모빌리티 예측은 단순한 통행 경로 예측을 넘어, 사회 전반의 효율성 및 안전성 향상을 위한 핵심 데이터를 제공한다는 점에서 중 요하다. 기존의 예측 기법은 시공간적 규칙성과 개인 이동 패턴의 통계적 특성 분석에 주로 의존하였으며, 최근 딥러닝 기반의 시공간 모델링을 통해 예측 성능이 향상되었다. 그러나 여전히 개인 통행의 단기·장기적 시공간 의존성 및 복잡한 패턴을 처리하는 데 한계가 존재한다. 이를 극복하기 위해, 본 연구는 대규모 사전 학습된 거대 언어 모델(Large Language Model; LLM)을 도입하여, 개인 속성뿐 만 아니라 실제 통행 데이터를 반영한 객체 단위 통행 생성 프레임워크를 제안한다. LLM 기반(ChatGPT-4o) 객체 단위 통행 생성 프레 임워크는 (1) 개인 모빌리티 패턴 학습, (2) 통행 생성의 두 단계로 이루어진다. 이후 한국교통연구원의 개인통행 실태조사(2021) 데이 터를 이용하여 프레임워크의 통행 생성 성능을 확인하였다. 통행 시작·출발 시간 분포, 출발·도착지 장소 유형, 통행목적, 이용 교통수 단의 정확도를 확인한 결과, 대부분 항목에서 70% 이상의 정확도를 보였다. 하지만 통행목적은 13개의 목적 중 하나를 예측해야 하기 에 정확도가 다른 항목에 비해 약 40%로 낮게 나타났다. 본 연구는 통행 생성 프레임워크를 설계하고, 이에 맞춰 입력 데이터를 가공 및 프롬프트 엔지니어링을 수행함으로써 LLM 기반 통행 생성 기술의 가능성을 확인하였다. 향후 프레임워크의 예측 성능 검증 및 개 선을 위한 추가 연구가 필요하며, 날씨, 대규모 행사 등과 같은 외부 요인들을 고려하면 더욱 정교하고 현실적인 통행일지를 생성할 수 있을 것이다.

포장상태 평가를 위한 노면영상 촬영은 라인스캔 방식이 주를 이루고 있다. 라인스캔 특성 상, 조사환경이나 장비특성이 달라질 경 우 밝기가 상이한 노면영상을 취득할 수 있고 이는 U-net과 같은 픽셀 단위 segmentation 딥러닝 모델의 균열 자동검출 성능에 영향을 미친다. 본 연구에서는 인공지능 검출 모델의 변경 없이 영상의 밝기 최적화와 morphology 연산기법을 노면영상 전·후처리 방법으로 제시하고 그 효과를 분석하였다. 영상 처리를 통해 과다 검출경향을 보인 이상치들이 제거되었으며 정답으로 간주할 수 있는 전문요 원 분석결과인 GT 균열률과의 상관성 또한 향상됨을 확인하였다.

이동 물체의 전역 경로 탐색에 있어 출발지점과 도착지점은 반드시 필요한 조건 중 하나이다. 선박의 경로 탐색에 있어 도착 가능 지점은 부두 이외 선박의 입출항 전 대기 장소 및 선박 수리 등 다양한 목적으로 이용되는 정박지(Anchorage)도 포함될 수 있다. 이 러한 정박지는 연안 해역 환경에 따라 특정 형태로 설계된 공간으로 경로 탐색을 위한 도착지점은 선박이 정박을 위한 투묘 지점이라고 볼 수 있다. 이에, 본 연구에서는 샘플링 기반 탐색 알고리즘 중 PRM 및 계산 기하학 알고리즘을 통해 정박지라는 특정 공간에 대해 다른 선박이 점유하지 않는 공간 탐색을 통한 투묘 지점 산출 방법을 제시하였다. 또한, 개발된 알고리즘을 검증하기 위하여 국내 목포항 11번 정박지를 대상 해역으로 선정하고 시뮬레이션을 수행한 결과 다른 선박이 점유하지 않는 공간에 대해 투묘 지점을 탐색할 수 있었다. 본 연구의 결과는 향후 선박의 의사 결정 및 VTS의 정박지 관리를 위한 지원 방안으로 활용될 수 있을 것으로 기대된다.

Distribution and logistics industries contribute some of the biggest GDP(gross domestic product) in South Korea and the number of related companies are quarter of the total number of industries in the country. The number of retail tech companies are quickly increased due to the acceleration of the online and untact shopping trend. Furthermore, major distribution and logistics companies try to achieve integrated data management with the fulfillment process. In contrast, small and medium distribution companies still lack of the capacity and ability to develop digital innovation and smartization. Therefore, in this paper, a deep learning-based demand forecasting & recommendation model is proposed to improve business competitiveness. The proposed model is developed based on real sales transaction data to predict future demand for each product. The proposed model consists of six deep learning models, which are MLP(multi-layers perception), CNN(convolution neural network), RNN(recurrent neural network), LSTM(long short term memory), Conv1D-BiLSTM(convolution-long short term memory) for demand forecasting and collaborative filtering for the recommendation. Each model provides the best prediction result for each product and recommendation model can recommend best sales product among companies own sales list as well as competitor’s item list. The proposed demand forecasting model is expected to improve the competitiveness of the small and medium-sized distribution and logistics industry.

