A Survey of User-Centred Approaches for Smart Home Transfer Learning and New User Home Automation Adaptation

Recent smart home applications enhance the quality of people’s home experiences by detecting their daily activities and providing them services that make their daily life more comfortable and safe. Human activity recognition is one of the fundamental tasks that a smart home should accomplish. However, there are still several challenges for such recognition in smart homes, with the target home adaptation process being one of the most critical, since new home environments do not have sufficient data to initiate the necessary activity recognition process. The transfer learning approach is considered the solution to this challenge, due to its ability to improve the adaptation process. This paper endeavours to provide a concrete review of user-centred smart homes along with the recent advancements in transfer learning for activity recognition. Furthermore, the paper proposes an integrated, personalised system that is able to create a dataset for target homes using both survey and transfer learning approaches, providing a personalised dataset based on user preferences and feedback.     

一种基于智能家居的用户行为预测方法

随着移动通信技术、物联网技术和传感器技术等的快速发展,智能家居行业发展迅速。由于人们生活水平的提高,对智能家居可以提供的智能服务需求正在增加。然而,现有的智能家居系统只能根据预设的控制方法和规则简单地重复运行,并且根据用户的日常生活习惯,不能随时提供满足其个性化需求的服务。试图为智能家居提供个性化服务,使智能家居的服务能够更加灵活、智能和人性化,报告了智能家居和关联规则挖掘的研究现状,对提高Apriori算法的效率进行了研究,设计了原型系统中的数据采集和预处理,网关以及行为识别和预测3个功能模块的总体实现方案。实验结果表明,采用关联规则数据挖掘的方法可以预测智能家居环境下用户未来的行为,同时基于散列技术的Apriori算法提高了智能家居下用户行为预测过程中的效率。     

An efficient steganographic approach for protecting communication in the Internet of Things (IoT) critical infrastructures

ABSTRACT

With the manifestation of the Internet of Things (IoT) and fog computing, the quantity of edge devices is escalating exponentially all over the world, providing better services to the end user with the help of existing and upcoming communication infrastructures. All of these devices are producing and communicating a huge amount of data and control information around this open IoT environment. A large amount of this information contains personal and important information for the user as well as for the organization. The number of attack vectors for malicious users is high due to the openness, distributed nature, and lack of control over the whole IoT environment. For building the IoT as an effective service platform, end users need to trust the system. For this reason, security and privacy of information in the IoT is a great concern in critical infrastructures such as the smart home, smart city, smart healthcare, smart industry, etc. In this article, we propose three information hiding techniques for protecting communication in critical IoT infrastructure with the help of steganography, where RGB images are used as carriers for the information. We hide the information in the deeper layer of the image channels with minimum distortion in the least significant bit (lsb) to be used as indication of data. We analyze our technique both mathematically and experimentally. Mathematically, we show that the adversary cannot predict the actual information by analysis. The proposed approach achieved better imperceptibility and capacity than the various existing techniques along with better resistance to steganalysis attacks such as histogram analysis and RS analysis, as proven experimentally.     

A user-centric approach to dynamic adaptation of reusable communication services

The pervasiveness of electronic devices coupled with increasing resources within these devices has aided the explosion of available software services. While reusable software services have become more accessible and the cost of using these services has become cheaper, the increased number of services and access methods also increases the complexity for the user of these services, demanding too much attention from the user. On the other hand, automation can alleviate some of the complexity issues but at the expense of user control. We propose a balance between smart reusable integration, automation and user controllability, through a dynamically adaptive user-centric approach that utilizes goal-oriented intent modeling. This work leverages the convergence of services and providers for the user through reuse, autonomic adaptation of services to relieve the user’s of laborious and tedious tasks, while ensuring that the user’s end-goal remains central at all times. We applied our approach to the domains of collaborative communication as demonstration of the feasibility of the approach.     

