Visual tracking using convolutional features with sparse coding

Artificial Intelligence Review - Visual object tracking has become one of the most active research topics in computer vision, and it has been applied in several commercial...     

Dynamics of localizable entanglement in a qutrit chain with Dzyaloshinskii–Moriya interaction

Dynamics of localizable entanglement in a qutrit chain, in the presence of the Dzyaloshinskii–Moriya (DM) interaction is studied. Three distinct initial states, namely, superposition of the ground and the first excited state (SGE), a GHZ state and a superposition of qutrit coherent states (SQCS) are considered in this investigation. While the ground and the first excited state exhibit the maximum of entanglement, the latter is diminished for any superposition of the states. In both SGE and GHZ cases, localizable entanglement (LE) oscillates and its period is a decreasing function of the ratio of the strength of DM interaction and the spin coupling constant (DS ratio), but its maximum value is independent of the latter. In SQCS case, LE also oscillates in time at small values of DS ratio; its average is reduced as the strength of the DM interaction increases and gains its maximum average and the highest peaks at a specific value of the coherence parameter.     

The use of coevolution and the artificial immune system for ensemble learning

This paper presents two new approaches for constructing an ensemble of neural networks (NN) using coevolution and the artificial immune system (AIS). These approaches are extensions of the CLONal Selection Algorithm for building ENSembles (CLONENS) algorithm. An explicit diversity promotion technique was added to CLONENS and a novel coevolutionary approach to build neural ensembles is introduced, whereby two populations representing the gates and the individual NN are coevolved. The former population is responsible for defining the ensemble size and selecting the members of the ensemble. This population is evolved using the differential evolution algorithm. The latter population supplies the best individuals for building the ensemble, which is evolved by AIS. Results show that it is possible to automatically define the ensemble size being also possible to find smaller ensembles with good generalization performance on the tested benchmark regression problems. More interestingly, the use of the diversity measure during the evolutionary process did not necessarily improve generalization. In this case, diverse ensembles may be found using only implicit diversity promotion techniques.     

An adaptive genetic-based signature learning system for intrusion detection

Rule-based intrusion detection systems generally rely on hand crafted signatures developed by domain experts. This could lead to a delay in updating the signature bases and potentially compromising the security of protected systems. In this paper, we present a biologically-inspired computational approach to dynamically and adaptively learn signatures for network intrusion detection using a supervised learning classifier system. The classifier is an online and incremental parallel production rule-based system.A signature extraction system is developed that adaptively extracts signatures to the knowledge base as they are discovered by the classifier. The signature extraction algorithm is augmented by introducing new generalisation operators that minimise overlap and conflict between signatures. Mechanisms are provided to adapt main algorithm parameters to deal with online noisy and imbalanced class data. Our approach is hybrid in that signatures for both intrusive and normal behaviours are learnt.The performance of the developed systems is evaluated with a publicly available intrusion detection dataset and results are presented that show the effectiveness of the proposed system.     

Neural-Based Learning Classifier Systems

UCS is a supervised learning classifier system that was introduced in 2003 for classification in data mining tasks. The representation of a rule in UCS as a univariate classification rule is straightforward for a human to understand. However, the system may require a large number of rules to cover the input space. Artificial neural networks (NNs), on the other hand, normally provide a more compact representation. However, it is not a straightforward task to understand the network. In this paper, we propose a novel way to incorporate NNs into UCS. The approach offers a good compromise between compactness, expressiveness, and accuracy. By using a simple artificial NN as the classifier's action, we obtain a more compact population size, better generalization, and the same or better accuracy while maintaining a reasonable level of expressiveness. We also apply negative correlation learning (NCL) during the training of the resultant NN ensemble. NCL is shown to improve the generalization of the ensemble.     

Effect of Iron sulfate as electrolyte additive on plasma electrolytic oxidation of aluminum alloy

This study has been carried out to investigate the incorporation of Iron(II) sulfate as an additive of electrolyte on formed AA1010 aluminum alloy, using plasma electrolytic oxidation method in silicate-based electrolytes containing Iron(II) sulfate. In order to fabricate nanocomposite coating, silicon nitride nanopowder was added to electrolyte. The effects of iron(II) sulfate additive on the voltage-time trend, microstructure, compositions, wear, and corrosion resistances of PEO coatings were investigated. In addition, current density and concentration of additive were studied as parameters that were effective on coating. Results showed that although FeSO₄ enters to the coating structure, but it does not develop a new phase. The corrosion and wear behavior of coated samples with FeSO₄ indicate an improvement as compared to those without additive.     