PURPOSES : This study aims to provide quantitative profile values for the objective evaluation of concrete surface profile (CSP) grades in concrete structures. The main aims are to quantify the CSP grade required for concrete surface pretreatment and proposing a more suitable CSP grade for structural maintenance. METHODS : Initially, the challenges in measuring concrete surface profiles were outlined by analyzing pretreatment work and profile samples of concrete pavements. Theoretical foundations for quantifying concrete surface roughness were established, and regression models including linear regression, cubic regression, and log regression were selected. Additionally, the interquartile range anomaly removal technique was employed to preprocess the data for regression modeling. RESULTS : Concrete CSP profiles were measured through indoor tests, and the measured data were quantified. Linear regression, cubic regression, and log regression models were applied to each CSP grade for comparative analysis of the results. Furthermore, comparative studies were conducted through adhesion strength tests based on the CSP grade. CONCLUSIONS : Our results are expected to establish objective standards for the pretreatment stage of concrete repair and reinforcement. The derived reference values can inform standards for the restoration and reinforcement of concrete structures, thereby contributing to performance improvement. Moreover, our results may serve as primary data for the repair and reinforcement of various concrete structures such as airports, bridges, highways, and buildings.

교통량이 증가하고 교량과 같은 특수구조물에 아스팔트 포장이 시공되는 사례가 증가함에 따라 일반적으로 사용되는 아스팔트보다 높은 성능을 가진 아스팔트에 대한 수요가 증가하고 있다. 일반 아스팔트 혼합물은 내구연한이 지나면 재생첨가제 등을 사용하여 다 시 도로포장재료로서 재활용할 수 있는 방안이 마련되어 있으나, 개질 아스팔트가 사용된 폐아스팔트 혼합물은 매립재로 사용하는 것 이외에는 별다른 대안이 없는 실정이다. 이에 본 연구에서는 국토부 지침에 규정된 재활용 아스팔트 혼합물 배합설계법을 적용하여 개질 폐아스팔트 혼합물을 재활용할 수 있는지를 검토해보고자 하였다. 이를 위해 개질 아스팔트를 활용하여 혼합물을 제작하였으며, 현장에서 수거되는 폐아스팔트 혼합물의 노화상태를 모사하기 위해 AASHTO R 30을 참고하여 강제 노화를 실시하였다. 노화 및 추출 과정에서 아스팔트의 물성 변화를 확인하기 위해 절대점도, DSR, MSCR 시험을 실시하였다. 시험결과, 추출 후 바인더의 절대점도는 감소하였으나 G*(복합전단계수)와 δ(위상각)은 증가하는 경향을 보였다. 소성변형 저항성을 확인하기 위해 MSCR(다중 응력 크리프 및 회복) 시험을 실시한 결과,  이 2배 가까이 증가하여 소성변형 저항성이 감소한 것을 확인할 수 있었다. 이러한 결과는 추출시 사용 되는 용매가 개질첨가제를 추출하지 못하여 기인한 결과로 판단된다. 따라서 개질 폐아스팔트 혼합물을 재활용하기 위해서는 기존과 는 다른 별도의 배합설계법이 개발되어야 할 것으로 판단되었다.

Chelating agents, such as EDTA, NTA, and citric acid, possess the capacity to establish complexes with radionuclides, potentially enhancing the migration of such radionuclides from the disposal sites. Hence, quantification of these chelating agents in radioactive wastes is required to ensure secure disposal protocols. The determination of chelating agents in radioactive wastes is mainly composed of two steps, e.g. extraction and detection. However, there are little information on the extraction of the chelators in various radioactive wastes. We endeavored to optimize the extraction conditions for citric acid (CA) found within concrete, a prevalent component in the context of dismantled waste materials. Given the inherent high solubility of CA in water, we applied an aliquot of deionized water to the concrete and conducted a one-hour ultrasonic leaching procedure to facilitate chelate extraction. Subsequently, following the preparation of the concrete leachate via vacuum filtration and centrifugation to yield a clarified solution, we quantified the concentration of CA within the solution using Ion Chromatography (IC). To enhance leaching efficiency, we examined the % recovery variation with respect to the pH of the leaching solution. The optimized extraction method will be applied to diverse chelating agents and radioactive waste categories.

