• Journal of Life Science
• /
• v.33 no.6
• /
• pp.490-497
• /
• 2023

Pregnant women may need to take medications to treat preexisting diseases or diseases that develop during pregnancy. However, some drugs may be fetotoxic and lead to, for example, teratogenicity and growth retardation. Predicting the fetotoxicity of drugs is thus important for the health of the mother and fetus. The fetotoxicity of many drugs has not been established because various challenges hinder the ability of researchers to determine their fetotoxicity. The need exists for in silico-based fetotoxicity assessment models, as they can modernize the testing paradigm, improve predictability, and reduce the use of animals and the costs of fetotoxicity testing. In this study, we collected data on the fetotoxicity of drugs and constructed fetotoxicity prediction models based on various machine learning algorithms. We optimized the models for more precise predictions by tuning the hyperparameters. We then performed quantitative performance evaluations. The results indicated that the constructed machine learning-based models had high performance (AUROC >0.85, AUPR >0.9) in fetotoxicity prediction. We also analyzed the feature importance of our model's predictions, which could be leveraged to identify the specific features of drugs that are strongly associated with fetotoxicity. The proposed model can be used to prescreen drugs and drug candidates at a lower cost and in less time. It provides a predictive score for fetotoxicity risk, which may be beneficial in the design of studies on fetotoxicity in human pregnancy.

• Journal of Intelligence and Information Systems
• /
• v.29 no.2
• /
• pp.23-34
• /
• 2023

Wearable technology for military applications has received considerable attention as a means of personal status check and monitoring. Among many, an implementation to recognize specific motion states of a human is promising in that allows active management of troops by immediately collecting the operational status and movement status of individual soldiers. In this study, as an extension of military wearable application research, a new ankle wearable device is proposed that can glean the information of a soldier on the battlefield on which action he/she takes in which environment. Presuming a virtual situation, the soldier's upper limbs are easily exposed to uncertainties about circumstances. Therefore, a sensing module is attached to the ankle of the soldier that may always interact with the ground. The obtained data comprises 3-axis accelerations and 3-axis rotational velocities, which cannot be interpreted by hand-made algorithms. In this study, to discern the behavioral characteristics of a human using these dynamic data, a data-driven model is introduced; four features extracted from sliced data (minimum, maximum, mean, and standard deviation) are utilized as an input of the model to learn and classify eight primary military movements (Sitting, Standing, Walking, Running, Ascending, Descending, Low Crawl, and High Crawl). As a result, the proposed device could recognize a movement status of a solider with 95.16% accuracy in an arbitrary test situation. This research is meaningful since an effective way of motion recognition has been introduced that can be furtherly extended to various military applications by incorporating wearable technology and artificial intelligence.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.22 no.3
• /
• pp.73-87
• /
• 2023

Furnishing traffic safety information can contribute to providing hazard warnings to drivers, thereby avoiding crashes. A smart road lighting platform that instantly recognizes road conditions using various sensors and provides appropriate traffic safety information has therefore been developed. This study analyzes the short-term traffic safety improvement effects of the smart road lighting's tunnel traffic safety information service using surrogate safety measures (SSM). Individual driving behavior was investigated by applying the vehicle trajectory data collected with RADAR in the Anin Avalanche 1 and 2 tunnel sections in Gangneung. Comparing accumulated speeding, speed variation, time-to-collision, and deceleration rate to avoid the crash before and after providing traffic safety information, all SSMs showed significant improvement, indicating that the tunnel traffic safety information service is beneficial in improving traffic safety. Analyzing potential crash risk in the subdivided tunnel and access road sections revealed that providing traffic safety information reduced the probability of traffic accidents in most segments. The results of this study will be valuable for analyzing the short-term quantitative effects of traffic safety information services.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2020.06a
• /
• pp.146-146
• /
• 2020

