Artificial Neural Networks in Smart Homes

The technology of Smart Homes (SH), as an instance of ambient assisted living technologies, is designed to assist the homes' residents accomplishing their daily-living activities and thus having a better quality of life while preserving their privacy. A SH system is usually equipped with a collection of inter-related software and hardware components to monitor the living space by capturing the behaviour of the resident and understanding his activities. By doing so the system can inform about risky situations and take actions on behalf of the resident to his satisfaction. The present survey will address technologies and analysis methods and bring examples of the state of the art research studies in order to provide background for the research community. In particular, the survey will expose infrastructure technologies such as sensors and communication platforms along with artificial intelligence techniques used for modeling and recognizing activities. A brief overview of approaches used to develop Human-Computer (HC) interfaces for SH systems is given. The survey also highlights the challenges and research trends in this area.

show abstract

“…MLP is the most commonly used ANN models for activity recognition [8]. A precursory work using MLP for SHs is presented in [78].…”

Section: Artificial Neural Networkmentioning

confidence: 99%

A review of smart homes in healthcare

Amiribesheli

Benmansour

Bouchachia

2015

J Ambient Intell Human Comput

154

123

View full text Add to dashboard Cite

show abstract

“…In this context, for example, artificial neural networks (ANNs) have the potential to provide excellent support especially regarding monitoring and controlling aspects of a smart home [4]. Sági et al also use a neuronal network to reduce the energy consumption of a smart environment by optimally scheduling device activities [15] without interrupting the inhabitants.…”

Section: Alternative Approachesmentioning

confidence: 99%

Competitive Agents for Intelligent Home Automation

Michalski

Pohling

Holthaus

2017

Proceedings of the 5th International Conference on Human Agent Interaction

View full text Add to dashboard Cite

Technologies that aim to achieve intelligent automation in smart homes typically involve either trigger-action pairs or machine learning. These, however, are often complex to configure or hard to comprehend for the user. To maximize automation efficiency while keeping the configuration simple and the effects comprehensible, we thus explore an alternative agent-based approach. With the help of a survey, we put together a set of intelligent agents that act autonomously in the environment. Conflicts between behaviors, identified with a secondary study, are thereby resolved with a competitive combination of agents. We finally present the draft of a user interface that allows for individual configuration of all agents.

show abstract

“…• interaction protocols used to negotiate users' needs, • decision making and distributed problem solving to adapt these needs to energy limitation [10], [11], • data-mining to match the specific situation to a previously observed one [12]... The associate tools are [13], [14], [15], [16], [17].…”

Section: B Physical Environment Models Are Not Realisticmentioning

confidence: 99%