Ontology-Based High-Level Context Inference for Human Behavior Identification

Villalonga, Claudia; Razzaq, Muhammad Asif; Khan, Wajahat Ali; Pomares, H.; Rojas, Ignacio; Lee, Sungyoung; Baños, Oresti

doi:10.3390/s16101617

Cited by 22 publications

(13 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…There are others ADL ontologies available in the literature (Riboni and Bettini 2011;Chen and Nugent 2009b;Bae 2014;Okeyo et al 2014;Villalonga et al 2016). However, most of them describe activities from a high level of abstraction.…”

Section: An Ontology For the Description Of Adlmentioning

confidence: 99%

Methodology for improving classification accuracy using ontologies: application in the recognition of activities of daily living

Salguero

Medina

Delatorre

et al. 2018

J Ambient Intell Human Comput

View full text Add to dashboard Cite

Feature construction and selection are two key factors in the field of machine learning (ML). Usually, these are very timeconsuming and complex tasks because the features have to be manually crafted. The features are aggregated, combined or split to create features from raw data. In this paper, we propose a methodology that makes use of ontologies to automatically generate features for the ML algorithms. The features are generated by combining the concepts and relationships that are already in the knowledge base, expressed in form of ontology. The proposed methodology has been evaluated with three different activities of a popular dataset, showing its effectiveness in the recognition of activities of daily living (ADL). The obtained successful results indicate that the use of extended feature vectors provided by the use of ontologies offers a better accuracy, regarding the original feature vectors of the classic approach, where each feature corresponds to the activation of a sensor. Although the classic approach produces classifiers with accuracies above 92%, the proposed methodology improves those results by 1.9%, on average, without adding more information to the dataset.

show abstract

Section: An Ontology For the Description Of Adlmentioning

confidence: 99%

Methodology for improving classification accuracy using ontologies: application in the recognition of activities of daily living

Salguero

Medina

Delatorre

et al. 2018

J Ambient Intell Human Comput

View full text Add to dashboard Cite

show abstract

“…This knowledge builds mapping from activity entity, appliance entity and context (sensor entity, sensor value entity), temporal-spatial traits, hierarchical methodology, and rules (formulas) [16,17]. This method has shown a good performance in using directly to overcome "cold start" problem [18]. The general rules of the model represent most residents' activity habits which have a high reusability, while the preference, details, and sufficient description of one activity cannot be taken into full consideration.…”

Section: Introductionmentioning

confidence: 99%

A hybrid approach to inferring the Internet of Things for complex activity recognition

Ning

Zhu

et al. 2019

J Wireless Com Network

View full text Add to dashboard Cite

With the rapid development and large-scale uptake of the Internet of Things, smart home is evolving from a vision towards a realistically viable solution for assisted living. Activity recognition is one of the fundamental tasks in order to provide accurate and timely assistance and service. As daily living scenarios are full of similar activities, missing data, and noise, inferring complex activities using knowledge-driven reasoning algorithms suffers from several drawbacks, e.g., real-time raw sensor data segmentation, poor generalization, higher computational complexity, and scalability. To address these problems, this paper proposes a hybrid approach to complex daily activity recognition by merging the first-order logic and probability graphic modeling. Specifically, we develop a novel "Markov logic network" combining data-driven multi-feature and simplified rule-based modeling and inference, thus enabling and supporting the applicability and robustness of daily activity recognition. To evaluate the approach and associated methods, we design a testing scenario with a number of similar activity groups, missing data, or disturbance test datasets in a multi-modeling sensor scene. Initial results show our approach outperforms the traditional approach with a better accuracy in the situations of similar activities with missing data and noise disturbance. Experiments are also conducted to compare the Gibbs sampling and MC-SAT sampling algorithms for Markov logic network, and the results show that the Gibbs is better in our experimental settings.

show abstract

“…There is a necessity for a shift towards a combination of different context reasoning methods [7]. Ontological reasoning [15] is the widely used context reasoning method as it could can ontology consistency and concept subsumption. SWRL (Semantic Web Rule Language) [16] rules are proposed to be incorporated into ontologies and could mitigate the lack of ontologies in determining useful information based on rules [17].…”

Section: Introductionmentioning

confidence: 99%

Towards a Hybrid Approach to Context Reasoning for Underwater Robots

Martínez-Ortega

Rubio

2017

Applied Sciences

View full text Add to dashboard Cite

Abstract:Ontologies have been widely used to facilitate semantic interoperability and serve as a common information model in many applications or domains. The Smart and Networking Underwater Robots in Cooperation Meshes (SWARMs) project, aiming to facilitate coordination and cooperation between heterogeneous underwater vehicles, also adopts ontologies to formalize information that is necessarily exchanged between vehicles. However, how to derive more useful contexts based on ontologies still remains a challenge. In particular, the extreme nature of the underwater environment introduces uncertainties in context data, thus imposing more difficulties in context reasoning. None of the existing context reasoning methods could individually deal with all intricacies in the underwater robot field. To this end, this paper presents the first proposal applying a hybrid context reasoning mechanism that includes ontological, rule-based, and Multi-Entity Bayesian Network (MEBN) reasoning methods to reason about contexts and their uncertainties in the underwater robot field. The theoretical foundation of applying this reasoning mechanism in underwater robots is given by a case study on the oil spill monitoring. The simulated reasoning results are useful for further decision-making by operators or robots and they show that the consolidation of different reasoning methods is a promising approach for context reasoning in underwater robots.

show abstract

Ontology-Based High-Level Context Inference for Human Behavior Identification

Cited by 22 publications

References 27 publications

Methodology for improving classification accuracy using ontologies: application in the recognition of activities of daily living

Methodology for improving classification accuracy using ontologies: application in the recognition of activities of daily living

A hybrid approach to inferring the Internet of Things for complex activity recognition

Towards a Hybrid Approach to Context Reasoning for Underwater Robots

Contact Info

Product

Resources

About