Ontological user modelling and semantic rule-based reasoning for personalisation of Help-On-Demand services in pervasive environments

Existing context-aware applications are limited in their support of user personalisation. Nevertheless, the increase in the use of context-aware technologies has sparked the growth in assistive applications resulting in a need to enable adaptation to reflect the changes in user behaviours. This paper introduces a systematic approach to service personalisation for mobile users in pervasive environments and presents a service-oriented distributed system architecture. The developed approach makes use of semantic technologies for user modelling and personalisation reasoning. In the paper we characterise user behaviours and needs in pervasive environments upon which ontological user models are created with special emphasis being placed on ontological modelling of dynamic and adaptive user profiles. We develop a rule-based personalisation mechanism that exploits semantic web rule mark-up language for rule design and a combination of semantic and rule-based reasoning for personalisation. We use two case studies focusing on providing personalised travel assistance for people using Help-on-Demand services deployed on a smart-phone to contextualise the discussions within the paper. The proposed approach is implemented in a prototype system, which includes Help-on-Demand services, content management services, user models and personalisation mechanisms in addition to application specific rules. Experiments have been designed and conducted to test and evaluate the approach with initial results demonstrating the functionality of the approach.     

Design and evaluation of a smart home voice interface for the elderly: acceptability and objection aspects

Smart homes equipped with ambient intelligence technology constitute a promising direction to enable the growing number of elderly to continue to live in their own home as long as possible. However, this calls for technological solutions that suit their specific needs and capabilities. The Sweet-Home project aims at developing a new user friendly technology for home automation based on voice command. This paper reports a user evaluation assessing the acceptance and fear of this new technology. Eight healthy persons between 71 and 88 years old, 7 relatives (child, grandchild or friend) and 3 professional carers participated in a user evaluation. During about 45 min, the persons were questioned in co-discovery in the Domus smart home alternating between interview and wizard of Oz periods followed by a debriefing. The experience aimed at testing four important aspects of the project: voice command, communication with the outside world, domotics system interrupting a person’s activity, and electronic agenda. Voice interface appeared to have a great potential to ease daily living for elderly and frail persons and would be better accepted than more intrusive solutions. By considering still healthy and independent elderly people in the user evaluation, an interesting finding that came up is their overall acceptance provided the system does not drive them to a lazy lifestyle by taking control of everything. This particular fear must be addressed for the development of smart homes that support daily living by giving them more ability to control rather than putting them away from the daily routine.     

A Hybrid Modular Context-aware Services Adaptation for a Smart Living Room

Smart spaces have attracted considerable amount of interest over the past few years. The introduction of sensor networks, powerful electronics and communication infrastructures have helped a lot in the realization of smart homes. The main objective of smart homes is the automation of tasks that might be complex or tedious for inhabitants by distracting them from concentrating on setting and configuring home appliances. Such automation could improve comfort, energy savings, security, and tremendous benefits for elderly persons living alone or persons with disabilities. Context awareness is a key enabling feature for development of smart homes. It allows the automation task to be done proactively according to the inhabitant’s current context and in an unobtrusive and seamlessly manner. Although there are several works conducted for the development of smart homes with various technologies, in most cases, robust. However, the context-awareness aspect of services adaptation was not based on clear steps for context elements extraction (resp. clear definition of context). In this paper, we use the divide and conquer approach to master the complexity of automation task by proposing a hybrid modular system for context-aware services adaptation in a smart living room. We propose to use for the context-aware adaptation three techniques of machine learning, namely Naïve Bayes, fuzzy logic and case-based reasoning techniques according to their convenience.     

