Model of an intelligent smart home system based on ambient intelligence and user profiling

With the development of science and technology, people's demands for life are getting higher and higher, smart home has become the new theme of the times. Smart home more and more people to become a necessary way to pursue a comfortable life. When the smart home gateway to the family in a variety of home appliances through the home bus technology together, it constitutes a powerful, highly intelligent modern smart home system. This paper mainly introduces the wisdom of home, and its related concepts and core technology, as well as from domestic and foreign market situation and the application of electronic technology in intelligent home.

The growing digital transformation creates new ways of living. In recent years, intelligent smart homes (SHs) have increased rapidly. The article gives a status quo overview of the SH literature with regard to the interactions between SHs and their end-users and structures the literature into three categories (SH systems, SH application areas, and SH end-users) and 15 corresponding concepts. The analysis implies that SH is a broad and relevant research topic with different subjects, research gaps, and emerging benefits but also with challenges for all the players in the SH market. SH success depends on many critical success factors (CSF), such as acceptance of usability or interface design. Implications for research and practice to meet these challenges are presented. Several future research directions are suggested.

The rapid advancement of Internet of Things and artificial intelligence technologies has driven significant growth in the demand for smart home products, with household penetration projected to increase from 77.6% in 2025 to 92.5% in 2029. Despite this growth, much of the existing research adopts a technology-push approach, focusing primarily on user adoption and acceptance from the perspective of technology providers rather than addressing the evolving needs and experiences of users. This study seeks to bridge this gap by conducting a comprehensive review of 20 years of smart home literature (2000-2023) using bibliometric and thematic analysis. The objective is to align future research with user needs and market trends by examining technology, user behavior, and service perspectives to inform academic and industry developments. The analysis was carried out in four steps: (1) collecting 5981 abstracts from the Web of Science database (from 2000 to the first half of 2023), (2) preprocessing and refining the data, (3) applying topic modeling to 1003 selected papers, and (4) combining bibliometric network analysis with qualitative, in-depth interpretation. This study identified 110 key topics across 4 distinct periods, providing insights into 2 decades of advancements in technology, applications, and user-centered research. The findings illustrate the progression of smart home technologies from wireless networks to Internet of Things and artificial intelligence, the expansion of services from basic monitoring to applications such as energy management and health care, and a shift in user profiles from early adopters to underserved populations. The study highlights the limitations of the technology-push approach and underscores the importance of understanding diverse user groups and improving user experiences. It also emphasizes the potential of ambient intelligence environments to intuitively adapt to the health and lifestyle needs of all residents, simplifying and enriching daily life. This research delivers valuable academic and practical insights into the evolution of the smart home domain, showcasing a shift from technology-push strategies to user-centered approaches. By prioritizing user satisfaction and quality of life-especially in health care-the findings open new commercial opportunities and pave the way for innovative, real-world smart home solutions tailored to contemporary user needs.

Recent advances in the Internet of things (IoT) have led to renewed interests in the integration of wireless sensors, ubiquitous connectivity, and ambient intelligence technologies for developing contextually intelligent smart homes for the elderly. While tremendous results have emerged out of these efforts, the question of how to support the elderly to interact meaningfully and intuitively with intelligent devices in an IoT-enabled smart home environment remains underexplored. The different shades of physical and cognitive impairments that come with aging mean that the elderly require a uniquely different personalization approach for engaging with digital technologies. As a result, designing effective models of interaction for smart home applications for the elderly is a challenging task and will require approaches that are based on clearly defined models of context and system software architecture, as well as a systematic application of user-centered design principles. This chapter proposes a cognitive middleware for managing an elderly person’s interaction with intelligent devices in a smart home. A key contribution of the chapter is the introduction of a cognitive mechanism – that learns the habits, lifestyles, and preferences of an elderly person – into the traditional middleware. It provides a homogeneous interface involving interactive context management capabilities for adapting application behaviors to the changing environments and interaction requirements of an elderly person in a smart home.

With the rapid development of Internet of Things and mobile communication technology, smart home emerges as the times require and is widely loved by the public. Based on FPGA programmable chip, this paper designs a intelligent home system which runs on the embedded system based on FPGA. The system can be programmed on the spot according to needs, and use FPGA to realize, complete a series of operations such as data verification, analysis and processing, and then transmit to the terminal equipment to check the field information through the interface. In addition, the system can execute multiple tasks at the same time, greatly saving the task execution time and enhancing the user experience.

