNPs by eliminating overlapped SNPs from HapMap samples, and the ethnicity-specific SNPs were mapped to the UCSC RefGene lists. Ethnicity-specific genes were identified as follows: 22 genes in the USA (CEU) individuals, 25 genes in the Japanese (JPT) individuals, and 332 genes in the African (YRI) individuals. To analyze the biologically functional implications for ethnicity-specific SNPs, we focused on constructing a semantic network model. Entities for the network represented by "Gene," "Pathway," "Disease," "Chemical," "Drug," "ClinicalTrials," "SNP," and relationships between entity-entity were obtained through curation. Our semantic modeling for ethnicity-specific SNPs showed interesting results in the three categories, including three diseases ("AIDS-associated nephropathy," "Hypertension," and "Pelvic infection"), one drug ("Methylphenidate"), and five pathways ("Hemostasis," "Systemic lupus erythematosus," "Prostate cancer," "Hepatitis C virus," and "Rheumatoid arthritis"). We found ethnicity-specific genes using the semantic modeling, and the majority of our findings was consistent with the previous studies - that an understanding of genetic variability explained ethnicity-specific disparities.