A Real-Time Visual Inspection System for Railway Maintenance: Automatic Hexagonal-Headed Bolts Detection

Rail inspection is a very important task in railway maintenance, and it is periodically needed for preventing dangerous situations. Inspection is operated manually by trained human operator walking along the track searching for visual anomalies. This monitoring is unacceptable for slowness and lack of objectivity, as the results are related to the ability of the observer to recognize critical situations. The correspondence presents a patent-pending real-time Visual Inspection System for Railway (VISyR) maintenance, and describes how presence/absence of the fastening bolts that fix the rails to the sleepers is automatically detected. VISyR acquires images from a digital line-scan camera. Data are simultaneously preprocessed according to two discrete wavelet transforms, and then provided to two multilayer perceptron neural classifiers (MLPNCs). The "cross validation" of these MLPNCs avoids (practically-at-all) false positives, and reveals the presence/absence of the fastening bolts with an accuracy of 99.6% in detecting visible bolts and of 95% in detecting missing bolts. A field-programmable gate array-based architecture performs these tasks in 8.09 mus, allowing an on-the-fly analysis of a video sequence acquired at 200 km/h     

Antennas and Propagation for On-Body Communication Systems

On-body communication channels are of increasing interest for a number of applications, such as medical-sensor networks, emergency-service workers, and personal communications. This paper describes investigations into channel characterization and antenna performance at 2.45 GHz. It is shown that significant channel fading occurs during normal activity, due primarily to the dynamic nature of the human body, but also due to multipath around the body and from scattering by the environment. This fading can be mitigated by the use of antenna diversity, and gains of up to 10 dB are obtained. Separation of the antenna's performance from the channel characteristics is difficult, but results show that for many channels, an antenna polarized normal to the body's surface gives the best path gain. Simulation and modeling present many challenges, particularly in terms of the problem's scale, and the need for accurate modeling of the body and its movement.     

Bayesian networks in reliability

Over the last decade, Bayesian networks (BNs) have become a popular tool for modelling many kinds of statistical problems. We have also seen a growing interest for using BNs in the reliability analysis community. In this paper we will discuss the properties of the modelling framework that make BNs particularly well suited for reliability applications, and point to ongoing research that is relevant for practitioners in reliability.     

FraRI: an algorithm to account for the discontinuity at 60° N in MODIS temperature products

The Moderate Resolution Imaging Spectroradiometer (MODIS) on NASA's Terra and Aqua satellites conducts continuous monitoring of the Earth's land surface and oceans. Recently, a sharp discontinuity (averaging 1.9°C) has been noticed at 60° N in both MODIS daytime and night-time land surface temperature (LST) products. This linear artefact arises because the CO₂ high cloud test in the operational code for the generation of the MODIS cloud mask product is used only in the non-polar region (between 60° N and 60° S). The resulting discontinuity clearly has negative implications for any statistical applications of these temperature data. In this technical note we present a new algorithm, which minimizes this discontinuity. The method uses edge detection and elimination based on a mixture of Sobel and non-linear Laplacian filters (edge detection and quantification), cubic splines (edge modelling), and a controllable power function for image restoration. The implementation of this algorithm is demonstrated on an image of average minimum night-time LST between 2001 and 2008.     

Case-Base Maintenance in a Multimodal Reasoning System

The definition of suitable case-base maintenance policies is widely recognized as a major key to success for case-based systems; underestimating this issue may lead to systems that either do not fulfill their role of knowledge management and preservation or that do not perform adequately under performance dimensions, namely, computation time and competence and quality of solutions. The goal of this article is to analyze some automatic case-base management strategies in the context of a multimodal architecture combining case-based reasoning and model-based reasoning. We propose and compare two different methodologies, the first one, called replace , is a competence-based strategy aimed at replacing a set of stored cases with the current one, if the latter exhibits an estimated competence comparable with the estimated competence of the considered set of stored cases. The second one, called learning by failure with forgetting (LFF), is based on incremental learning of cases interleaved with off-line processes of forgetting (deleting) cases whose usage does not fulfill specific utility conditions. Results from an extensive experimental analysis in an industrial plant diagnosis domain are reported, showing the usefulness of both strategies with respect to the maintenance of suitable performance levels for the target system.     

