Keywords: Independent Components Analysis (ICA) Validation Durbin-Watson criterionIndependent Components Analysis is a Blind Source Separation method that aims to find the pure source signals mixed together in unknown proportions in the observed signals under study. It does this by searching for factors which are mutually statistically independent. It can thus be classified among the latent-variable based methods. Like other methods based on latent variables, a careful investigation has to be carried out to find out which factors are significant and which are not. Therefore, it is important to dispose of a validation procedure to decide on the optimal number of independent components to include in the final model. This can be made complicated by the fact that two consecutive models may differ in the order and signs of similarly-indexed ICs. As well, the structure of the extracted sources can change as a function of the number of factors calculated. Two methods for determining the optimal number of ICs are proposed in this article and applied to simulated and real datasets to demonstrate their performance.

The study of temperature gradients in cold stores and containers is a critical issue in the food industry for the quality assurance of products during transport, as well as for minimizing losses. The objective of this work is to develop a new methodology of data analysis based on phase space graphs of temperature and enthalpy, collected by means of multidistributed, low cost and autonomous wireless sensors and loggers. A transoceanic refrigerated transport of lemons in a reefer container ship from Montevideo (Uruguay) to Cartagena (Spain) was monitored with a network of 39 semi-passive TurboTag RFID loggers and 13 i-button loggers. Transport included intermodal transit from transoceanic to short shipping vessels and a truck trip. Data analysis is carried out using qualitative phase diagrams computed on the basis of Takens which characterizes the cyclic behaviour of temperature. Areas within the enthalpy phase diagram computed for the short sea shipping transport were 5 times higher than those computed for the long sea shipping, with coefficients of variation above 100 % for both periods. This new methodology for data analysis highlights the significant heterogeneity of thermohygrometric conditions at different locations in the container.

No abstract

The viability of Near Infra Red (NIR) Spectrometry for internal quality assessment in fruit and vegetables is accepted world wide even for real-time applications. However, the transfer of technology to the agroindustry is still a challenge due to a high number of uncontrolled sources of variation which modify the spectral information, and reduce the accuracy of estimations. Some of these sources of variation are: the internal temperature of the product and the spectrometer (Hernández-Sánchez et al., 2003), the skin thickness (Krivoshiev et al., 2000), and the presence of boundary layers and voids inside the product (Fraser et al., 2003).A main issue when developing a new NIR application is selection of the interaction mode between the light and the sample: reflectance, interactance or transmittance. The interactance mode, though it is the most difficult situation for online implementation, has shown encouraging results for obtaining good predictive models (Schaare and Fraser, 2000). AbstractThe transfer of NIR spectroscopy to industry relies on the possibility of real time identification of abnormal spectra as well as uncontrolled sources of variation. This study proposes an unsupervised procedure for the identification under an industrial application of daily events (general changes) and abnormal observations. It consists in defining a spectral database at the beginning of a season, performing a principal component (PC) analysis, and calculating the PC scores over time. Process control statistics (Hotelling T 2 , Q) are used for multivariate supervision of the industrial application. Within this procedure 10,400 average spectra of onion bulbs were evaluated identifying events in 12 out of 66 work dates, as well as spectral trends throughout the season of 2002.

No abstract