Skip to content
DraconiticResearch
Search Sources API
184,937 studies31 sourcesUpdated 12 min ago
PreprintarXiv licencearXiv

StarBOA: Real-Time Mamba State-Space Unrolling for Sparse Radar Micro-Doppler in ISAC Networks

  • Mustafa Bora Çelik
  • Ceren Çelik
  • Orhan Gazi
Open at sourcePDFDOICite

Abstract

In Integrated Sensing and Communications (ISAC), radar sensing must operate under chirp subsampling with up to 90\% missing data. An attention-based baseline, limited to a 52~ms buffer, collapses toward maximum uniform entropy (H=2.584 bits) as sparsity increases, failing to capture long-range gait-cycle context. We propose StarBOA, which replaces attention with a causal Mamba state-space model that updates incrementally on a per-window basis without re-scanning past reconstructions. By maintaining a persistent state, StarBOA integrates over 100× more temporal history at no additional per-step computational cost. StarBOA outperforms the baseline's published results across all sparsity levels, with SSIM gains increasing from +0.0379 at 50\% missing data to +0.2472 at 90\%. Each window is processed in 1.53~ms with zero lookahead, demonstrating efficient causal reconstruction under extreme chirp subsampling.

Related

  1. Jacobian-Free Unrolling: memory efficient unrolled network for 3D SPECT Reconstruction
    Corentin Constanza, Théo Kaprelian, Ane Etxebeste +1
    IEEE Transactions on Radiation and Plasma Medical SciencesPeer-reviewedPublisher termsFull textSystems & synthetic biologyOptimisation & controlHAL
  2. On Associative Neural Networks for Sparse Patterns with Large Capacities
    Matthias Löwe, Franck Vermet
    Journal of Statistical PhysicsPeer-reviewedLicence not statedGeneral mathematicsHAL
  3. Sparse Bayesian Neural Networks via Sticky Piecewise Deterministic Markov Processes
    August Arnstad, Geir Olve Storvik, Filippo Pagani +1
    arXivPreprintarXiv licenceFull textStatisticsarXiv
  4. Optimizing Sparse Boolean Rule Networks using Mixed Integer Linear Programming
    Thomas Pammer, Johannes Fürnkranz, Markus Sinnl
    arXivPreprintCC BY 4.0Full textStatisticsarXiv
  5. SelectPFN: Amortized Bayesian Variable Selection for Sparse Nonlinear Regression with Prior-Data Fitted Networks
    Bin Luo
    arXivPreprintarXiv licenceFull textStatisticsarXiv

Cite

BibTeXRIS
BibTeX
@misc{celik2026starboa,
  title = {{StarBOA: Real-Time Mamba State-Space Unrolling for Sparse Radar Micro-Doppler in ISAC Networks}},
  author = {Mustafa Bora Çelik and Ceren Çelik and Orhan Gazi},
  howpublished = {arXiv},
  year = {2026},
  month = sep,
  doi = {10.48550/arxiv.2609.33408},
  eprint = {2609.33408},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2609.33408},
}
RIS
TY  - UNPB
TI  - StarBOA: Real-Time Mamba State-Space Unrolling for Sparse Radar Micro-Doppler in ISAC Networks
AU  - Mustafa Bora Çelik
AU  - Ceren Çelik
AU  - Orhan Gazi
PY  - 2026
DA  - 2026/09/27
PB  - arXiv
DO  - 10.48550/arxiv.2609.33408
UR  - https://arxiv.org/abs/2609.33408
AB  - In Integrated Sensing and Communications (ISAC), radar sensing must operate under chirp subsampling with up to 90\% missing data. An attention-based baseline, limited to a 52~ms buffer, collapses toward maximum uniform entropy (H=2.584 bits) as sparsity increases, failing to capture long-range gait-cycle context. We propose StarBOA, which replaces attention with a causal Mamba state-space model that updates incrementally on a per-window basis without re-scanning past reconstructions. By maintaining a persistent state, StarBOA integrates over 100× more temporal history at no additional per-step computational cost. StarBOA outperforms the baseline's published results across all sparsity levels, with SSIM gains increasing from +0.0379 at 50\% missing data to +0.2472 at 90\%. Each window is processed in 1.53~ms with zero lookahead, demonstrating efficient causal reconstruction under extreme chirp subsampling.
ER  -