• Proceedings of the Korea Water Resources Association Conference
• /
• 2023.05a
• /
• pp.289-289
• /
• 2023

4차산업 혁명이 도래한 이후로 전세계적으로 AI 기술이 유래 없는 속도로 발달 및 활용되고 있으며, 다양한 분야에서 AI 기법을 도입한 연구가 활발히 진행 중에 있다. 최근 수자원 분야에서는 단기 강우 예측, 댐 유입량 예측 및 하천 수위 예측 등의 분야에서 AI 기술이 접목되어 꾸준한 기술 개발이 이루어지고 있다. 그러나 단변량으로 축척된 자료를 활용하여 중·장기 모형 개발 연구가 다수 진행되고 있지만, 급격한 기후변화 현상과 복잡한 매커니즘을 보이고 있는 기상현상의 경우 단변량 분석으로서는 정확도가 저하 될 수 있는 우려가 있는 것이 현실이다. 이에 본 연구에서는 상기에 제시된 단점을 극복하고자 다양한 기상자료를 검증·예측인자로 활용함과 동시에 Deeplearning 모형과 결합하여 신뢰성 있는 단기 강수 예측이 가능한 모형을 개발하였다. 본 연구에서는 유럽중기예보센터(ECMWF, European Center for Medium-Range Weather Forecasts)에서 제공하고 있는 ERA5 재해석 자료를 활용하였으며, Deeplearning 모형과 결합하여 단기 강우 예측이 가능한 모형을 개발하였다. 1차적으로 격자자료(25km×25km)로 제공되고 있는 ERA5 자료를 상세화(downscaling) 모형에 적용하여 기상청 관측소와 비교·검증하였으며, Deeplearning 모형을 통해 단기 예측이 가능한 모형으로 확장하였다. 이때 Deeplearning의 다양한 모형 중 시계열 분석에 있어 예측 성능이 높은 LSTM 모형을 활용하였으며, 제공되고 있는 대기 변수의 상호관계를 노드간 연결을 통해 결과의 정확도와 신뢰성을 확보하였다. 본 연구 결과는 기관별로 제공하고 있는 예측 수준을 상회하는 결과를 도출하였으며, 홍수기에 집중되는 강우량을 예측하여 대비·대책을 선제적으로 마련할 수 있는 자료로써의 활용성이 높을 것으로 사료된다.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2022.05a
• /
• pp.145-145
• /
• 2022

Availability of abundant water resources data in developing countries is a great concern that has hindered the adoption of deep learning techniques (DL) for disaster prevention and mitigation. On the contrary, over the last two decades, a sizeable amount of DL publication in disaster management emanated from developed countries with efficient data management systems. To understand the current state of DL adoption for solving water-related disaster management in developing countries, an extensive bibliometric review coupled with a theory-based analysis of related research documents is conducted from 2003 - 2022 using Web of Science, Scopus, VOSviewer software and PRISMA model. Results show that four major disasters - pluvial / fluvial flooding, land subsidence, drought and snow avalanche are the most prevalent. Also, recurrent flash floods and landslides caused by irregular rainfall pattern, abundant freshwater and mountainous terrains made India the only developing country with an impressive DL adoption rate of 50% publication count, thereby setting the pace for other developing countries. Further analysis indicates that economically-disadvantaged countries will experience a delay in DL implementation based on their Human Development Index (HDI) because DL implementation is capital-intensive. COVID-19 among other factors is identified as a driver of DL. Although, the Long Short Term Model (LSTM) model is the most frequently used, but optimal model performance is not limited to a certain model. Each DL model performs based on defined modelling objectives. Furthermore, effect of input data size shows no clear relationship with model performance while final model deployment in solving disaster problems in real-life scenarios is lacking. Therefore, data augmentation and transfer learning are recommended to solve data management problems. Intensive research, training, innovation, deployment using cheap web-based servers, APIs and nature-based solutions are encouraged to enhance disaster preparedness.

