Elon·Musk is a business man who attracts the world’s most attention, not only because of its unusual business mind, advanced challenging consciousness and legendary entrepreneurial experience which made him the world's richest man, but also because he is good at using the trend of social network society (SNS) platform to achieve social interaction. This study uses python 3.11 software to capture and filter Musk's Weibo articles on August 18th, 2023, and makes logical analysis based on the chronological related events, so as to extract Musk’s cognitive characteristics of Chinese social media. This paper finds that Chinese social media builds Musk's image cognition through reporting and judging his career development and hot issues, the cognition varies with the dynamic changes of character events; Chinese social media focuses on fields of Tesla intelligent driving, spaceship and brain neural technology, as well as social media; Weibo articles’ cognitive characteristics of Musk's image are extreme, where the extremely positive proportion accounts for more than 60%, and the extremely negative proportion accounts for more than 10%.

목적: 본 연구는 국내 초고령자를 대상으로 삶의 만족도 및 우울과 라이프스타일신( 체활동, 식습관, 참여빈도, 참여다양성) 간의 상관관계를 확인하고, 삶의 만족도와 우울에 영향을 미치는 라이프스타일 요인을 분석 및 확인하고자 하였다. 연구방법: 본 연구의 독립변수는 라이프스타일 요인으로 신체활동, 규칙적 식습관, 참여빈도, 참여다양성이었으 며, 종속변인은 삶의 만족도와 우울이었다. 분석을 위해 SPSS를 이용해 상관관계분석 및 다중회귀분석을 실시하였다. 결과: 다중회귀분석을 통해 삶의 만족도에 영향을 미치는 요인으로는 참여빈도(t = 6.262, p < 0.001)와 규칙적 식습관(t = 4.627, p < 0.001)이 통계적 유의성을 가지는 것으로 확인되었으며, 우울에 영향을 미치는 요인으로는 참여빈도(t = 6.540, p < 0.001)와 규칙적 식습관(t = 4.061, p < 0.001)이 통계적 유의성을 가지는 것으로 확인되었다. 결론: 본 연구를 통하여 국내 초고령자의 삶의 만족도와 우울에 영향을 주는 라이프스타일 요인을 확인하였다. 따라서 본 연구 결과를 토대로 초고령자의 삶의 만족도와 우울 개선을 위해서는 라이프스타일을 기반으로 하는 다면적 중재 프로그램이 필요하다.

자율주행차 상용화 시대를 가속화하기 위해 실제 도로에서 다양한 실증 프로젝트를 수행중이다. 그러나, 자율주행차와 비자율주행차 가 혼재된 혼합교통류 환경에서 발생할 수 있는 다양한 문제의 원인을 파악하고 선제적인 안전대책을 강구하는 노력은 미비한 실정이 다. 특히, 기존 비자율주행차 측면의 주행안전성을 고려하여 설계된 도로 시설 특성으로 인해 자율주행차의 주행안전성이 저하될 수 있다. 또한 기존 비자율주행차의 주행안전성을 저해함과 동시에 자율주행차의 주행안전성도 저해하는 도로 시설 특성이 존재할 가능 성이 있다. 본 연구에서는 상암 자율주행차 시범운행지구에서 수집된 automated vehicle data (AVD)를 활용하여 자율주행차와 비자율주 행차의 주행안전성을 평가하고 도로 시설 특성 측면의 영향요인을 도출하였다. 주행모드별 주행안전성 평가를 위해 autonomous emergency braking system (AEBS) 위험 이벤트 기반의 driving risk index (DRI)를 개발하였다. 구간별 DRI가 발생하지 않은 구간을 very good으로 정의하고 발생한 구간을 25 percentile로 구분하여 good, moderate, poor, very poor 등급으로 정의하여 총 5개의 등급으로 구분 하였다. 또한, 현장조사을 수행함으로써 구간별 포함되어 있는 도로 시설 특성을 수집하였다. 주행모드별 주행안전성에 영향을 미치는 도로 시설 특성을 도출하기 위해 이항로지스틱 회귀분석을 수행하였다. 종속 변수의 경우 DRI 기반 안전등급 중 poor 이상 등급을 1, 그 외의 등급을 0으로 정의하였으며, 독립변수의 경우 현장조사를 통해 수집된 교차로 유형, 차로 수, 차로 폭, 추가차로 유무, 차량 진행방향, 불법주정차 유무, 버스정류장 유무, 자전거 차로 유무에 대해 명목형 변수로 설정하였다. 도출된 주행모드별 주행안전성 영 향 요인을 검토하고 향후 자율주행차 시대에 대비하여 선제적으로 개선이 요구되는 도로 시설 특성을 도출하고 도로 운영성 및 효율 성, 안전성 측면의 개선 방향을 제시하였다.

