• Synthetic Datasets

    R package chemosensors

    The development of chemosensors package was originated in NEUROChem project with requirements of large-scale gas sensor array data to run simulations on artificial olfaction. This package introduces a software tool that allows for the design of synthetic experiments with so-called virtual gas sensor arrays.The current status on 20 Jan 2011 is a beta-development stage with a released code on the web of R-forge.

    Installation

    Chemosensors package can be installed as a regular R package from the R-Forge repository. The command to type in R:

    install.packages("chemosensors", dep=TRUE, repos="http://r-forge.r-project.org")

    That will install the latest development version with all dependencies.

    Documetation

    The R standard help pages in html format are published on this server http://neurochem.sisbio.recerca.upc.edu/public/chemosensors/html/00Index.html. That includes description of basic classes and modeling methods with code examples and figures. The pages also describe results of execution of package demos (page names start with “demo-”).

    Code examples

    You might prefer to start with the demos of the package. To see the list of available demos type in R:

    demo(package="chemosensors")

    Basic commands to generate synthetic data from a virtual sensor array could be:

    # concentration matrix of 3 gas classes: A, C and AC
    conc = matrix(0, 300, 3)
    conc[1:100, 1] = 0.05 # A
    conc[101:200, 3] = 1 # C
    conc[201:300, 1] = 0.05 # AC
    conc[201:300, 3] = 1 # AC

    # sensor array of 5 sensors with parametrized noise parameters
    sa = SensorArray(num=1:5, csd=0.1, ssd=0.1, dsd=0.1)

    # get information about the array
    print(sa)
    plot(sa)

    # generate the data
    sdata = predict(sa, conc)

    # plot the data
    plot(sa, "prediction", conc=conc)

    Datasets

    You may be interested in Public Datasets that could be useful for the benchmarking of statistical pattern recognition in artificial olfaction. These datasets will be publised asap on the license free base.