The technological maturity of AI solutions has been consistently increasing over the years, expanding its application scope and domains. Smart home systems have evolved to act as proactive assistants for their residents, autonomously detecting behavioral patterns, inferring needs, and making decisions pertaining to the management and control of various home subsystems. The implementation of explainable AI (XAI) solutions in this challenging domain can improve user experience and trust by providing clear and understandable explanations of the system’s behavior. The article discusses the increasing importance of explainable artificial intelligence (XAI) in smart home systems, which are becoming progressively smarter and more accessible to end-users, and presents an agent-based approach for developing explainable Internet of things (IoT) systems and an experiment conducted at the Centre of Real Time Computer Systems at the Kaunas University of Technology. The proposed method was adapted to build an explainable, rule-based smart home system for controlling light, heating, and ventilation. The results of this study serve as a demonstration of the feasibility and effectiveness of the proposed theoretical approach in real-world scenarios.

This paper investigates the feasibility of employing expert knowledge-based Explainable Artificial Intelligence (XAI) for smart house control through low-power Internet of Things (IoT) devices that possess limited computational capabilities. By integrating Explainable AI, we seek to enhance the transparency of the model’s decision-making process, thereby increasing its reliability for the end user. The Arduino Uno board was selected for IoT development because of its extensive popularity and affordability. A model of heating control has been developed using temperature sensors based on the presence of residents in the room. The operational prototype was evaluated by measuring the time taken between data input and decision-making, accompanied by an explanation, to identify any potential bottlenecks that may hinder the performance of the microcontroller. To enhance communication security, we developed a pseudo-random number generation function using chaos-based cryptography with hardware implementation, thus improving communication security without incurring additional computational costs. The method has demonstrated a time efficiency improvement of up to 67% for novice users, 58% for intermediate users, and 50% for expert users.