Research map / Time series / Causal and generative time series
Evolving Markov Chains: Online Mode Discovery and Recognition From Data Streams
Kutalmış Coşkun, Borahan Tümer, Bjarne C. Hiller, Martin Becker
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 |
|---|---|---|---|
| use online EMC instead of offline EPSTM with true change points | mode discovery on synthetic streams · Synthetic mode discovery and recognition | ARI: 0.98 -> 0.85 | Hurt |
| give EPSTM change points delayed by EMC's mean recognition lag | EPSTM · Synthetic mode discovery and recognition | ARI | Hurt |
| count only predictions made in steady condition (phi=1) for ARI | EMC · EEG Eye State | ARI: ARI becomes 0.9 | Improved |
| use longer sliding window as regime duration grows | MC-SW · Synthetic probability tracking | MAE of conditional probabilities | Improved |
| use adaptive ADWIN window instead of fixed window | MC-SW · Synthetic probability tracking | MAE of conditional probabilities | Hurt |
| use stream clustering (CluStream, DBStream) instead of temporal Markov modeling | mode discovery · Synthetic mode discovery and recognition | ARI | Hurt |
Closest papers by meaning
- Mixture of Switching Linear Dynamics to Discover Behavior Patterns in Object Tracks (TPAMI 2016 · similarity 0.86)
- Learning system dynamics without forgetting (ICLR 2025 · similarity 0.84)
- Identifying latent state transitions in non-linear dynamical systems (ICLR 2025 · similarity 0.83)
- Mechanistic Interpretability of RNNs emulating Hidden Markov Models (NeurIPS 2025 · similarity 0.83)
- Probabilistic Decomposed Linear Dynamical Systems for Robust Discovery of Latent Neural Dynamics (NeurIPS 2024 · similarity 0.83)
- Learning Time-Varying Multi-Region Brain Communications via Scalable Markovian Gaussian Processes (ICML 2025 · similarity 0.83)
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.
