@inproceedings{hartmann2021featurespace,
  title = {Feature Space Reduction for Human Activity Recognition based on Multi-channel Biosignals},
  author = {Hartmann, Yale and Liu, Hui and Schultz, Tanja},
  booktitle = {Proceedings of the 14th International Joint Conference on Biomedical Engineering Systems and Technologies (BIOSTEC 2021)},
  pages = {215--222},
  organization = {INSTICC},
  publisher = {SCITEPRESS - Science and Technology Publications},
  year = {2021},
  isbn = {978-989-758-490-9},
  issn = {2184-4305},
  doi = {10.5220/0010260802150222},
  url = {https://www.csl.uni-bremen.de/cms/images/documents/publications/HartmannLiuSchultz_Biosignals2021.pdf},
  abstract = {In this paper, we study the effect of Feature Space Reduction for the task of Human Activity Recognition (HAR). For this purpose, we investigate a Linear Discriminant Analysis (LDA) trained with Hidden Markov Models (HMMs) force-aligned targets. HAR is a typical application of machine learning, which includes finding a lower-dimensional representation of sequential data to address the curse of dimensionality. This paper uses three datasets (CSL19, UniMiB, and CSL18), which contain data recordings from humans performing more than 16 everyday activities. Data were recorded with wearable sensors integrated into two devices, a knee bandage and a smartphone. First, early-fusion baselines are trained, utilizing an HMM-based approach with Gaussian Mixture Models to model the emission probabilities. Then, recognizers with feature space reduction based on stacking combined with an LDA are evaluated and compared against the baseline. Experimental results show that feature space reduction improves balanced accuracy by ten percentage points on the UniMiB and seven points on the CSL18 datasets while remaining the same on the CSL19 dataset. The best recognizers achieve 93.7 ± 1.4{\%} (CSL19), 69.5 ± 8.1{\%} (UniMiB), and 70.6 ± 6.0{\%} (CSL18) balanced accuracy in a leave-one-person-out cross-validation.}
}