bus: Automatic vehicle recognition data

In rrcov: Scalable Robust Estimators with High Breakdown Point

Automatic vehicle recognition data

Description

The data set bus (Hettich and Bay, 1999) corresponds to a study in automatic vehicle recognition (see Maronna et al. 2006, page 213, Example 6.3)). This data set from the Turing Institute, Glasgow, Scotland, contains measures of shape features extracted from vehicle silhouettes. The images were acquired by a camera looking downward at the model vehicle from a fixed angle of elevation. Each of the 218 rows corresponds to a view of a bus silhouette, and contains 18 attributes of the image.

Usage

data(bus)

Format

A data frame with 218 observations on the following 18 variables:

V1

compactness

V2

circularity

V3

distance circularity

V4

radius ratio

V5

principal axis aspect ratio

V6

maximum length aspect ratio

V7

scatter ratio

V8

elongatedness

V9

principal axis rectangularity

V10

maximum length rectangularity

V11

scaled variance along major axis

V12

scaled variance along minor axis

V13

scaled radius of gyration

V14

skewness about major axis

V15

skewness about minor axis

V16

kurtosis about minor axis

V17

kurtosis about major axis

V18

hollows ratio

Source

Hettich, S. and Bay, S.D. (1999), The UCI KDD Archive, Irvine, CA:University of California, Department of Information and Computer Science, 'http://kdd.ics.uci.edu'

References

Maronna, R., Martin, D. and Yohai, V., (2006). Robust Statistics: Theory and Methods. Wiley, New York.

Examples

    ## Reproduce Table 6.3 from Maronna et al. (2006), page 213
    data(bus)
    bus <- as.matrix(bus)
    
    ## calculate MADN for each variable
    xmad <- apply(bus, 2, mad)      
    cat("\nMin, Max of MADN: ", min(xmad), max(xmad), "\n")


    ## MADN vary between 0 (for variable 9) and 34. Therefore exclude 
    ##  variable 9 and divide the remaining variables by their MADNs.
    bus1 <- bus[, -9]
    madbus <- apply(bus1, 2, mad)
    bus2 <- sweep(bus1, 2, madbus, "/", check.margin = FALSE)

    ## Compute classical and robust PCA (Spherical/Locantore, Hubert, MCD and OGK)    
    pca  <- PcaClassic(bus2)
    rpca <- PcaLocantore(bus2)
    pcaHubert <- PcaHubert(bus2, k=17, kmax=17, mcd=FALSE)
    pcamcd <- PcaCov(bus2, cov.control=CovControlMcd())
    pcaogk <- PcaCov(bus2, cov.control=CovControlOgk())

    ev    <- getEigenvalues(pca)
    evrob <- getEigenvalues(rpca)
    evhub <- getEigenvalues(pcaHubert)
    evmcd <- getEigenvalues(pcamcd)
    evogk <- getEigenvalues(pcaogk)

    uvar    <- matrix(nrow=6, ncol=6)
    svar    <- sum(ev)
    svarrob <- sum(evrob)
    svarhub <- sum(evhub)
    svarmcd <- sum(evmcd)
    svarogk <- sum(evogk)
    for(i in 1:6){
        uvar[i,1] <- i
        uvar[i,2] <- round((svar - sum(ev[1:i]))/svar, 3)
        uvar[i,3] <- round((svarrob - sum(evrob[1:i]))/svarrob, 3)
        uvar[i,4] <- round((svarhub - sum(evhub[1:i]))/svarhub, 3)
        uvar[i,5] <- round((svarmcd - sum(evmcd[1:i]))/svarmcd, 3)
        uvar[i,6] <- round((svarogk - sum(evogk[1:i]))/svarogk, 3)
    }
    uvar <- as.data.frame(uvar)
    names(uvar) <- c("q", "Classical","Spherical", "Hubert", "MCD", "OGK")
    cat("\nBus data: proportion of unexplained variability for q components\n")
    print(uvar)
 
    ## Reproduce Table 6.4 from Maronna et al. (2006), page 214
    ##
    ## Compute classical and robust PCA extracting only the first 3 components
    ## and take the squared orthogonal distances to the 3-dimensional hyperplane
    ##
    pca3 <- PcaClassic(bus2, k=3)               # classical
    rpca3 <- PcaLocantore(bus2, k=3)            # spherical (Locantore, 1999)
    hpca3 <- PcaHubert(bus2, k=3)               # Hubert
    dist <- pca3@od^2
    rdist <- rpca3@od^2
    hdist <- hpca3@od^2

    ## calculate the quantiles of the distances to the 3-dimensional hyperplane
    qclass  <- round(quantile(dist, probs = seq(0, 1, 0.1)[-c(1,11)]), 1)
    qspc <- round(quantile(rdist, probs = seq(0, 1, 0.1)[-c(1,11)]), 1)
    qhubert <- round(quantile(hdist, probs = seq(0, 1, 0.1)[-c(1,11)]), 1)
    qq <- cbind(rbind(qclass, qspc, qhubert), round(c(max(dist), max(rdist), max(hdist)), 0))
    colnames(qq)[10] <- "Max"
    rownames(qq) <- c("Classical", "Spherical", "Hubert")
    cat("\nBus data: quantiles of distances to hiperplane\n")
    print(qq)

    ## 
    ## Reproduce Fig 6.1 from Maronna et al. (2006), page 214
    ## 
    cat("\nBus data: Q-Q plot of logs of distances to hyperplane (k=3) 
    \nfrom classical and robust estimates. The line is the identity diagonal\n")
    plot(sort(log(dist)), sort(log(rdist)), xlab="classical", ylab="robust")
    lines(sort(log(dist)), sort(log(dist)))
   
    

rrcov documentation built on May 29, 2024, 1:13 a.m.