The joint use of sequence features combination and modified weighted SVM for improving daily activity recognition
Abidine, Bilal M’hamed; Fergani, Lamya; Fergani, Belkacem; Oussalah, Mourad (2018-02-02)
Abidine, B.M., Fergani, L., Fergani, B. et al. The joint use of sequence features combination and modified weighted SVM for improving daily activity recognition. Pattern Anal Applic 21, 119–138 (2018). https://doi.org/10.1007/s10044-016-0570-y
© Springer-Verlag London 2016. This is a post-peer-review, pre-copyedit version of an article published in Pattern Analysis and Applications. The final authenticated version is available online at: https://doi.org/10.1007/s10044-016-0570-y.
Two serious problems affecting the implementation of human activity recognition algorithms have been acknowledged. The first one corresponds to non-informative sequence features. The second is the class imbalance in the training data due to the fact that people do not spend the same amount of time on the different activities. To address these issues, we propose a new scheme based on a combination of principal component analysis, linear discriminant analysis (LDA) and the modified weighted support vector machines. First we added the most significant principal components to the set of features extracted using LDA. This work shows that a suitable sequence feature set combined with the modified WSVM based on our criterion classifier achieves good improvement and efficiency over the traditional used methods.
- Avoin saatavuus