• Journal of Biomedical Engineering Research
• /
• v.40 no.2
• /
• pp.62-67
• /
• 2019

The purpose of this study was to evaluate the performance of deep neural network model in order to determine whether there is a risk factor for coronary artery disease based on the cardiac variation parameter. The study used unidentifiable 297 data to evaluate the performance of the model. Input data consists of heart rate parameters, which are SDNN (standard deviation of the N-N intervals), PSI (physical stress index), TP (total power), VLF (very low frequency), LF (low frequency), HF (high frequency), RMSSD (root mean square of successive difference) APEN (approximate entropy) and SRD (successive R-R interval difference), the age group and sex. Output data are divided into normal and patient groups, and the patient group consists of those diagnosed with diabetes, high blood pressure, and hyperlipidemia among the various risk factors that can cause coronary artery disease. Based on this, a binary classification model was applied using Deep Neural Network of deep learning techniques to classify normal and patient groups efficiently. To evaluate the effectiveness of the model used in this study, Kernel SVM (support vector machine), one of the classification models in machine learning, was compared and evaluated using same data. The results showed that the accuracy of the proposed deep neural network was train set 91.79% and test set 85.56% and the specificity was 87.04% and the sensitivity was 83.33% from the point of diagnosis. These results suggest that deep learning is more efficient when classifying these medical data because the train set accuracy in the deep neural network was 7.73% higher than the comparative model Kernel SVM.

• Journal of the Architectural Institute of Korea Planning & Design
• /
• v.35 no.11
• /
• pp.101-108
• /
• 2019

In this study, Le Corbusier's ideas were investigated from the view point of modern dualism. Le Corbusier, pioneer of modern architecture, insisted a rationalistic architecture for the industrial period, considering a house as 'machine for living'. In the other way, he tried to arouse emotions through architecture, mentioning a house as 'machine for affecting'. In his writings and paintings, he divided the world in the two opposed things (ex: human and nature, reason and sensation, chaos and order, orthogonal and libre curve, man and woman, sun and moon, lightness and darkness, bull and woman, and etc), and tried to combined the these two divided things. In architecture, he amalgamated his white buildings with the green vegetation, which is styled in the harmony of contrast(nature and articial). In urbanism, Le Corbusier did not divide nature only into three material elements for living(sunlight, air, green space), but also pursued poetic and aesthetic nature through buildings under the rays of sun and among the vegetation. Le Corbusier's dualistic ideas are based on Descartes's modern dualism, which divided the world into the material and the spiritual and into the objective and the subjective. Due to this original division, modern dualism contains the limits of extreme subjectification on human signification and of separation from the world and nature. Le Corbusier pursued the combination of the two divided things to overcome the contradiction of dualism, but his ideas and works contain the limits of the modern dualism.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.23 no.10
• /
• pp.1311-1319
• /
• 2019

Currently, the web environment is a commonly used area for sharing information and conducting business. It is becoming an attack point for external hacking targeting on personal information leakage or system failure. Conventional signature-based detection is used in cyber threat but signature-based detection has a limitation that it is difficult to detect the pattern when it is changed like polymorphism. In particular, injection attack is known to the most critical security risks based on web vulnerabilities and various variants are possible at any time. In this paper, we propose a novelty detection technique to detect abnormal state that deviates from the normal state on web-server log dataset(WSLD). The proposed method is a machine learning-based technique to detect a minor anomalous data that tends to be different from a large number of normal data after replacing strings in web-server log dataset with vectors using machine learning-based embedding algorithm.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.13 no.6
• /
• pp.85-96
• /
• 2003

Wireless LAM in itself is vulnerable to eavesdropping and modification attack, and thus, IEEE 802.11i and IEEE 802. 1x/1aa have been defined to secure the wireless channel. These protocols accompanied by RADIUS and EAP-TLS provide users of wireless LAM with integrity and confidentiality services, and also they perform authentication and access control of wireless ports. In this paper, we suggest a method to implement accounting session using authentication session of IEEE 802. 1x and accounting state machine is designed with the accounting session. Also, we propose a key exchange mechanism to establish secure channel between stations and an access point. The mechanism is designed to be inter-operable with IEEE 802. 1aa.

• The Journal of the Korea Contents Association
• /
• v.21 no.3
• /
• pp.602-608
• /
• 2021

For the comparison of bond strength between the Co-Cr alloy and ceramic, which are clinically used, test samples made with a traditional casting method as a control group), and Milling and SLM(3d printing group) samples were made as an experimental group. The metal-ceramic bond strength was measured with a universal testing machine. For the measurement, a three-point bending test was conducted. After the bond strength was measured, metal-ceramic interface was observed. According to the test result, casting group had 53.59 MPa, milling group had 45.90 MPa, and 3d printing group had 58.34 MPa. There was no statistical significance. With regard to failure pattern, most of the samples in two groups, showed mixed failure. This study showed a clinically applicable value when measuring the bond strength of alloy-ceramic material with an alloy produced by 3D printing.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.25 no.3
• /
• pp.361-367
• /
• 2021

Information search in video streaming services such as YouTube is replacing traditional information search services. To find desired detailed information in such a video, users should repeatedly navigate several points in the video, resulting in a waste of time and network traffic. In this paper, we propose a method to assist users in searching for information in a video by using DBSCAN clustering and LSTM. Our LSTM model is trained with a dataset that consists of user search sequences and their final target points categorized by DBSCAN clustering algorithm. Then, our proposed method utilizes the trained model to suggest an expected category for the user's desired target point based on a partial search sequence that can be collected at the beginning of the search. Our experiment results show that the proposed method successfully finds user destination points with 98% accuracy and 7s of the time difference by average.

