Research map / Architectures and efficiency / RNNs and normalization
End-to-End Signal Classification in Signed Cumulative Distribution Transform Space
Abu Hasnat Mohammad Rubaiyat, Shiying Li, Xuwang Yin, Mohammad Shifat‐E‐Rabbi, Yan Zhuang, Gustavo Kunde Rohde
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 |
|---|---|---|---|
| replace single-template SCDT-NS with multi-template nearest local subspace | SCDT classifier · InsectEPGRegularTrain | accuracy (%): 73.43 -> 90.82 | Improved |
| replace single-template SCDT-NS with multi-template nearest local subspace | SCDT classifier · PLAID | accuracy (%): 58.29 -> 70.95 | Improved |
| replace single-template SCDT-NS with multi-template nearest local subspace | SCDT classifier · ECG5000 | accuracy (%): 93.4 -> 97.6 | Improved |
| use SCDT-NLS instead of 1NN-DTW | time series classifier · InsectEPGRegularTrain | accuracy (%): 82.61 -> 90.82 | Improved |
| use SCDT-NLS instead of 1NN-DTW | time series classifier · Wafer | accuracy (%): 98.16 -> 95.60 | Hurt |
| use SCDT-NLS instead of 1NN-DTW | time series classifier · PLAID | accuracy (%): 73.56 -> 70.95 | Hurt |
| use SCDT-NLS instead of LSTM-FCN | time series classifier · ECG (MLII) | accuracy (%): 66.42 -> 68.83 | Improved |
| use SCDT-NLS instead of LSTM-FCN | time series classifier · PLAID | accuracy (%): 39.57 -> 70.95 | Improved |
| use SCDT-NLS instead of 1D-VGG | time series classifier · Sonar | accuracy (%): 80.57 -> 78.85 | Hurt |
| lower MPCE with SCDT-NLS than 1NN-DTW | time series classifier · 10 datasets | MPCE: 0.049 -> 0.038 | Improved |
| apply SCDT-NLS to frequency-domain gearbox signals instead of raw time-domain signals (ablation) | SCDT-NLS · gearbox fault diagnosis | accuracy | Improved |
| use SCDT-NLS on unsegmentable raw gearbox vibration signals | SCDT-NLS · gearbox fault diagnosis (time domain) | accuracy | Hurt |
Closest papers by meaning
- IncepSeqNet: Advancing Signal Classification with Multi-Shape Augmentation (Student Abstract) (AAAI 2024 · similarity 0.80)
- Content-aware Balanced Spectrum Encoding in Masked Modeling for Time Series Classification (AAAI 2025 · similarity 0.78)
- Adaptive Estimation and Learning under Temporal Distribution Shift (ICML 2025 · similarity 0.78)
- Learning Neural Networks with Distribution Shift: Efficiently Certifiable Guarantees (ICLR 2025 · similarity 0.78)
- Learning Temporal Resolution in Spectrogram for Audio Classification (AAAI 2024 · similarity 0.78)
- Classification Diffusion Models: Revitalizing Density Ratio Estimation (NeurIPS 2024 · similarity 0.78)
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.
