2018 IEEE International Symposium on Medical Measurements and Applications (MeMeA) 2018
DOI: 10.1109/memea.2018.8438750
|View full text |Cite
|
Sign up to set email alerts
|

Human Activity Recognition by Wearable Sensors : Comparison of different classifiers for real-time applications

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
32
0
2

Year Published

2018
2018
2022
2022

Publication Types

Select...
4
3
1
1

Relationship

0
9

Authors

Journals

citations
Cited by 68 publications
(42 citation statements)
references
References 18 publications
0
32
0
2
Order By: Relevance
“…The feature extraction methods of the HAR system can be divided into three categories, namely, time features, frequency features, and a combination of both [9]. Jarraya et al selected 280 features from a total of 561 by means of a nonlinear Choquet integral feature selection approach, classified six basic actions by using the random forest, and finally obtained a better classification effect.…”
Section: Introductionmentioning
confidence: 99%
“…The feature extraction methods of the HAR system can be divided into three categories, namely, time features, frequency features, and a combination of both [9]. Jarraya et al selected 280 features from a total of 561 by means of a nonlinear Choquet integral feature selection approach, classified six basic actions by using the random forest, and finally obtained a better classification effect.…”
Section: Introductionmentioning
confidence: 99%
“…This architecture was deemed sufficient after the initial segmentation based on laboratory experiments and an analysis of the literature. As seen in Reference [ 36 ], an MLP implemented with 1 hidden layer, 20 neurons, 8 output classes and a sigmoid transfer function accomplishes a accuracy per subject. The data set consists of 15 healthy subjects and 8 different human activities.…”
Section: Materials and Methodsmentioning
confidence: 99%
“…To perform feature selection we used genetic algorithms (GAs), that is, heuristic algorithms belonging to the computational intelligence field. 25,26 Each GA solution was coded as a binary 24 bits vector, one bit representing a feature: a "0" in a given position identified a feature not selected whereas a "1" labeled a feature included in the final subset. Each solution of the GA was evaluated by a fitness function that measured the ability of the corresponding feature subset to obtain a Gaussian naïve Bayesian classifier able to classify metastases of the training set.…”
Section: Feature Selection and Radiomics Model Developmentmentioning
confidence: 99%