Reproduce “MRMS-Net and LMRMS-Net: Scalable Multi-Representation Multi-Scale Networks for Time Series Classification” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Celal Alagöz, Mehmet Kurnaz, Farhan Aadil
The authors introduce MRMS-Net and LMRMS-Net for univariate time-series classification, combining transformed views of each signal with convolutional branches that capture different temporal scales. Across 142 UCR/UEA datasets, LiteMV has the highest mean accuracy and macro-F1, MRMS-Net the lowest NLL, and LMRMS-Net lower computational cost. LMRMS-Net reports accuracy of 0.827 versus Lite’s 0.828, with shorter training and test times; this does not establish a universal winner or show that early exit caused the cost difference.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.