Research map / Time series / Causal and generative time series
Functional MRI Time Series Generation via Wavelet-Based Image Transform and Spectral Flow Matching for Brain Disorder Identification
Hwa Hui Tew, Junn Yong Loo, Leong Fang Yu, Julia K. Lau, Ding Fan, Hernando Ombao, Raphael CW Phan, Chee Pin Tan, Chee-Ming Ting
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add DSFM synthetic data augmentation (1x) | BrainNetCNN · MDD | accuracy: 58.90 -> 70.84 | Improved |
| add DSFM synthetic data augmentation (1x) | BrainNetCNN · ABIDE | accuracy: 64.67 -> 71.54 | Improved |
| add Vanilla-GAN augmentation | BrainNetCNN · MDD | accuracy: 58.90 -> 58.86 | No clear effect |
| use ECS normalization instead of MinMax (ablation) | DSFM · MDD | Context-FID: 1.505 -> 0.098 | Improved |
| use ECS normalization instead of MinMax (ablation) | DSFM · MDD | Correlational score: 57.3 -> 18.2 | Improved |
| use block size 4 instead of 2 (ablation) | DSFM · MDD | Context-FID: 0.121 -> 0.098 | No clear effect |
| use Haar instead of dB-4 wavelet (ablation) | DSFM · MDD | Context-FID: 0.199 -> 0.098 | No clear effect |
| use wavelet plus DCT spectral flow matching instead of Fourier (ablation) | DSFM · MDD | Correlational score: 107.90 -> 18.20 | Improved |
| use flow matching instead of diffusion on wavelet representation (ablation) | DSFM · MDD | Context-FID: 3.57 -> 2.19 | Improved |
| add dual-spectral DCT stage to wavelet flow matching (ablation) | DSFM · MDD | Context-FID: 2.19 -> 0.10 | Improved |
| include mid-frequency LH3 and LH4 subbands (ablation) | DSFM FC classification · MDD | accuracy: 63.30 -> 70.84 | Improved |
| include LL and LH5 high-pass subbands (vs. high-pass setting) (ablation) | DSFM FC classification · MDD | accuracy: 65.40 -> 70.84 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- Diffusion-TS — Diffusion-TS: Interpretable Diffusion for General Time Series Generation (ICLR 2024) · better on 3 of 4 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- FAST-Brain: A Flow-Aligned Spatio-Temporal Surrogate Brain Model (NeurIPS 2026 · similarity 0.88)
- Brain-OF: An Omnifunctional Foundation Model for fMRI, EEG and MEG (NeurIPS 2026 · similarity 0.86)
- A scalable generative model for dynamical system reconstruction from neuroimaging data (NeurIPS 2024 · similarity 0.86)
- B[FM]$^2$: Brain Foundation Model via Flow Matching with SplitUNet (NeurIPS 2026 · similarity 0.85)
- NeuroBOLT: Resting-state EEG-to-fMRI Synthesis with Multi-dimensional Feature Mapping (NeurIPS 2024 · similarity 0.85)
- A Compact Implicit Neural Representation for Efficient Storage of Massive 4D Functional Magnetic Resonance Imaging (AAAI 2025 · similarity 0.84)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
