Fall recognition system using feature selection and SVM: an empirical study

Maldonado-Mendez, Carolina; Hernandez-Mendez, Sergio

doi:10.1109/conielecomp.2019.8673195

Cited by 4 publications

(3 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In [34], the authors decided to use only seven actions and to exclude the grasp action. They calculated the speed and acceleration in 20-frame windows, and then selected eight features using GA. Fourteen samples (two sequences of each action) were used for feature selection, and the remaining 217 samples (31 sequences of each action) were used to train and test the model.…”

Section: ) Comparison With Results Using the Tst V2 Datasetmentioning

confidence: 99%

See 1 more Smart Citation

Vision-Based Fall Detection Using ST-GCN

Keskes

Noumeir

2021

IEEE Access

View full text Add to dashboard Cite

Falls are a growing issue in society and has become a hot topic in the healthcare domain. Falls are more likely to occur to due to age or health problems such as cardiovascular issues and muscle weakness. In this work we focus on fall detection. The aftereffects of falls often lead to the use of prescription pain medications. We are motivated to help prevent suicide attempts by overdose in the Canadian correctional services. Most previous studies were based on hand-crafted features which limit the robustness and generality of the system. We therefore propose a general vision-based system, using Spatial Temporal Graph Convolutional Networks (ST-GCN). This system has proven its efficiency and robustness in the action recognition domain. Contrary to previous works, this model can be applied directly to new data without the need to retrain the model while offering good accuracy. Additionally, with the help of transfer learning we can solve the insufficient data problem. By using three public datasets: the NTU RGB-D dataset, the TST Fall detection dataset v2 and the Fallfree dataset to validate our method, we achieved a 100% accuracy, surpassing the state-of-the-art.

show abstract

Section: ) Comparison With Results Using the Tst V2 Datasetmentioning

confidence: 99%

“…They contain different types of falls and ADL actions. In addition, they have been used to evaluate fall detection algorithms [20], [29] [28], [31] [32], [33] [22], [34] [35]. Both of these aspects make them good options with which to evaluate our method.…”

Section: B Datasetmentioning

confidence: 99%

Vision-Based Fall Detection Using ST-GCN

Keskes

Noumeir

2021

IEEE Access

View full text Add to dashboard Cite

show abstract

“…In addition to the elderly, another category of people which is considerably affected by falls incidents is workers. According to reports established by (i) the Occupational Safety and Health Administration [6] and (ii) the United States Department of Labor Statistics [7], more than 247,120 non-fatal cases of falls and trips have been recorded causing nearly 800 deaths in 2014 alone.…”

Section: Introduction and Related Workmentioning

confidence: 99%

A Survey on Recent Advances in Fall Detection Systems Using Machine Learning Formalisms

Zerrouki

Harrou

Sun

et al. 2022

2022 7th International Conference on Frontiers of Signal Processing (ICFSP)

View full text Add to dashboard Cite

As reported by numerous World Health Organization studies, fall incidents are considered one of the leading causes of loss of autonomy, injuries, and even deaths, and this is not only among elderly people but also in other categories such as workers. Fall incidents also have a considerable impact on the budget allocated to the care of people suffering from the effects of falls. This work presents a comprehensive review of state-of-the-art fall detection technologies considering the most powerful machine learning methodologies, both classical formalism (shallow methods), and approaches based on deep learning formalism. The authors reviewed the most recent and effective methods for fall detection and presented the used sensors, cameras, applied pre-treatments, generated attributes, and algorithms used in this field of application. The present work is completed by a discussion presenting some limitations that need to be analyzed and taken into account to further improve the quality of fall detection and reduce their impacts.

show abstract