Multi-sensor Data Fusion within the Belief Functions Framework

Pietropaoli, Bastien; Dominici, Michele; Weis, Frédéric

doi:10.1007/978-3-642-22875-9_11

Cited by 6 publications

(9 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These can be dynamically revised to reflect the quality of sensor readings. For example, the impact of the battery level of a sensor can be taken into account [12]. An implementation of the algorithm has been realized and preliminary tests showed encouraging results on resource-constrained hardware [12].…”

Section: Perception Layermentioning

confidence: 96%

“…In particular, uncertainty is intrinsic to the physical sensors that are used in the capture [12]. The consequence is that uncertainty has to be propagated, cumulated and considered at every layer of the system.…”

Section: Uncertainty Managementmentioning

confidence: 99%

“…More specifically, data are aggregated from homogeneous as well as heterogeneous sensors. As explained in [12], evidence provided by sensor data is accumulated to calculate the probability that a given contextual abstraction assumes a particular value. For example, inferring the presence of a person combining sensors of movement and sound can be difficult, even when the individual sensors are extremely reliable.…”

Section: Perception Layermentioning

confidence: 99%

“…It is the demonstrator of an interdisciplinary project that brings together industry and researchers from the fields of ubiquitous computing and cognitive ergonomics. The aim is to develop a smart home system that is able to prevent energy waste and preserve inhabitants' comfort, leveraging realistic human activity models [5,4,12]. The key requirement is to provide functionalities that are seamlessly adapted to ongoing situations and activities of inhabitants, avoiding bothering them with inappropriate interventions.…”

Section: Prototype Architecturementioning

confidence: 99%

See 3 more Smart Citations

Towards a feasibility-driven uncertainty-aware layered architecture for recognizing complex domestic activity

Dominici¹,

Pietropaoli²,

Weis³

2011

Proceedings of the 2011 International Workshop on Situation Activity &Amp; Goal Awareness - SAGAware '11

Self Cite

View full text Add to dashboard Cite

International audienceThis paper illustrates some recommended design principles for activity recognition techniques in the smart home domain. These include considerations about acceptability and feasibility and the adoption of realistic human activity models. The paper also presents the architecture of a smart home prototype that is currently under development. In this system, contextual information is obtained through successive abstractions. Mechanisms for assessing and propagating the uncertainty of the recognition process are also discussed

show abstract

Section: Perception Layermentioning

confidence: 96%

Section: Uncertainty Managementmentioning

confidence: 99%

Section: Perception Layermentioning

confidence: 99%

Section: Prototype Architecturementioning

confidence: 99%

See 2 more Smart Citations

Towards a feasibility-driven uncertainty-aware layered architecture for recognizing complex domestic activity

Dominici¹,

Pietropaoli²,

Weis³

2011

Proceedings of the 2011 International Workshop on Situation Activity &Amp; Goal Awareness - SAGAware '11

Self Cite

View full text Add to dashboard Cite

show abstract

“…These improvements are only possible as a result of the improved understanding of the state of a system, in the form of context awareness. One can even go on to consider the likely next context [16], allowing systems to adapt proactively.…”

Section: Introductionmentioning

confidence: 99%

Adaptive sampling in context-aware systems: a machine learning approach

Wood¹,

Merrett²,

Gunn³

et al. 2012

IET Conference on Wireless Sensor Systems (WSS 2012)

View full text Add to dashboard Cite

As computing systems become ever more pervasive, there is an increasing need for them to understand and adapt to the state of the environment around them: that is, their context. This understanding comes with considerable reliance on a range of sensors. However, portable devices are also very constrained in terms of power, and hence the amount of sensing must be minimised. In this paper, we present a machine learning architecture for context awareness which is designed to balance the sampling rates (and hence energy consumption) of individual sensors with the significance of the input from that sensor. This significance is based on predictions of the likely next context. The architecture is implemented using a selected range of user contexts from a collected data set. Simulation results show reliable context identification results. The proposed architecture is shown to significantly reduce the energy requirements of the sensors with minimal loss of accuracy in context identification.

show abstract

Creating Smarter Spaces to Unleash the Potential of Health Apps

Bonnin

Weis

2018

Lecture Notes in Computer Science

Self Cite

View full text Add to dashboard Cite

Technologies necessary for the development of pervasive health apps with intensive and seamless interactions with their environments are now widely available. Research studies and experimentations have demonstrated the real ability for health apps to interact with their environment. However, designing, testing and ensuring the maintenance and evolution of pervasive health apps remains very complex. In particular, there is a lack of tools to enable developers to design apps that can adapt to increasingly complex and changing environments (sensors added or removed, failures, mobility etc.). This paper reflects our vision to reduce this complexity and is based on our current research work on smart environment and personalized health monitoring apps. It uses SAM, a smart asthma monitoring app as an illustration to highlight the need for a comprehensive set of new interactions to help health app developers interact with the users' environment, and more specifically get a smarter access to the data. Some requirements can be on the minimum quality level of the data and the way to adapt to the diversity of the sources (data fusion / aggregation), on the network mechanisms used to collect the data (network/link level) and on the collection of the raw data (sensors). It discusses possible solutions to address these needs.

show abstract

Multi-sensor Data Fusion within the Belief Functions Framework

Cited by 6 publications

References 18 publications

Towards a feasibility-driven uncertainty-aware layered architecture for recognizing complex domestic activity

Towards a feasibility-driven uncertainty-aware layered architecture for recognizing complex domestic activity

Adaptive sampling in context-aware systems: a machine learning approach

Creating Smarter Spaces to Unleash the Potential of Health Apps

Contact Info

Product

Resources

About