Unsupervised discovery of activities of daily living characterized by their periodicity and variability

Soulas, Julie; Lenca, Philippe; Thépaut, Antoine

doi:10.1016/j.engappai.2015.06.006

Cited by 23 publications

(16 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Offline analysis of recorded activities from these trials was conducted to compare a custom mobility classifier to de-facto machine learning algorithms, including cart, c4.5, multi-layer perceptron, SVM, and naïve Bayes. Those analysis indicated that smartphone accelerometers together with chest sensors are capable of recognizing a range of variable activities including sitting, lying, running, standing, walking and cycling with accuracies as high as 98% [10].…”

Section: Introductionmentioning

confidence: 99%

Accelerometer-based Activity Recognition: Reengineering Study

Kedwan¹

2019

IJCA

View full text Add to dashboard Cite

show abstract

Section: Introductionmentioning

confidence: 99%

Accelerometer-based Activity Recognition: Reengineering Study

Kedwan¹

2019

IJCA

View full text Add to dashboard Cite

show abstract

“…Smart Homes used for elderly home care, can increase independent living time and reduce long-term care costs. By monitoring Activities of Daily Living (ADL), behavior patterns, their changes and their evolution, it is possible to infer a person's health status and her ability to live independently [14].…”

Section: Introductionmentioning

confidence: 99%

Representing and Learning Human Behavior Patterns with Contextual Variability

Lago

Roncancio

Jiménez-Guarín

et al. 2017

Lecture Notes in Computer Science

View full text Add to dashboard Cite

For Smart Environments used for elder care, learning the inhabitant's behavior patterns is fundamental to detect changes since these can signal health deterioration. A precise model needs to consider variations implied by the fact that human behavior has an stochastic nature and is affected by context conditions. In this paper, we model behavior patterns as usual activity start times. We introduce a Frequent Pattern Mining algorithm to estimate probable start times and their variations due to context conditions using only one single scan of the activity data stream. Experimentation using the Aruba CASAS and the Contex-tAct@A4H datasets and comparison with a Gaussian Mixture Model show our proposition provides adequate results for smart home environments domains with a lower computational time complexity. This allows the evaluation of behavior variations at different context dimensions and varied granularity levels for each of them.

show abstract

“…The emergence of smart homes and wearable sensor technologies allows the nonintrusive collection of activity data [5]. Thus, health-related events such as Activities of Daily Living (ADLs, e.g., feeding, sleeping) can be captured without the patient's active participation.…”

Section: The Monitoring Of Activity Of Daily Living and Episodic Epismentioning

confidence: 99%

“…In particular, we presented a system that is able to identify behavioral changes. Nevertheless, eB2 may also be of interest in the assessment of physical activity in therapeutic programs or in the identification of ALD in the elderly [19].…”

Section: Future Applicationmentioning

confidence: 99%

“…Advances in sensors technology, and novel textile-electronic integration technics also draw new perspectives for behavior ecological assessment (BEA). Moreover, it is currently possible to find commercially available wearable sensing technologies for several wellness and clinical purposes, ranging from simple heart rate monitors (HR) to monitors of physical activity [5], rehabilitation after surgical intervention [3] or sleep quality assessment [4]. Overall, an extensive panel of physical and mental conditions (e.g., insomniac, elderly, diabetic, cardiac, with respiratory problems, etc.)…”

Section: Data Capture In Patient Environmentmentioning

confidence: 99%

See 1 more Smart Citation

Combining Continuous Smartphone Native Sensors Data Capture and Unsupervised Data Mining Techniques for Behavioral Changes Detection: A Case Series of the Evidence-Based Behavior (eB2) Study (Preprint)

Berrouiguet¹,

Ramírez²,

Barrigón³

et al. 2018

Preprint

View full text Add to dashboard Cite

Background:The emergence of smart homes and wearable sensor technologies allows the nonintrusive collection of activity data. Thus, health-related events such as Activities of Daily Living (ADLs, e.g., feeding, sleeping) can be captured without the patient's active participation. We designed a system able to perform continuous monitoring based on smartphone's native sensors and advanced machine learning and signal processing techniques.

show abstract

Unsupervised discovery of activities of daily living characterized by their periodicity and variability

Cited by 23 publications

References 39 publications

Accelerometer-based Activity Recognition: Reengineering Study

Accelerometer-based Activity Recognition: Reengineering Study

Representing and Learning Human Behavior Patterns with Contextual Variability

Combining Continuous Smartphone Native Sensors Data Capture and Unsupervised Data Mining Techniques for Behavioral Changes Detection: A Case Series of the Evidence-Based Behavior (eB2) Study (Preprint)

Contact Info

Product

Resources

About