Modeling of Ambient Comfort Affect Reward based on multi-agents in cloud interconnection environment for developing the sustainable home controller

A. A. Bielskis, E. Guseinoviene, L. Zutautas, D. Drungilas, D. Dzemydiene, G. Gricius

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

    Abstract

    The paper presents a research based on a vision of a multi-agent model working for the ambient comfort measurement and environment control system. Such means are used for developing the Smarter Eco-Social Laboratory (SrESL). The human Ambient Comfort Affect Reward (ACAR) index is proposed for development of the Reinforcement Learning Based Ambient Comfort Controller (RL-ACC) for experiments using equipment of SrESL. The ACAR index is recognized as dependent on human physiological parameters, such as the temperature, the electrocardiogram (ECG) and the electro-dermal activity (EDA). The fuzzy logic is used to approximate the ACAR index function by defining two fuzzy inference systems: the Arousal-Valence System, and the Ambient Comfort Affect Reward (ACAR) System. The goal of the RL-ACC is to find such the environmental state characteristics that create an optimal comfort for people affected by this environment. The Radial Basis Neural Network is used as the main component of the RL-ACC to performing of two roles: the policy structure, known as the Actor, used to select actions, and the estimated value function, known as the Critic that criticizes the actions made by the Actor. The Actor which manages Critic processes was used as a value function approximation of the continuous learning tasks of the RL-ACC and presented in this paper.

    Original languageEnglish
    Title of host publication2013 8th International Conference and Exhibition on Ecological Vehicles and Renewable Energies, EVER 2013
    DOIs
    Publication statusPublished - 2013
    Event2013 8th International Conference and Exhibition on Ecological Vehicles and Renewable Energies, EVER 2013 - Monte Carlo, Monaco
    Duration: Mar 27 2013Mar 30 2013

    Other

    Other2013 8th International Conference and Exhibition on Ecological Vehicles and Renewable Energies, EVER 2013
    CountryMonaco
    CityMonte Carlo
    Period3/27/133/30/13

    Fingerprint

    Reinforcement learning
    Controllers
    Fuzzy inference
    Electrocardiography
    Fuzzy logic
    Neural networks
    Control systems
    Experiments
    Temperature

    Keywords

    • Ambient intelligence
    • cloud computing
    • digital control
    • wireless communication

    ASJC Scopus subject areas

    • Renewable Energy, Sustainability and the Environment
    • Automotive Engineering

    Cite this

    Bielskis, A. A., Guseinoviene, E., Zutautas, L., Drungilas, D., Dzemydiene, D., & Gricius, G. (2013). Modeling of Ambient Comfort Affect Reward based on multi-agents in cloud interconnection environment for developing the sustainable home controller. In 2013 8th International Conference and Exhibition on Ecological Vehicles and Renewable Energies, EVER 2013 [6521585] https://doi.org/10.1109/EVER.2013.6521585

    Modeling of Ambient Comfort Affect Reward based on multi-agents in cloud interconnection environment for developing the sustainable home controller. / Bielskis, A. A.; Guseinoviene, E.; Zutautas, L.; Drungilas, D.; Dzemydiene, D.; Gricius, G.

    2013 8th International Conference and Exhibition on Ecological Vehicles and Renewable Energies, EVER 2013. 2013. 6521585.

