• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.11 no.3
• /
• pp.920-925
• /
• 2010

A home network system is made up of home devices and wire and wireless network can not only be the subject of cyber attack from a variety factors of threatening, but also have security weakness in cases of hacking, vicious code, worm virus, DoS attack, tapping of communication network, and more. As a result, a variety of problems such as abuse of private life, and exposure and stealing of personal information arose. Therefore, the necessity for a security protocol to protect user asset and personal information within a home network is gradually increasing. Thus, this dissertation designs and suggests a home network security protocol using user authentication and approach-control technology to prevent the threat by unauthorized users towards personal information and user asset in advance by providing the gradual authority to corresponding devices based on authorized information, after authorizing the users with a Public Key Certificate.

• Journal of the Institute of Convergence Signal Processing
• /
• v.11 no.4
• /
• pp.303-309
• /
• 2010

We proposes a new approach for testing the self visual-acuity by using the KS standard optotype. The proposed system provides their hand-gesture recognition method for the convenient response of subjects in the visual acuity measurement. Also, this system can measure a visual-acuity that excludes the examiner's subjective judgement or the subject's memorized guess, because of presenting a random optotype automatically by computer without a examiner. Especially, Our system guarantees the reliability by using the KS standard optotype and its presentation(KS P ISO 8596), which is defined by the Korea Standards Association in 2006. And the database management function of our system can provide the visual-acuity data to the EMR client easily. As a result, Our system shows the 98% consistency in the limit of the ${\pm}1$ visual-acuity level error by comparing the visual-acuity chart test.

• Geomechanics and Engineering
• /
• v.9 no.6
• /
• pp.775-791
• /
• 2015

Due to the extension of communication ways (metro, highways, railways), hence, to improve traffic flow imposes often the difficult crossing that generally drive to the construction of underground works (tunnel, water conveyance tunnel...) plays a major role in the redevelopment of urban areas. This study is focused on the assessment of the interaction response of parallel tunnels, so this study uses the results from the simulation of two tunnels to illustrate a few observations that may aid in practical designs. In this article, simultaneous drilling of highway's twin tunnels is simulated by means of Finite Element Method (FEM) implemented in Plaxis program. So the treated subject appears in a setting of geotechnical where one can be to construct several tunnels sometimes in a ground of weak mechanical characteristics. The objective of this study is to simulate numerically the interaction effects caused by construction of two parallels tunnels. This is an important factor in the study of the total answer of the problem interaction between parallels underground works. The importance of the effects transmitted is function of several parameters as the type of the works, and the mechanical characteristics (tunnel size, depth, and the relative position between two tunnels, lining thickness...). This article describes numerical analyses of two parallels tunnels interaction. This study will be applied to a real case of a section tunnel T4 of the highway East-West (Algeria); the study presented below comprises a series of numerical simulations of two tunnels using the computer program Plaxis which is used in the analyses is based on Finite Element Method.

• Journal of Convergence for Information Technology
• /
• v.11 no.11
• /
• pp.66-74
• /
• 2021

With the development of the Internet, user authentication technology that proves me online is improving. Existing ID methods pose a threat of personal information leakage if the service provider manages personal information and security is weak, and the information subject is to the service provider. In this study, as online identification technology develops, we propose a DID-based self-authentication model to prevent the threat of leakage of personal information from a centralized format and strengthen sovereignty. The proposed model allows users to directly manage personal information and strengthen their sovereignty over information topics through VC issued by the issuing agency. As a research method, a self-authentication model that guarantees security and integrity is presented using a decentralized identifier method based on distributed ledger technology, and the security of the attack method is analyzed. Because it authenticates through DID Auth using public key encryption algorithms, it is safe from sniffing, man in the middle attack, and the proposed model can replace real identity card.

• Journal of Practical Engineering Education
• /
• v.13 no.2
• /
• pp.233-242
• /
• 2021

In this paper, as a liberal arts course for non-majors, we proposed a supervised learning artificial neural network parameter optimization method and a basic education method for activation function to design a basic artificial neural network subject curriculum. For this, a method of finding a parameter optimization solution in a spreadsheet without programming was applied. Through this training method, you can focus on the basic principles of artificial neural network operation and implementation. And, it is possible to increase the interest and educational effect of non-majors through the visualized data of the spreadsheet. The proposed contents consisted of artificial neurons with sigmoid and ReLU activation functions, supervised learning data generation, supervised learning artificial neural network configuration and parameter optimization, supervised learning artificial neural network implementation and performance analysis using spreadsheets, and education satisfaction analysis. In this paper, considering the optimization of negative parameters for the sigmoid neural network and the ReLU neuron artificial neural network, we propose a training method for the four performance analysis results on the parameter optimization of the artificial neural network, and conduct a training satisfaction analysis.

