ADL recognition based on the combination of RFID and accelerometer sensing

Stikic, Maja; Huỳnh, Tâm; Laerhoven, Kristof Van; Schiele, Bernt

doi:10.1109/pcthealth.2008.4571084

Cited by 120 publications

(74 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Spatiotemporal traces are used in [18] to derive high-level activities such as shopping or dining out. Observations regarding the user's surrounding environment (in particular, objects' use), possibly coupled with body-worn sensor data, are the basis of many other activity recognition systems (e.g., [27,25,10,12]). However, as anticipated in the introduction, these systems suffer from serious scalability issues with respect to the number of considered context data.…”

Section: Related Workmentioning

confidence: 99%

COSAR: hybrid reasoning for context-aware activity recognition

Riboni

Bettini

2010

Pers Ubiquit Comput

247

159

View full text Add to dashboard Cite

Human activity recognition is a challenging problem for context-aware systems and applications. Research in this field has mainly adopted techniques based on supervised learning algorithms, but these systems suffer from scalability issues with respect to the number of considered activities and contextual data. In this paper, we propose a solution based on the use of ontologies and ontological reasoning combined with statistical inferencing. Structured symbolic knowledge about the environment surrounding the user allows the recognition system to infer which activities among the candidates identified by statistical methods are more likely to be the actual activity that the user is performing. Ontological reasoning is also integrated with statistical methods to recognize complex activities that cannot be derived by statistical methods alone. The effectiveness of the proposed technique is supported by experiments with a complete implementation of the system using commercially available sensors and an Android-based handheld device as the host for the main activity recognition module.

show abstract

Section: Related Workmentioning

confidence: 99%

COSAR: hybrid reasoning for context-aware activity recognition

Riboni

Bettini

2010

Pers Ubiquit Comput

247

159

View full text Add to dashboard Cite

show abstract

“…). Observations regarding the user's surrounding environment (in particular, the use of specific objects), possibly coupled with body-worn sensor data, are the basis of many other activity recognition systems (e.g., [17,18,3]). There are also techniques based on probabilistic methods such as Bayesian networks and Markov models; for instance, relational Markov networks are used in [1] to derive high-level activities such as shopping or dining out.…”

Section: Related Workmentioning

confidence: 99%

OWL 2 modeling and reasoning with complex human activities

Riboni

Bettini

2011

Pervasive and Mobile Computing

136

View full text Add to dashboard Cite

In recent years, there has been a growing interest in the adoption of ontologies and ontological reasoning to automatically recognize complex context data such as human activities. In particular, the Web Ontology Language (OWL) emerged as the language of choice, being a standard for the Semantic Web, and supported by a number of tools for knowledge engineering and reasoning. However, the limitations of OWL 1 in terms of expressiveness have been recognized in various fields, and important research e↵orts have been made to extend the language while preserving decidability of its OWL 1 DL fragment. The result of such work is OWL 2. In this paper we investigate the use of OWL 2 for modeling complex activities and reasoning with them. We show that the new language constructors of OWL 2 overcome the main limitations of OWL 1 for the representation of activities; OWL 2 axioms can be used to represent certain rules and rule-based reasoning previously demanded to hybrid approaches, with the advantage of having a unique semantics, avoiding potential inconsistencies. Then, we propose a system architecture showing the integration of a novel OWL 2 activity ontology and reasoning modules with distributed modules for sensor data aggregation and reasoning. The feasibility of our solution is shown by an extensive experimental evaluation with simulations of di↵erent intelligent environments.

show abstract

“…These inputs are used to create models using dynamic Bayesian networks, that are then used for the identification of the activities. In [17], an approach that augments the use of RFIDs with an accelerometer mounted on the glove with the RFID reader is presented. In this work, RFID tag readings are used to narrow down the set of activities based on the type of object being used.…”

Section: Related Workmentioning

confidence: 99%

“…For that purpose, custom-made mobile sensor platforms are built and used for identification of context related to human activity and are optimized to boost classification performance [13], [17], [16]. In practice, however, the main challenge is the usability of the chosen solution.…”

Section: Introductionmentioning

confidence: 99%

Multisensor Fusion in Smartphones for Lifestyle Monitoring

Ganti

Srinivasan

Gacic

2010

2010 International Conference on Body Sensor Networks

View full text Add to dashboard Cite

Abstract-Smartphones with diverse sensing capabilities are becoming widely available and pervasive in use. With the phone becoming a mobile personal computer, integrated applications can use multi-sensory data to derive information about the user's actions and the context in which these actions occur. This paper develops a novel method to assess daily living patterns using a smartphone equipped with microphones and inertial sensors. We develop a feature-space combination approach for fusion of information from sensors sampled at different rates and present a computationally light-weight algorithm to identify various high level activities. Preliminary results from an initial deployment among eight users indicate the potential for accurate, contextaware, and personalized sensing.

show abstract

ADL recognition based on the combination of RFID and accelerometer sensing

Cited by 120 publications

References 11 publications

COSAR: hybrid reasoning for context-aware activity recognition

COSAR: hybrid reasoning for context-aware activity recognition

OWL 2 modeling and reasoning with complex human activities

Multisensor Fusion in Smartphones for Lifestyle Monitoring

Contact Info

Product

Resources

About