교통사고는 인적요인, 도로 기하구조, 교통류, 환경적 요인 등 복합적인 요인에 의해 발생하고 속도는 교통사고와 밀접한 연관성이 있다. 또한, 교통사고는 교통 혼잡도와 관련이 있으며 사고와 실시간 교통상황 간의 상관관계를 통해 사고 발생 개연성을 추정하고 도 로 안전성 분석이 필요하다. 모바일 센서와 통신 기술의 급속한 발전으로 스마트폰 보급률이 증가하였으며 내장된 센서를 기반으로 생성된 차량 주행 데이터 수집이 가능하다. 기술의 발달로 데이터 수집이 쉬워졌음에도 불구하고, 스마트폰을 기반으로 수집된 위험 운전 이벤트를 활용한 도로 위험도 평가에 대한 연구는 부족한 실정이다. 본 연구는 스마트폰 센서 기반의 위험 운전 이벤트 데이터 중 하나인 급감속 위험 운전 이벤트 데이터를 도로 위험도 평가 기법에 활용하는 것을 목적으로 한다. 급감속 위험 운전 이벤트 데이 터는 주행 차량이 3초간 속도를 40km/h 이상 감소하는 위험 이벤트가 발생할 때 시간과 위치를 기록한 자료를 의미한다. 본 연구의 범위는 대한민국 내 인구와 교통량이 많은 지역인 수도권을 대상으로 서울, 경기, 인천을 연결하는 고리 형태의 도로인 수도권제1순환 선을 대상으로 하였다. 먼저, 개별 차량 데이터는 좌표 기반의 내비게이션 데이터로 집계하여 VDS 링크 데이터와 매칭하였다. 다음으 로는 개별 차량의 위험 운전 이벤트 데이터와 차량 검지기의 교통 매개변수를 결합한 새로운 지표를 개발하였다. 또한, 시·공간적 교 통류의 특성을 반영하여 다양한 도로 위험도 평가 방법에 활용하고자 하였다. 마지막으로 위험 운전 지표와 이력 자료를 기반으로 통 계적으로 유의한 안전성능함수를 개발하였으며, 다양한 시간 단위의 집계 수준을 활용하여 도로 구간별 최적의 모형을 제안하였다. 본 연구는 스마트폰 센서를 기반으로 식별한 개별 차량의 위험과 교통류 차원의 위험을 결합하여 새로운 위험 지표를 개발하고 도로 위 험도 평가에 활용한다는 것에 의의가 있다. 결과물은 향후 스마트폰 센서 기반 개별 차량 위험 운전 이벤트 데이터와 교통 조건을 통 합하는 도로 위험도 평가의 기초자료로써 활용될 것으로 기대된다.

This study utilizes social big data to investigate the factors influencing the awareness, attitude, and behavior toward vegan fashion consumption among global and Korean consumers. Social media posts containing the keyword “vegan fashion” were gathered, and meaningful discourse patterns were identified using semantic network analysis and sentiment analysis. The study revealed that diverse factors guide the purchase of vegan fashion products within global consumer groups, while among Korean consumers, the predominant discourse involved the concepts of veganism and ethics, indicating a heightened awareness of vegan fashion. The research then delved into the factors underpinning awareness (comprehension of animal exploitation, environmental concerns, and alternative materials), attitudes (both positive and negative), and behaviors (exploration, rejection, advocacy, purchase decisions, recommendations, utilization, and disposal). Global consumers placed great significance on product-related information, whereas Korean consumers prioritized ethical integrity and reasonable pricing. In addition, environmental issues stemming from synthetic fibers emerged as a significant factor influencing the awareness, attitude, and behavior regarding vegan fashion consumption. Further, this study confirmed the potential presence of cultural disparities influencing overall awareness, attitude, and behavior concerning the acceptance of vegan fashion, and offers insights into vegan fashion marketing strategies tailored to specific cultures, aiming to provide vegan fashion companies and brands with a deeper understanding of their consumer base.