In recent years much research and development effort has been directed towards the broad field of ambient intelligence (AmI), and this trend is set to continue for the foreseeable future. AmI aims at seamlessly integrating services within smart infrastructures to be used at home, at work, in the car, on the move, and generally in most environments inhabited by people. It is a relatively new paradigm rooted in ubiquitous computing, which calls for the integration and convergence of multiple disciplines, such as sensor networks, portable devices, intelligent systems, human-computer and social interactions, as well as many techniques within artificial intelligence, such as planning, contextual reasoning, speech recognition, language translation, learning, adaptability, and temporal and hypothetical reasoning. The term AmI was coined by the European Commission, when in 2001 one of its Programme Advisory Groups launched the AmI challenge (Ducatel et al., 2001), later updated in 2003 (Ducatel et al., 2003). But although the term AmI originated from Europe, the goals of the work have been adopted worldwide, see for example (The Aware Home, 2007), (The Oxygen Project, 2007), and (The Sony Interaction Lab, 2007). The foundations of AmI infrastructures are based on the impressive progress we are witnessing in wireless technologies, sensor networks, display capabilities, processing speeds and mobile services. These developments help provide much useful (row) information for AmI applications. Further progress is needed in taking full advantage of such information in order to provide the degree of intelligence, flexibility and naturalness envisaged. This is where artificial intelligence and multi-agent techniques have important roles to play. In this paper we will review the progress that has been made in intelligent systems, discuss the role of artificial intelligence and agent technologies and focus on the application of AmI for independent living.

A complete intelligent voice-controlled home system should include voice capture, voice recognition, authentication, voice result processing, and other processes. Based on the intelligent voice interaction model of Raspberry Pi 3b+ and Alibaba Cloud platform, this paper realized a high recognition accurate, stable, and efficient intelligent voice-controlled home system. We used the Raspberry Pi to control the hardware interface, collected voice data through an external microphone, and performed command control with external sensors and controllable devices in the hardware part; The software was based on Alibaba Cloud intelligent voice interaction platform to realize voice data recognition. The system constructed can achieve the expected function after repeatedly testing the controlled device. The test results show that the recognition accuracy and recognition efficiency of the system's voice control instructions are both high in a relatively quiet environment.

One of the critical situations facing the society across the globe is the problem of elderly homecare services (EHS) due to the aggravation of the society coupled with diseases and limited social resources. This problem has been typically dealt with by manual assistance from caregivers and/or family members. The emerging Ambience Intelligence (AmI) technology suggests itself to be of great potential for EHS applications, owing to its strength in constructing a pervasive computing environment that is sensitive and responsive to the presence of human users. The key challenge of AmI implementation lies in context awareness, namely how to align with the specific decision making scenarios of particular EHS applications. This paper proposes a context-aware information model in a smart home to tackle the EHS problem. Mainly, rough set theory is applied to construct user activity models for recognizing various activities of daily living (ADLs) based on the sensor platform constructed in a smart home environment. Subsequently, issues of case comprehension and homecare services are also discussed. A case study in the smart home environment is presented. Initial findings from the case study suggest the importance of the research problem, as well as the feasibility and potential of the proposed framework.

Solutions from information and communication technology (ICT) can contribute to the better care of chronic patients and the elderly. Personal health systems (PHS) are designed for remote health monitoring of home-residing patients (especially chronic patients), while intelligent living environments facilitate everyday tasks for the sick and disabled prolonging their independence and reducing the pressure on health institutions and nursing homes.The widespread prevalence of chronic diseases and the market potential of both PHS and intelligent homes indicate a potential user group for both types of systems. We believe that a tighter integration of the two types of systems could have beneficial results from both the technical implementation and cost of service, as well as from improved usability due to the lower number of different user devices and interfaces.Three of our pilot projects have integrated PHS in intelligent home systems. In the case of the IRIS Smart Home, we developed a system for monitoring blood pressure and integrated it into an existing solution for home environment control. We continued the work with the IDT project where we developed a comprehensive intelligent home solution designed for providing services within an operator's environment. ‘Moje zdravje’ (My health) was the third pilot project; here, we integrated health services into a next-generation TV user interface.The results of the pilot projects support the logic behind the suggested systems integration. The main benefits are the more effective technical implementation, improved usability, and lower cost of service. Further challenges lie in forming appropriate business models, creating adequate links to the health care information system, and proper inclusion of medical staff in the telehealth services.

Home automation is undergoing a paradigm shift from connected IoT environments with rule based control to intelligent homes exhibiting ambient intelligence and proactive adaptation. Artificial intelligence, privacy-preserving sensing, and converging connectivity standards are the primary forces driving this transition. This systematic literature review synthesizes the technological foundations, architectural developments, emerging paradigms, and socio-technical challenges characterizing the next generation of smart homes, evaluated against the original Ambient Intelligence (AmI) vision. Following PRISMA 2020 guidelines, searches were conducted across four databases—IEEE Xplore, ACM Digital Library, Scopus, and Web of Science—covering studies published between January 2020 and June 2025. From 3450 records, 113 studies were selected through a two-reviewer screening procedure with inter-rater reliability assessments. Quality was assessed using a modified JBI Critical Appraisal Checklist, and findings were synthesized through thematic analysis. Three converging technological pillars were identified: multi-modal privacy-preserving sensing including mmWave radar; a hierarchical cloud-edge TinyML intelligence engine; and unified connectivity through the Matter/Thread standard. Emerging paradigms include LLM-based cognitive orchestration, hyper-personalization, Digital Twin simulation, and grid-interactive prosumer energy management. Realizing that the intelligent home vision requires addressing the privacy–security–trust trilemma, algorithmic bias, system reliability, and human–agent collaboration, a research roadmap encompassing explainable AI, privacy-by-design, lifelong learning, and standardized ethical auditing is proposed.

