Package: PhysioML
Title: Leakage-Aware Machine Learning for Physiological Time Series
Version: 0.4.2
Authors@R: 
    person(given = "Yusuke",
           family = "Matsui",
           role = c("aut", "cre"),
           email = "mail.to.matsui@gmail.com")
Description: Provides leakage-aware, reproducible feature transforms
        and reference deep-learning workflows for physiological time
        series stored in PhysioExperiment objects. Canonical catch22
        characteristics are computed through the official R backend,
        while ROCKET and MiniRocket transforms use guarded optional
        Python backends. Guarded optional torch and luz backends
        provide case-aware datasets, compact neural architectures,
        training, and prediction. Explicit contracts preserve case,
        channel, feature, normalization, backend, and model provenance
        without claiming clinical validation. Named transfer-learning
        policies, leakage-safe CORAL alignment, and immutable
        hash-verified foundation-model caches provide bounded reuse
        across domains.
Depends: R (>= 4.2), PhysioExperiment (>= 2.0.0)
Imports: digest, jsonlite, methods, S4Vectors, SummarizedExperiment,
        stats
Suggests: PhysioCore, Rcatch22, reticulate, torch, luz, testthat (>=
        3.2.0), knitr, rmarkdown
License: MIT + file LICENSE
Encoding: UTF-8
Roxygen: list(markdown = TRUE)
VignetteBuilder: knitr
Config/testthat/edition: 3
Collate: 'PhysioML-package.R' 'feature-input.R' 'features-catch22.R'
        'features-rocket.R' 'reduced-features.R' 'torch-input.R'
        'torch-dataset.R' 'torch-models.R' 'torch-train.R'
        'torch-predict.R' 'onnx-contract.R' 'onnx-export.R'
        'onnx-import.R' 'onnx-predict.R' 'transfer.R' 'domain-adapt.R'
        'foundation-cache.R' 'foundation.R' 'zzz.R'
URL: https://github.com/x-biosignal/PhysioML,
        https://x-biosignal.r-universe.dev/PhysioML,
        https://x-biosignal.github.io/PhysioML/
BugReports: https://github.com/x-biosignal/PhysioML/issues
Config/roxygen2/version: 8.0.0
RoxygenNote: 7.3.3
Config/pak/sysreqs: zlib1g-dev
Repository: https://x-biosignal.r-universe.dev
Date/Publication: 2026-10-03 13:11:43 UTC
RemoteUrl: https://github.com/x-biosignal/PhysioML
RemoteRef: HEAD
RemoteSha: 9d10f45581685a9592b0846fe7d16ff93741ad30
NeedsCompilation: no
Packaged: 2026-10-03 13:41:58 UTC; root
Author: Yusuke Matsui [aut, cre]
Maintainer: Yusuke Matsui <mail.to.matsui@gmail.com>