본 연구에서는 빅데이터를 통해 교사의 융합교육역량에 대한 사회적 인식을 살펴봄으로써 교사의 융합 교육역량 증진 방안 마련을 위한 기초자료를 제공하는데 목적이 있었다. 본 연구목적을 달성하기 위해 Textom에서 제공하는 빅데이터를 활용하여 􍾧교사 + 융합교육 + 역량􍾨을 키워드로 rawDATA를 수집하였 다. 수집된 데이터는 1차􌝆2차 정제과정을 마친 데이터들 중 빈도분석 결과를 바탕으로 200개 핵심 키워드 를 선정하였으며, 이를 1-모드 매트릭스 데이터 셋으로 변환하여 키워드 네트워크 분석을 실시하였다. 연 구결과는 다음과 같다: 첫째, 빈도분석에서는 교육, 인공지능, 강화, 연수, 수업이 가장 빈번하게 출현하는 것으로 나타났다. 둘째, 전체 네트워크 분석에서는 교육, 학생, 연수, 강화, 대상이 모든 중심성에서 높게 나타났다. 셋째, 에고 네트워크 분석에서는 교사, 융합교육, 역량을 중심으로 다양하게 논의되고 있음을 확 인할 수 있었다. 이러한 결과를 바탕으로 교사의 융합교육역량과 관련된 후속연구 및 증진방안에 대해 제 언하였다.

Truck no-show behavior has posed significant disruptions to the planning and execution of port operations. By delving into the key factors that contribute to truck appointment no-shows and proactively predicting such behavior, it becomes possible to make preemptive adjustments to port operation plans, thereby enhancing overall operational efficiency. Considering the data imbalance and the impact of accuracy for each decision tree on the performance of the random forest model, a model based on the Borderline Synthetic Minority Over-Sampling Technique and Weighted Random Forest (BSMOTE-WRF) is proposed to predict truck appointment no-shows and explore the relationship between truck appointment no-shows and factors such as weather conditions, appointment time slot, the number of truck appointments, and traffic conditions. In order to illustrate the effectiveness of the proposed model, the experiments were conducted with the available dataset from the Tianjin Port Second Container Terminal. It is demonstrated that the prediction accuracy of BSMOTE-WRF model is improved by 4%-5% compared with logistic regression, random forest, and support vector machines. Importance ranking of factors affecting truck no-show indicate that (1) The number of truck appointments during specific time slots have the highest impact on truck no-show behavior, and the congestion coefficient has the secondhighest impact on truck no-show behavior and its influence is also significant; (2) Compared to the number of truck appointments and congestion coefficient, the impact of severe weather on truck no-show behavior is relatively low, but it still has some influence; (3) Although the impact of appointment time slots is lower than other influencing factors, the influence of specific time slots on truck no-show behavior should not be overlooked. The BSMOTE-WRF model effectively analyzes the influencing factors and predicts truck no-show behavior in appointment-based systems.

In this study, we propose a novel approach to analyze big data related to patents in the field of smart factories, utilizing the Latent Dirichlet Allocation (LDA) topic modeling method and the generative artificial intelligence technology, ChatGPT. Our method includes extracting valuable insights from a large data-set of associated patents using LDA to identify latent topics and their corresponding patent documents. Additionally, we validate the suitability of the topics generated using generative AI technology and review the results with domain experts. We also employ the powerful big data analysis tool, KNIME, to preprocess and visualize the patent data, facilitating a better understanding of the global patent landscape and enabling a comparative analysis with the domestic patent environment. In order to explore quantitative and qualitative comparative advantages at this juncture, we have selected six indicators for conducting a quantitative analysis. Consequently, our approach allows us to explore the distinctive characteristics and investment directions of individual countries in the context of research and development and commercialization, based on a global-scale patent analysis in the field of smart factories. We anticipate that our findings, based on the analysis of global patent data in the field of smart factories, will serve as vital guidance for determining individual countries' directions in research and development investment. Furthermore, we propose a novel utilization of GhatGPT as a tool for validating the suitability of selected topics for policy makers who must choose topics across various scientific and technological domains.

