A Machine Learning Based WSN System for Autism Activity Recognition

Alwakeel, Sami S.; Alhalabi, Bassem; Aggoune, Hadi; Alwakeel, Mohammed M.

doi:10.1109/icmla.2015.46

Cited by 22 publications

(9 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In [ 15 ], the authors proposed a machine-learning-based WSN system for autistic-activity recognition. The system included a wearable device that tracked autistic patients using a global-positioning-sensor (GPS) module and communicated the location to caregivers.…”

Section: Related Workmentioning

confidence: 99%

Using Smart Virtual-Sensor Nodes to Improve the Robustness of Indoor Localization Systems

Pedrollo

Konzen

Morais

et al. 2021

Sensors

View full text Add to dashboard Cite

Young, older, frail, and disabled individuals can require some form of monitoring or assistance, mainly when critical situations occur, such as falling and wandering. Healthcare facilities are increasingly interested in e-health systems that can detect and respond to emergencies on time. Indoor localization is an essential function in such e-health systems, and it typically relies on wireless sensor networks (WSN) composed of fixed and mobile nodes. Nodes in the network can become permanently or momentarily unavailable due to, for example, power failures, being out of range, and wrong placement. Consequently, unavailable sensors not providing data can compromise the system’s overall function. One approach to overcome the problem is to employ virtual sensors as replacements for unavailable sensors and generate synthetic but still realistic data. This paper investigated the viability of modelling and artificially reproducing the path of a monitored target tracked by a WSN with unavailable sensors. Particularly, the case with just a single sensor was explored. Based on the coordinates of the last measured positions by the unavailable node, a neural network was trained with 4 min of not very linear data to reproduce the behavior of a sensor that become unavailable for about 2 min. Such an approach provided reasonably successful results, especially for areas close to the room’s entrances and exits, which are critical for the security monitoring of patients in healthcare facilities.

show abstract

Section: Related Workmentioning

confidence: 99%

Using Smart Virtual-Sensor Nodes to Improve the Robustness of Indoor Localization Systems

Pedrollo

Konzen

Morais

et al. 2021

Sensors

View full text Add to dashboard Cite

show abstract

“…Nugyen et al [ 54 ] have used binary rules that map sensor states to an activity label to classify new instances in near real-time (5 min time slices). Other straightforward approaches use real-time threshold based classification [ 92 ] or a mapping between gyroscope orientation and activities [ 81 ].…”

Section: Real-time Centralized Activity Recognitionmentioning

confidence: 99%

From Offline to Real-Time Distributed Activity Recognition in Wireless Sensor Networks for Healthcare: A Review

Baghezza

Bouchard

Bouzouane

et al. 2021

Sensors

View full text Add to dashboard Cite

This review presents the state of the art and a global overview of research challenges of real-time distributed activity recognition in the field of healthcare. Offline activity recognition is discussed as a starting point to establish the useful concepts of the field, such as sensor types, activity labeling and feature extraction, outlier detection, and machine learning. New challenges and obstacles brought on by real-time centralized activity recognition such as communication, real-time activity labeling, cloud and local approaches, and real-time machine learning in a streaming context are then discussed. Finally, real-time distributed activity recognition is covered through existing implementations in the scientific literature, and six main angles of optimization are defined: Processing, memory, communication, energy, time, and accuracy. This survey is addressed to any reader interested in the development of distributed artificial intelligence as well activity recognition, regardless of their level of expertise.

show abstract

“…Once the set of features to be used has been defined, a classifier algorithm is required to generate the model. In the works on children’s activity recognition, there are different classifier algorithms that are implemented, such as random forest, k-nearest neighbor, support vector machines, Bayesian networks and artificial neural networks, among others [ 14 , 25 , 26 ]. Specifically, in the generation of children’s activity classification models using environmental sound, classical classifying algorithms, such as support vector machines, k-nearest neighbors, random forest, extra trees, gradient boosting and artificial neural networks, are used and compared, reaching accuracies between 40% and 99% [ 18 , 19 , 20 ].…”

Section: Related Workmentioning

confidence: 99%

Children’s Activity Classification for Domestic Risk Scenarios Using Environmental Sound and a Bayesian Network

et al. 2021

View full text Add to dashboard Cite

Children’s healthcare is a relevant issue, especially the prevention of domestic accidents, since it has even been defined as a global health problem. Children’s activity classification generally uses sensors embedded in children’s clothing, which can lead to erroneous measurements for possible damage or mishandling. Having a non-invasive data source for a children’s activity classification model provides reliability to the monitoring system where it is applied. This work proposes the use of environmental sound as a data source for the generation of children’s activity classification models, implementing feature selection methods and classification techniques based on Bayesian networks, focused on the recognition of potentially triggering activities of domestic accidents, applicable in child monitoring systems. Two feature selection techniques were used: the Akaike criterion and genetic algorithms. Likewise, models were generated using three classifiers: naive Bayes, semi-naive Bayes and tree-augmented naive Bayes. The generated models, combining the methods of feature selection and the classifiers used, present accuracy of greater than 97% for most of them, with which we can conclude the efficiency of the proposal of the present work in the recognition of potentially detonating activities of domestic accidents.

show abstract

A Machine Learning Based WSN System for Autism Activity Recognition

Cited by 22 publications

References 5 publications

Using Smart Virtual-Sensor Nodes to Improve the Robustness of Indoor Localization Systems

Using Smart Virtual-Sensor Nodes to Improve the Robustness of Indoor Localization Systems

From Offline to Real-Time Distributed Activity Recognition in Wireless Sensor Networks for Healthcare: A Review

Children’s Activity Classification for Domestic Risk Scenarios Using Environmental Sound and a Bayesian Network

Contact Info

Product

Resources

About