Control and Learning of Ambience by an Intelligent Building

Rutishauser, Ueli; Joller, J.; Douglas, Rodney J.

doi:10.1109/tsmca.2004.838459

Cited by 75 publications

(32 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Most of these approaches perform time series analysis based on sensory data collected. In particular, data mining prediction techniques (e.g., casebased reasoning [22]), soft computing prediction techniques (e.g., fuzzy rule based learning [23]) and statistical modeling prediction techniques (e.g., based on Markov chains [24]) are used often. Usually cognitive models underlying human behavior are not considered in these approaches.…”

Section: Discussionmentioning

confidence: 99%

An ambient agent system assisting humans in complex tasks by analysis of a human's state and performance

Bosse

Both

Duell

et al. 2013

IJIIDS

View full text Add to dashboard Cite

Abstract. Human task performance varies depending on the task, environment, and states of the human over time. To ensure high effectiveness and efficiency in the execution of complex tasks, adaptive automated assistance of the human may be required. In this paper, a generic design for a multi-agent system architecture is presented and a personal assistant agent is presented that makes use of the proposed architecture. The agent constantly monitors the task execution and well-being of the human via non-intrusive sensors, and intervenes when a problem is detected. A human is given a complex task, while the future performance is predicted using observations and a dynamical model for the human's work pressure and exhaustion. If the predicted exhaustion becomes too high, the ambient agent can assist the human in a number of ways. Experiments show that the support system increases performance with around 13%, and that it enhances the feeling of control of the situation.

show abstract

Section: Discussionmentioning

confidence: 99%

An ambient agent system assisting humans in complex tasks by analysis of a human's state and performance

Bosse

Both

Duell

et al. 2013

IJIIDS

View full text Add to dashboard Cite

show abstract

“…This implies that the data acquisition process and feedback obtaining process have to be carried out as unobtrusively as possible (Rutishauser et al, 2005); for example, by means of sensors installed in standard devices. The concept of an ideal proactive environment suggests an environment where the interaction with the user is carried out through standard devices such as switches or remote controls, but when this is not possible, friendly multimodal interfaces are considered (Turunen et al, 2007;Partala et al, 2006;Coen, 1998).…”

Section: Importance Of the Usermentioning

confidence: 99%

Discovering frequent user--environment interactions in intelligent environments

Aztiria

Augusto

Basagoiti

et al. 2011

Pers Ubiquit Comput

View full text Add to dashboard Cite

“…On a question-by-question basis, one BigScreen-related question (6) and three overall questions (13,14,16) elicited significantly higher responses (t-test, p < 0.05) from the active group. It is clear that active people were more positive about the Ada exhibit as a whole; however, passive visitors were more likely to say that they were imitating the actions of others (Q12).…”

Section: B Visitor Opinions and Behaviormentioning

confidence: 96%

“…However, realtime interactions over larger areas and with larger numbers of users have proved to be more difficult to achieve. Building control systems have been developed that can learn user preferences by using passive infra-red sensors and light switches to control room lighting and window blinds [14], and input-only (non-robotic) surveillance systems have been created that can track humans and other objects over relatively large areas [9,[15][16][17][18]. Despite these advances, the technical and logistical challenges of tracking large numbers of willing human subjects and providing them with repeatable stimuli still present a considerable barrier to conducting behavioral experiments.…”

Section: Introductionmentioning

confidence: 99%

Collective Human Behavior in Interactive Spaces

Eng

Mintz

Verschure

Proceedings of the 2005 IEEE International Conference on Robotics and Automation

View full text Add to dashboard Cite

-We extend the study of human-robot interaction into the area of large-scale, multi-user, robotic interactive environments.Using our experimental infrastructure -the interactive space Ada, an exhibit at the Swiss national expo in 2002 that received 553,700 visitors -we show that human movement is predictive of key attitudes towards a space and other humans, and that subjects' behavior and attitudes are influenced by subtle modifications of environmental parameters.We also found several demographic effects on visitors' opinions of interactive spaces. These findings enhance our quantitative understanding of collective human behavior in interactive spaces and are a first step towards the construction of active environments that can automatically influence human motion and experience. This knowledge will be important in the design and construction of future interactive environments for enhancing the safety and enjoyment of shared areas for large numbers of people.Index Terms -human-machine interaction, interactive space, crowd behavior, human movement, human attitudes

show abstract

Control and Learning of Ambience by an Intelligent Building

Cited by 75 publications

References 15 publications

An ambient agent system assisting humans in complex tasks by analysis of a human's state and performance

An ambient agent system assisting humans in complex tasks by analysis of a human's state and performance

Discovering frequent user--environment interactions in intelligent environments

Collective Human Behavior in Interactive Spaces

Contact Info

Product

Resources

About