This study was conducted to investigate whether there were differences in eco-friendly food, home meal replacement (HMR) purchases, and eating-out behavior according to the level of agri-food consumer competence. The data for the study were extracted from main food consumers (n=3,321) in the 2022 Food Consumption Behavior Survey. The competence index was divided into awareness-attitude-practice items, and three groups were classified by competence level. The results showed an agri-food consumer competency score of 70.62, with the highest score for awareness (73.96), followed by practice (69.28) and attitude (66.18). The frequency of purchasing eco-friendly food was higher in the excellent group compared to other groups, and quality and price satisfaction was higher with higher competency (p<0.001). Regarding HMR, the results showed that the shortage group had the lowest HMR consumption rate, and satisfaction decreased as competence decreased (p<0.001). The main reason for eating-out was to enjoy food in all groups (59.0%), followed by a lack of cooking time in the excellent group (15.7%) and hassle with food preparation in the moderate and shortage groups (17.3%, 16.6%) (p<0.001). In short, agri-food consumption competency showed differences by contents and components, and differences in food purchases and eating-out behavior by competency level were found.

The genus Desmodesmus (Chodat) S.S. An, T. Friedl & E. Hegewald is ubiquitous in freshwater ecosystems, such as rivers, ponds, and wetlands. The actual species diversity and distribution of the genus is unknown because of morphological plasticity affected by habitats. Currently, 38 Desmodesmus species have been reported in Korea most of which transferred from the genus Scenedesmus recently, however, no phylogenetic relationships have been studied yet. Despite the challenges in analyzing relationships among Desmodesmus species through the morphology, ecology, and original description, this study focused on examining species-level relationships using the FBCC culture strains isolated from Korea. A total of 299 sequences (66 of 18S rRNA, 47 of atpB, 67 of petA, 52 of rbcL, and 67 of tufA) were newly determined and used for phylogenetic analysis. Four plastid genes tend to have higher variation than 18S rRNA in the variable sites and P-distance. From the combined phylogeny, the Desmodesmus included six clades such as Clade-1: D. pseudoserratus and D. serratus, Clade-2: D. communis, D. dispar, D. maximus, D. pannonicus, unidentified Desmodesmus sp., Clade-3: D. bicaudatus and D. intermedius, Clade-4: D. microspina, D. multivariablis, D. pleiomorphus, D. subspicatus, Clade-5: D. abundans, D. kissii, and D. spinosus, and Clade-6: D. armatus, D. armatus var. longispina, D. opoliensis, unidentified Desmodesmus spp. The new sequence data from FBCC strains will be used to identify species and study the molecular ecology of scenedesmacean green algae in freshwater ecosystems. The phylogenetic information from this study will expand our understanding of Desmodesmus species diversity in Korea.

PURPOSES : This study aims to perform a quantitative analysis of Forward Collision Warning and crash frequency using heavy vehicle driving data collected in expressway driving environments, and to classify the driving environments where Forward Collision Warnings of heavy vehicles occur for accident-prone areas and analyze their occurrence characteristics. METHODS : A bivariate Gaussian mixture model based on inter-vehicle distance gap and speed-acceleration parameters is used to classify the environment in which Forward Collision Warning occurs for heavy vehicles driving on expressways. For this analysis, Probe Vehicle Data of 80 large trucks collected by C-ITS devices of Korea Expressway Corporation from May to June 2022. Combined with accident information from the past five years, a detailed analysis of the classified driving environments is conducted. RESULTS : The results of the clustering analysis categorizes Forward Collision Warning environments into three groups: Group I (highdensity, high-speed), Group II (high-density, low-speed), and Group III (low-density, high-speed). It reveals a positive correlation between Forward Collision Warning frequency and accident rates at these points, with Group I prevailing. Road characteristics at sites with different accident incidences showed that on-ramps and toll gates had high occurrences of both accidents and warnings. Furthermore, acceleration deviation at high-accident sites was significant across all groups, with variable speed deviations noted for each warning group. CONCLUSIONS : The Forward Collision Warning of heavy vehicles on expressways is classified into three types depending on the driving environment, and the results of these environmental classifications can be used as a basis for building a road environment that reduces the risk of crashes for heavy vehicles.

2015년부터 2022년도까지 6개목(딱정벌레목, 노린재목, 나비목, 벌목, 파리목, 총채벌레목) 곤충들에 대해서 식물검역현장 검출실적과 국내 보고된 미기록종을 분석하였다. 해당기간 동안 국경검역에서 6개목 곤충은 총 45,084건이 검출되었다. 같은 기간 국내에서는 총 545종이 미기록종 으로 보고되었으며, 이중 9종은 국경검역에서도 검출된 것으로 확인되었다. 검역현장에서는 딱정벌레목, 총채벌레목, 노린재목이 높은 검출률을 보 였으며, 국내 미기록종 중에서는 벌목이 176종으로 가장 많이 보고되었다. 본 연구를 통해 침입압력(국경검역 검출)과 실제 침입(국내 미기록종 발 견) 사이에 비동시성이 확인되었다. 향후 보다 장기적인 분석이 필요할 뿐만 아니라 지속적인 식물검역시스템 개선이 필요할 것으로 판단된다.

