There has been increasing interest in artificial intelligence (AI) in various fields. This phenomenon calls for human resources to be equipped with the knowledge and skills of AI and data. The Korean Ministry of Education has opened up introductory courses in AI to high school students since the second half of 2021. It will also include AI education in the 2022 revised curriculum for elementary, middle, and high school students. Despite these efforts to enhance students’ digital literacy through the innovation of the national curriculum, opportunities for taking advantage of AI and data education should be reached for more diverse learners. At the same time, the courses need to be designed with not only theoretical but practical contents and activities based on learner needs. Under these circumstances, the Science Data Education Center at the Korean Institute of Science and Technology Information (KISTI) has been providing AI and data education programs either online or face-to-face for university members, such as undergraduates, graduates, researchers, and professors. In this study, we aim to present cases of educational programs on AI and data operated by the Science Data Education Center, especially regarding those for the university components. Pertinent implications derived from the results of operating the programs will be discussed.

PURPOSES : This study aimed to predict the number of future COVID-19 confirmed cases more accurately using public and transportation big data and suggested priorities for introducing major policies by region. METHODS : Prediction analysis was performed using a long short-term memory (LSTM) model with excellent prediction accuracy for time-series data. Random forest (RF) classification analysis was used to derive regional priorities and major influencing factors. RESULTS : Based on the daily number of COVID-19 confirmed cases from January 26 to December 12, 2020, as well as the daily number of confirmed cases in Gyeonggi Province, which was expected to occur on December 24 and 25, depending on social distancing, the accuracy of the LSTM artificial neural network was approximately 95.8%. In addition, as a result of deriving the major influencing factors of COVID-19 through random forest classification analysis, according to the number of people, social distancing stages, and masks worn, Bucheon, Yongin, and Pyeongtaek were identified as regions expected to be at high risk in the future. CONCLUSIONS : The results of this study can help predict pandemics such as COVID-19.

PURPOSES : This study defines private and public service providers connected to a public data hub in a smart city and examines the information that should be exchanged between them. The information exchange scheme covers data exchange at a minimum level. METHODS : First, we reviewed the entities participating in the emergency charging service and designed the scope of information linkages between the entities. Second, we diagnosed the main information linkages according to a service flowchart. Third, we reviewed the basic information requirements linked to actors participating in the service. Finally, we derived and presented information linked to the subjects. RESULTS : In addition to the basic requirements, the number of data-exchange information sets specified was four, which was the scope of the aforementioned study. We defined and analyzed an efficient information exchange system between various actors involved in emergency charging services. Data were defined based on interactions between service users, operators, providers, and data hubs. Each set had a different scope and purpose. CONCLUSIONS : Information collected and provided by emergency charging service providers in connection with a data hub that manages urban energy was proposed.

PURPOSES : We propose a framework to evaluate the reliability of integrating homogeneous or heterogeneous mobility data to produce the various data required for greenhouse gas emission estimation. METHODS : The mobility data used in the framework were collected at a fixed time from a specific point and were based on raster data. In general, the traffic volume for all traffic measurement points over 24 h can be considered raster data. In the future, the proposed framework can be applied to specific road points or road sections, depending on the presence or absence of raster data. RESULTS : The activity data required to calculate greenhouse gas emissions were derived from the mobility data analysis. With recent developments in information, communication, and artificial intelligence technologies, mobility data collected from different sources with the same collection purpose can be integrated to increase the reliability and accuracy of previously unknown or inaccurate information. CONCLUSIONS : This study will help assess the reliability of mobility data fusion as it is collected on the road, and will ultimately lead to more accurate estimates of greenhouse gas emissions.

Until now, research on consumers’ purchasing behavior has primarily focused on psychological aspects or depended on consumer surveys. However, there may be a gap between consumers’ self-reported perceptions and their observable actions. In response, this study aimed to investigate consumer purchasing behavior utilizing a big data approach. To this end, this study investigated the purchasing patterns of fashion items, both online and in retail stores, from a data-driven perspective. We also investigated whether individual consumers switched between online websites and retail establishments for making purchases. Data on 516,474 purchases were obtained from fashion companies. We used association rule analysis and K-means clustering to identify purchase patterns that were influenced by customer loyalty. Furthermore, sequential pattern analysis was applied to investigate the usage patterns of online and offline channels by consumers. The results showed that high-loyalty consumers mainly purchased infrequently bought items in the brand line, as well as high-priced items, and that these purchase patterns were similar both online and in stores. In contrast, the low-loyalty group showed different purchasing behaviors for online versus in-store purchases. In physical environments, the low-loyalty consumers tended to purchase less popular or more expensive items from the brand line, whereas in online environments, their purchases centered around items with relatively high sales volumes. Finally, we found that both high and low loyalty groups exclusively used a single preferred channel, either online or in-store. The findings help companies better understand consumer purchase patterns and build future marketing strategies around items with high brand centrality.