Self Organising Maps for variable selection: Application to human saliva analysed by nuclear magnetic resonance spectroscopy to investigate the effect of an oral healthcare product

SOMs (Self Organising Maps) are derived from the machine learning literature and serve as a valuable method for representing data. In this paper, the use of SOMs as a technique for determining the most significant variables (or markers) in a dataset is described. The method is applied to the NMR spectra of 96 human saliva samples, half of which have been treated with an oral rinse formulation and half of which are controls, and 49 variables consisting of bucketed intensities. In addition, three simulations, two of which consist of the same number of samples and variables as the experimental dataset and a third that contains a much larger number of variables, are described. Two of the simulations contain known discriminatory variables, and the remaining is treated as a null dataset without any specific discriminatory variables added. The described SOM method is contrasted to Partial Least Squares Discriminant Analysis, and a list of the markers determined to be most significant using both approaches was obtained and the differences arising are discussed. A SOM Discrimination Index (SOMDI) is defined, whose magnitude relates to how strongly a variable is considered to be a discriminator. In order to ensure that the model is stable and not dependent on the random starting point of the SOM, one hundred iterations were performed and variables that were consistently of high rank were selected. A variety of approaches for data representation are illustrated, and the main theoretical principles of employing SOMs for determining which variables are most significant are outlined. Software used in this paper was written in-house, allowing greater flexibility over existing packages, and tailored for the specific application in hand.     

A thermal model of the immobilization of low-level radioactive waste as grout in concrete vaults

Salt solution, from radioactive waste generated by the production of plutonium and tritium in nuclear reactors at the Savannah River Site, will be mixed with cement and flyash/slag to form a grout which will be poured into above ground concrete vaults. The curing process is exothermic, and a transient thermal model of the pouring and curing process is herein described. A peak temperature limit of 85 °C for the curing grout restricts the rate at which it can be poured into a vault. The model is used to optimize the pouring.     

Effective components of TORDIA cognitive–behavioral therapy for adolescent depression: Preliminary findings.

In this report, we conducted a secondary analysis of the Treatment of SSRI-Resistant Depression in Adolescents (TORDIA) study to explore the impact of specific cognitive–behavioral therapy (CBT) treatment components on outcome. In TORDIA, 334 youths (ages 12 to 18 years) with major depressive disorder who had failed to respond to an adequate course of selective serotonin reuptake inhibitor (SSRI) medication were randomized to a medication switch (either to an alternative SSRI or venlafaxine) with or without 12 weeks of adjunctive CBT. Participants who had more than 9 CBT sessions were 2.5 times more likely to have adequate treatment response than those who had 9 or fewer sessions. CBT participants who received problem-solving and social skills treatment components, controlling for number of sessions and other confounding variables, were 2.3 and 2.6 times, respectively, more likely to have a positive response. These preliminary findings underscore the importance of receiving an adequate number of sessions to attain an adequate clinical response. Finally, social skills and problem solving may be active elements in CBT for adolescent depression and should be considered in treatment by those working with seriously depressed youths. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

UWB-based sensor networks for localization in mining environments

Wireless sensor networks (WSN) have attached a great attention in the last few years. WSN offer several advantages over the traditional sensor networks, such as elimination of costly wires, security and larger area coverage. In the last few years, there has been great interest commercial applications based on Ultra Wideband (UWB). It has potentially low complexity, low cost and an excellent time domain resolution which facilitates location and tracking applications. Therefore, UWB provide a good combination of high performance with low complexity for WSN applications. Localization has attracted considerable attention in many fields. Accurate estimation of an individual location can be a difficult task, producing ambiguous results particularly in harsh environment. In this paper, we focus on feasibility study (via simulation and measurements) of using UWB based-WNS as future solution for localization in underground mines.