• Development and Reproduction
• /
• v.27 no.1
• /
• pp.25-37
• /
• 2023

Acetaminophen [Paracetamol, N-acetyl-para-aminophenol (APAP)] is a common over-the-counter analgesic agent as nonsteroidal anti-inflammatory drugs (NSAIDs). The high doses or the long-term treatment of acetaminophen via usual gavage feeding resulted in damage of testicles that presented recoverable impairment, as well as liver and kidney. The influence of acetaminophen was examined in male golden hamsters treated with acetaminophen-containing diet feeding. They were divided into 5 groups and subjected to this experiment for 4 weeks: animals housed in long photoperiod (LP) as LP control, animals housed in short photoperiod (SP) for 4 weeks as SP control (SP4), and groups of animals treated with low, middle, and high concentrations of acetaminophen (Low, Middle, High groups). Also animals housed in SP for 8 weeks were included (SP8) to contrast testicular activities, if necessary. As results, spermatozoa filled the seminiferous tubules of the testicles of animals in LP control and SP4 groups. The aspects were seen in the animals taken diets of low and middle doses of acetaminophen. The animals who fed high dose of acetaminophen showed large or small testicles. The large testicles displayed all germ cells at the steps of spermatogenesis. The small testicles presented no sperm as the animals housed in SP for 8 weeks. Thus these results indicate that acetaminophen invokes the antigonadal effects and accelerates the regressing process of the testicles in the animals compared to the animals exposed to SP.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.22 no.1
• /
• pp.103-114
• /
• 2023

This study collected various data of urban roadways to analyze the effect of travel speed change, and a GRU-based short-term travel speed prediction model was developed using such big data. The baseline model and the double exponential smoothing model were selected as comparison models, and prediction errors were evaluated using the RMSE index. The model evaluation results revealed that the average RMSE of the baseline model and the double exponential smoothing model were 7.46 and 5.94, respectively. The average RMSE predicted by the GRU model was 5.08. Although there are deviations for each of the 15 links, most cases showed minimal errors in the GRU model, and the additional scatter plot analysis presented the same result. These results indicate that the prediction error can be reduced, and the model application speed can be improved when applying the GRU-based model in the process of generating travel speed information on urban roadways.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.17 no.5
• /
• pp.1396-1412
• /
• 2023

Conversation modeling is an important and challenging task in the field of natural language processing because it is a key component promoting the development of automated humanmachine conversation. Most recent research concerning conversation modeling focuses only on the current utterance (considered as the current question) to generate a response, and thus fails to capture the conversation's logic from its beginning. Some studies concatenate the current question with previous conversation sentences and use it as input for response generation. Another approach is to use an encoder to store all previous utterances. Each time a new question is encountered, the encoder is updated and used to generate the response. Our approach in this paper differs from previous studies in that we explicitly separate the encoding of the question from the encoding of its context. This results in different encoding models for the question and the context, capturing the specificity of each. In this way, we have access to the entire context when generating the response. To this end, we propose a deep neural network-based model, called the Context Model, to encode previous utterances' information and combine it with the current question. This approach satisfies the need for context information while keeping the different roles of the current question and its context separate while generating a response. We investigate two approaches for representing the context: Long short-term memory and Convolutional neural network. Experiments show that our Context Model outperforms a baseline model on both ConvAI2 Dataset and a collected dataset of conversational English.

• Genomics & Informatics
• /
• v.20 no.4
• /
• pp.45.1-45.7
• /
• 2022

Food security will be affected by climate change worldwide, particularly in the developing world, where the most important food products originate from plants. Plants are often exposed to environmental stresses that may affect their growth, development, yield, and food quality. Auxin is a hormone that plays a critical role in improving plants' tolerance of environmental conditions. Auxin controls the expression of many stress-responsive genes in plants by interacting with specific cis-regulatory elements called auxin-responsive elements (AuxREs). In this work, we performed an in silico prediction of AuxREs in promoters of five auxin-responsive genes in Zea mays. We applied a data fusion approach based on the combined use of Dempster-Shafer evidence theory and fuzzy sets. Auxin has a direct impact on cell membrane proteins. The short-term auxin response may be represented by the regulation of transmembrane gene expression. The detection of an AuxRE in the promoter of prolyl oligopeptidase (POP) in Z. mays and the 3-fold overexpression of this gene under auxin treatment for 30 min indicated the role of POP in maize auxin response. POP is regulated by auxin to perform stress adaptation. In addition, the detection of two AuxRE TGTCTC motifs in the upstream sequence of the bx1 gene suggests that bx1 can be regulated by auxin. Auxin may also be involved in the regulation of dehydration-responsive element-binding and some members of the protein kinase superfamily.

