Incorporation of antimicrobial peptides on functionalized cotton gauzes for medical applications

A large group of low molecular weight natural compounds that exhibit antimicrobial activity has been isolated from animals and plants during the past two decades. Among them, peptides are the most widespread resulting in a new generation of antimicrobial agents with higher specific activity. In the present study we have developed a new strategy to obtain antimicrobial wound-dressings based on the incorporation of antimicrobial peptides into polyelectrolyte multilayer films built by the alternate deposition of polycation (chitosan) and polyanion (alginic acid sodium salt) over cotton gauzes. Energy dispersive X ray microanalysis technique was used to determine if antimicrobial peptides penetrated within the films. FTIR analysis was performed to assess the chemical linkages, and antimicrobial assays were performed with two strains: Staphylococcus aureus (Gram-positive bacterium) and Klebsiella pneumonia (Gram-negative bacterium). Results showed that all antimicrobial peptides used in this work have provided a higher antimicrobial effect (in the range of 4 log–6 log reduction) for both microorganisms, in comparison with the controls, and are non-cytotoxic to normal human dermal fibroblasts at the concentrations tested.

Adhesive bioactive coatings inspired by sea life

Inspired by nature, in particular by the marine mussels adhesive proteins (MAPs) and by the tough brick-and-mortar nacre-like structure, novel multilayered films are prepared in the present work. Organic-inorganic multilayered films, with an architecture similar to nacre based on bioactive glass nanoparticles (BG), chitosan and hyaluronic acid modified with catechol groups, which are the main responsible for the outstanding adhesion in MAPs, are developed for the first time. The biomimetic conjugate is prepared by carbodiimide chemistry and analyzed by ultraviolet-visible spectrophotometry. The build-up of the multilayered films is monitored with a quartz crystal microbalance with dissipation monitoring and their topography is characterized by atomic force microscopy. The mechanical properties reveal that the films containing catechol groups and BG present an enhanced adhesion. Moreover, the bioactivity of the films upon immersion in a simulated body fluid solution for 7 days is evaluated by scanning electron microscopy coupled with energy dispersive X-ray spectroscopy, Fourier transform infrared spectroscopy and X-ray diffraction. It was found that the constructed films promote the formation of bone-like apatite in vitro. Such multifunctional mussel inspired LbL films, which combine enhanced adhesion and bioactivity, could be potentially used as coatings of a variety of implants for orthopedic applications.

A behavior-based scheme using reinforcement learning for autonomous underwater vehicles

This paper presents a hybrid behavior-based scheme using reinforcement learning for high-level control of autonomous underwater vehicles (AUVs). Two main features of the presented approach are hybrid behavior coordination and semi on-line neural-Q_learning (SONQL). Hybrid behavior coordination takes advantages of robustness and modularity in the competitive approach as well as efficient trajectories in the cooperative approach. SONQL, a new continuous approach of the Q_learning algorithm with a multilayer neural network is used to learn behavior state/action mapping online. Experimental results show the feasibility of the presented approach for AUVs

Using a Parameterization of a Radiative Transfer Model to Build High-Resolution Maps of Typical Clear-Sky UV Index in Catalonia, Spain

To perform a climatic analysis of the annual UV index (UVI) variations in Catalonia, Spain (northeast of the Iberian Peninsula), a new simple parameterization scheme is presented based on a multilayer radiative transfer model. The parameterization performs fast UVI calculations for a wide range of cloudless and snow-free situations and can be applied anywhere. The following parameters are considered: solar zenith angle, total ozone column, altitude, aerosol optical depth, and single-scattering albedo. A sensitivity analysis is presented to justify this choice with special attention to aerosol information. Comparisons with the base model show good agreement, most of all for the most common cases, giving an absolute error within 0.2 in the UVI for a wide range of cases considered. Two tests are done to show the performance of the parameterization against UVI measurements. One uses data from a high-quality spectroradiometer from Lauder, New Zealand [45.04°S, 169.684°E, 370 m above mean sea level (MSL)], where there is a low presence of aerosols. The other uses data from a Robertson–Berger-type meter from Girona, Spain (41.97°N, 2.82°E, 100 m MSL), where there is more aerosol load and where it has been possible to study the effect of aerosol information on the model versus measurement comparison. The parameterization is applied to a climatic analysis of the annual UVI variation in Catalonia, showing the contributions of solar zenith angle, ozone, and aerosols. High-resolution seasonal maps of typical UV index values in Catalonia are presented

Incremental neural networks for function approximation

A new strategy for incremental building of multilayer feedforward neural networks is proposed in the context of approximation of functions from R-p to R-q using noisy data. A stopping criterion based on the properties of the noise is also proposed. Experimental results for both artificial and real data are performed and two alternatives of the proposed construction strategy are compared.