Nuclear power plants in Korea stores approximately 3,800 drums of paraffin solidification products. Due to the lack of homogeneity, these solidification products are not allowed to be disposed of. There is therefore a need for the separation of paraffin from the solidification products. This work developed an equipment for a selective separation of paraffin from the solidification product using the vacuum evaporation and condensational recovery method in a closed system. The equipment mainly consists of a vacuum evaporator and a condensational deposition recovery chamber. Nonisothermal vacuum TGAs, kinetic analyses and kinetic predictions were conducted to set appropriate operation conditions. Its basic operability under the established conditions was first confirmed using pure paraffin solid. Simulated paraffin solidification product fixing dried boric acid waste including nonradioactive Co and Cs were then fabricated and tested for the capability of selective separation of paraffin from the simulated waste. Paraffin was selectively separated without entertainment of Co and Cs. It was confirmed that the developed equipment could separate and recover paraffin in the form of nonradioactive waste.

Various types of spent fuel assembly in nuclear power plants have been transported to a post irradiation examination facility (PIEF) in KAERI to examine the mechanical and chemical properties of fuel and cladding. Once the fuel assembly arrive at PIEF, it is dismantled in a pool area to extract the fuel rods. Dismantling of the fuel assembly is performed by cutting the top nozzle. Currently, couple of dismantled assemblies have been stored in a storage pool without the top nozzle in PIEF. These assemblies cannot be handled directly using a gantry crane in the pool, and thus are contained in a special basket to handle. In this research, we developed a restoration method for a dismantled spent fuel assembly, especially for 16×16 Korea Optimized Fuel Assembly (KOFA). After reviewing the original design document and reports of KOFA, two tools are devised; an assembly tool and a tightening tool for a bolt. Since the top nozzle and dismantled KOFA can be re-assembled using a bolt, we follow the original design, size, and materials of the previously used bolt. The bolt to restore the top nozzle of KOFA is made of 321 stainless steel and has a design that fits the guideline of DIN 13-21 international standard. Our procedure can potentially be used to restore and repair the dismantled spent fuel assembly.

The development of advanced nuclear facilities is progressing rapidly around the world. Newly designed facilities have differences in structure and operation from existing nuclear facilities, so Safeguards by Design (SBD), which applies safeguards at the design stage, is important. To this end, designers should consider the safeguardability of nuclear facilities when designing the system. Safeguardability represents a measure of the ease of safeguards, and representative evaluation methodologies are Facility Safeguardability Analysis (FSA) and Safeguardability Check-List (SCL). Those two have limitations in the quantification of safeguardability. Accordingly, in this study, the Safeguardability Evaluation Method (SEM), which has clear evaluation criteria based on engineering formulas, was developed. Nuclear Material Accountancy (NMA), a key element of Safeguards, requires the Material Balance Area (MBA) of the target facility and performs Material Balance Evaluation (MBE) based on the quantitative evaluation of nuclear materials entering or leaving the MBA. In this study, about 10 factors related to NMA were developed, including MBA, Key Measurement Point (KMP), Uncertainty of a detector, Radiation signatures, and MUF (Material Unaccounted For). For example, one of the factors, MUF is used in MBA to determine diversion through analysis of unquantified nuclear materials and refers to the difference between Book Inventory and Physical Inventory, as well as errors occurring during the process in bulk facilities, errors in measurement, or intentional use of nuclear materials. This occurs in situations such as attempted diversion, and accurate MUF evaluation is essential for solid Safeguards implementation. MUF can be evaluated using the following formula (MUF=(PB+X-Y)-PE). The IAEA’s Safeguards achievement conditions (MUF < SQ) should be met. Considering this, MUF-related factors were developed as follows. (􀜵􀜧􀜯 = 1 − 􀯆􀯎􀮿 􀯌􀯊 ) In this way, about 10 factors were developed and described in the text. This factors is expected to serve as an important factor in evaluating the safeguardability of NMA, and in the future, safeguardability factors related to Containment & Surveillance (C&S) and Design Information Verification (DIV) will be additionally developed to conduct a comprehensive safeguardability evaluation of the target facility. This methodology can significantly enhance safeguardability during the design stage of nuclear facilities.