Investigation of the microstructure and oxidation behavior of Cr-modified aluminide coatings on γ-TiAL alloys

The microstructure and oxidation behavior of aluminide coatings are investigated. The layers are examined by the optical microscopy, scanning electron microscopy (SEM) equipped with EDS, and the X-ray diffraction method. The isothermal oxidation behaviors of samples are investigated at 950°C for 200 h. The results show that TiAl₃ is formed on the substrate. In addition, the aluminide coating improves the oxidation resistance of γ-TiAl alloys by forming a protective alumina scale. Moreover, during oxidation treatment, the interdiffusion of the TiAl₃ layer with γ-TiAl substrate results in the depletion of aluminum in the TiAl₃ layer and the growth of the TiAl₂ layer. After the oxidation treatment, the coating layer preserves a microstructure with phases including TiAl₃, TiAl₂, and Al₂O₃.     

SiAlON–epoxy nanocomposite coatings: Corrosion and wear behavior

In this study, epoxy powder as a matrix was combined with different contents of silicon–aluminum–oxygen–nitrogen (SiAlON) nanoparticles using a planetary ball mill. Pure epoxy and nanocomposite powders were applied on the surface of plain carbon steel components by the electrostatic spraying method. Curing of the coatings was done in an oven or microwave for the appropriate time. The coating structure and morphology of the SiAlON nanoparticles were studied by scanning electron microscopy and transmission electron microscopy, respectively. The corrosion properties of the coatings were assessed by immersion, Tafel polarization, and electrochemical impedance spectroscopy tests in 3.5% NaCl solution. The results show that addition of 10 wt % SiAlON nanoparticles markedly increases the corrosion resistance of epoxy coatings. Thus, it can be inferred that the corrosion rate of these coatings is 15 to 18 times lower than that of pure epoxy samples and 8 to 11 times lower than coatings with 20 wt % SiAlON. The higher corrosion resistance of nanocomposite coatings can be attributed to the barrier properties of SiAlON nanoparticles. The tribological performance of the coatings was studied with the pin‐on‐disk test. The results of wear testing show that the samples containing 10 wt % SiAlON provide about five times more wear resistance than pure ones and about two times more than coatings with 20 wt % SiAlON. However, the coefficient of friction for nanocomposite coatings is reduced about 50% compared to the pure sample. Also, the curing process in either regime (oven or microwave) has the same effect on the corrosion and wear properties, and the coatings are completely crosslinked. © 2016 Wiley Periodicals, Inc. J. Appl. Polym. Sci. 2016 , 133, 43855.     

Toxicity assay for deoxynivalenol using Caenorhabditis elegans

The progeny production and development rates of the nematode Caenorhabditis elegans when treated with deoxynivalenol (DON) were examined. Both purified DON and a crude extract from Fusarium graminearum cultured on rice were tested on C. elegans wild-type (Bristol N2) and a mutant strain (AU1). Significant effects (Tukey-HSD, p<0.05) on brood size and the rate of larval development from egg to adulthood were observed. Both N2 and AU1 strains showed lower rates of development and smaller brood sizes when exposed to purified DON at concentrations of 500 and 1000 μg ml(-1) When they were exposed to crude extract containing 250 μg ml(-1) DON, the inhibition of egg hatching and a greatly reduced development rate were observed. The results suggest that selection of a more sensitive C. elegans mutant strain could be used as a suitable animal model for conducting DON toxicity assays.     

Investigation of pretreatment effects on the formation of lanthanum based conversion coating on AA2024-T3

The effects of a pretreatment process on the formation and properties of lanthanum based conversion coatings on AA2024-T3 was investigated using optical and scanning electron microscopy (SEM), X-ray diffraction (XRD) and open circuit potential (OCP) measurements. The results indicate that the conventional alkaline activation pretreatment with acidic desmutting could not create a suitable condition to produce lanthanum based conversion coating on AA2024-T3. Therefore, in this study, a new approach to produce lanthanum based conversion coating on AA2024-T3 by acidic pretreatment is proposed. The pretreatment of the alloy in acidic and chloride environments (90 s at 30 vol % HCl) creates more cathodic sites on AA2024-T3 compared to alkaline activation with acidic desmutting. Additionally, it was found that the formation stages of lanthanum based conversion coating is similar to those of cerium based conversion coating on AA2024-T3 except lanthanum ions require more localized pH increase to deposit on the alloy.