Statistical analysis and modelling of weather radar beam propagation conditions in the Po Valley (Italy)

Ground clutter caused by anomalous propagation (anaprop) can affect seriously radar rain rate estimates, particularly in fully automatic radar processing systems, and, if not filtered, can produce frequent false alarms. A statistical study of anomalous propagation detected from two operational C-band radars in the northern Italian region of Emilia Romagna is discussed, paying particular attention to its diurnal and seasonal variability. The analysis shows a high incidence of anaprop in summer, mainly in the morning and evening, due to the humid and hot summer climate of the Po Valley, particularly in the coastal zone. Thereafter, a comparison between different techniques and datasets to retrieve the vertical profile of the refractive index gradient in the boundary layer is also presented. In particular, their capability to detect anomalous propagation conditions is compared. Furthermore, beam path trajectories are simulated using a multilayer ray-tracing model and the influence of the propagation conditions on the beam trajectory and shape is examined. High resolution radiosounding data are identified as the best available dataset to reproduce accurately the local propagation conditions, while lower resolution standard TEMP data suffers from interpolation degradation and Numerical Weather Prediction model data (Lokal Model) are able to retrieve a tendency to superrefraction but not to detect ducting conditions. Observing the ray tracing of the centre, lower and upper limits of the radar antenna 3-dB half-power main beam lobe it is concluded that ducting layers produce a change in the measured volume and in the power distribution that can lead to an additional error in the reflectivity estimate and, subsequently, in the estimated rainfall rate.

The sampling of ignitable liquids on suspects' hands

In arson cases, the collection and detection of traces of ignitable liquids on a suspect's hands can provide information to a forensic investigation. Police forces currently lack a simple, robust, efficient and reliable solution to perform this type of swabbing. In this article, we describe a study undertaken to develop a procedure for the collection of ignitable liquid residues on the hands of arson suspects. Sixteen different collection supports were considered and their applicability for the collection of gasoline traces present on hands and their subsequent analysis in a laboratory was evaluated. Background contamination, consisting of volatiles emanating from the collection supports, and collection efficiencies of the different sampling materials were assessed by passive headspace extraction with an activated charcoal strip (DFLEX device) followed by gas chromatography-mass spectrometry (GC-MS) analysis. After statistical treatment of the results, non-powdered latex gloves were retained as the most suitable method of sampling. On the basis of the obtained results, a prototype sampling kit was designed and tested. This kit is made of a three compartment multilayer bag enclosed in a sealed metal can and containing three pairs of non-powdered latex gloves: one to be worn by the sampler, one consisting of a blank sample and the last one to be worn by the person suspected to have been in contact with ignitable liquids. The design of the kit was developed to be efficient in preventing external and cross-contaminations.

Optical-geometrical effects on the photoluminescence spectra of Si nanocrystals embedded in SiO2

We demonstrate that thickness, optical constants, and details of the multilayer stack, together with the detection setting, strongly influence the photoluminescence spectra of Si nanocrystals embedded in SiO2. Due to multiple reflections of the visible light against the opaque silicon substrate, an interference pattern is built inside the oxide layer, which is responsible for the modifications in the measured spectra. This interference effect is complicated by the depth dependence of (i) the intensity of the excitation laser and (ii) the concentration of the emitting nanocrystals. These variations can give rise to apparent features in the recorded spectra, such as peak shifts, satellite shoulders, and even splittings, which can be mistaken as intrinsic material features. Thus, they can give rise to an erroneous attribution of optical bands or estimate of the average particle size, while they are only optical-geometrical artifacts. We have analyzed these effects as a function of material composition (Si excess fraction) and thickness, and also evaluated how the geometry of the detection setup affects the measurements. To correct the experimental photoluminescence spectra and extract the true spectral shape of the emission from Si nanocrystals, we have developed an algorithm based on a modulation function, which depends on both the multilayer sequence and the experimental configuration. This procedure can be easily extended to other heterogeneous systems.

White luminescence from Si+ and C+ ion-implanted SiO2 films

The microstructural and optical analysis of SiO2 layers emitting white luminescence is reported. These structures have been synthesized by sequential Si+ and C+ ion implantation and high-temperature annealing. Their white emission results from the presence of up to three bands in the photoluminescence (PL) spectra, covering the whole visible spectral range. The microstructural characterization reveals the presence of a complex multilayer structure: Si nanocrystals are only observed outside the main C-implanted peak region, with a lower density closer to the surface, being also smaller in size. This lack of uniformity in their density has been related to the inhibiting role of C in their growth dynamics. These nanocrystals are responsible for the band appearing in the red region of the PL spectrum. The analysis of the thermal evolution of the red PL band and its behavior after hydrogenation shows that carbon implantation also prevents the formation of well passivated Si/SiO2 interfaces. On the other hand, the PL bands appearing at higher energies show the existence of two different characteristics as a function of the implanted dose. For excess atomic concentrations below or equal to 10%, the spectra show a PL band in the blue region. At higher doses, two bands dominate the green¿blue spectral region. The evolution of these bands with the implanted dose and annealing time suggests that they are related to the formation of carbon-rich precipitates in the implanted region. Moreover, PL versus depth measurements provide a direct correlation of the green band with the carbon-implanted profile. These PL bands have been assigned to two distinct amorphous phases, with a composition close to elemental graphitic carbon or stoichiometric SiC.

Roughness and light scattering of ion-beam-sputtered fluoride coatings for 193 nm

Scattering characteristics of multilayer fluoride coatings for 193 nm deposited by ion beam sputtering and the related interfacial roughnesses are investigated. Quarter- and half-wave stacks of MgF2 and LaF3 with increasing thickness are deposited onto CaF2 and fused silica and are systematically characterized. Roughness measurements carried out by atomic force microscopy reveal the evolution of the power spectral densities of the interfaces with coating thickness. Backward-scattering measurements are presented, and the results are compared with theoretical predictions that use different models for the statistical correlation of interfacial roughnesses.

Multitask learning of environmental spatial data

The present research deals with an application of artificial neural networks for multitask learning from spatial environmental data. The real case study (sediments contamination of Geneva Lake) consists of 8 pollutants. There are different relationships between these variables, from linear correlations to strong nonlinear dependencies. The main idea is to construct a subsets of pollutants which can be efficiently modeled together within the multitask framework. The proposed two-step approach is based on: 1) the criterion of nonlinear predictability of each variable ?k? by analyzing all possible models composed from the rest of the variables by using a General Regression Neural Network (GRNN) as a model; 2) a multitask learning of the best model using multilayer perceptron and spatial predictions. The results of the study are analyzed using both machine learning and geostatistical tools.

Deep learning via semi-supervised embedding

We show how nonlinear embedding algorithms popular for use with shallow semi-supervised learning techniques such as kernel methods can be applied to deep multilayer architectures, either as a regularizer at the output layer, or on each layer of the architecture. This provides a simple alternative to existing approaches to deep learning whilst yielding competitive error rates compared to those methods, and existing shallow semi-supervised techniques.

Multiway Array Decomposition Analysis of EEGs in Alzheimer’s Disease

Methods for the extraction of features from physiological datasets are growing needs as clinical investigations of Alzheimer’s disease (AD) in large and heterogeneous population increase. General tools allowing diagnostic regardless of recording sites, such as different hospitals, are essential and if combined to inexpensive non-invasive methods could critically improve mass screening of subjects with AD. In this study, we applied three state of the art multiway array decomposition (MAD) methods to extract features from electroencephalograms (EEGs) of AD patients obtained from multiple sites. In comparison to MAD, spectral-spatial average filter (SSFs) of control and AD subjects were used as well as a common blind source separation method, algorithm for multiple unknown signal extraction (AMUSE). We trained a feed-forward multilayer perceptron (MLP) to validate and optimize AD classification from two independent databases. Using a third EEG dataset, we demonstrated that features extracted from MAD outperformed features obtained from SSFs AMUSE in terms of root mean squared error (RMSE) and reaching up to 100% of accuracy in test condition. We propose that MAD maybe a useful tool to extract features for AD diagnosis offering great generalization across multi-site databases and opening doors to the discovery of new characterization of the disease.

A Robust Multiple Feature Approach To Endpoint Detection In Car Environment Based On Advanced Classifiers

In this paper we propose an endpoint detection system based on the use of several features extracted from each speech frame, followed by a robust classifier (i.e Adaboost and Bagging of decision trees, and a multilayer perceptron) and a finite state automata (FSA). We present results for four different classifiers. The FSA module consisted of a 4-state decision logic that filtered false alarms and false positives. We compare the use of four different classifiers in this task. The look ahead of the method that we propose was of 7 frames, which are the number of frames that maximized the accuracy of the system. The system was tested with real signals recorded inside a car, with signal to noise ratio that ranged from 6 dB to 30dB. Finally we present experimental results demonstrating that the system yields robust endpoint detection.

Machine learning for geospatial data : algorithms, software tools and case studies

Résumé Cette thèse est consacrée à l'analyse, la modélisation et la visualisation de données environnementales à référence spatiale à l'aide d'algorithmes d'apprentissage automatique (Machine Learning). L'apprentissage automatique peut être considéré au sens large comme une sous-catégorie de l'intelligence artificielle qui concerne particulièrement le développement de techniques et d'algorithmes permettant à une machine d'apprendre à partir de données. Dans cette thèse, les algorithmes d'apprentissage automatique sont adaptés pour être appliqués à des données environnementales et à la prédiction spatiale. Pourquoi l'apprentissage automatique ? Parce que la majorité des algorithmes d'apprentissage automatiques sont universels, adaptatifs, non-linéaires, robustes et efficaces pour la modélisation. Ils peuvent résoudre des problèmes de classification, de régression et de modélisation de densité de probabilités dans des espaces à haute dimension, composés de variables informatives spatialisées (« géo-features ») en plus des coordonnées géographiques. De plus, ils sont idéaux pour être implémentés en tant qu'outils d'aide à la décision pour des questions environnementales allant de la reconnaissance de pattern à la modélisation et la prédiction en passant par la cartographie automatique. Leur efficacité est comparable au modèles géostatistiques dans l'espace des coordonnées géographiques, mais ils sont indispensables pour des données à hautes dimensions incluant des géo-features. Les algorithmes d'apprentissage automatique les plus importants et les plus populaires sont présentés théoriquement et implémentés sous forme de logiciels pour les sciences environnementales. Les principaux algorithmes décrits sont le Perceptron multicouches (MultiLayer Perceptron, MLP) - l'algorithme le plus connu dans l'intelligence artificielle, le réseau de neurones de régression généralisée (General Regression Neural Networks, GRNN), le réseau de neurones probabiliste (Probabilistic Neural Networks, PNN), les cartes auto-organisées (SelfOrganized Maps, SOM), les modèles à mixture Gaussiennes (Gaussian Mixture Models, GMM), les réseaux à fonctions de base radiales (Radial Basis Functions Networks, RBF) et les réseaux à mixture de densité (Mixture Density Networks, MDN). Cette gamme d'algorithmes permet de couvrir des tâches variées telle que la classification, la régression ou l'estimation de densité de probabilité. L'analyse exploratoire des données (Exploratory Data Analysis, EDA) est le premier pas de toute analyse de données. Dans cette thèse les concepts d'analyse exploratoire de données spatiales (Exploratory Spatial Data Analysis, ESDA) sont traités selon l'approche traditionnelle de la géostatistique avec la variographie expérimentale et selon les principes de l'apprentissage automatique. La variographie expérimentale, qui étudie les relations entre pairs de points, est un outil de base pour l'analyse géostatistique de corrélations spatiales anisotropiques qui permet de détecter la présence de patterns spatiaux descriptible par une statistique. L'approche de l'apprentissage automatique pour l'ESDA est présentée à travers l'application de la méthode des k plus proches voisins qui est très simple et possède d'excellentes qualités d'interprétation et de visualisation. Une part importante de la thèse traite de sujets d'actualité comme la cartographie automatique de données spatiales. Le réseau de neurones de régression généralisée est proposé pour résoudre cette tâche efficacement. Les performances du GRNN sont démontrées par des données de Comparaison d'Interpolation Spatiale (SIC) de 2004 pour lesquelles le GRNN bat significativement toutes les autres méthodes, particulièrement lors de situations d'urgence. La thèse est composée de quatre chapitres : théorie, applications, outils logiciels et des exemples guidés. Une partie importante du travail consiste en une collection de logiciels : Machine Learning Office. Cette collection de logiciels a été développée durant les 15 dernières années et a été utilisée pour l'enseignement de nombreux cours, dont des workshops internationaux en Chine, France, Italie, Irlande et Suisse ainsi que dans des projets de recherche fondamentaux et appliqués. Les cas d'études considérés couvrent un vaste spectre de problèmes géoenvironnementaux réels à basse et haute dimensionnalité, tels que la pollution de l'air, du sol et de l'eau par des produits radioactifs et des métaux lourds, la classification de types de sols et d'unités hydrogéologiques, la cartographie des incertitudes pour l'aide à la décision et l'estimation de risques naturels (glissements de terrain, avalanches). Des outils complémentaires pour l'analyse exploratoire des données et la visualisation ont également été développés en prenant soin de créer une interface conviviale et facile à l'utilisation. Machine Learning for geospatial data: algorithms, software tools and case studies Abstract The thesis is devoted to the analysis, modeling and visualisation of spatial environmental data using machine learning algorithms. In a broad sense machine learning can be considered as a subfield of artificial intelligence. It mainly concerns with the development of techniques and algorithms that allow computers to learn from data. In this thesis machine learning algorithms are adapted to learn from spatial environmental data and to make spatial predictions. Why machine learning? In few words most of machine learning algorithms are universal, adaptive, nonlinear, robust and efficient modeling tools. They can find solutions for the classification, regression, and probability density modeling problems in high-dimensional geo-feature spaces, composed of geographical space and additional relevant spatially referenced features. They are well-suited to be implemented as predictive engines in decision support systems, for the purposes of environmental data mining including pattern recognition, modeling and predictions as well as automatic data mapping. They have competitive efficiency to the geostatistical models in low dimensional geographical spaces but are indispensable in high-dimensional geo-feature spaces. The most important and popular machine learning algorithms and models interesting for geo- and environmental sciences are presented in details: from theoretical description of the concepts to the software implementation. The main algorithms and models considered are the following: multi-layer perceptron (a workhorse of machine learning), general regression neural networks, probabilistic neural networks, self-organising (Kohonen) maps, Gaussian mixture models, radial basis functions networks, mixture density networks. This set of models covers machine learning tasks such as classification, regression, and density estimation. Exploratory data analysis (EDA) is initial and very important part of data analysis. In this thesis the concepts of exploratory spatial data analysis (ESDA) is considered using both traditional geostatistical approach such as_experimental variography and machine learning. Experimental variography is a basic tool for geostatistical analysis of anisotropic spatial correlations which helps to understand the presence of spatial patterns, at least described by two-point statistics. A machine learning approach for ESDA is presented by applying the k-nearest neighbors (k-NN) method which is simple and has very good interpretation and visualization properties. Important part of the thesis deals with a hot topic of nowadays, namely, an automatic mapping of geospatial data. General regression neural networks (GRNN) is proposed as efficient model to solve this task. Performance of the GRNN model is demonstrated on Spatial Interpolation Comparison (SIC) 2004 data where GRNN model significantly outperformed all other approaches, especially in case of emergency conditions. The thesis consists of four chapters and has the following structure: theory, applications, software tools, and how-to-do-it examples. An important part of the work is a collection of software tools - Machine Learning Office. Machine Learning Office tools were developed during last 15 years and was used both for many teaching courses, including international workshops in China, France, Italy, Ireland, Switzerland and for realizing fundamental and applied research projects. Case studies considered cover wide spectrum of the real-life low and high-dimensional geo- and environmental problems, such as air, soil and water pollution by radionuclides and heavy metals, soil types and hydro-geological units classification, decision-oriented mapping with uncertainties, natural hazards (landslides, avalanches) assessments and susceptibility mapping. Complementary tools useful for the exploratory data analysis and visualisation were developed as well. The software is user friendly and easy to use.