Nuclear Material Accountancy (NMA) system quantitatively evaluates whether nuclear material is diverted or not. Material balance is evaluated based on nuclear material measurements based on this system and these processes are based on statistical techniques. Therefore, it is possible to evaluate the performance based on modeling and simulation technique from the development stage. In the performance evaluation, several diversion scenarios are established, nuclear material diversion is attempted in a virtual simulation environment according to these scenarios, and the detection probability is evaluated. Therefore, one of the important things is to derive vulnerable diversion scenario in advance. However, in actual facilities, it is not easy to manually derive weak scenario because there are numerous factors that affect detection performance. In this study, reinforcement learning has been applied to automatically derive vulnerable diversion scenarios from virtual NMA system. Reinforcement learning trains agents to take optimal actions in a virtual environment, and based on this, it is possible to develop an agent that attempt to divert nuclear materials according to optimal weak scenario in the NMA system. A somewhat simple NMA system model has been considered to confirm the applicability of reinforcement learning in this study. The simple model performs 10 consecutive material balance evaluations per year and has the characteristic of increasing MUF uncertainty according to balance period. The expected vulnerable diversion scenario is a case where the amount of diverted nuclear material increases in proportion to the size of the MUF uncertainty, and total amount of diverted nuclear material was assumed to be 8 kg, which corresponds to one significant quantity of plutonium. Virtual NMA system model (environment) and a divertor (agent) attempting to divert nuclear material were modeled to apply reinforcement learning. The agent is designed to receive a negative reward if an action attempting to divert is detected by the NMA system. Reinforcement learning automatically trains the agent to receive the maximum reward, and through this, the weakest diversion scenario can be derived. As a result of the study, it was confirmed that the agent was trained to attempt to divert nuclear material in a direction with a low detection probability in this system model. Through these results, it is found that it was possible to sufficiently derive weak scenarios based on reinforcement learning. This technique considered in this study can suggest methods to derive and supplement weak diversion scenarios in NMA system in advance. However, in order to apply this technology smoothly, there are still issues to be solved, and further research will be needed in the future.

축산물 중 잔류허용기준이 설정되어 관리하고 있는 농약 azocyclotin, cyhexatin, fenbutatin oxide는 대표적인 유 기주석계 살비제이다. 기존 시험법은 가스크로마토그래피 를 사용하여 정량한계가 높고 분석 시 재현성이 떨어져 이에 대한 개선이 필요한 실정으로 본 연구에서는 비교적 간편하며 시간이 적게 소요되는 QuEChERS법을 활용하여 azocyclotin, cyhexatin, fenbutatin oxide의 시험법을 마련하 고자 하였다. 1% 아세트산을 함유한 아세트산에틸:아세토 니트릴(1:1) 혼합액을 이용하여 진탕 추출 후 d-SPE로 정 제하고 이를 농축 후 LC-MS/MS를 이용한 시험법을 개발 하였다. Azocyclotin, cyhexatin 및 fenbutatin oxide의 결정 계수(R2)는 0.99 이상으로 높은 직선성을 확인하였으며 정 량한계는 0.01 mg/kg으로 높은 감도를 나타내었다. 대표 축산물 5종(소, 돼지, 닭, 계란, 우유)에서 LOQ(0.01 mg/ kg), MRL(0.05 mg/kg), MRL 10배(0.5 mg/kg)의 농도에서 회수율 실험을 한 결과 평균 회수율이 76.4-115.3% 및 84.4-110.8%이었으며, 상대표준편차는 25.3% 이하로 나타 났다. 본 연구는 Codex 가이드라인(CAC/GL 40-1993, 2003) 및 ‘식품의약품안전처 식품의약품안전평가원의 식 품등 시험법 마련 표준절차에 관한 가이드라인(2016)’에 적합한 수준임을 확인하였다. 따라서 본 연구에서 확립한 시험법은 축산물 중 잔류할 수 있는 azocyclotin, cyhexatin, fenbutatin oxide의 안전관리를 위한 공정시험법으로 활용 가능할 것으로 판단된다.

A machine learning-based algorithms have used for constructing species distribution models (SDMs), but their performances depend on the selection of backgrounds. This study attempted to develop a noble method for selecting backgrounds in machine-learning SDMs. Two machine-learning based SDMs (MaxEnt, and Random Forest) were employed with an example species (Spodoptera litura), and different background selection methods (random sampling, biased sampling, and ensemble sampling by using CLIMEX) were tested with multiple performance metrics (TSS, Kappa, F1-score). As a result, the model with ensemble sampling predicted the widest occurrence areas with the highest performance, suggesting the potential application of the developed method for enhancing a machine-learning SDM.

Benthic attached diatoms (BADs), a major primary producer in lotic stream and river ecosystems are micro-sized organisms and require a highly magnified microscopic technique in the observation work. Thus, it is often not easy to ensure accuracy and precision in both qualitative and quantitative analyses. This study proposed a new technique applicable to improve quality control of aquatic ecosystem monitoring and assessment using BADs. In order to meet the purpose of quality control, we developed a permanent mounting slide technique which can be used for both qualitative and quantitative analyses simultaneously. We designed specimens with the combination of grid on both cover and slide glasses and compared their efficiency. As a result of observation and counting of BADs, the slide glass designed with the color-lined grid showed the highest efficiency compared to other test conditions. We expect that the method developed in this study could be effectively used to analyze BADs and contributed to improve the quality control in aquatic ecosystem health monitoring and assessment.