Context Driven Observation of Human Activity

Crowley, James L.

doi:10.1007/978-3-540-39863-9_9

Cited by 24 publications

(11 citation statements)

References 22 publications

(12 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Finally, a few additional papers were included into the set, after the detailed review of the related work of the selected papers. Computer scientists, such as Dey [42], [43], Strang [19], Crowley [38], [31] and colleagues, made many valuable contributions. Finally, the last two periods of time focus on addressing the challenges inherent in the representation, acquisition, handling, and provisioning of context information.…”

Section: Survey Summarymentioning

confidence: 99%

“…Finally, pre-processing features such as filtering and classification are related to basic transformations of context information to provide symbolic observables at the appropriate level of abstraction [30], [31]. The context management system proposed by Hu et al supports pre-processing of raw context data by implementing chains of atomic processes.…”

Section: Context Managementmentioning

confidence: 99%

See 1 more Smart Citation

Managing Dynamic Context to Optimize Smart Interactions and Services

Villegas

Müller

2010

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract. With the rapid growth of socio-technical ecosystems, smart interactions and services are permeating every walk of life. As smart interactions must managed automatically and interactively in response to evolving user's matters of concern, the smart Internet requires creative approaches where services and interactions are implemented with awareness of, and dynamic adaptation to, users, computational environments, changing policies and unknown requirements. Consequently, modeling and managing dynamic context is critical for implementing smart services and smart interactions effectively. Thus, smart interactions need infrastructure to acquire, compose, and distribute context information to multiple execution endpoints. Moreover, context management must be controlled and governed to optimize system properties. This chapter surveys context modeling and management approaches intended for the optimization of smart interactions and services, discusses the main challenges and requirements of context-awareness in the smart Internet, and provides a feature-based framework useful for the evaluation and implementation of context modeling and management mechanisms.

show abstract

Section: Survey Summarymentioning

confidence: 99%

Section: Context Managementmentioning

confidence: 99%

Managing Dynamic Context to Optimize Smart Interactions and Services

Villegas

Müller

2010

Lecture Notes in Computer Science

View full text Add to dashboard Cite

show abstract

“…Instead of following the BDI paradigm, each agent (or service) in the CHIL Framework can use its own "situation model", which describes the transition from one state to the next [8] according to environment conditions or state of other agents. Starting at a given state, and given a set of contextual information that captures the state of the environment, the agent or service can trigger appropriate actions depending on whether such a transition is possible.…”

Section: The Chil Agent Frameworkmentioning

confidence: 99%

Agent-based architectural framework enhancing configurability, autonomy and scalability of context-aware pervasive services

Dimakis

Soldatos

Polymenakos

et al. 2009

Auton Agent Multi-Agent Syst

View full text Add to dashboard Cite

Multi-agent software architectures have gained in popularity due to their beneficial behavior in designing and implementing sophisticated applications. However, current approaches in implementing such architectures have led to application-specific, non-scalable implementations which limit the reusablity and improvement of the whole architecture. Moreover, these attempts lack features to enhance the user experience, thus slowing the adoption of the resulting services. In this paper we describe a fully-fledged multi-agent architecture covering a large variety of preferred features including capabilities of 'plugging' ubiquitous services, servicing mobile users, interconnecting remote similar architectures and interfacing with advanced software components such as knowledge bases. This framework exploits a wide-range of context-aware components making it essentially context-aware, allowing for the development of ubiquitous context-aware human-centric services, which are the focus of our research. To illustrate the flexibility of this architectural framework, we present four services which were built using this architectural paradigm by different development teams and elaborate on their overall behavior

show abstract

“…Our approach for modeling social situations is inspired by the cognitive models for situation proposed by Johnson-Laird [14] in which situations are modeled as relations between entities. In previous work, we have generalized situation models with the introduction of the concept of "role" [8] and experimented with the use of machine learning techniques for automatically acquiring situation models. In this paper we extend this approach to the problem of learning social common sense.…”

Section: Situated Social Common Sensementioning

confidence: 99%

“…While his model, as well as much of the subsequent literature in this area, has been concerned with spatial reasoning or linguistic understanding [14], these concepts can be adopted for the construction of software systems and services for understanding social interaction. In previous work, [8] we have described the use of situation models for context aware services. As in the cognitive modeling literature, situations are defined as a set of relations between entities, where entities may be agents, objects or any abstract concepts observed as a correlated set of properties.…”

Section: Situation Models For Social Interactionmentioning

confidence: 99%

Learning polite behavior with situation models

Barraquand

Crowley

2008

Proceedings of the 3rd ACM/IEEE International Conference on Human Robot Interaction

Self Cite

View full text Add to dashboard Cite

In this paper, we describe experiments with methods for learning the appropriateness of behaviors based on a model of the current social situation. We first review different approaches for social robotics, and present a new approach based on situation modeling. We then review algorithms for social learning and propose three modifications to the classical Q-Learning algorithm. We describe five experiments with progressively complex algorithms for learning the appropriateness of behaviors. The first three experiments illustrate how social factors can be used to improve learning by controlling learning rate. In the fourth experiment we demonstrate that proper credit assignment improves the effectiveness of reinforcement learning for social interaction. In our fifth experiment we show that analogy can be used to accelerate learning rates in contexts composed of many situations. Categories and Subject Descriptors Situated Social Common SenseWith current technology, systems and services are unable to discriminate between appropriate and inappropriate behaviors. As a result, most attempts at proactive user services produce systems that are highly disruptive of human activity. In short, computing systems lack social common sense.Common sense is the collection of shared concepts and ideas that are accepted as correct by a community of people. Social common sense refers to the shared rules for polite, social interaction that implicitly rule behavior within a social group. To a large extent, such common sense is developed using implicit feedback during interaction between individuals. Our goal in this research is to develop methods to endow an artificial agent with the ability to acquire social common sense using the implicit feedback obtained from interaction with people. We believe that such methods can provide a foundation for socially polite man-machine interaction, and ultimately for other forms of cognitive abilities.In this paper, we propose to focus on a key aspect of social common sense: the ability to act appropriately in social situations. In this work, we have sought to train an association between behavior and social situation. Our approach for modeling social situations is inspired by the cognitive models for situation proposed by Johnson-Laird [14] in which situations are modeled as relations between entities. In previous work, we have generalized situation models with the introduction of the concept of "role" [8] and experimented with the use of machine learning techniques for automatically acquiring situation models. In this paper we extend this approach to the problem of learning social common sense. It is our intention that these methods may be used with any system that can spontaneously act to propose information or services.Rules for polite social interaction tend to be highly dependent on context, as well as specific to individuals or groups. Thus we have sought methods that would allow systems to learn the appropriateness of actions using the natural social feedback that people provide in mo...

show abstract

Context Driven Observation of Human Activity

Cited by 24 publications

References 22 publications

Managing Dynamic Context to Optimize Smart Interactions and Services

Managing Dynamic Context to Optimize Smart Interactions and Services

Agent-based architectural framework enhancing configurability, autonomy and scalability of context-aware pervasive services

Learning polite behavior with situation models

Contact Info

Product

Resources

About