Activity recognition from acceleration data based on discrete consine transform and SVM
By Zhenyu He, Lianwen Jin. IEEE International Conference on Systems, Man and Cybernetics, 2009
304 citations recorded by the source corpus.
Subfields: Artificial Intelligence, Biomedical Engineering, Computer Vision and Pattern Recognition
View Paper: https://www.semanticscholar.org/paper/95f0bbfc41fab715cb88bb31a66b08115758bb8b
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Miguel A. Labrador
- Oscar D. Lara
- Senem Velipasalar
- Geyong Min
- Yuqing Chen
- Yu Zheng
- Lida Xu
- Koray Ozcan
In Biomedical Engineering
- Oscar D. Lara
- Miguel A. Labrador
- Senem Velipasalar
- Yuqing Chen
- Yu Zheng
- Lida Xu
- Koray Ozcan
- Maria Cornacchia
In Computer Vision and Pattern Recognition
- Miguel A. Labrador
- Ignacio Rojas
- Miguel Damas
- Oscar D. Lara
- Senem Velipasalar
- Héctor Pomares
- Oresti Banos
- Yuqing Chen
Citations in the corpus
- A Deep Learning Approach to Human Activity Recognition Based on Single Accelerometer (2015, methodology): “There are also some other features like Principal Component Analysis (PCA) [6], Autoregressive Model (AR) [5] and Haar filters [10], which have been used in experiments and returned good results.”
- Window Size Impact in Human Activity Recognition (2014, background): “Less obtrusively, in [15], the subjects are asked to stand still for a few seconds to better identify the start and stop of each activity.”
- Convolutional Neural Networks for human activity recognition using mobile sensors (2014, methodology): “The PCA based on empirical cumulative distribution function (ECDF) is proposed [23] to preserve structural information of the signal.”
- A Survey on Activity Detection and Classification Using Wearable Sensors (2017, methodology): “Works such as those by Mantyjarvi et al. [25], Song et al. [40], He et al. [48], and He and Jin [49] employed these limited feature sets with a single selected classification algorithm.”
- A Survey on Human Activity Recognition using Wearable Sensors (2013, methodology): “Several papers have reported high recognition accuracy 92.25% [29], 95% [38], 97% [35], and up to 98% [39], under different evaluation methodologies.”
- Advanced internet of things for personalised healthcare systems: A survey (2017, background): “Likewise, SVM is capable to address the issue of either wearable sensors for precisely observing abnormal activities [121], or static postures detection for healthcare measurement [102], as well as in clinical outcome classification and prediction (e.g., disease diagnosis) [31].”