Summary of Multi-task Learning For Lung Sound & Lung Disease Classification, by Suma K V et al.
Multi-Task Learning for Lung sound & Lung disease classification
by Suma K V, Deepali Koppad, Preethi Kumar, Neha A Kantikar, Surabhi Ramesh
First submitted to arxiv on: 5 Apr 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Artificial Intelligence (cs.AI); Sound (cs.SD)
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 novel approach uses multi-task learning (MTL) to classify lung sounds and lung diseases simultaneously, leveraging four different deep learning models: 2D CNN, ResNet50, MobileNet, and Densenet. The ICBHI 2017 Respiratory Sound Database is employed to evaluate the model’s performance. The MTL for MobileNet model achieves an accuracy of 74% for lung sound analysis and 91% for lung disease classification, demonstrating the efficacy of this approach. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This research uses a new way called multi-task learning to help doctors diagnose lung diseases better. It combines four different types of deep learning models to analyze lung sounds and diseases at the same time. The team tested their method using real recordings of lung sounds from 2017. Their best model got accurate results for both sound analysis and disease classification, showing that this approach can be helpful. |
Keywords
* Artificial intelligence * Classification * Cnn * Deep learning * Multi task
