• Journal of the Korea Society of Computer and Information
• /
• v.26 no.3
• /
• pp.1-7
• /
• 2021

In this paper, optimized media data retrieval and transmission based on the Hybrid CDN/P2P architecture and selective storage through user's prediction of requestability enable seamless data transfer to users and reduction of unnecessary traffic. We also propose a new media management method to minimize the possibility of transmission delay and packet loss so that media can be utilized in real time. To this end, we construct each media into logical segments, continuously compute weights for each segment, and determine whether to store segment data based on the calculated weights. We also designate scattered computing nodes on the network as local groups by distance and ensure that storage space is efficiently shared and utilized within those groups. Experiments conducted to verify the efficiency of the proposed technique have shown that the proposed method yields a relatively good performance evaluation compared to the existing methods, which can enable both initial latency reduction and seamless transmission.

• Journal of Industrial Convergence
• /
• v.18 no.6
• /
• pp.1-7
• /
• 2020

In this study, we hypothesized that the needs for start-up support services may vary depending on the founder's psychological characteristics, such as self-efficacy or his attitude toward uncertainty. To verify this, a survey was conducted on the founders of 86 companies located in Business Incubators at Seoul and Daejeon and an empirical analysis was conducted based on the data. According to the analysis, the higher the self-efficacy of the founder, the more active he expressed his willingness to accept the start-up support service, which aims to provide start-up zones to busy areas outside the university. While the founder, who has experienced failure in the past, responded positively to attracting customers located outside the university. The results of this study supported the hypothesis and suggest that differentiated start-up support services should be designed by including not only characteristics at the level of start-up companies, such as industries and growth stages, but also the psychological characteristics of start-ups in important consideration.

• Journal of The Korean Association of Information Education
• /
• v.24 no.6
• /
• pp.633-641
• /
• 2020

The development of intelligent information technology based on intelligence and data and network technology implemented by artificial intelligence has instigated innovation in society as a whole and has shown wide social and economic impact. Therefore, not only overseas but also in Korea, AI education is in a hurry to cultivate talents who will lead the upcoming society. Data is an important part of artificial intelligence, and data literacy, which can collect, process, and analyze data, to make data-based decisions, can be seen as an important competency to be developed along with AI literacy. Therefore, in this study, an AI data science education program that can increase data literacy of elementary school students was developed and applied to the experimental group, and its effectiveness was verified through a pre- and post response sample t-test. As a result, all of the four detailed competencies of data literacy, data understanding, collection, analysis, and expression, showed statistically significant improvement, indicating that the AI data science education program was effective in improving students' data literacy.

• Journal of the Computational Structural Engineering Institute of Korea
• /
• v.34 no.6
• /
• pp.347-353
• /
• 2021

In this study, we presented a novel size optimization framework to control the linear buckling temperature and several buckling modes of plates, by optimizing thickness values of composite structures for practical engineering applications. Predicting the buckling temperature and mode shape of structures is a vital research topic in engineering to achieve structural stability. However, optimizing designs of engineering structures through engineering intuition is challenging. To address this limitation, we proposed a method that combines finite element simulation and size optimization. Based on the idea that the structural buckling temperature and mode shape of a plate are affected by the thickness of the structure, the thickness values of the nodes of the target structure were set as the design variables in this optimization method; and the buckling temperature values, and buckling mode shapes were set as the objective functions. This size optimization method enabled the determination of optimal thickness distributions, to induce the desired buckling temperature values and mode shapes. The validity of the proposed method was verified in terms of their buckling temperature values and buckling mode shapes, using several numerical examples of rectangular composite structures.

• The Journal of the Korea Contents Association
• /
• v.22 no.10
• /
• pp.535-545
• /
• 2022

The purpose of this study is to classify the various problems in surface road according to their severity and to propose a priority decision making process for road policy makers. For this purpose, the road problems reported by Cheok-cheok app were classified, and the EPDO was adopted and calculated as an index of their severity. To test applicability of the proposed process, some images of road problems reported by the app were classified and annotated, and the Deep Learning was used for machine learning of the curated images, and then the other images of road problems were used for verification. The detecting success rate of the road problems with high severity such as road kills, obstacles in a lane, road surface cracks was over 90%, which shows the applicability of the proposed process. It is expected that the proposed process will make the app possible to be used in the filed to make a priority decision making by classifying the level of severity of the reported road problems automatically.

• Journal of IKEEE
• /
• v.26 no.3
• /
• pp.373-379
• /
• 2022

In this paper, since the APD(Avalanche Photo Diode) for LTV(Light to Voltage) conversion uses a high voltage in the operating range unlike other PD(Photo Diode)s, the quenching resistor must be connected in series to prevent overcurrent when using the TIA(Transimpedance Amplifier). In such a case, quenching resistance may affect the transfer function of the TIA circuit, resulting in serious stability. Therefore, in this paper, by analyzing the effect of APD quenching resistance on the voltage and current loop transfer function of TIA, we propose a loop analysis and a method for determining the quenching resistance value to improve stability. TIA circuit with quenching resistance was designed by the proposed method and the stability of operation was verified through simulation and chip fabrication.

