Summary of A Multimodal Intermediate Fusion Network with Manifold Learning For Stress Detection, by Morteza Bodaghi et al.
A Multimodal Intermediate Fusion Network with Manifold Learning for Stress Detection
by Morteza Bodaghi, Majid Hosseini, Raju Gottumukkala
First submitted to arxiv on: 12 Mar 2024
Categories
- Main: Computer Vision and Pattern Recognition (cs.CV)
- Secondary: Artificial Intelligence (cs.AI)
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 paper introduces an intermediate multimodal fusion network with manifold learning-based dimensionality reduction for stress detection. The proposed network generates independent representations from biometric signals and facial landmarks using 1D-CNN and 2D-CNN, which are then fused and fed to another 1D-CNN layer followed by a fully connected dense layer. The authors compared various dimensionality reduction techniques for different variations of unimodal and multimodal networks and found that the intermediate-level fusion with Multi-Dimensional Scaling (MDS) manifold method showed promising results with an accuracy of 96.00% in a Leave-One-Subject-Out Cross-Validation (LOSO-CV) paradigm. The MDS method had the highest computational cost among manifold learning methods, but reduced the computational cost by 25% compared to conventional feature selection methods. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The paper makes a deep learning network that combines different types of signals to better detect stress. This is useful because stress detection is important for our health and well-being. The network uses special techniques to reduce the amount of information it needs to process, which makes it faster and more efficient. The authors tested their network with many different variations and found that one way they combined the information worked really well, giving an accuracy of 96%. This was better than other ways they tried, and it was also faster. |
Keywords
» Artificial intelligence » Cnn » Deep learning » Dimensionality reduction » Feature selection » Manifold learning