Physical protection education was legislated by the Ministry of Education, Science and Technology (MEST) in November 2010. KINAC (Korea Institute of Nuclear Nonproliferation and Control) was designated as the exclusive institution for physical protection education and training by MEST in October 2011, and it has since functioned as the sole institution responsible for this critical aspect of nuclear security education in the country. Over the past decade, KINAC has undertaken a variety of training initiatives aimed at enhancing the capabilities of nuclear operators’ physical protection personnel. Furthermore, it has consistently pursued annual curriculum revisions based on insights gleaned from surveys and workshops. In conventional curriculum assessments, general surveys often rely on Likert scale or short-answer questions as primary indicators, mainly due to their ease of data processing. Descriptive questions, while capable of capturing diverse opinions, have historically been relegated to a secondary role owing to the inherent challenges associated with data analysis. While physical protection education has made concerted efforts to solicit diverse opinions through descriptive questions, difficulties in organizing and leveraging this valuable data have resulted in it primarily serving as reference material. This study introduces a novel approach by employing ChatGPT, a chatbot, to conduct a comprehensive analysis of the descriptive questions from the physical protection education survey administered in the first half of 2023. The primary objective is to formulate a robust plan for curriculum enhancement based on a wide spectrum of opinions. Following the completion of physical protection training by 2,014 individuals in the first half of 2023, a survey was distributed, yielding an impressive response rate of 95.7% with 1,927 respondents. Chatbots were harnessed to extract major keywords and perform frequency analyses on approximately 360 responses to descriptive questions in the survey. The analysis revealed that certain keywords emerged with notable frequency, in the following order: “drone” (mentioned 51 times), “access management” (mentioned 28 times), “inspection and search” (mentioned 27 times), and “cybersecurity” (mentioned 20 times). Further analysis of these major keywords and related content revealed a consensus among trainees that there is a pressing need to incorporate topics addressing drone threats and responses, as well as strategies to fortify access management into the curriculum. This study underscores the potential to harness standardized data analysis techniques to synthesize and integrate trainees’ subjective opinions, thereby providing a solid foundation for the refinement of the curriculum.

Spent nuclear fuel continues to be generated domestically and abroad, and various studies are actively being conducted for interim dry storage and disposal of spent nuclear fuel. The characteristics vary depending on the type of spent nuclear fuel and the initial specifications, and based on these characteristics, it is essential to estimate the burnup and enrichment of spent nuclear fuel as a nondestructive assay. In particular, it is important to estimate the characteristics of spent nuclear fuel with non-destructive tests because destructive tests cannot be performed on all encapsulated spent nuclear fuel in case of intrusion traces in safeguards. Data is made by measuring spent nuclear fuel directly to evaluate burnup of spent nuclear fuel, but computer simulation research is also important to understand its characteristics because past burnup history is not accurately written, and destructive testing is difficult. In Sweden, the dependency of the burnup history in source strength and mass of light-water reactor-type spent nuclear fuel was evaluated, and this part was also applied to MAGNOX in consideration of the possibility of being used to verify DPRK’s denuclearization. SCALE 6.2 TRITON modeling was performed based on public information on DPRK’s 5 MWe Yongbyon reactor, and the source strength of Nb-95, Zr-95, Ru-106, Cs-134, Cs-137, Ce-141, Ce- 144, Eu-154 nuclides were evaluated. Since the burnup of MAGNOX is lower than that of lightwater reactors, major nuclides in decay heat were not considered. The cooling period was evaluated based on 0, 5, 10, and 20 years. In case the discharge timing was different, the total period of discharge and reloading was the same, and the end-cycle burnup was the same, calculations showed that the source strength emitted from major nuclides was evaluated within 2-3% except for Ru-106 and Ce-144 nuclides. Even the burnup step of nuclear fuel is the same, and the reloaded length after discharge is different, i.e., the cooling period between is different at 5, 10, and 20, the source strength of Nb-95, Zr-95, Ce-144, and Cs-137 was evaluated as an error of 1%. Except for Ru-106 and Ce-144, nuclides are highly dependent on burnup. Compared to the case of light-water reactors, the possibility of a decrease in error needs to be considered later because the specific power is low. As a result, radionuclides in released fuel depend on the effects of burnup, discharged and reloaded period, and a cooling period after release, and research is needed to correct the cooling period within the future burnup history. In addition, in this study, it is necessary to select a scenario -based burnup because the standard burnup due to the statistical treatment of discharged fuels was not considered as conducted in previous studies.

