Summary of Multi-agent Based Transfer Learning For Data-driven Air Traffic Applications, by Chuhao Deng and Hong-cheol Choi and Hyunsang Park and Inseok Hwang
Multi-Agent Based Transfer Learning for Data-Driven Air Traffic Applications
by Chuhao Deng, Hong-Cheol Choi, Hyunsang Park, Inseok Hwang
First submitted to arxiv on: 23 Jan 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Multiagent Systems (cs.MA); Systems and Control (eess.SY); Machine Learning (stat.ML)
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 The proposed Multi-Agent Bidirectional Encoder Representations from Transformers (MA-BERT) model addresses long training times and limited datasets by leveraging air traffic controllers’ decisions. A pre-training and fine-tuning transfer learning framework is developed to leverage large datasets, saving significant training time. This framework enables high-performance models for newly adopted procedures and constructed airports with minimal data. The MA-BERT is tested on automatic dependent surveillance-broadcast data from three South Korean airports in 2019. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Air traffic control uses special computers to manage planes safely taking off and landing. These computers need lots of training data to work well, but that can take a long time. Researchers created a new model called MA-BERT that helps these computers learn by considering how air traffic controllers make decisions. They also developed a way to train the model using existing data from one airport and then fine-tune it for other airports. This means they can create models quickly for new airports or procedures without needing lots of data. |
Keywords
* Artificial intelligence * Bert * Encoder * Fine tuning * Transfer learning
