The rapid growth of smart home technologies, driven by the expansion of the Internet of Things (IoT), has introduced both opportunities and challenges in automating daily routines and orchestrating device interactions. Traditional rule-based automation systems often fall short in adapting to dynamic conditions, integrating heterogeneous devices, and responding to evolving user needs. To address these limitations, this study introduces a novel smart home orchestration framework that combines generative Artificial Intelligence (AI), Retrieval-Augmented Generation (RAG), and the modular OSGi framework. The proposed system allows users to express requirements in natural language, which are then interpreted and transformed into executable service bundles by large language models (LLMs) enhanced with contextual knowledge retrieved from vector databases. These AI-generated service bundles are dynamically deployed via OSGi, enabling real-time service adaptation without system downtime. Manufacturer-provided device capabilities are seamlessly integrated into the orchestration pipeline, ensuring compatibility and extensibility. The framework was validated through multiple use-case scenarios involving dynamic device discovery, on-demand code generation, and adaptive orchestration based on user preferences. Results highlight the system’s ability to enhance automation efficiency, personalization, and resilience. This work demonstrates the feasibility and advantages of AI-driven orchestration in realising intelligent, flexible, and scalable smart home environments.
Smart textiles offer promising opportunities to address multiple aspects of relaxation-focused mental health interventions, which include monitoring and therapy. This paper presents a usability evaluation of a cushion-based smart textile system called Amiga, designed to guide users through breathing exercises that could be used in the future to support relaxation-focused interventions intended for independent use. A experimental user study with 20 participants was conducted to assess the system’s effectiveness, user performance, user experience, and overall satisfaction using structured interviews and validated usability questionnaires. The system achieved a mean System Usability Scale (SUS) score of 81.875 with standard deviation ( = 11.8), exceeding the established SUS benchmark of 68 and corresponding to the ‘Excellent’ category rating, under a predefined assistance-free criterion. The system was designed for respiratory phases (Ph) and respiration rate (RR) monitoring through a guided-breathing exercise where 90% completed with only 40% passing the quality criteria, achieving an average pace synchronization accuracy (PSA) of 61.2 % and phase duration accuracy (PDA) of 30% with a tolerance of ±1 s, thus providing a initial baseline for autonomous use and highlighting opportunities to improve on-boarding and in-application guidance. Most participants reported positive feedback regarding their confidence and overall satisfaction. Usability challenges were identified related to physical interaction with the cushion and clarity of on-screen instructions, providing clear directions for future design refinement. These findings demonstrate the feasibility of smart textile-based devices for home-based breathing exercises.