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

    Bielskis, AA, Guseinoviene, E, Zutautas, L, Drungilas, D, Dzemydiene, D & Gricius, G 2013, Modeling of Ambient Comfort Affect Reward based on multi-agents in cloud interconnection environment for developing the sustainable home controller. in 2013 8th International Conference and Exhibition on Ecological Vehicles and Renewable Energies, EVER 2013., 6521585, 2013 8th International Conference and Exhibition on Ecological Vehicles and Renewable Energies, EVER 2013, Monte Carlo, Monaco, 3/27/13. https://doi.org/10.1109/EVER.2013.6521585
    Bielskis AA, Guseinoviene E, Zutautas L, Drungilas D, Dzemydiene D, Gricius G. Modeling of Ambient Comfort Affect Reward based on multi-agents in cloud interconnection environment for developing the sustainable home controller. In 2013 8th International Conference and Exhibition on Ecological Vehicles and Renewable Energies, EVER 2013. 2013. 6521585 https://doi.org/10.1109/EVER.2013.6521585
    Bielskis, A. A. ; Guseinoviene, E. ; Zutautas, L. ; Drungilas, D. ; Dzemydiene, D. ; Gricius, G. / Modeling of Ambient Comfort Affect Reward based on multi-agents in cloud interconnection environment for developing the sustainable home controller. 2013 8th International Conference and Exhibition on Ecological Vehicles and Renewable Energies, EVER 2013. 2013.
    @inproceedings{9bad087bb14b450f91d8176e72ab8392,
    title = "Modeling of Ambient Comfort Affect Reward based on multi-agents in cloud interconnection environment for developing the sustainable home controller",
    abstract = "The paper presents a research based on a vision of a multi-agent model working for the ambient comfort measurement and environment control system. Such means are used for developing the Smarter Eco-Social Laboratory (SrESL). The human Ambient Comfort Affect Reward (ACAR) index is proposed for development of the Reinforcement Learning Based Ambient Comfort Controller (RL-ACC) for experiments using equipment of SrESL. The ACAR index is recognized as dependent on human physiological parameters, such as the temperature, the electrocardiogram (ECG) and the electro-dermal activity (EDA). The fuzzy logic is used to approximate the ACAR index function by defining two fuzzy inference systems: the Arousal-Valence System, and the Ambient Comfort Affect Reward (ACAR) System. The goal of the RL-ACC is to find such the environmental state characteristics that create an optimal comfort for people affected by this environment. The Radial Basis Neural Network is used as the main component of the RL-ACC to performing of two roles: the policy structure, known as the Actor, used to select actions, and the estimated value function, known as the Critic that criticizes the actions made by the Actor. The Actor which manages Critic processes was used as a value function approximation of the continuous learning tasks of the RL-ACC and presented in this paper.",
    keywords = "Ambient intelligence, cloud computing, digital control, wireless communication",
    author = "Bielskis, {A. A.} and E. Guseinoviene and L. Zutautas and D. Drungilas and D. Dzemydiene and G. Gricius",
    year = "2013",
    doi = "10.1109/EVER.2013.6521585",
    language = "English",
    isbn = "9781467352703",
    booktitle = "2013 8th International Conference and Exhibition on Ecological Vehicles and Renewable Energies, EVER 2013",

    }

    TY - GEN

    T1 - Modeling of Ambient Comfort Affect Reward based on multi-agents in cloud interconnection environment for developing the sustainable home controller

    AU - Bielskis, A. A.

    AU - Guseinoviene, E.

    AU - Zutautas, L.

    AU - Drungilas, D.

    AU - Dzemydiene, D.

    AU - Gricius, G.

    PY - 2013

    Y1 - 2013

    N2 - The paper presents a research based on a vision of a multi-agent model working for the ambient comfort measurement and environment control system. Such means are used for developing the Smarter Eco-Social Laboratory (SrESL). The human Ambient Comfort Affect Reward (ACAR) index is proposed for development of the Reinforcement Learning Based Ambient Comfort Controller (RL-ACC) for experiments using equipment of SrESL. The ACAR index is recognized as dependent on human physiological parameters, such as the temperature, the electrocardiogram (ECG) and the electro-dermal activity (EDA). The fuzzy logic is used to approximate the ACAR index function by defining two fuzzy inference systems: the Arousal-Valence System, and the Ambient Comfort Affect Reward (ACAR) System. The goal of the RL-ACC is to find such the environmental state characteristics that create an optimal comfort for people affected by this environment. The Radial Basis Neural Network is used as the main component of the RL-ACC to performing of two roles: the policy structure, known as the Actor, used to select actions, and the estimated value function, known as the Critic that criticizes the actions made by the Actor. The Actor which manages Critic processes was used as a value function approximation of the continuous learning tasks of the RL-ACC and presented in this paper.

    AB - The paper presents a research based on a vision of a multi-agent model working for the ambient comfort measurement and environment control system. Such means are used for developing the Smarter Eco-Social Laboratory (SrESL). The human Ambient Comfort Affect Reward (ACAR) index is proposed for development of the Reinforcement Learning Based Ambient Comfort Controller (RL-ACC) for experiments using equipment of SrESL. The ACAR index is recognized as dependent on human physiological parameters, such as the temperature, the electrocardiogram (ECG) and the electro-dermal activity (EDA). The fuzzy logic is used to approximate the ACAR index function by defining two fuzzy inference systems: the Arousal-Valence System, and the Ambient Comfort Affect Reward (ACAR) System. The goal of the RL-ACC is to find such the environmental state characteristics that create an optimal comfort for people affected by this environment. The Radial Basis Neural Network is used as the main component of the RL-ACC to performing of two roles: the policy structure, known as the Actor, used to select actions, and the estimated value function, known as the Critic that criticizes the actions made by the Actor. The Actor which manages Critic processes was used as a value function approximation of the continuous learning tasks of the RL-ACC and presented in this paper.

    KW - Ambient intelligence

    KW - cloud computing

    KW - digital control

    KW - wireless communication

    UR - http://www.scopus.com/inward/record.url?scp=84879910214&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=84879910214&partnerID=8YFLogxK

    U2 - 10.1109/EVER.2013.6521585

    DO - 10.1109/EVER.2013.6521585

    M3 - Conference contribution

    AN - SCOPUS:84879910214

    SN - 9781467352703

    BT - 2013 8th International Conference and Exhibition on Ecological Vehicles and Renewable Energies, EVER 2013

    ER -