Applications of Artificial Neural Networks in integrated water management: fiction or future?

An Artificial Neural Network (ANN) is nowadays recognized as a very promising tool for relating input data to output data. It is said that the possibilities of artificial neural networks are unlimited. Here we focus on the potential role of neural networks in integrated water management. An Artificial Neural Network (ANN) is a mathematical methodology which describes relations between cause (input data) and effects (output data) irrespective of the process laying behind and without the need for making assumptions considering the nature of the relations. The applications are widespread and vary from optimization of measuring networks, operational water management, prediction of drinking water consumption, on-line steering of wastewater treatment plants and sewage systems, up to more specific applications such as establishing a relationship between the observed erosion of groyne field sediments and the characteristics of passing vessels on the river Rhine. Especially where processes are complex, neural networks can open new possibilities for understanding and modelling these kinds of complex processes. Besides explaining the method of ANN this paper shows different applications. Three examples have been worked out in more detail. An intelligent monitoring system is shown for the on-line prediction of water consumption, ANN are successfully used for sludge cost monitoring and optimizing wastewater treatment and the usage of ANN is shown in optimizing and monitoring water quality measuring networks. An ANN appears to be a multiuse and powerful tool for modelling complex processes.     

Pneumoperitoneum does not potentiate the nephrotoxicity of aminoglycosides in rats

OBJECTIVES: Pneumoperitoneum is associated with transient renal dysfunction. To our knowledge, the safety of administering nephrotoxins such as aminoglycosides during pneumoperitoneum has not been studied. Our hypothesis was that pneumoperitoneum potentiates the nephrotoxicity of aminoglycosides. METHODS: From 29 rats we obtained preprocedure 24-hour urine collections. In the pneumoperitoneum group (n = 7), carbon dioxide was insufflated intra-abdominally at 15 mm Hg pressure for 2 hours. In the gentamicin group (n = 7), 10 mg/kg gentamicin was administered intravenously. In the combined pneumoperitoneum/gentamicin group (n = 8), the same dose of gentamicin was administered 10 minutes before pneumoperitoneum. Sham rats (n = 7) received anesthesia only. Urine was collected for the 24 hours after the procedure, and 1 week later blood for creatinine determination and final 24-hour urine collections were obtained. All urine samples were assayed for creatinine and N-acetyl-beta-glucosaminidase (NAG). RESULTS: Only the gentamicin and combined pneumoperitoneum/gentamicin groups presented day 1 values for NAG excretion that were significantly greater than same day sham or paired preprocedure values; the rest of the urinary creatinine and NAG day 1 levels and all the day 7 levels were not significantly different from same day sham or paired preprocedure levels. Day 7 serum creatinine and creatinine clearance did not differ significantly among the groups. CONCLUSIONS: We found that intravenous gentamicin transiently increased urinary excretion of NAG in rats, which resolved within 1 week. Pneumoperitoneum for 2 hours at 15 mm Hg did not increase urinary NAG, either alone or in gentamicin-treated rats. Moreover, our data are sufficient to refute with 95% certainty the possibility that gentamicin plus pneumoperitoneum decreases creatinine clearance more than approximately 60%. These results do not support the hypothesis that pneumoperitoneum potentiates the nephrotoxicity of aminoglycosides.     

Simulation of TaNx deposition by Reactive PVD

The subject of this paper is the extension of the simulation tool T2 for the application to Reactive Physical Vapor Deposition. The implemented models are briefly described and applied to the deposition of TaN_x barriers. The influence of the nitrogen flow and the substrate bias on the deposition rate, the thickness uniformity, and the film composition is discussed.     

Relationships between colour parameters,phenolic content and sensory changes of processed blueberry,elderberry and blackcurrant commercial juices

There is an increased interest in the consumption of fruits containing high phenolic concentrations such as berry fruits. Attractive colour of berries plays a vital role for consumer acceptance. The aim of this work was to evaluate colour parameters (a*, b*, L*), phenolic content and sensory changes of blueberry, elderberry and blackcurrant (BC) pasteurised commercial juices during accelerate storage. Initial phenolic concentration was 3.21, 10.06, 10.72 g GAE L^?1 for blueberry, elderberry and BC, respectively. Moreover, phenolic concentration of all juices decreased by approximately 40% throughout the first 30 days. Blueberry exhibited a substantial decrease in a* (40%) in the first 30 days, while elderberry presented a gradual decrease and BC only presented a slight decrease (7%) at the end of storage. Colour preferences decreased when storage time increased. However, when consumers were informed that ‘the juices are a rich source of phenolics, which contribute to reducing risk of suffering chronic diseases’, a high level of purchase intention was obtained.     

Soft-Mode Behavior in Ternary Silicides MAlSi (M=Ca, Sr, Ba)

We present a combined experimental and theoretical investigation of the lattice dynamics and electron–phonon coupling of the ternary silicides MAlSi (M = Ca, Sr, Ba). Temperature dependent inelastic neutron-scattering measurements of the generalized phonon density-of-states provide evidence for a soft-mode behavior for CaAlSi which is absent for the other two compounds. Density-functional-based calculations of phonon spectra and electron–phonon coupling support this interpretation and identify the soft mode as strong coupling out-of-plane Al vibrations, in agreement with previous theoretical work. Observed differences in superconducting properties, in particular in T _c , among the investigated compounds can be explained by the presence of the soft mode.     

Modelling of the extractive membrane bioreactor process based on natural fluorescence fingerprints and process operation history.

A method for non-mechanistic and non-linear modelling of complex biological processes is presented, using the example of the extractive membrane bioreactor (EMB). The model is based on artificial neural networks (ANN), which are able to predict the state of the process from a combination of reactor operational parameters and natural fluorescence fingerprints. Current as well as historic process operation is included in the ANN input vector, in order to account for lag-times within the reactor system and for biofilm dynamics that are dependent on process history. The model is especially relevant for practitioners, as it does not require assumptions on underlying process mechanisms, and it relies on routinely available operational data and on an easy-to-install, non-invasive, in-situ, on-line monitoring method. Moreover, it focuses on the prediction of overall process performance parameters, which are of immediate relevance in practice. The developed model was able to predict the process state very well. Sensitivity analysis revealed that the main impact on process performance stems from process operation rather than the physiological state of the biological culture, and that in the EMB configuration employed process operation history decisively impacts on the process outcome.     

Demonstration with field trails of a satellite-terrestrial synergistic approach for digital multimedia broadcasting to mobile users

The close synergy between a satellite system and terrestrial mobile cellular networks for cost-efficient content delivery to mobile users lies at the core of the satellite digital multimedia broadcasting system concept. Having already rich research and design work behind it, much of which has been carried out in the framework of European R&D projects, the system has recently seen the end of its first field trials, which relied on an experimental platform representing the future operational system. The article reports the outcomes of these trials that confirmed the technical feasibility of the system concept and provided valuable hints for the subsequent system design stages.