Peptides secondary structure prediction with neural networks: acriterion for building appropriate learning sets

Artificial neural networks have been recently applied with success for protein secondary structure prediction. So far, one of the two main aspects on which neural net performance depends, the topology of the net, has been considered. The present work addresses the other main aspect, the building up of the learning set. The author presents a criterion to build up suitable learning sets based on the α-helix percentage. Starting from a set of several well known proteins, the author formed 7 groups of proteins with similar helix percentages and used them for the learning of the same neural net. The author found that the best secondary structure prediction for each of the tested proteins (not belonging to the initial set) was the one obtained using the learning set whose helix percentage was closest to that of the tested protein. The accuracy of correct prediction of the author's method on 3 types of secondary structure (α-helix, β-sheet and coil), has been compared with the accuracy of other secondary structure prediction methods     

Sustainability of a wind power plant: Application to different Moroccan sites

In this paper, three main steps allowing the definition of the sustainability of a wind power plant (WPP) are described in detail. The first step is to choose a site with a good wind potential. In this respect, two approaches have been introduced: traditional wind statistical estimations based on the identification of the Weibull probability density function on specific sites; and an innovative Kriging approach based on artificial neural networks to reconstruct the profile of the mean wind speed of the territory. In the second step, given technical details, the energetic sustainability of a WPP installation is assessed according to a model computing the wind energy production per year, as well as the details of its efficiency. Finally, as third step, a cost/benefit evaluation on the overall reduction in CO₂ emissions with respect to traditional fossil fuel energy plants is reported. From a wind speed characterisation viewpoint, the case study is referred to the overall Moroccan territory. From a WPP model viewpoint, the case study is referred to the installation of a specific WPP, which would allow the production of more than 2 GWh per year in the south Atlantic coast and of nearly 1 GWh per year in the Mediterranean coast in the neighbourhood of Tangier.     

Hunting for "key residues" in the modeling of globular protein folding: an artificial neural network-based approach

An approach to modeling globular protein folding based on artificial neural networks (ANNs) is presented. This approach, that can be regarded as an inverse protein folding problem, investigates whether and when a protein fragment needs a specific residue in the center of its primary structure as a necessary condition to fold as observed. To perform this analysis, an ANN has been trained on a set of 55 proteins, searching for a relation between protein fragments modeled by 13/spl alpha/ torsion angles and the residue corresponding to the central /spl alpha/ torsion angle of the fragment. The results obtained show that only Asp, Gly, Pro, Ser and Val residues are often a necessary, even though not sufficient, condition to obtain a specific folded fragment structure, playing therefore, the role of "key residue" of this fragment.     

Ionic channel current burst analysis by a machine learning based approach

A new method to analyze single ionic channel current conduction is presented. It is based on an automatic classification by K-means algorithm and on the concept of information entropy. This method is used to study the conductance of multistate ion current jumps induced by tetanus toxin in planar lipid bilayers. A comparison is presented with the widely used Gaussian best fit approach, whose main drawback is the fact that it is based on the manual choice of the base line and of meaningful fragments of current signal. On the contrary, the proposed method is able to automatically process a great amount of information and to remove spurious transitions and multichannels. The number of levels and their amplitudes do not have to be known a priori. In this way the presented method is able to produce a reliable evaluation of the conductance levels and their characteristic parameters in a short time.     

Monthly and seasonal assessment of wind energy characteristics at four monitored locations in Liguria region (Italy)

The aim of this paper is to investigate the monthly and seasonal variation of the wind characteristics in term of wind energy potential using the wind speed data collected between 2002 and 2008 for four meteorological stations in Liguria region, in Northwest of Italy, namely Capo Vado, Casoni, Fontana Fresca and Monte Settepani. The results show that Capo Vado is the best site with a monthly mean wind speed between 2.80 and 9.98 m/s at a height of 10 m and a monthly wind power density between 90.71 and 1177.97 W/m², while the highest energy produced may be reached in December with a value of 3800 MWh. This study may provide information for developing wind energy sites and planning economical wind turbines capacity for the electricity production in Liguria region, as well as an example of how, deepening the analysis at monthly and seasonal scale, the characteristics of the sites might fall in quite different classes of power density.     

