Summary of Sangria: Stacked Autoencoder Neural Networks with Gradient Boosting For Indoor Localization, by Danish Gufran et al.
SANGRIA: Stacked Autoencoder Neural Networks with Gradient Boosting for Indoor Localization
by Danish Gufran, Saideep Tiku, Sudeep Pasricha
First submitted to arxiv on: 3 Mar 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Artificial Intelligence (cs.AI); Signal Processing (eess.SP)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary A novel fingerprinting-based framework called SANGRIA is proposed for indoor localization, using stacked autoencoder neural networks with gradient boosted trees. This approach addresses the device heterogeneity challenge that can lead to uncertainty in wireless signal measurements across embedded devices used for localization. Compared to several state-of-the-art frameworks, SANGRIA demonstrates a 42.96% lower average localization error across diverse indoor locales and heterogeneous devices. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Indoor localization is important for many applications like tracking assets or navigating in real-time. A new method called SANGRIA helps solve this problem by using special types of neural networks and trees. This makes it better at working with different devices that can be used for localization. SANGRIA is compared to other methods and does a lot better, lowering the error rate by 42.96%. |
Keywords
* Artificial intelligence * Autoencoder * Tracking