Interaction‐Feature Enhanced Multiuser Model Learning for a Home Environment Using Ambient Sensors

Activity recognition (AR) is a key enabler for a context‐aware smart home since knowing what the residents’ current activities helps a smart home provide more desirable services. This is why AR is often used in assistive technologies for cognitively impaired people to evaluate their abilities to undertake activities of daily living. In a real‐life scenario, multiple‐resident AR has been considered as a very challenging problem, primarily due to the complexity of data association. In addition, most prior research has not considered the potential interpersonal interactions among residents to simplify complexity, especially in an environment monitored by ambient sensors. In this study, we propose two types of multiuser activity models, both of which are derived from an interaction‐feature enhanced multiuser model learning framework. These two models consider interpersonal interactions and data association for multiuser AR using ambient sensors. We then compare their performance with the other two baseline models with or without consideration of data association and interpersonal interactions. The experimental results show that the derived models outperform other baseline classifiers. Therefore, the proposed approach can increase the opportunities for providing context‐aware services for a multiresident smart home.     

Sensor Selection to Support Practical Use of Health-Monitoring Smart Environments

The data mining and pervasive sensing technologies found in smart homes offer unprecedented opportunities for providing health monitoring and assistance to individuals experiencing difficulties living independently at home. In order to monitor the functional health of smart home residents, we need to design technologies that recognize and track activities that people normally perform as part of their daily routines. One question that frequently arises, however, is how many smart home sensors are needed and where should they be placed in order to accurately recognize activities? We employ data mining techniques to look at the problem of sensor selection for activity recognition in smart homes. We analyze the results based on six data sets collected in five distinct smart home environments.     

Context-aware hybrid reasoning framework for pervasive healthcare

Pervasive computing has emerged as a viable solution capable of providing technology-driven assistive living for elderly. The pervasive healthcare system, Context-Aware Real-time Assistant (CARA), is designed to provide personalized healthcare services for elderly in a timely and appropriate manner by adapting the healthcare technology to fit in with normal activities of the elderly and working practices of the caregivers. The work in this paper introduces a personalized, flexible, and extensible hybrid reasoning framework for CARA system in a smart home environment which provides context-aware sensor data fusion as well as anomaly detection mechanisms that supports activity of daily living analysis and alert generation. We study how the incorporation of rule-based and case-based reasoning enables CARA to become more robust and to adapt to a changing environment by continuously retraining with new cases. Noteworthy about the work is the use of case-based reasoning to detect conditional anomalies for home automation, and the use of hierarchical fuzzy rule-based reasoning to deal with exceptions and to achieve query-sensitive case retrieval and case adaptation. Case study for evaluation of this hybrid reasoning framework is carried out under simulated but realistic smart home scenarios. The results indicate the feasibility of the framework for effective at-home monitoring.     

Human home daily living activities recognition based on a LabVIEW implemented hidden Markov model

The recognition of human daily living activities within a house represents an efficient tool to model its power consumption and is also a good indicator for monitoring the health status of the inhabitants. The problematic of activities recognition in smart homes has been extensively addressed in several studies. In this paper, we present an original interactive tool developed under LabVIEW environment with a graphical user interface allowing the modeling of the daily living activities, based on a machine learning Hidden Markov Model. After an overview of the advantage for the consideration of this model in current human activities, we examine how the associated scientific problematic can find an interest and a solution by the integration of machine learning tools. Thus, the application based on a Hidden Markov model approach, is presented and evaluated using two sets of experimental data from literature. Comparing with results obtained by other daily living activities recognition methods, we point out the very satisfactory recognition performance of the Hidden Markov Model and the likelihood of our development associated to a user-friendly graphical interface. This work opens the way to applications dedicated to the supervision of human daily living activities and / or to the management of the electrical consumption within a smart home equipped with non-intrusive sensors.

     

Smart home safety handwriting pattern recognition with innovative technology

Intelligent home security control equipment has become indispensable in daily life. This study uses an innovative handwriting recognition technology to confirm user identity and to manage door security. Smart phones are used for security system management and control actions, and identity confirmation is performed in two stages. In the first stage, the user enters a user name and password into a smart phone and waits for successful identity recognition. In the second stage, the user must write a text or symbol pattern previously set into the smart phone. After successful identification in the second stage, the user is given permission to control the electronic lock and enter the door. The proposed home security system is implemented using a RNN (Recurrent Neural Network) with associative memory for training and recognition. The RNN used in the handwriting recognition step performs some recognition iterative processes.     