Detecting vegetable oil adulteration in hazelnut paste (Corylus avellana L.)

The possibilities of detecting hazelnut paste adulterated with refined and non-refined vegetable oils have been studied. Research was focussed mainly on peanut, high oleic-acid sunflower, corn and soybean oils which have a similar composition to hazelnut oil. The analytical procedures to detect fatty acid (FA), triacylglycerol (TAG) and tocopherol profiles as indicators of adulteration were determined. The better indicators experimentally determined were seven FA (palmitic, stearic, linoleic, linolenic, arachidonic, behenic and lignoceric acids) and different TAG with three unsaturated FA (the code letters used for FA are: P = C_16:0; S = C_18:0; O = C_18:1; L = C_18:2;; L_n = C_18:3) (LLL_n, LLL and OOO), two unsaturated FA (POL, PLL and SOO), and one unsaturated FA (PPL). As expected, when refined vegetable oils were added to hazelnut paste, the increment of stigmasta-3,5-diene allowed detection at levels of 2% oil added. Limits of detection were measured using standard and adulterated hazelnut with different amounts of non-refined vegetable oils added (5%, 10%, 20% and 30%). The distribution of tocopherols and tocotrienols is highly useful, except in the case of added sunflower oil. The differences between the experimental and theoretical values of the TAG with equivalent carbon number (ΔECN) of 42 does not improve the detection limit of hazelnut paste adulterated with peanut or sunflower oils. Similarly, tocopherols usually added to refined vegetable oils as an antioxidant were also determined.     

The importance of landscape in wine quality perception: An integrated approach using choice-based conjoint analysis and combination-based permutation tests

This work’s aim is to evaluate the importance of landscape in wine quality perception using a novel integrated approach based on two statistical techniques, i.e. choice-based conjoint analysis (Gustafsson et al., 2001) and combination-based permutation tests (Corain and Salmaso, 2004, Pesarin and Salmaso, 2009a). To this end we developed a preference choice experiment which was submitted to a sample of respondents during blind wine tasting meetings. The obtained results allow us to weigh up and emphasise the importance of an attractive landscape to the perception of a finer quality of wine. Indeed, we noticed that associating wine to an image of greater visual impact, i.e. an evocative landscape, induces a significantly higher preference for the tasted wine. Moreover, the integrated application of choice-based conjoint analysis and combination-based permutation tests allows us to identify the specific relationship each market segment has with landscape, price and wine quality.     

Influence of mediator immobilization on the electrochemically assisted microbial dechlorination of trichloroethene (TCE) and cis‐dichloroethene (cis‐DCE)

BACKGROUND: A bioelectrochemical process for trichloroethene (TCE) dechlorination was developed. In this new process, a solid‐state electrode polarized to ?450 mV versus the standard hydrogen electrode (SHE), in combination with a redox mediator (i.e., methyl viologen, MV) is employed as an electron donor for the microbial reductive dechlorination of TCE. In this study we compared the performance of the process with the redox mediator immobilized at the surface of electrodes or dissolved in the bulk liquid, using both a culture highly enriched in Desulfitobacterium spp., capable of dechlorinating TCE to cis‐dichloroethene (cis‐DCE), and a culture highly enriched in Dehalococcoides spp. capable of dechlorinating cis‐DCE to ethene. RESULTS: Short‐term potentiostatic (?450 mV versus SHE) experiments showed that TCE or cis‐DCE was dechlorinated both in the presence of soluble (500 µmol L^?1) and immobilized MV. However, TCE or cis‐DCE dechlorination rates with MV‐modified electrodes were remarkably lower than with soluble MV. Both cultures produced significant amounts of H₂ in the presence of electrically reduced, soluble MV, whereas no H₂ was produced when the mediator was immobilized at the electrode surface, regardless of the potential applied to the electrode, in the range ?425 to ?500 mV versus SHE. CONCLUSIONS: The process, operated with modified electrodes, supports the microbial dechlorination of TCE to ethene. Immobilization not only allows retention of the mediator within the system, but also increases process efficiency by preventing bioelectrochemical H₂ formation. On the other hand, strategies to increase dechlorination rates with modified electrodes need to be developed. Copyright © 2009 Society of Chemical Industry