Multioccupant Activity Recognition in Pervasive Smart Home Environments

Benmansour, Asma; Bouchachia, Abdelhamid; Feham, Mohammed

doi:10.1145/2835372

Cited by 107 publications

(66 citation statements)

References 44 publications

(175 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The homes which are equipped with monitoring facilities are known as smart homes. Different techniques have been proposed in literature for smart homes [187]. Beside, vision-based techniques, a number of sensor-based techniques have also been presented in the literature [188].…”

Section: Ambient Assisted Livingmentioning

confidence: 99%

A Comprehensive Review on Handcrafted and Learning-Based Action Representation Approaches for Human Activity Recognition

2017

View full text Add to dashboard Cite

Human activity recognition (HAR) is an important research area in the fields of human perception and computer vision due to its wide range of applications. These applications include: intelligent video surveillance, ambient assisted living, human computer interaction, human-robot interaction, entertainment, and intelligent driving. Recently, with the emergence and successful deployment of deep learning techniques for image classification, researchers have migrated from traditional handcrafting to deep learning techniques for HAR. However, handcrafted representation-based approaches are still widely used due to some bottlenecks such as computational complexity of deep learning techniques for activity recognition. However, approaches based on handcrafted representation are not able to handle complex scenarios due to their limitations and incapability; therefore, resorting to deep learning-based techniques is a natural option. This review paper presents a comprehensive survey of both handcrafted and learning-based action representations, offering comparison, analysis, and discussions on these approaches. In addition to this, the well-known public datasets available for experimentations and important applications of HAR are also presented to provide further insight into the field. This is the first review paper of its kind which presents all these aspects of HAR in a single review article with comprehensive coverage of each part. Finally, the paper is concluded with important discussions and research directions in the domain of HAR.

show abstract

Section: Ambient Assisted Livingmentioning

confidence: 99%

A Comprehensive Review on Handcrafted and Learning-Based Action Representation Approaches for Human Activity Recognition

2017

View full text Add to dashboard Cite

show abstract

“…8 Probabilistic graphical models have proven to be effective in modeling users' behaviors, and users' data traces in AAL environments. 17 Thus far, Markov chains and hidden Markov models (HMMs), 9,10,18 conditional random fields (CRFs), 19 Bayesian networks, 20 and their several variants have been adapted for human behavior modeling. These schemes are based on the Markov assumption that: the next step of a user's activity depends on a limited history of the previous steps and sensors' observations.…”

Section: Related Workmentioning

confidence: 99%

Modeling Users’ Data Traces in Multi-Resident Ambient Assisted Living Environments

Ghasemi¹,

Pouyan²

2017

IJCIS

View full text Add to dashboard Cite

Modeling users' data traces is of crucial importance for human behavior analysis and context-aware applications in ambient assisted living (AAL) environments. However, learning the parameters of the underlying model is a challenging task in multi-occupant environments; because, the anonymous users' data traces are aggregated temporally. This paper proposes a novel method for modeling users' data traces in multi-resident sensor-based AAL environments. A Markov chain was considered as the underlying model. We aimed at estimating the parameters of the Markov chain directly out of users' aggregate data. For this purpose, we hired the idea of conditional least squares (CLS) estimation. However, the CLS estimations can be inconsistent in the circumstances of AAL environments. To tackle this problem, we proposed to regularize the CLS estimations using spatial information of sensors. This information was extracted using an accessibility graph, made out of the deployed sensor network. To evaluate the proposed method, a well-known and publicly available dataset was used. The proposed method was compared with the standard CLS, using Kullback-Leibler (KL) divergence, and mean squared error (MSE) criteria. The results conveyed that the proposed method results in estimations with lower KL divergences from ground truth, compared to CLS. Also, the proposed method outperformed CLS with a MSE of 2.7 × 10 −3 .

show abstract

“…Shoaib et al [5] present a survey of the methods that are currently in use for on-line activity recognition using mobile phones. A good overview of recent research on multi-occupant activity recognition is presented by Benmansour et al [6]. …”

Section: Related Workmentioning

confidence: 99%

Inferring Human Activity Recognition with Ambient Sound on Wireless Sensor Nodes

Salomons

Havinga

Leeuwen

2016

Sensors

View full text Add to dashboard Cite

A wireless sensor network that consists of nodes with a sound sensor can be used to obtain context awareness in home environments. However, the limited processing power of wireless nodes offers a challenge when extracting features from the signal, and subsequently, classifying the source. Although multiple papers can be found on different methods of sound classification, none of these are aimed at limited hardware or take the efficiency of the algorithms into account. In this paper, we compare and evaluate several classification methods on a real sensor platform using different feature types and classifiers, in order to find an approach that results in a good classifier that can run on limited hardware. To be as realistic as possible, we trained our classifiers using sound waves from many different sources. We conclude that despite the fact that the classifiers are often of low quality due to the highly restricted hardware resources, sufficient performance can be achieved when (1) the window length for our classifiers is increased, and (2) if we apply a two-step approach that uses a refined classification after a global classification has been performed.

show abstract

Multioccupant Activity Recognition in Pervasive Smart Home Environments

Cited by 107 publications

References 44 publications

A Comprehensive Review on Handcrafted and Learning-Based Action Representation Approaches for Human Activity Recognition

A Comprehensive Review on Handcrafted and Learning-Based Action Representation Approaches for Human Activity Recognition

Modeling Users’ Data Traces in Multi-Resident Ambient Assisted Living Environments

Inferring Human Activity Recognition with Ambient Sound on Wireless Sensor Nodes

Contact Info

Product

Resources

About