• Journal of Advanced Navigation Technology
• /
• v.26 no.5
• /
• pp.312-318
• /
• 2022

Currently, the Republic of Korea is facing the problem of a decrease in military service resources due to the demographic cliff, and is pursuing military restructuring and changes in the military force structure in order to respond to this. In this situation, the Army is pushing forward the deployment of a drone-bot combat system that will lead the future battlefield. The battlefield of the future will be changed into an integrated battlefield concept that combines command and control, surveillance and reconnaissance, and precision strike. According to these changes, unmanned combat system, including dronebots, will be widely applied to combat situations that are high risk and difficult for humans to perform in actual combat. In this paper, as one of the countermeasures to these changes, autonomous behavior software with a BDI architecture-based decision-making system was developed. The autonomous behavior software applied a framework structure to improve applicability to multiple models. Its function was verified in a PC-based environment by assuming that the target UAV is a battalion-level surveillance and reconnaissance UAV.

• Journal of the Korea Society of Computer and Information
• /
• v.27 no.12
• /
• pp.69-76
• /
• 2022

This paper proposes a method of refining and processing time-series data using Medical Information Mart for Intensive Care (MIMIC-IV) v2.0 data. In addition, the significance of the processing method was validated through a machine learning-based pressure ulcer early warning system using a dataset processed based on the proposed method. The implemented system alerts medical staff in advance 12 and 24 hours before a lesion occurs. In conjunction with the Electronic Medical Record (EMR) system, it informs the medical staff of the risk of a patient's pressure ulcer development in real-time to support a clinical decision, and further, it enables the efficient allocation of medical resources. Among several machine learning models, the GRU model showed the best performance with AUROC of 0.831 for 12 hours and 0.822 for 24 hours.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2023.05a
• /
• pp.56-56
• /
• 2023

남양호는 농업용수 공급을 위해 건설된 하구 담수호로 과도한 영양물질 축적으로 인해 매년 여름 녹조류가 번성한다. 따라서 본 연구에서는 조류발생 특성을 분석하고자 식물성 플랑크톤 및 관련 분해 산물에 의해 고유 광학특성을 가지고 있는 Chlorophyll-a(Chl-a)의 추정을 통한 녹조 발생을 파악하고자 Sentinel-2 Multi Spectral Image(MSI)의 원격 반사율 광학 스펙트럼을 사용하였다. Chl-a 추정알고리즘 개발을 위하여 Sentinel-2 A, B의 교차 방문주기인 5일 간격에 맞추어 현장수질자료(2022년: 27회 2023년: 27회)를 측정하였다. Chl-a 농도는 EXO-YSI를이용하여 측정하였으며 해당기간동안 9.4 ~ 127.1 mg/L의 범위를 보였으며, Sentine-2 자료는 A, B자료에서 B1(443 nm) ~ B8A(865 nm)파장의 값을 기상조건(구름, 안개, 강수)을 고려하여 현장수질측정 위치에서 반사도를 추출하였다. 입력자료는 대기 및 방사영향을 고려해 반사도 간의 비율자료와 선행연구에서 활용된 반사도를 활용하였으며 알고리즘은 다중선형회귀분석(Multi Linear Regression Model)과 Random Forest를 활용하였다. MLR의 경우 결정계수(R2)가 학습 및 검증에서 각각 0.68, 0.59의 성능을 보였으며, RF의 경우 각각 0.94, 0.85의 성능을 보였다. 해당알고리즘으로 생성된 Chl-a 시공간농도 자료는 담수호내 조류발생 특성을 분석하고 효율적 조류관리 및 대처에 활용될 것으로 판단된다.

• KIPS Transactions on Software and Data Engineering
• /
• v.12 no.8
• /
• pp.333-340
• /
• 2023

Efficient prediction of corporate bankruptcy is an important part of making appropriate lending decisions for financial institutions and reducing loan default rates. In many studies, classification models using artificial intelligence technology have been used. In the financial industry, even if the performance of the new predictive models is excellent, it should be accompanied by an intuitive explanation of the basis on which the result was determined. Recently, the US, EU, and South Korea have commonly presented the right to request explanations of algorithms, so transparency in the use of AI in the financial sector must be secured. In this paper, an artificial intelligence-based interpretable classification prediction model was proposed using corporate bankruptcy data that was open to the outside world. First, data preprocessing, 5-fold cross-validation, etc. were performed, and classification performance was compared through optimization of 10 supervised learning classification models such as logistic regression, SVM, XGBoost, and LightGBM. As a result, LightGBM was confirmed as the best performance model, and SHAP, an explainable artificial intelligence technique, was applied to provide a post-explanation of the bankruptcy prediction process.