KMITL

Permanent URI for this communityhttps://dspace.kmitl.ac.th/handle/123456789/1

Browse

Settings

Has files: NoSubject: search.filters.subject.Discriminant analysis

Search Results

Now showing 1 - 2 of 2
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Publication,
    Use of near infrared hyperspectral imaging as a nondestructive method of determining and classifying shelf life of cakes
    (2021-01-01)
    Sricharoonratana, Manunchaya
    ;
    Thompson, Anthony Keith
    ;
    Teerachaichayut, Sontisuk
    Many types of cake deteriorated rapidly due to microbial infection, which gives them a short shelf life. Accordingly, near-infrared hyperspectral imaging (NIR-HSI), in the range of range of 935–1720 nm, was tested to determinate whether it could be used as a nondestructive method to determine the shelf life and classify cakes based on microorganism infections during storage. The average spectrum from a region of interest (ROI) in the spectral image of each sample was acquired by NIR-HSI. Partial least squares regression (PLSR) was used to establish the model in order to predict storage time of sponge cakes. The model proved accurate with a correlation coefficient (R) of 0.835 and the root mean square error of prediction (RMSEP) of 1.242 days. Partial least squares discriminant analysis (PLS-DA) was applied to establish the classification model for distinguishing between non-expired and expired of sponge cakes. The results showed the accuracy of prediction was 91.3%. The predictive images showed different colors based on their storage time that could be inspected visually. Therefore NIR-HSI was shown to have potential to be used for predicting storage time of cakes and classifying cakes into expired and non-expired, which has potential for application in the bakery industry.
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Publication,
    Minimally destructive assessment of mangosteen translucency based on electrical impedance measurements
    (2016-02-01)
    Nakawajana, Natrapee
    ;
    Terdwongworakul, Anupun
    ;
    Teerachaichayut, Sontisuk
    Electrical impedance spectroscopy in a frequency range of 1 kHz-200 kHz was studied to develop a classifying model for translucent mangosteen. The optimal configuration of the measurement was investigated. Transverse alignment of two measuring needles with the stem-calyx axis and with the measured position on the part of the pericarp pertinent to the largest flesh segment proved to be the optimal configuration. The optimal electrical parameters were selected at frequencies of 1, 4, 7, 8, 14, 47, 73, and 81 kHz as the classifying variables based on the student t-test analysis for a significant difference between the normal and translucent mangosteen and the largest difference of the average values of the electrical parameters. The differences in the electrical parameters and their reciprocals were the optimal classifying variables. The model constructed from the samples from two seasons was robust in terms of seasonality, providing a classification accuracy of 82.7%. The difference in the initial moisture content of the pericarp was justifiably compensated by the differences in the electrical parameters. The EIS technique was suitable for measurement of mangosteen samples at the maturity color stage in which the sample contained no yellow latex in the pericarp.