최근 하천의 유사 중 소류사량을 계측하기 위해 사용된 기존의 물리적 소류사 샘플러를 이용한 직접계측방법은 홍수 시에 깊은 수위와 빠른 유속, 계측 절차상의 위험성 때문에 현장관측이 매우 어려운 한계를 극복하기 위해 현업에서는 소류사량을 간접적으로 추정하는 이론식에 의한 방법이 광범위하게 활용되고 있으나 이 방법 또한 추정이론식의 적용지역, 적용방법에 따라 결과가 수십배 이상 큰 차이를 나타나 실제 활용성에 대한 문제점이 있다. 이러한 기존의 소류사량 측정 방법의 문제점을 보완하기 위해 소류사량을 간접계측하는 방법이 활발히 제안되고 있다. 대표적인 방법으로 하상 이동 시 소류사의 충돌음을 음향센서로 계측하여 신호처리를 통해 소류사량을 추정하는 계측기기인 하이드로폰이 있다. 그러나 국외의 소류사량 간접계측 장치는 소류사량의 운송량이 많을 경우 음향신호 중접으로 인해 펄스 수의 감소, 감지 가능한 입경크기의 제한 등의 문제가 있다. 또한 국내의 백무평(2018)이 제안한 소류사 분석 방법인 대역통과방법(B-P Method)는 소류사량 추정에 있어서 기존의 방법과는 달리 주파수 특성을 반영하여 이전 연구들에 비하여 펄스 검출률을 향상시겼지만 이 방법은 극히 낮은 저유속과 작은 입경이라는 실험조건에서 이루어졌다는 제한사항이 있다. 따라서 본 연구는 다양한 입경과 고유속에 대하여 소류사량을 정량화할 수 있는 방법을 제시하기 위해 소류사 입경이 하이드로폰에 충돌할 때 발생하는 단독입자의 충돌음을 계측하기 위한 실외 수로실험장치를 구축하여 계측을 수행하였다. 실험은 현장에서 대표 시료로 분류된 몇 가지 입경에 대해서 유량 변화에 따른 충돌음향과 소류사량 그리고 소류사 입경크기에 따른 하이드로폰에서 인지되는 음향 특성을 계측 및 분석하였다. 연구결과 입경 크기 및 수리조건 변화에 따른 하이드로폰의 충돌음향 특성을 파악하여 단일 입경별 소류사량 추정관계식을 산출하였다. 또한 산출된 추정 관계식의 특성치와 공급 소류사량 간의 관계를 유도해 보았다. 향후 혼합입경에 대한 실험과 추정 관계식 신뢰성 검토 후 추가적으로 다양한 실험조건을 고려하여 실제 하천에 운송되는 소류사량과의 교정관계 확립을 진행한다면 국내 소류사량 데이터 수집을 위한 현장 설치까지 가능할 것으로 사료된다.

• Korean Journal of Heritage: History & Science
• /
• v.56 no.1
• /
• pp.162-180
• /
• 2023

The World Heritage Committee decided to make "cultural landscapes" a world heritage category in the 16th Session of the UNESCO General Conference. The decision was made from a recognition of the importance of interactions between human beings and the natural environment or between cultural heritage and natural heritage. Many countries have created policies and institutions to protect their own cultural landscapes along with the changing times. Korea, however, has not obviously defined the concepts and categories of its cultural landscapes, but manages policies and institutions based on the concept of a scenic spot, which has some similar meanings. In addition, it even borrows the "list of landscape adjectives," one of the representative methods for managing landscapes, from foreign countries. With this background, this paper suggested how to define cultural landscapes according to the global development flow. It created a list of cultural landscape adjectives by gathering the adjectives that can properly express local cultural landscapes in Korea. In particular, it collected 4,556 articles from a local newspaper by focusing on the case of Shinan-gun, Jeollanam-do, and analyzed key words and adjectives included in them by using big data analysis. The results suggested by this paper, such as the "classification table of cultural landscape types," "list of cultural landscape adjectives" and "network map of nouns/adjectives" can be applied to research on other localities, and furthermore, used as basic data for finding and protecting the characteristics of local cultural landscapes in Korea.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.28 no.6C
• /
• pp.367-377
• /
• 2008

As part of study to develop LRFD (Load and Resistance Factor Design) codes for foundation structures in Korea, resistance factors for static bearing capacity of driven steel pipe piles were calibrated in the framework of reliability theory. The 57 data sets of static load tests and soil property tests conducted in the whole domestic area were collected and these load test piles were sorted into two cases: SPT N at pile tip less than 50, SPT N at pile tip equal to or more than 50. The static bearing capacity formula and the Meyerhof method using N values were applied to calculate the expected design bearing capacities of the piles. The resistance bias factors were evaluated for the two static design methods by comparing the representative measured bearing capacities with the expected design values. Reliability analysis was performed by two types of advanced methods: the First Order Reliability Method (FORM), and the Monte Carlo Simulation (MCS) method using resistance bias factor statistics. The target reliability indices are selected as 2.0 and 2.33 for group pile case and 2.5 for single pile case, in consideration of the reliability level of the current design practice, redundancy of pile group, acceptable risk level, construction quality control, and significance of individual structure. Resistance factors of driven steel pipe piles were recommended based on the results derived from the First Order Reliability Method and the Monte Carlo Simulation method.

