Conventional fixed-time traffic signal operations at urban intersections are typically based on prescheduled plans that presume stable and recurring traffic patterns, particularly during peak commuting hours. However, recent societal changes—including flexible work schedules, telecommuting, and evolving workweek structures—have introduced greater variability in traffic demand, thereby diminishing the effectiveness of traditional peak-hour-focused control strategies. This study investigated the performance of an AI-based adaptive traffic signal control system that operated independently of predefined time plans. A field demonstration was conducted in Jeju City, South Korea, where the system was deployed in both the cyclic and acyclic operation modes. By leveraging real-time traffic data obtained from AI-enabled video detectors, the system adjusted the signal timings on a per-second basis in response to dynamic traffic conditions. The performance was evaluated against the conventional time-of-day (TOD) control method under diverse traffic scenarios, including typical weekdays, weekends, and local event days. The AI-based system achieved substantial reductions in intersection delays—24.3% on weekdays, 22.2% on weekends, and 17.1% on event days—compared with the TOD baseline. Moreover, it preserved a comparable level of traffic progression (measured by the proportion of non-stop vehicle flows) even during acyclic operations. The greatest efficiency gains were observed during the nighttime and low-traffic periods, underscoring the capacity of the system to minimize unnecessary delays under variable conditions. These results highlighted the potential of AI-based adaptive signal control as a viable alternative to conventional fixed-time operations, offering enhanced responsiveness and operational flexibility in increasingly complex urban traffic environments. Future research will focus on scaling the system to larger networks and developing integrated optimization strategies across multiple intersections.

The operation time of a disposal repository is generally more than one hundred years except for the institutional control phase. The structural integrity of a repository can be regarded as one of the most important research issues from the perspective of a long-term performance assessment, which is closely related to the public acceptance with regard to the nuclear safety. The objective of this study is to suggest the methodology for quantitative evaluation of structural integrity in a nuclear waste repository based on the adaptive artificial intelligence (AI), fractal theory, and acoustic emission (AE) monitoring. Here, adaptive AI means that the advanced AI model trained additionally based on the expert’s decision, engineering & field scale tests, numerical studies etc. in addition to the lab. test. In the process of a methodology development, AE source location, wave attenuation, the maximum AE energy and crack type classification were subsequently studied from the various lab. tests and Mazars damage model. The developed methodology for structural integrity was also applied to engineering scale concrete block (1.3 m × 1.3 m × 1.3 m) by artificial crack generation using a plate jacking method (up to 30 MPa) in KURT (KAERI Underground Research Tunnel). The concrete recipe used in engineering scale test was same as that of Gyeongju low & intermediate level waste repository. From this study, the reliability for AE crack source location, crack type classification, and damage assessment increased and all the processes for the technology development were verified from the Korea Testing Laboratory (KTL) in 2022.

현재 온라인 게임에 있어서 지능적인 AI(Artificial Intelligence) 구현에 대한 많은 연구가 진행이 되고 있다. 그러나 온라인 게임 분야에서는 게임 자원을 제한적으로 사용할 수밖에 없는 한계로 인하여 인간적인 현명한 AI를 적용하기가 쉽지 않다. 본 논문에서 제안하는 Fuzzy Extension 기법을 이용한 AI 기법은 시스템에 적은 부하를 발생시키므로 온라인 게임에 적합하고 그러면서도 좀 더 인간에 가까운 AI 구현이 가능한 기법이다. 이러한 AI 구현을 위해 본 논문에서는 Fuzzy기반의 온라인게임에 적합한 지능적 AI 시스템 설계 기법 및 시스템 구성을 제안하고 이를 바탕으로 제작된 데모를 통하여 실제 적용할 수 있는 방안을 제시한다.