Summary of Minimally Supervised Topological Projections Of Self-organizing Maps For Phase Of Flight Identification, by Zimeng Lyu et al.
Minimally Supervised Topological Projections of Self-Organizing Maps for Phase of Flight Identification
by Zimeng Lyu, Pujan Thapa, Travis Desell
First submitted to arxiv on: 17 Feb 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Neural and Evolutionary Computing (cs.NE)
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 In this paper, researchers propose a novel approach to identifying phases of flight in general aviation using minimally supervised self-organizing maps (MS-SOMs). The method leverages nearest neighbor majority votes in the SOM U-matrix for class estimation. The proposed approach is tested on a large-scale dataset and achieves results comparable to those obtained with a naive SOM approach requiring full labeled data. Additionally, the MS-SOM is found to be more robust to class imbalance issues common in this type of data. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary In general aviation, knowing which phase of flight data is collected can help detect safety or hazardous events. The problem is that labeling this data manually is expensive and training classification models faces class imbalance problems. This paper finds a way to use just 30 labeled datapoints per class to identify phases of flight using self-organizing maps (SOMs). The new method works well even when the data is unbalanced, making it more robust than previous approaches. |
Keywords
* Artificial intelligence * Classification * Nearest neighbor * Supervised