Wind energy potential in Liguria region

In this work, the aim is to assess the current wind energy potential in the Liguria region, Italy, by the application of well assessed methodologies that are recalled within the paper. Data for a monitored period up to six and half years from 25 stations distributed over the four provinces of Liguria (i.e., La Spezia, Genoa, Savona and Imperia) have been analyzed.From the data obtained on the 25 stations, only 4 of them seem to be eligible for energy production, but, due to other constraints such as environmental protected areas, only one of them seems the only one where the wind potential – which has been quite stable in the years – can be effectively exploited. However, as usual in these cases, also due to the complex orography of Liguria region, a monitoring campaign on the field should be additionally performed on the site.     

A decision support system for planning biomass-based energy production

Environmental decision support systems (EDSS) are recognized as valuable tools for environmental planning and management. In this paper, a geographic information system (GIS)-based EDSS for the optimal planning of forest biomass use for energy production is presented. A user-friendly interface allows the creation of Scenarios and the running of the developed decision and environmental models. In particular, the optimization model regards decisions over a long-term period (e.g. years) and includes decision variables related to plant locations, conversion processes (pyrolisis, gasification, combustion), harvested biomass. Moreover, different energy products and different definitions of the harvesting and pre-treatment operations are taken into account. The correct management of the forest is considered through specific constraints, security factors, and procedures for parcel selection. The EDSS features and capabilities are described in detail, with specific reference to a case study. Discussion and further research are reported.     

Enhancing Workflow Management in the Manufacturing Information System of a Small-Medium Enterprise: An Agent-Based Approach

One shortcoming of manufacturing information systems is their inability to integrate and to enhance different information and related functionalities, such as those found in workflow management. Software agents, once added as a new software layer to an existing system, can overcome this problem. Of the fields applying software agent technology, manufacturing, and especially workflow management, is perhaps the most promising for the development of distributed systems. This potential is reflected in the several ongoing research projects that focus on workflow management and share the final aim of integrating and coordinating plant and business activities.The approach presented in this paper can be regarded as an agent-based architecture applied to an existing workflow management system in order to manage new functionalities, e.g., customer relationship management in electronic commerce. This approach is particularly suitable for small medium enterprises with simple manufacturing information requirements and simple or nonexistent computer based workflow management.The model and some important features of system implementation, such as the knowledge modeling graphical user interface, the communication model, and a simple practical example of the architecture's use, are described.     

Introduction to the special section humans and industry 4.0

Cognition, Technology & Work - Since the start of industrialization, machine capabilities have increased in such a way that human control of processes has evolved from simple (with...     

Modelling and control of hydrogen and energy flows in a network of green hydrogen refuelling stations powered by mixed renewable energy systems

The planning of a hydrogen infrastructure with production facilities, distribution chains, and refuelling stations is a hard task. Difficulties may rise essentially in the choice of the optimal configurations. An innovative design of hydrogen network has been proposed in this paper. It consists of a network of green hydrogen refuelling stations (GHRSs) and several production nodes. The proposed model has been formulated as a mathematical programming, where the main decisions are the selection of GHRSs that are powered by the production nodes based on distance and population density criteria, as well the energy and hydrogen flows exchanged among the system components from the production nodes to the demand points. The approaches and methodologies developed can be taken as a support to decision makers, stakeholders and local authorities in the implementation of new hydrogen infrastructures. Optimal configurations have been reported taking into account the presence of an additional hydrogen industrial market demand and a connection with the electrical network. The main challenge that has been treated within the paper is the technical feasibility of the hydrogen supply chain, that is mainly driven by uncertain, but clean solar and wind energy resources. Using a Northern Italian case study, the clean hydrogen produced can be technically considered feasible to supply a network of hydrogen refuelling stations. Results show that the demands are satisfied for each time period and for the market penetration scenarios adopted.