Artificial Neural Networks (ANNs) are being used increasingly to predict and forecast water resources variables. In this paper, the steps that should be followed in the development of such models are outlined. These include the choice of performance criteria, the division and pre-processing of the available data, the determination of appropriate model inputs and network architecture, optimisation of the connection weights (training) and model validation. The options available to modellers at each of these steps are discussed and the issues that should be considered are highlighted. A review of 43 papers dealing with the use of neural network models for the prediction and forecasting of water resources variables is undertaken in terms of the modelling process adopted. In all but two of the papers reviewed, feedforward networks are used. The vast majority of these networks are trained using the backpropagation algorithm. Issues in relation to the optimal division of the available data, data pre-processing and the choice of appropriate model inputs are seldom considered. In addition, the process of choosing appropriate stopping criteria and optimising network geometry and internal network parameters is generally described poorly or carried out inadequately. All of the above factors can result in non-optimal model performance and an inability to draw meaningful comparisons between different models. Future research efforts should be directed towards the development of guidelines which assist with the development of ANN models and the choice of when ANNs should be used in preference to alternative approaches, the assessment of methods for extracting the knowledge that is contained in the connection weights of trained ANNs and the incorporation of uncertainty into ANN models.

Neural networks for the prediction and forecasting of water resources variables: a review of modelling issues and applications

A review on plants extract mediated synthesis of silver nanoparticles for antimicrobial applications: A green expertise.

A new method for detecting spikes in acoustic Doppler velocimeter data sequences is suggested. The method combines three concepts: (1) that differentiation enhances the high frequency portion of a signal, (2) that the expected maximum of a random series is given by the Universal threshold, and (3) that good data cluster in a dense cloud in phase space or Poincare maps. These concepts are used to construct an ellipsoid in three-dimensional phase space, then points lying outside the ellipsoid are designated as spikes. The new method is shown to have superior performance to various other methods and it has the added advantage that it requires no parameters. Several methods for replacing sequences of spurious data are presented. A polynomial fitted to good data on either side of the spike event, then interpolated across the event, is preferred by the authors.

Despiking Acoustic Doppler Velocimeter Data

Data-driven Soft Sensors in the process industry

Microorganisms synthesise a wide range of surface-active compounds (SAC), generally called biosurfactants. These compounds are mainly classified according to their molecular weight, physico-chemical properties and mode of action. The low-molecular-weight SACs or biosurfactants reduce the surface tension at the air/water interfaces and the interfacial tension at oil/water interfaces, whereas the high-molecular-weight SACs, also called bioemulsifiers, are more effective in stabilising oil-in-water emulsions. Biosurfactants are attracting much interest due to their potential advantages over their synthetic counterparts in many fields spanning environmental, food, biomedical, and other industrial applications. Their large-scale application and production, however, are currently limited by the high cost of production and by limited understanding of their interactions with cells and with the abiotic environment. In this paper, we review the current knowledge and the latest advances in biosurfactant applications and the biotechnological strategies being developed for improving production processes and future potential.

/pdf/microbial-biosurfactants-production-applications-and-future-1jbia11tup.pdf

Microbial biosurfactants production, applications and future potential

An ant colony approach for clustering

Particle swarm and ant colony algorithms hybridized for improved continuous optimization

Gas hydrates have been proposed as a potential technology for a number of applications, such as separation of gas mixtures, CO2 capture, transportation, and sequestration, methane storage and transport, and seawater desalination. Most of these applications will benefit from reduced induction time of hydrate nucleation, enhanced hydrate growth rate, and maximum water-to-hydrate conversion. The addition of surfactants to the gas–water system serves this purpose in a very effective manner. This review focuses on different surfactants that were utilized for gas hydrate formation studies; insights have been provided on the possible mechanisms of action through which these surfactants affect hydrate formation kinetics. A thorough analysis of the existing literature on surfactants suggests that enhanced rate of hydrate nucleation and growth kinetics may not be directly linked to micelle formation. Conversely, reduced surface tension in the presence of surfactants not only enhances the mass transfer but also chan...

Role of Surfactants in Promoting Gas Hydrate Formation

Comparative assessment of downstream processing options for lactic acid

Negativity of the conditional Lyapunov exponents is a necessary and in many cases a sufficient condition for the occurrence of synchronization between a chaotic drive and the response subsystem. Treating one of the variables of coupled logistic maps as the drive, our numerical simulations show that the negativity of the conditional Lyapunov exponents does not always guarantee synchronization and, additionally, the domain of initial conditions for the drive variables needs to be specified in which case the synchronization occurs. Additionally, an example showing the pitfalls of the numerical study of synchronization when the conditional Lyapunov exponent is positive is presented.

Bhaskar D. Kulkarni

Papers

An ant colony approach for clustering

Particle swarm and ant colony algorithms hybridized for improved continuous optimization

Role of Surfactants in Promoting Gas Hydrate Formation

Comparative assessment of downstream processing options for lactic acid

Driving systems with chaotic signals.