Reproduce “Computation harvesting in road traffic dynamics” 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
Hiroyasu Ando, T. Okamoto, H. Chang, T. Noguchi, Shinji Nakaoka
Computation harvesting treats observed traffic time series as a computational substrate, using naturally occurring dynamics from multiple intersections and a ridge-regression linear readout to predict traffic entering intersection 5e. For Day 1, at forecast horizon τ=7, its NRMSE was 0.526, versus 0.651 for an autoregressive model; this is one tested setting, not evidence of broad superiority.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.