Dynamic Quantification of Activity Recognition Capabilities in Opportunistic Systems

Kurz, Marc; Hölzl, Gerold; Ferscha, Alois; Sagha, Hesam; Millán, José del R.; Chavarriaga, Ricardo

doi:10.1109/vetecs.2011.5956356

Cited by 20 publications

(30 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In that sense, it could be more suitable for dynamic classifier ensembles -where sensors (and their corresponding trained classifiers (Kurz et al, 2011a;Calatroni et al, 2011)) -may be added or removed from the network on runtime. Having said so, in this approach the length of the window should be carefully chosen in order to have a reasonable estimate of the mutual information.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

On-line anomaly detection and resilience in classifier ensembles

Sagha

Bayati

Millán

et al. 2013

Pattern Recognition Letters

Self Cite

View full text Add to dashboard Cite

Section: Discussionmentioning

confidence: 99%

“…This measure can then be used to dynamically reconfigure the ensemble, taking into account different specifications including classification performance, as well as communication costs or energy consumption (Kurz et al, 2011b).…”

Section: Discussionmentioning

confidence: 99%

On-line anomaly detection and resilience in classifier ensembles

Sagha

Bayati

Millán

et al. 2013

Pattern Recognition Letters

Self Cite

View full text Add to dashboard Cite

“…This is particularly important as it simplifies the computation of the score; moreover, it reduces the amount of information that has to be stored to characterize potential ensembles. In the case of an architecture relying on nodes self-descriptions, as proposed by Kurz et al [12], each node has to store only its mutual information with respect to other sensors instead of all the possible node combination.…”

Section: Discussionmentioning

confidence: 99%

“…A recent approach has been proposed to support this aspect by relying on nodes that are able to self-describe themselves and advertise their capabilities (e.g. activities they are able to recognize) [12]. Accordingly, upon the appearance of a new node, its selfdescription information can be used to include it into the pool of available classifiers and decide whether it should be part of the ensemble (i.e.…”

Section: E Ensemble Reconfigurationmentioning

confidence: 99%

Ensemble creation and reconfiguration for activity recognition: An information theoretic approach

Chavarriaga

Sagha

Millán

2011

2011 IEEE International Conference on Systems, Man, and Cybernetics

Self Cite

View full text Add to dashboard Cite

Abstract-Advances in sensing, portable computing devices, and wireless communication has lead to an increase in the number and variety of sensing enabled devices (e.g. smartphones or sensing garments). Pervasive computing and activity recognition systems should be able to take advantage of these sensors, even if they are not always available or appear in runtime. These sensors can be integrated into an ensemble that fuse their information to obtain the final decision. There is therefore a need for mechanisms to select which sensors should compose the ensemble, as well as techniques for dynamically reconfigure the ensemble so as to integrate new sensors.Sensors can be integrated into an ensemble where information from each of them is fused to obtain the final decisions. From the machine learning point of view, this corresponds to the combination of classifiers where measures of the accuracy and diversity of the ensemble are used to select the elements that may lead to the highest performance. Recent works propose measures of accuracy and diversity based on an information theoretical approach. In this paper we study the use of these measures for selecting ensembles in activity recognition based on body sensor networks. Besides a comparison with traditional diversity measures (e.g., Q-, κ-statistics), we also present mechanisms to exploit these measures for the dynamic reconfiguration of the ensemble and detection of changes in the network.

show abstract

“…Similarly the development in ambient sensors to recognize the physical as well as cognitive aspects has progressed well beyond the video and audio streams analysis and has entered into implicit interaction paradigm [128,130]. General purpose sensing architectures have been developed, serving multi-purpose, multi-sensor, spontaneous and opportunistic sensing missions [66,[82][83][84].…”

Section: Exploiting Social Contextmentioning

confidence: 99%

Socio-inspired ICT

Ferscha

Farrahi

Hoven

et al. 2012

Eur. Phys. J. Spec. Top.

View full text Add to dashboard Cite

Abstract. Modern ICT (Information and Communication Technology) has developed a vision where the "computer" is no longer associated with the concept of a single device or a network of devices, but rather the entirety of situated services originating in a digital world, which are perceived through the physical world. It is observed that services with explicit user input and output are becoming to be replaced by a computing landscape sensing the physical world via a huge variety of sensors, and controlling it via a plethora of actuators. The nature and appearance of computing devices is changing to be hidden in the fabric of everyday life, invisibly networked, and omnipresent, with applications greatly being based on the notions of context and knowledge. Interaction with such globe spanning, modern ICT systems will presumably be more implicit, at the periphery of human attention, rather than explicit, i.e. at the focus of human attention. Socio-inspired ICT assumes that future, globe scale ICT systems should be viewed as social systems. Such a view challenges research to identify and formalize the principles of interaction and adaptation in social systems, so as to be able to ground future ICT systems on those principles. This position paper therefore is concerned with the intersection of social behaviour and modern ICT, creating or recreating social conventions and social contexts through the use of pervasive, globe-spanning, omnipresent and participative ICT.

show abstract

Dynamic Quantification of Activity Recognition Capabilities in Opportunistic Systems

Cited by 20 publications

References 4 publications

On-line anomaly detection and resilience in classifier ensembles

On-line anomaly detection and resilience in classifier ensembles

Ensemble creation and reconfiguration for activity recognition: An information theoretic approach

Socio-inspired ICT

Contact Info

Product

Resources

About