This study analyzes consumer fashion purchase patterns from a big data perspective. Transaction data from 1 million transactions at two Korean fashion brands were collected. To analyze the data, R, Python, the SPADE algorithm, and network analysis were used. Various consumer purchase patterns, including overall purchase patterns, seasonal purchase patterns, and age-specific purchase patterns, were analyzed. Overall pattern analysis found that a continuous purchase pattern was formed around the brands’ popular items such as t-shirts and blouses. Network analysis also showed that t-shirts and blouses were highly centralized items. This suggests that there are items that make consumers loyal to a brand rather than the cachet of the brand name itself. These results help us better understand the process of brand equity construction. Additionally, buying patterns varied by season, and more items were purchased in a single shopping trip during the spring season compared to other seasons. Consumer age also affected purchase patterns; findings showed an increase in purchasing the same item repeatedly as age increased. This likely reflects the difference in purchasing power according to age, and it suggests that the decision-making process for purchasing products simplifies as age increases. These findings offer insight for fashion companies’ establishment of item-specific marketing strategies.

국내 소비자들의 식품 영양성분에 대한 관심이 계속적 으로 증가하고 있지만 영양성분과 관련된 식품의 소비자 선호도 분석 연구는 부족한 실정이다. 본 연구는 대국민 정보 서비스인 식품영양성분 데이터베이스 플랫폼에 수집 된 빅데이터의 로그분석을 수행하여 소비자들이 영양학적 측면에서 관심을 가지는 식품에 대한 선호도 결과를 제시 하였다. 수집 기간은 2020년 1월부터 2022년 12월까지의 3개년으로 설정하여 총 2,243,168건의 식품명 검색어가 수 집되었으며, 식품명을 병합하여 품목대표 식품명으로 가 공하였다. 분석도구는 R프로그램을 이용하였으며, 영양정 보를 확인하고자 하는 식품명의 검색 빈도를 전체 기간 및 계절별로 분석하였다. 전체 기간 동안 빈도수 분석 결 과, 한국인이 일반적으로 자주 섭취하는 쌀밥, 닭고기, 달 걀의 빈도수가 가장 높았다. 계절성에 따른 선호도 분석 결과, 봄과 여름에는 대체적으로 국물이 없고 뜨겁지 않 은 음식의 빈도수가 높았으며, 가을과 겨울에는 국물이 있 고 따뜻한 음식의 빈도수가 높았다. 또한, 외식업체에서 계절식품으로 판매하는 냉면, 콩국수 등과 같은 식품의 빈 도수도 계절성을 가지는 것으로 확인되었다. 이러한 결과 는 소비자들이 일반적으로 자주 섭취하는 식품의 영양정 보에 관심을 가지는 패턴을 확인할 수 있었으며, 소비 트 렌드와 간접적인 연관성을 가진다는 점에서 외식업계에서 계절별 마케팅 전략 수립 시 기초 자료로 활용될 수 있을 것으로 기대된다.

PURPOSES : Traffic volume, an important basic data in the field of road traffic, is collected from traffic survey equipment installed at certain locations, which sometimes results in missing traffic volume data and abnormal detection. Therefore, this study presents various missing correction techniques using traffic characteristic analysis to obtain accurate traffic volume statistics. METHODS : The fundamental premise behind the development of a traffic volume correction and prediction model is to set the corrected data as the reference value, and the traffic volume correction and prediction process for the outliers and missing values in the raw data were performed based on the set values. RESULTS : The simulation results confirmed that the algorithm combining seasonal composition, quantile AD, and aggregation techniques showed a detection performance of more than 91% compared with actual values. CONCLUSIONS : Raw data collected due to difficulties faced by traffic survey equipment will result in missing traffic volume data and abnormal detection. If these abnormal data are used without appropriate corrections, it is difficult to accurately predict traffic demand. Therefore, it is necessary to improve the accuracy of demand prediction through characteristic analysis and the correction of missing data or outliers in the traffic data.