Intelligent home products have serious information security risks, threatening the privacy of users. In this paper, a method of password protection using hyper-chaos based one-way hash function and secure information transmission method based on spatiotemporal chaos are proposed. The proposed method creates a unidirectional hash function using the delay induced hyper-chaotic system and the key stream iteration to protect user password and to realize user authentication. At the same time, the chaotic time series generated by the one way coupled map lattice system is used to encrypt the plaintext information for the data secure communication, which increases the security of the intelligent home system. An intelligent home system prototype is built based on a Zigbee network, cloud server, and Android system.

The design and realization of Ambient Intelligence (AmI) systems using Artificially Intelligent (AI) agents is a rising field of research. However, the absence of clearly defined working criteria, supporting the generation and evaluation of AmI agent system designs, is a conspicuous obstacle to their advancement. The contribution of this paper is that we determine and test a framework for the generation and evaluation of AmI system designs, based on user experience and business criteria. Specifically, the process of designing a personal lighting AI agent, in collaboration with a leading lighting design company, is used as a case study to determine and test a framework for the generation and evaluation of AmI system designs based on feasibility and acceptability. First, we use storytelling videos to describe and communicate the user values and design scenarios to the stakeholders. Second, we generate design proposals for a lighting AmI agent based on five distinct systemic factors, namely: (a) the context of interaction; (b) the required system data; (c) the required sensing input; (d) the required user input; and (e) the desired system output. Finally third we determine an evaluation framework that is based on three distinct levels of in-built system intelligence, from lower to higher. The three levels reflect the feasibility and acceptability of the system. Feasibility is what a specific company is capable of producing, and in what timeframe. Acceptability is the potential of familiarity and trust that the users can feel while interacting with the AI agent.

The terms smart homes, intelligent homes, home networking have been used for more than a decade to introduce the concept of networking devices and equipment in the house. According to the Smart Homes Foundation the best definition of smart home technology is the integration of technology and services through home networking for a better quality of living. If simple plug-and- play tools for controlling lights are included (e.g. X10 tools) or the computer network in houses are accounted for as smart home technology, hundred thousands of homes all over the world may be called smart homes as well. Only recently, some dozens of projects with smart technology in the houses of older people have been realised or started. The aim of introducing smart technology in these houses is the wish of the tenants to stay independent in their own house as long as possible. Applications are focussed on safety and security, care and comfort. In this presentation an overview will be given of the detailed applications in both new built houses and renovation projects. A summary of the first findings of experiences and reactions of older tenants will be included. Key factors in the further technical development of smart homes are the proper electrotechnical infrastructure, flexible solutions in infrastructure and applications because of shifting needs and wishes, acceptable user interfaces, and costs. Even more important for acceptance and breakthrough will be the content and services that can be delivered to the home. A wide range of companies is developing business models to serve the end consumer. Reference will be made to The Smartest House of the Netherlands, a new demonstration house of the Smart Homes Foundation, where both consumers and companies give feedback on the current market developments. The Internet and mobile telephony have been keen drivers to stimulate the interest of technology in the household. But also several economic and socio-cultural factors will cause changes in society in which smart home technology will really break through. The ageing western societies and the clearly expressed needs of older people have raised particular awareness of the several parties in the building process for the opportunities of smart home technology. Finally, based on expected product launches and technical developments at major international companies, as well as based on the feedback of older people currently living in smart homes, some expectations for the near future will be given.

An intelligent home system controlled via GSM, GPRS and the Internet was developed to investigate the control system of intelligent home. The home environment including concentration of carbon dioxide, UV intensity, light intensity, smoke concentration, temperature and humidity were real-time transmitted to the host computer monitoring platform. The intelligent home system supports four different control methods with the remote control functions of household appliances, security locks of doors, lighting system and smart curtains realized through a variety of network.

With the rapid growth of smart home IoT devices, users are increasingly exposed to various security risks, as evident from recent studies. While seeking answers to know more on those security concerns, users are mostly left with their own discretion while going through various sources, such as online blogs, and technical manuals; which may render higher complexity to the regular users to extract the necessary information from. This requirement does not go along with the common mindsets of smart home users and hence threatens the security of smart homes furthermore. In this paper, we aim to identify and address the major user-level security concerns in smart homes. Specifically, we develop a novel dataset of Q&A from public forums, capturing practical security challenges faced by smart home users. We extract major security concerns in smart homes from our dataset by leveraging the Latent Dirichlet Allocation (LDA). We fine-tune relatively “smaller” transformer models, such as T5 and Flan-T5, on this dataset to build a QA system tailored for smart home security. Unlike larger models like GPT and Gemini, which are powerful but often resource hungry, and requiring data sharing, smaller models are more feasible for deployment in resource-constrained or privacy-sensitive environments, like smart homes. The dataset is manually curated and supplemented with synthetic data to explore its potential impact on model performance. This approach significantly improves the system’s ability to deliver accurate and relevant answers, helping users address common security concerns with smart home IoT devices. Our experiments on real-world user concerns show that our work improves the performance of the base models.