Hierarchical SVM structure and support vector memory optimization achieve up to 56% memory savings in activity recognition experiments, with a controllable accuracy trade-off.
Low-energy formulations of support vector machine kernel functions for biomedical sensor applications,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2019 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Resource-Efficient Computing in Wearable Systems
Hierarchical SVM structure and support vector memory optimization achieve up to 56% memory savings in activity recognition experiments, with a controllable accuracy trade-off.