• Journal of Practical Engineering Education
• /
• v.12 no.2
• /
• pp.265-273
• /
• 2020

In this paper, to design a basic data science practice curriculum as a liberal arts subject for non-majors, we proposed an educational method using an Excel(spreadsheet) data analysis tool. Tools for data collection, data processing, and data analysis include Excel, R, Python, and Structured Query Language (SQL). When it comes to practicing data science, R, Python and SQL need to understand programming languages and data structures together. On the other hand, the Excel tool is a data analysis tool familiar to the general public, and it does not have the burden of learning a programming language. And if you practice basic data science practice with Excel, you have the advantage of being able to concentrate on acquiring data science content. In this paper, a basic data science practice curriculum for one semester and weekly Excel practice contents were proposed. And, to demonstrate the substance of the educational content, examples of Linear Regression Analysis were presented using Excel data analysis tools.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.24 no.8
• /
• pp.978-984
• /
• 2020

In this study, the correlation between sports records and weather data was analyzed using the big data analysis method. To this end, data was collected by API and crawling, data was processed, statistics were performed, and data visualization was performed. The subject of this study was a player who entered the regular at-bat among outfielders in the 2019 KBO League. In addition, meteorological data were analyzed by using the unpleasant index and above 70 and below 70. As a result of the study, in the various hitting indicators, which are the records that pitchers intervene, the higher the unpleasant index, the better the outfielder's record, but pitchers, walks, pitches, pitching success rates, pitches per turn, pitches per game From the records of the back, it was found that the outfielder made the pitcher difficult. It is expected that this study will help the development of the sports data industry and the performance of baseball players, baseball teams, and coaching staff.

• Imaging Science in Dentistry
• /
• v.52 no.3
• /
• pp.239-244
• /
• 2022

Purpose: Despite the proliferation of numerous morphometric and anthropometric methods for sex identification based on linear, angular, and regional measurements of various parts of the body, these methods are subject to error due to the observer's knowledge and expertise. This study aimed to explore the possibility of automated sex determination using convolutional neural networks(CNNs) based on lateral cephalometric radiographs. Materials and Methods: Lateral cephalometric radiographs of 1,476 Iranian subjects (794 women and 682 men) from 18 to 49 years of age were included. Lateral cephalometric radiographs were considered as a network input and output layer including 2 classes(male and female). Eighty percent of the data was used as a training set and the rest as a test set. Hyperparameter tuning of each network was done after preprocessing and data augmentation steps. The predictive performance of different architectures (DenseNet, ResNet, and VGG) was evaluated based on their accuracy in test sets. Results: The CNN based on the DenseNet121 architecture, with an overall accuracy of 90%, had the best predictive power in sex determination. The prediction accuracy of this model was almost equal for men and women. Furthermore, with all architectures, the use of transfer learning improved predictive performance. Conclusion: The results confirmed that a CNN could predict a person's sex with high accuracy. This prediction was independent of human bias because feature extraction was done automatically. However, for more accurate sex determination on a wider scale, further studies with larger sample sizes are desirable.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.25 no.12
• /
• pp.1935-1941
• /
• 2021

In order to develop an algorithm using deep learning, which has been recently applied to various fields, it is necessary to have rich, high-quality learning data. In this paper, we propose an acquisition system for biological signals that simultaneously collects bio-signal data such as optical videos, thermal videos, and voices, which are mainly used in developing deep learning algorithms and useful in derivation of information, and transmit them to the server. To increase the portability of the collector, it was made based on Raspberry Pi, and the collected data is transmitted to the server through the wireless Internet. To enable simultaneous data collection from multiple collectors, an ID for login was assigned to each subject, and this was reflected in the database to facilitate data management. By presenting an example of biological data collection for fatigue measurement, we prove the application of the proposed acquisition system.

• KIPS Transactions on Computer and Communication Systems
• /
• v.12 no.12
• /
• pp.357-362
• /
• 2023

Bridges are important transportation infrastructure, but they are subject to damage and cracking due to various environmental factors and constant traffic loads, which accelerate their aging. With many bridges now older than their original construction, there is a need for systems to ensure safety and diagnose deterioration. Bridges are already utilizing structural health monitoring (SHM) technology to monitor the condition of bridges in real time or periodically. Along with this technology, the development of intelligent bridge monitoring technology utilizing artificial intelligence and Internet of Things technology is underway. In this paper, we study an edge system technique for predicting bridge safety using fast Fourier transform and dimensionality reduction algorithm for maintenance of aging bridges. In particular, unlike previous studies, we investigate whether it is possible to form a dataset using sensor data collected from actual bridges and check the safety of bridges.