The narrative approach to personalisation

This article describes the narrative approach to personalisation. This novel approach to the generation of personalised adaptive hypermedia experiences employs runtime reconciliation between a personalisation strategy and a number of contextual models (e.g. user and domain). The approach also advocates the late binding of suitable content and services to the generated personalised pathway resulting in an interactive composition that comprises services as well as content. This article provides a detailed definition of the narrative approach to personalisation and showcases the approach through the examination of two use-cases: the personalised digital educational games developed by the ELEKTRA and 80Days projects; and the personalised learning activities realised as part of the AMAS project. These use-cases highlight the general applicability of the narrative approach and how it has been applied to create a diverse range of real-world systems.     

Agent-based execution of personalised home care treatments

Home Care services are notoriously difficult to deliver efficiently, due to the heterogeneity of the involved actors and the usual co-morbidity of the patients assisted at home. The K4Care platform proposes an agent-based three-layered architecture aimed at addressing these two issues and facilitate the provision of these services. The development of the platform was supported by a methodology to help the automation of the modelling and implementation of the multi-agent system. The intelligent agents of the platform, which personify the Home Care domain actors, have the capability to guide the execution of administrative and medical processes, driving the flux of knowledge and control among all the involved professionals, simplifying their interactions and capturing new medical knowledge emerging from physicians. The platform also provides tools that allow medical practitioners to develop personalised treatments, adapted to the clinical and social circumstances of each patient and based on the standard international recommendations for the most frequent Home Care pathologies. The paper describes the architecture of the system, how personalised treatments are created, and how they are executed through the co-ordinated work of agents. A comparison with other relevant guideline execution systems and an evaluation of the actual state of the work are also provided.     

A TRIZ-inspired knowledge-driven approach for user-centric smart product-service system: A case study on intelligent test tube rack design

With the advancement of information and communication technologies, smart product-service system (PSS) has attracted increasing research attention to integrate diverse providers/stakeholders and deliver value-added services. Many studies have thusly been conducted to design and develop the smart PSS, while i) how to identify multi-source requirements through reviewing the entire service interaction cycle, ii) how to define and deduce the innovative smart connected products (SCPs) features under contradictory interests, and iii) how to specify the functional and data service configuration solutions are still unclear. To tackle these problems, a knowledge-driven approach was introduced to better organize the multi-source design knowledge and deduce service recommendations for personalized user demands. Specifically, a user journey map-based method was proposed for knowledge elicitation of the specific user demands. To organize the user knowledge for better understanding, hierarchical personalized user requirements (PURs) analytics were proposed to quantitively transfer PURs into proper design engineering parameters. To inspire the problem-solving logic for design solution generation, TRIZ inventive principles were retrieved and referred to. With the generated design concept, the service logic diagrams were structured to define the personalized service content of SCPs. Having the service logic and SCPs, the overall service network of the user-centric smart PSS can be outlined. The proposed approach was demonstrated and validated in the digital health area via a case study on smart test tube rack (STTR) design, and it was validated from an economic feasibility perspective. It showed that the STTR was promising to reduce manual work, improve the nurses' performance, and enhance patients’ medical experience. Furthermore, it was suggested that the proposed approach can effectively guide the innovative SCPs creation in a straightforward and instructive manner, and is promising to process the service solution deduction and improve the efficiency of service creation in real practice.     

