A plethora of Artificial Intelligence (AI) based methods have been published for adaptive traffic control. However, the demonstration of real-world applications is often overlooked. An effective and widely accepted solution for traffic signalization is the use of Programmable Logic Controllers (PLCs), especially in safety-critical infrastructures. This paper presents a reinforcement learning (RL)-based traffic control system deployed directly on an industrial PLC, representing a fundamentally novel integration of AI in a deterministic control environment. In contrast to prior approaches that focus solely on optimization, our system ensures compliance with strict traffic safety rules by restricting the agent’s action space using a safety constraint matrix. Despite limited computational resources, the system achieved measurable improvements in CO2emissions while maintaining safe and stable runtime behavior. The results confirm that AI-based control is not only feasible but reliable on PLCs when supported by appropriate architectural and safety mechanisms, opening pathways for further industrial AI deployments.

Businesses are increasingly overwhelmed by inquiries related to their services or products. Relying on human agents to handle inquiries via email results in higher costs and delayed responses, contributing to customer dissatisfaction. In response to these challenges, this pilot study leverages advancements in Large Language Models (LLMs) by proposing a fully automated method for generating a knowledge graph from unstructured data in help pages, which is then utilized to power a fully automated dialogue management system. By transitioning to a chat-based approach, our method aims to handle ambiguous, incomplete, or nonspecific inquiries more effectively and enhance customer satisfaction with tailored, natural responses. We also implement explicit safeguards to improve intent identification and prevent response hallucinations. We validate our proposal in the hotel industry, demonstrating that our knowledge graph based AI agent outperforms the baseline Retrieval-Augmented Generation (RAG) model in accuracy while facilitating more natural and coherent dialogues.

We propose a supervised method of extracting event causalities like conduct slash-and-burn agriculture→exacerbate desertification from the web using se-mantic relation (between nouns), context, and association features. Experiments show that our method outperforms base-lines that are based on state-of-the-art methods. We also propose methods of generating future scenarios like conduct slash-and-burn agriculture→exacerbate desertification→increase Asian dust (from China)→asthma gets worse. Experi-ments show that we can generate 50,000 scenarios with 68 % precision. We also generated a scenario deforestation con-tinues→global warming worsens→sea temperatures rise→vibrio parahaemolyti-cus fouls (water), which is written in no document in our input web corpus crawled in 2007. But the vibrio risk due to global warming was observed in Baker-Austin et al. (2013). Thus, we “predicted ” the future event sequence in a sense. 1

The aim of the presented research is to elaborate a traffic-responsive optimal signal split algorithm taking uncertainty into account. The traffic control objective is to minimize the weighted link queue lengths within an urban network area. The control problem is formulated in a centralized rolling-horizon fashion in which unknown but bounded demand and queue uncertainty influences the prediction. An efficient constrained minimax optimization is suggested to obtain the green time combination, which minimizes the objective function when worst case uncertainty appears. As an illustrative example, a simulation study is carried out to demonstrate the effectiveness and computational feasibility of the robust predictive approach. By using real-world traffic data and microscopic traffic simulator, the proposed robust signal split algorithm is analyzed and compared with well-tuned fixed-time signal timing and to nominal predictive solutions under different traffic conditions.