Elderly activity recognition using smartphones and wearable devices

Zimmermann, Larissa Cardoso

doi:10.11606/d.55.2019.tde-10062019-080049

Cited by 2 publications

(4 citation statements)

References 46 publications

(70 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Para investigar o uso de sensores de smartphones e smartwatches no reconhecimento de atividades de pessoas idosas, Zimmermann [12] desenvolveu um conjunto de aplicativos que permitem a coleta de dados para a criação de datasets associados. Após aprovação do projeto de pesquisa (Plataforma Brasil CAAE: 57875016.3.0000.5390), em colaboração com uma gerontologista foram coletados dados de 15 mulheres e 17 homens com idade entre 60 e 75 anos enquanto realizavam as atividades de andar, correr, subir e descer escada, sentar e levantar -classificadas como atividades simples por Eun et al [5].…”

Section: Eardb Datasetunclassified

“…Para medir a acurácia do classificador no reconhecimento online de atividades, foi desenvolvida uma extensão (Figura 5) para um aplicativo de coleta de dados de Zimmermann [12]. Considerando os resultados reportados na seção anterior, na extensão foi implementado o algoritmo KNN com as características diff, mean_Ax, mean_Ay, mean_Az, std_Ax, std_Ay e std_Az (subconjunto #4) para classificar as atividades de sentar, ficar em pé, andar, descer escada e subir escada.…”

Section: Online Activity Recognitionunclassified

“…Utilizando o dataset EARDB [12], com dados capturados de 32 idosos enquanto realizam as atividades selecionadas, implementamos algoritmos de aprendizado de máquina que obtiveram acurácia de reconhecimento das atividades de 98.92% em processamento a posteriori. Como requisito para realizar o reconhecimento online com usuários idosos, investigamos a possibilidade do reconhecimento ser feito online por uma smartphone app que processa dados capturados do acelerômetro de um smartwatch.…”

Section: Introductionunclassified

See 2 more Smart Citations

Applying Machine Learning Techniques in Older People Activity Recognition usingWearable and Mobile Devices

Santana¹,

Rasteiro²,

Zimmermann³

et al. 2019

Anais Estendidos Do Simpósio Brasileiro De Sistemas Multimídia E Web (WebMedia)

Self Cite

View full text Add to dashboard Cite

We investigate the potential of the combined use of smartwatch accelerometer data and smartphone apps for online older adultsactivity recognition.We selected machine learning algorithms which resulted in a posteriori recognition accuracy of 98.92%. Our smartphone app, with the selected machine learning algorithms, carried out online recognition from data captured on the smartwatch. These results allow us, as future work, assess the accuracy of online recognition when the system is used by older adults.

show abstract

Section: Eardb Datasetunclassified

Section: Online Activity Recognitionunclassified

Section: Introductionunclassified

See 1 more Smart Citation

Applying Machine Learning Techniques in Older People Activity Recognition usingWearable and Mobile Devices

Santana¹,

Rasteiro²,

Zimmermann³

et al. 2019

Anais Estendidos Do Simpósio Brasileiro De Sistemas Multimídia E Web (WebMedia)

Self Cite

View full text Add to dashboard Cite

show abstract

“…For this reason, a correct recognition of activities in real time is important for an appropriate intervention, when required [13]. All these circumstances represent the need to establish a mechanism that monitors the behaviour patterns of this group of people [14] Electronics 2023, 12, 4772 2 of 24 through activity recognition technologies and algorithms [15]. Detecting an absence of activity is also very important as it can provide very important information about the user.…”

Section: Introductionmentioning

confidence: 99%

An Unsupervised Method to Recognise Human Activity at Home Using Non-Intrusive Sensors

Gómez-Ramos,

Duque-Domingo,

Zalama

et al. 2023

Electronics

View full text Add to dashboard Cite

As people get older, living at home can expose them to potentially dangerous situations when performing everyday actions or simple tasks due to physical, sensory or cognitive limitations. This could compromise the residents’ health, a risk that in many cases could be reduced by early detection of the incidents. The present work focuses on the development of a system capable of detecting in real time the main activities of daily life that one or several people can perform at the same time inside their home. The proposed approach corresponds to an unsupervised learning method, which has a number of advantages, such as facilitating future replication or improving control and knowledge of the internal workings of the system. The final objective of this system is to facilitate the implementation of this method in a larger number of homes. The system is able to analyse the events provided by a network of non-intrusive sensors and the locations of the residents inside the home through a Bluetooth beacon network. The method is built upon an accurate combination of two hidden Markov models: one providing the rooms in which the residents are located and the other providing the activity the residents are carrying out. The method has been tested with the data provided by the public database SDHAR-HOME, providing accuracy results ranging from 86.78% to 91.68%. The approach presents an improvement over existing unsupervised learning methods as it is replicable for multiple users at the same time.

show abstract

Elderly activity recognition using smartphones and wearable devices

Cited by 2 publications

References 46 publications

Applying Machine Learning Techniques in Older People Activity Recognition usingWearable and Mobile Devices

Applying Machine Learning Techniques in Older People Activity Recognition usingWearable and Mobile Devices

An Unsupervised Method to Recognise Human Activity at Home Using Non-Intrusive Sensors

Contact Info

Product

Resources

About