Commit 22b68e1d authored by Alexander Henkel's avatar Alexander Henkel
Browse files

final version

parent ba3f4871
......@@ -4,4 +4,4 @@ In this work, I have elaborated a personalization process for human activity rec
I evaluated personalization in general on a theoretical basis with supervised data. These revealed the impact of noise in the highly imbalanced data and how-soft labels can counter training errors. Based on these insights, several constellations and filter approaches for training data have been implemented to analyze the behavior of the resulting models under the different aspects. I found out that just using the predictions of the base model leads to performance decreases since they consist of too much label noise. However, even relying only on data covered by user feedback does not overcome the general model, although the training data hardly consists of false labels. Therefore more sophisticated denoising approaches are implemented that generate training data that consist of various samples with as few incorrect labels as possible. This data leads to personalized models that achieve higher F1 and S scores than the general model. Some of the configurations even result in similar performance as with supervised training.
Furthermore, I compared my personalization approach with an active learning implementation as a common personalization method. The sophisticated filter configurations achieve higher S scores, confirming my approach's robustness.\\
The real-world experiment in corporation with the University of Basel offered a great opportunity to evaluate my personalization approach to a large variety of users and their feedback behaviors. It confirms that in most cases, personalized models outperform the general model. Overall, the implemented personalization would reduce the false detections by $31\%$, and increase correct detections by $16\%$.
\ No newline at end of file
The real-world experiment in corporation with the University of Basel offered a great opportunity to evaluate my personalization approach to a large variety of users and their feedback behaviors. It confirms that in most cases, personalized models outperform the general model. Overall, the implemented personalization would reduce false detections by $31\%$, and increase correct detections by $16\%$. That leads to an increase in the estimated F1 score by ${\sim}10\%$ of the personalized model compared to the general model with adjusted kernel settings.
\ No newline at end of file
Supports Markdown
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment