A review and analysis of backpropagation neural networks for classification of remotely-sensed multi-spectral imagery

A literature survey and analysis of the use of neural networks for the classification of remotely-sensed multi-spectral imagery is presented. As part of a brief mathematical review, the backpropagation algorithm, which is the most common method of training multi-layer networks, is discussed with an emphasis on its application to pattern recognition. The analysis is divided into five aspects of neural network classification: (1) input data preprocessing, structure, and encoding, (2) output encoding and extraction of classes, (3) network architecture, (4) training algorithms, and (5) comparisons to conventional classifiers. The advantages of the neural network method over traditional classifiers are its nonparametric nature, arbitrary decision boundary capabilities, easy adaptation to different types of data and input structures, fuzzy output values that can enhance classification, and good generalization for use with multiple images. The disadvantages of the method are slow training time, inconsistent results due to random initial weights, and the requirement of obscure initialization values (e.g., learning rate and hidden layer size). Possible techniques for ameliorating these problems are discussed. It is concluded that, although the neural network method has several unique capabilities, it will become a useful tool in remote sensing only if it is made faster, more predictable, and easier to use.     

Cholesterol Oxidation in Baked Foods Containing Fresh and Powdered Eggs

The degree of cholesterol oxidation in commercial sweet baked foods (biscuits and snacks) and in laboratory baked biscuits, all containing fresh or powdered eggs, was determined. 7-Ketocholesterol was used as index of cholesterol oxidation and detected by two analytical methods. The analysis of the biscuits showed higher levels of 7-ketocholesterol and a more marked oxidative instability of cholesterol when prepared with powdered eggs. The significant amounts of 7-ketocholesterol found in some samples of commercial biscuits were attributed to the use of powdered eggs. These data are of importance to industries using eggs in sweet baked products which are mainly consumed by children.     

Cannabis and male reproduction: Impact on offspring via sperm epigenome

Cannabis is the most widely used drug in the Western societies particularly among adolescent and young adults. Epidemiological studies demonstrate that men use cannabis more frequently than women with higher risk in developing cannabis-related disorders. Although the direct adverse effects of cannabis on male reproductive functions have been studied both in humans and animal models, the possible long-term risks for the health of the users and their offspring are still an area of active research.     

The C-terminal Domain of Snf3p is Sufficient to Complement the Growth Defect of snf3 Null Mutations in Saccharomyces cerevisiae: SNF3 Functions in Glucose Recognition

The SNF3 protein, Snf3p, of Saccharomyces cerevisiae was initially thought to be a high affinity glucose transporter required for efficient catabolism of low glucose concentrations. We now report evidence suggesting that Snf3p is a regulatory protein and not a catabolic transporter. The C-terminal domain of Snf3p is able to complement the growth defect on solid media of snf3 null mutants independent of attachment to the membrane-spanning domains. However, the C-terminal domain is unable to fully restore high affinity glucose transport to a snf3 null strain. Examination of deletions of the C-terminal domain of intact SNF3 demonstrates that this region is required for both the growth and transport functions of Snf3p. Loss of the SNF3 gene leads to a long-term adaptation phenotype for cells grown in liquid medium at low substrate concentrations in the presence of the respiratory inhibitor, antimycin A. The presence of the C-terminal domain shortens the time required for adaptation in a snf3 null strain. Thus, Snf3p appears to affect ability to adapt to low substrate conditions, but does not confer an absolute defect in uptake of substrate. Taken together, these data suggest that Snf3p is a regulatory protein likely functioning in the detection of glucose. © 1997 by John Wiley & Sons, Ltd.     

Resveratrol-related compounds: Potential for cancer and beyond

The nutraceutical resveratrol is associated with a range of biological effects, from antibiotic to anti-inflammatory activities. One major axis of research has sought to harness its anti-tumour potential, with promising preclinical results and early clinical trials. A second strong interest relies on the anti-ageing effects ascribed to the compound and its application to stem cell research. It is becoming clear however that these possible favourable effects are conditioned by a set concentration range not easily controllable in vivo. Here we evoke novel developments in the field that could lead to more reliable conditions for the translational use of resveratrol-based compounds.     

Four-dimensional factor analysis of confocal image sequences (4D-FAMIS) to detect and characterize low copy numbers of human papillomavirus DNA by FISH in HeLa and SiHa cells

Visualization and localization of specific DNA sequences were performed by fluorescence in situ hybridization, confocal laser scanning microscopy (CLSM), and four-dimensional factor analysis of biomedical image sequences (4D-FAMIS). HeLa and SiHa cells containing, respectively 20–50 and 1–2 copies per cell of human papillomavirus (HPV) DNA type 18 and 16 integrated in cellular DNA were used as models. HPV-DNA was identified using DNA probes containing the whole genome of HPV-DNA type 18 or 16, and DNA–DNA hybrids were revealed by alkaline phosphatase and Fast Red. Cell nuclei were counterstained with thiazole orange (TO) or TOTO-iodide. 4D image sequences were obtained using successive dynamic or spectral sequences of images on different optical sections from CLSM. The location of fluorescent signals within the preparations was determined by FAMIS. This original method summarizes image sequences into a reduced number of images called factor images, and curves called factors. Factors estimate different individual physical behaviours in the sequence such as extinction velocity, spectral patterns and depth emission profiles. Factor images correspond to spatial distributions of the different factors. We distinguished between Fast Red and nucleus stainings in HPV-DNA hybridization signals by taking into account differences in their extinction velocities (fluorescence decay rate) or spectral patterns, and in their focus (depth emission profiles). In HeLa cells, factor images showed that Fast-Red-stained targets could be distinguished from nucleus stainings, and were located on different focal planes of the nuclei. In SiHa cells, 4D-FAMIS determined as few as 1–2 copies per cell of HPV-DNA type 16 located in continuous focal planes. Therefore, 4D-FAMIS, together with CLSM, made the detection and characterization of low copy numbers of genes in whole cells possible.