SESAME-S: Semantic Smart Home System for Energy Efficiency

As the urgent need for efficient and sustainable energy usage becomes ever more apparent, interest in Smart Homes is on the rise. The SESAME-S project (SEmantic SmArt Metering – Services for Energy Efficient Houses) uses semantically linked data to actively assist end-consumers in making well-informed decisions and controlling their energy consumption. By integrating smart metering and home automation functionality, SESAME-S works to effectively address the potential mass market of end-consumers with an easily customizable solution that can be widely implemented in domestic or business environments, with expected savings of over 20?% from the total energy bill. The developed system is a basis for conceptualizing, demonstrating, and evaluating a variety of innovative end-consumer services and their user interface paradigms. In this paper, we present the SESAME-S system as a whole and discuss the semantically enabled services, demonstrating that such systems may have broad acceptance in the future. The data obtained through such systems will be invaluable for future global energy-efficiency strategies and businesses.     

Identifying multiuser activity with overlapping acoustic data for mobile decision making in smart home environments

Smart services, one of the most intriguing areas of current Internet of Things(IoT) research, require improvement in terms of recognizing user activities. Sound is a useful medium for making decisions based on activity recognition in the smart home environment, which includes mobile devices such as sensors and actuators. Instead of visual sensors to recognize human activity, acoustic sensor data is acquired in an unobtrusive manner for greater privacy. However, multiuser activity provides a formidable challenge for acoustic data-based activity recognition systems because of the difficulty of identifying multiple sources of activity from among a variety of sounds. In our study, we propose a statistical method to detect the interval of interference, which is also known as the unexpected mesa, distinguishing activities based on the pre- and post-mesa intervals. The results suggest that the proposed method outperforms previously presented classification algorithms in terms of the accuracy of multiuser activity recognition. Future studies may utilize this method for improvement of existing smart home systems.     

Computer communication as an aid to independence for older adults

Abstract

Computer and communication technologies offer the potential of improving die quality of life for older people by providing them with links to information and services outside of the home. This study examined die feasibility of older people using an electronic text message system to perform routine communication tasks. In addition information was gathered to identify design parameters which facilitate the interactions of older people with such computer based systems. A specialized and simplified ‘communication computer’ was placed in the homes of 36 older women, aged 50–95 years. The system was provided with: a simple text-editor, basic electronic mail functions and access to news/ weather, movie reviews, and health information. Both performance data and user preference data were collected. Results indicated that the participants liked using the system, were able to use it with minimal difficulty, and that it provided a valuable means for social interaction and mental stimulation. The findings suggest that computer-based systems can be a valuable support tool for older adults if they are easy to use, and provide applications that are useful for them.     

A lightweight remote user authentication scheme for IoT communication using elliptic curve cryptography

Internet of things (IoT) has become a new era of communication technology for performing information exchange. With the immense increment of usage of smart devices, IoT services become more accessible. To perform secure transmission of data between IoT network and remote user, mutual authentication, and session key negotiation play a key role. In this research, we have proposed an ECC-based three-factor remote user authentication scheme that runs in the smart device and preserves privacy, and data confidentiality of the communicating user. To support our claim, multiple cryptographic attacks are analyzed and found that the proposed scheme is not vulnerable to those attacks. Finally, the computation and communication overheads of the proposed scheme are compared with other existing protocols to confirm that the proposed scheme is lightweight. A formal security analysis using AVISPA simulation tool has been done that confirms the proposed scheme is robust against relevant security threats.

     

ImAtHome: Making trigger-action programming easy and fun

ImAtHome is an iOS application for smart home configuration and management built over Apple HomeKit, a framework for communicating with and controlling home automation accessories. This paper describes the design and development of the visual interaction language made available in ImAtHome for empowering end users, without programming skills, to create event-condition-action rules that control home behavior. It can be regarded as an alternative approach to traditional trigger-action programming interfaces, where the user must define such rules by means of “if-then” constructs. Last but not least, attention has been put to make the interaction style as much coherent as possible with other iOS applications. The paper finally presents a user experiment, carried out with 30 participants according to a between-subject protocol, to evaluate the usability of ImAtHome and compare it with the official app for home automation recently released by Apple.