• The Journal of the Convergence on Culture Technology
• /
• v.9 no.3
• /
• pp.287-292
• /
• 2023

The U.S. National Aeronautics and Space Administration proposed a new concept of urban air mobility in the city's short-range air transport ecosystem in order to build a new low-altitude air, and the term uam is currently used worldwide. This paradigm is also being promoted by the Korean government with the goal of commercializing urban air transport services by 2025, and furthermore, the need to secure air maneuvers and transportation capacity is emerging due to the rapidly changing future operating environment and battlefield space. In other words, this study started to present the military necessity and military operation plan by introducing the 'Agility Prime' program of the US Air Force. 'Agility Prime' program was organized in order of background and concept of urban air mobility, development trend of Korean urban air mobility and analysis of the US Air Force's 'Agility Prime' program, and it is expected that this study will be followed by a follow-up study.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.46 no.3
• /
• pp.186-197
• /
• 2023

In this study, we focus on the improvement of data quality transmitted from a weather buoy that guides a route of ships. The buoy has an Internet-of-Thing (IoT) including sensors to collect meteorological data and the buoy's status, and it also has a wireless communication device to send them to the central database in a ground control center and ships nearby. The time interval of data collected by the sensor is irregular, and fault data is often detected. Therefore, this study provides a framework to improve data quality using machine learning models. The normal data pattern is trained by machine learning models, and the trained models detect the fault data from the collected data set of the sensor and adjust them. For determining fault data, interquartile range (IQR) removes the value outside the outlier, and an NGBoost algorithm removes the data above the upper bound and below the lower bound. The removed data is interpolated using NGBoost or long-short term memory (LSTM) algorithm. The performance of the suggested process is evaluated by actual weather buoy data from Korea to improve the quality of 'AIR_TEMPERATURE' data by using other data from the same buoy. The performance of our proposed framework has been validated through computational experiments based on real-world data, confirming its suitability for practical applications in real-world scenarios.

• Journal of Public Diplomacy
• /
• v.3 no.2
• /
• pp.1-34
• /
• 2023

This study finds that the South Korean government's public diplomacy efforts have focused on promotional activities such as the "K-wave" or responses to controversial historical issues. However, the South Korean government needs to be more prepared for strategic responses to unexpected crises and subsequent communications. This paper attempts to apply crisis communication research developed in the field of public relations to public diplomacy. To do so, this research reviewed theories in crisis communication, an essential area of public relations, and developed a crisis communication model. The model was then applied to several crisis case studies to suggest how to develop response strategies and conduct communications. As a result, this research developed an Ongoing Public Diplomacy Crisis Communication Model (PDCCM) that can be applied to public diplomacy research and practice. The model identifies four crisis communication principles (be quick, be open, be consistent, be authentic) that should be applied in six phases. Following continuous social listening and monitoring, governments should analyze crisis situations using sense-making, develop short- and long-term crisis response objectives, response strategies, and communication messages depending on the level of responsibility, implement crisis communication, and conduct post-crisis evaluation.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.18 no.2
• /
• pp.456-477
• /
• 2024

With information technology's rapid development, the Internet faces serious security problems. Studies have shown that malware has become a primary means of attacking the Internet. Therefore, adversarial samples have become a vital breakthrough point for studying malware. By studying adversarial samples, we can gain insights into the behavior and characteristics of malware, evaluate the performance of existing detectors in the face of deceptive samples, and help to discover vulnerabilities and improve detection methods for better performance. However, existing adversarial sample generation methods still need help regarding escape effectiveness and mobility. For instance, researchers have attempted to incorporate perturbation methods like Fast Gradient Sign Method (FGSM), Projected Gradient Descent (PGD), and others into adversarial samples to obfuscate detectors. However, these methods are only effective in specific environments and yield limited evasion effectiveness. To solve the above problems, this paper proposes a malware adversarial sample generation method (PixGAN) based on the pixel attention mechanism, which aims to improve adversarial samples' escape effect and mobility. The method transforms malware into grey-scale images and introduces the pixel attention mechanism in the Deep Convolution Generative Adversarial Networks (DCGAN) model to weigh the critical pixels in the grey-scale map, which improves the modeling ability of the generator and discriminator, thus enhancing the escape effect and mobility of the adversarial samples. The escape rate (ASR) is used as an evaluation index of the quality of the adversarial samples. The experimental results show that the adversarial samples generated by PixGAN achieve escape rates of 97%, 94%, 35%, 39%, and 43% on the Random Forest (RF), Support Vector Machine (SVM), Convolutional Neural Network (CNN), Convolutional Neural Network and Recurrent Neural Network (CNN_RNN), and Convolutional Neural Network and Long Short Term Memory (CNN_LSTM) algorithmic detectors, respectively.