• Journal of Korea Water Resources Association
• /
• v.56 no.7
• /
• pp.439-449
• /
• 2023

Recent advancements in data measuring technology have facilitated the installation of various sensors, such as pressure meters and flow meters, to effectively assess the real-time conditions of water distribution systems (WDSs). However, as cities expand extensively, the factors that impact the reliability of measurements have become increasingly diverse. In particular, demand data, one of the most significant hydraulic variable in WDS, is challenging to be measured directly and is prone to missing values, making the development of accurate data generation models more important. Therefore, this paper proposes an adversarially trained autoencoder (ATAE) model based on generative deep learning techniques to accurately estimate demand data in WDSs. The proposed model utilizes two neural networks: a generative network and a discriminative network. The generative network generates demand data using the information provided from the measured pressure data, while the discriminative network evaluates the generated demand outputs and provides feedback to the generator to learn the distinctive features of the data. To validate its performance, the ATAE model is applied to a real distribution system in Austin, Texas, USA. The study analyzes the impact of data uncertainty by calculating the accuracy of ATAE's prediction results for varying levels of uncertainty in the demand and the pressure time series data. Additionally, the model's performance is evaluated by comparing the results for different data collection periods (low, average, and high demand hours) to assess its ability to generate demand data based on water consumption levels.

• The Journal of the Convergence on Culture Technology
• /
• v.9 no.4
• /
• pp.401-408
• /
• 2023

The purpose of this study is to design textbook metadata as a basic task for building a textbook database. To this end, reading textbooks were defined as a category of textbooks, and a metadata development methodology was established through previous research. In order to ensure that bibliographically essential elements are not omitted, the catalog description elements of institutions that collect, accumulate, and service textbooks such as the National Library of Korea were investigated. The elements of Dublin Core, MODS, and KEM were mapped to derive elements suitable for describing textbooks. Finally, a set of textbook metadata elements consisting of 14 elements in three categories - bibliography, context, and textbook characteristics were presented by adding publication type, genre, and curriculum period elements. The 14 elements are titles, authors, publications, formats, identification sign, languages, locations, subject names, annotation, genres, table of contents, subjects, curriculum period, and curriculum information. In this study, we contributed to this field by discussing how to organize textbook resources with national knowledge resources, and in future studies, we proposed to evaluate usability by applying metadata elements to actual textbooks and revise and supplement them according to the evaluation results.

• The Journal of Bigdata
• /
• v.7 no.2
• /
• pp.235-244
• /
• 2022

The rental history data of public bicycles in Seoul were analyzed to examine how pandemic phenomena such as COVID-19 caused changes in people's micro mobility. Data for 2019 and 2021 were compared and analyzed by dividing them before and after COVID-19. Data were collected from public data portal sites, and data marts were created for in-depth analysis. In order to compare the changes in the two periods, the riding direction type dimension and the rental station type dimension were added, and the derived variables (rotation rate per unit, riding speed) were newly created. There is no significant difference in the average rental time before and after COVID-19, but the average rental distance and average usage speed decreased. Even in the mobility of Ttareungi, you can see the slow rhythm of daily life. On weekdays, the usage rate was the highest during commuting hours even before COVID-19, but it increased rapidly after COVID-19. It can be interpreted that people who are concerned about infection prefer Ttareungi to village buses as a means of micro-mobility. The results of data mart-based visualization and analysis proposed in this study will be able to provide insight into public bicycle operation and policy development. In future studies, it is necessary to combine SNS data such as Twitter and Instagram with public bicycle rental history data. It is expected that the value of related research can be improved by examining the behavior of bike users in various places.

• The Journal of the Convergence on Culture Technology
• /
• v.9 no.3
• /
• pp.789-795
• /
• 2023

Digital-Twin are recognized as an important core technology for the realization of Smart Factories by simulating and optimizing the monitoring and predictive maintenance of manufacturing equipment and the operation of production lines in a digital space. To implement this system, we adopt the IEC62541-based OPC-UA (Open Platform Communications Unified-Architecture) Protocol, which has strengths in interoperability and connectivity between heterogeneous platforms. Therefore, In this paper, We designed and implemented an IIoT(Industry Internet of Things) system that connects heterogeneous platforms, and developed an OPC-UA simulator based on IEC 62541. We will present whether the data will be applied to the Digital-Twin Platform and whether it will work, and proceed with performance tests and evaluations. We evaluate the operation performance and OPC-UA performance of the Digital-Twin platform lightened by the proposed device, and present the optimal IEC62514-based simulator system. We proceeded with the performance evaluation of sending and receiving data with OPC-UA wrapping with the proposed simulator, and found that a lightweight Digital-Twin platform can be operated. This research can apply the OPC-UA protocol for implementing smart factory and meta-factory in the manufacturing shop floor with limited resources, avoiding the waste of time and space on the shop floor through the OPC-UA simulator. We expect that this will contribute to a significant improvement in efficiency by minimizing.