• Geomechanics and Engineering
• /
• v.29 no.3
• /
• pp.321-329
• /
• 2022

Tunnel site where high water pressure is applied, such as subsea tunnel, generally selects the shield TBM (Tunnel Boring Machine) to maintain the tunnel excavation face. The shield TBM has cutters installed, and the cutters wear out during the process of excavation, so it should be checked and replaced regularly. This is called CHI (Cutterhead Intervention). The conventional CHI under high water pressure is very disadvantageous in terms of safety and economics because humans perform work in response to high water pressure and huge water inflow in the chamber. To overcome this disadvantage, this study proposes a new method to dramatically reduce water pressure and water ingress by injecting an appropriate grout solution into the front of the tunnel face through the shield TBM chamber, called New Face Grouting Method (NFGM). The tunnel model tests were performed to determine the characteristics, injection volume, and curing time of grout solution to be applied to the NFGM. Model test apparatus was composed of a pressure soil tank, a model shield TBM, a grout tank, and an air compressor to measure the amount of water inflow into the chamber. The model tests were conducted by changing the injection amount of the grout solution, the curing time after the grout injection, and the water/cement ratio of grout solution. From an economic point of view, the results showed that the injection volume of 1.0 L, curing time of 6 hours, and water/cement ratio of the grout solution between 1.5 and 2.0 are the most economical. It can be concluded that this study has presented a method to economically perform the CHI under the high water pressure.

• Journal of Korea Multimedia Society
• /
• v.25 no.5
• /
• pp.748-756
• /
• 2022

Thanks to the competition of AlphaGo and Sedol Lee, machine learning has received world-wide attention and huge investments. The performance improvement of computing devices greatly contributed to big data processing and the development of neural networks. Artificial intelligence not only imitates human beings in many fields, but also seems to be better than human capabilities. Although humans' creation is still considered to be better and higher, several artificial intelligences continue to challenge human creativity. The quality of some creative outcomes by AI is as good as the real ones produced by human beings. Sometimes they are not distinguishable, because the neural network has the competence to learn the common features contained in big data and copy them. In order to confirm whether artificial intelligence can express the inherent characteristics of different arts, this paper proposes a new neural network model called Humming. It is an experimental model that combines vgg16, which extracts image features, and DeepJ's architecture, which excels in creating various genres of music. A dataset produced by our experiment shows meaningful and valid results. Different results, however, are produced when the amount of data is increased. The neural network produced a similar pattern of music even though it was a different classification of images, which was not what we were aiming for. However, these new attempts may have explicit significance as a starting point for feature transfer that will be further studied.

• Journal of Internet Computing and Services
• /
• v.24 no.5
• /
• pp.107-120
• /
• 2023

The public bicycle of Seoul, Ttareungyi, was launched at October 2015 to reduce traffic and carbon emissions in downtown Seoul and now, 2023 Oct, the cumulative number of user is upto 4 million and the number of bike is about 43,000 with about 2700 stations. However, super growth of Ttareungyi has caused the several problems, especially demand/supply mismatch, and thus the Seoul citizen has been complained about out of stock. In this point, this study conducted a real time demand forecasting model to prevent stock out bike at stations. To develop the model, the research team gathered the rental·return transaction data of 20,000 bikes in whole 1600 stations for 2019 year and then analyzed bike usage, user behavior, bike stations, and so on. The forecasting model using machine learning is developed to predict the amount of rental/return on each bike station every hour through daily learning with the recent 90 days data with the weather information. The model is validated with MAE and RMSE of bike stations, and tested as a prototype service on the Seoul Bike Management System(Mobile App) for the relocation team of Seoul City.

• Journal of the Korean Society of Industry Convergence
• /
• v.27 no.2_2
• /
• pp.389-395
• /
• 2024

The purpose of this study was to evaluate the effect of different washing solvents and washing methods on the flexural strength of 3D printed temporary resin. A bar(25 × 2 × 2 mm) was produced with a layer thickness of 50 ㎛ using an LCD-type 3D printer and divided into 15 groups(n = 10, each) according to washing solution(IPA; 99% isopropyl alcohol, TPM; 93% Tripropylene glycol monomethylether, ETL; Ethanol, TWC; Twin 3D Cleaner, and DNC; DIO navi Cleaner) and washing method(Dip; Dip washing, Ultra; Ultrasonic washing, and Auto; Automated washing). All groups were washed for 5 minutes, and post-cured for 5 minutes using a UV LED light curing machine. The Flexural strength was measured using a three-point bending test using a universal testing machine. For statistical analysis, one-way ANOVA, Tukey HSD post hoc test, Kruskal-Wallis test and post-hoc by Bonferroni-Dunn test(𝛼=.05) were performed depending on whether the normality test was satisfied. In all washing solvents except TPM and DNC, the Dip group showed the lowest flexural strength values, while the Auto group showed the highest flexural strength values except for DNC. Additionally, the washing solution showed completely different flexural strength values depending on the washing method.