Skip to main content
SpringerLink
Log in

Development of agent system based on decision model for creating an ambient space

  • Original Article
  • Published:
AI & SOCIETY Aims and scope Submit manuscript

Abstract

This paper describes a decision model for an autonomous agent that provides an inhabitant with comfort based on information network technologies that connect home electric appliances with household equipment. The inhabitant enjoys the benefit of comfort, while he pays the cost for keeping that comfort. The autonomous agent should decide and control household equipment considering that cost from the inhabitant’s viewpoint. Thus, we utilized a representation scheme called an “influence diagram” that enabled us to model the decision-making process of the agent from the inhabitant’s point of view. First, decision modeling using the influence diagram is presented via an example. The presented model consists of three information-processing modules: a module for estimating the situation of an inhabitant based on information from home networks, a module for evaluating comfort of the inhabitant, and a module for making decisions that maximize the utility of the inhabitant from both the viewpoints of comfort and the cost paid for that comfort. Next, an experiment for verifying whether the presented model is effective or not, and its results are described. Finally, our model of the agent is discussed in relation to social intelligence design by investigating the interactive processes between the agent and the inhabitant.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12

Similar content being viewed by others

Notes

  1. In this figure, a chance node containing an observable variable is drawn as a bold line, while a chance node containing an unobservable variable is drawn as a normal line.

  2. The action state is manually discretized into three states. The working and still states are introduced for representing typical activity states of the inhabitant. These two states show an inhabitant exists, while the absent state shows he does not exist. The absent state is used for the agent to make a decision on turning off air conditioners from the viewpoint of energy conservation.

  3. The motion sensor state is also discretizcd into these three states. This is based on the hypothesis that the frequent, sometimes and rare states are probably associated with working, still and absent states, respectively.

  4. This simulation is done using the software of influence diagrams developed by Hugin Corporation.

  5. In this experiment, the mode of agent control is set to the comfort mode.

  6. As mentioned in Sect. 3.4.3, we consider three types: comfort, energy-saving or neutral.

  7. This estimation process is done mentioned in Sect. 3.3.3.

References

  • Brooks RA (1997) The Intelligent Room project, 2nd International conference on cognitive technology (CT ‘97), pp 271–278

  • Brumitt B, Meyers B, Krumm J, Kern A, Shafer S (2000) EasyLiving: technologies for intelligent environments. Handheld Ubiquitous Comput 1927:97–119

    Google Scholar 

  • Doctor F, Hagras H, Callagham V (2005) A fuzzy embedded agent-based approach for realizing ambient intelligence in intelligent inhabited environments. IEEE Trans SMC part A 35(1):55–65

    Google Scholar 

  • Fanger PO (1970) Thermal comfort. Danish Technical Press, Copenhagen

    Google Scholar 

  • Howard RA, Matheson JE (2005) Influence diagrams. Decis Anal 2(3):127–143

    Article  Google Scholar 

  • Kidd CD, Orr R, Abowd GD, Atkeson CG, Essa IA, MacIntyre B, Mynatt E, Starner TE, Newstetter W (1999) The aware home: a living laboratory for ubiquitous computing research. In: Proceedings of 2nd international workshop on cooperative buildings, position paper.

  • Kjaerulff UB, Madsen AL (2007) Bayesian networks and influence diagrams: a guide to construction and analysis. Springer, Berlin

    Google Scholar 

  • Li X, Ji Q (2005) Active affective state detection and user assistance with dynamic bayesian networks. IEEE Trans SMC part A 35(1):93–105

    MathSciNet  Google Scholar 

  • Miura T (1977) Hotness coldness and human being. Chuokoron-Shinsha, Japanese, p 189

    Google Scholar 

  • Nakayama K, Suzuki T, Kameyama K (2008) Thermal sensation measurement using fluctuations of peripheral skin temperature. Trans Hum Interface Soc 10(2):1–9 (in Japanese)

    Google Scholar 

  • Nishida T (2001) Social intelligence design–An overview. In: Proceedings of the joint JSAI 2001 workshop on new frontiers in artificial intelligence, Lecture notes in computer science, vol 2253, pp 3–10

  • Nishida T (2010) Social intelligence design for knowledge circulation. In: 6th international workshop on databases in networked information systems (DNIS 2010), pp 122–142

  • Nishida T, Sumi Y, Matsumura M (2009) Social intelligence design. Ohmsha, Japanese

    Google Scholar 

  • Remagnino P, Forest GL (2005) Ambient intelligence: a new multidisciplinary paradigm. IEEE Trans SMC 35(1):1–6

    Google Scholar 

  • Sawaragi T, Katai O, Iwai S, Tsutsui T, Fukuzawa T (1995) Decision-theoretic derivation of rule structures for knowledge-based control and its application to coordinated control of sewage disposal plant. Trans ISCIE 8(10):574–584 (in Japanese)

    Google Scholar 

  • Zelka E, Epstein B (1998) From Devices to Ambient Intelligence, Digital living room conferences, June

Download references

Author information

Authors and Affiliations

  1. Advanced Technologies Development Laboratory, Panasonic Electric Works Co., Ltd, 1048 Kadoma, Osaka, 571-8686, Japan

    Takashi Nishiyama

  2. New Product Technologies Development Department, Panasonic Electric Works Co., Ltd, 1048 Kadoma, Osaka, 571-8686, Japan

    Shinpei Hibiya

  3. Department of Mechanical Engineering and Science, Graduate School of Engineering, Kyoto University, Yoshida Honmachi, Sakyo, Kyoto, 606-8501, Japan

    Tetsuo Sawaragi

Authors
  1. Takashi Nishiyama
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Shinpei Hibiya
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Tetsuo Sawaragi
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Takashi Nishiyama.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Nishiyama, T., Hibiya, S. & Sawaragi, T. Development of agent system based on decision model for creating an ambient space. AI & Soc 26, 247–259 (2011). https://doi.org/10.1007/s00146-010-0305-3

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00146-010-0305-3

Keywords

Search

Navigation