Learning automata-based algorithms for finding cover sets in wireless sensor networks

Wireless sensor networks (WSNs) have been widely used in different applications. One of the most significant issues in WSNs is developing an efficient algorithm to monitor all the targets and, at the same time, extend the network lifetime. As sensors are often densely deployed, employing scheduling algorithms can be considered a promising approach that is able ultimately to result in extending total network lifetime. In this paper, we propose three learning automata-based scheduling algorithms for solving target coverage problem in WSNs. The proposed algorithms employ learning automata (LA) to determine the sensors that should be activated at each stage for monitoring all the targets. Additionally, we design a pruning rule and manage critical targets in order to maximize network lifetime. In order to evaluate the performance of the proposed algorithms, extensive simulation experiments were carried out, which demonstrated the effectiveness of the proposed algorithms in terms of extending the network lifetime. Simulation results also revealed that by a proper choice of the learning rate, a proper trade-off could be achieved between the network lifetime and running time.     

Solder joint inspection with multi-angle imaging and an artificial neural network

Machine vision has been widely deployed in many industrial applications. However, for solder joint inspection, it has yet to reach the desired maturity level. This paper presents a new inspection methodology using images from both orthogonal and oblique viewing directions to the solder joint. The oblique view was made possible through a mirror pyramid. Image capturing and selection of the soldered region were done manually, but could be automated if the positional coordinates were known. Combined orthogonal and oblique gray-level images at the pixel level were directly input to an artificial neural network (ANN) for processing, eliminating the need to determine heuristic features. Learning vector quantization architecture was used as the classifier. This study was focused on geometry-related joint defects, namely, excess and insufficient. Comparisons show that the oblique view provides more useful information compared to the orthogonal view. The experimental results indicate that the proposed system has an improved recognition rate and good resilience to noise.     

Effect of poly‐glutamate on uptake efficiency and cytotoxicity of cell penetrating peptides

Cell penetrating peptides (CPPs) were developed as vehicles for efficient delivery of various molecules. An ideal CPP‐peptide should not display any toxicity against cancer cells as well as healthy cells and efficiently enter into the cell. Because of the cationic nature and the intrinsic vector capabilities, these peptides can cause cytotoxicity. One of the possible reasons for toxicity of CPPs is direct translocation and consequently, pore formation on the plasma membrane. In this study it was demonstrated that interaction of poly‐glutamate with CPP considerably reduced their cytotoxicity in A549 cell. This strategy could be useful for efficient drug delivery mediated by CPP.Inspec keywords: cellular biophysics, polymers, drug delivery systems, biomedical materials, toxicology, molecular biophysicsOther keywords: drug delivery, A549 cell, plasma membrane, pore formation, cancer cells, poly‐glutamate, cytotoxicity, uptake efficiency, cell penetrating peptides     

Noise cancellation using selectable adaptive algorithm for speech in variable noise environment

Some of the teething problems associated in the use of two-sensor noise cancellation systems are the nature of the noise signals—a problem that imposes the use of highly complex algorithms in reducing the noise. The usage of such methods can be impractical for many real time applications, where speed of convergence and processing time are critical. At the same time, the existing approaches are based on using a single, often complex adaptive filter to minimize noise, which has been determined to be inadequate and ineffective. In this paper, a new mechanism is proposed to reduce background noise from speech communications. The procedure is based on a two-sensor adaptive noise canceller that is capable of assigning an appropriate filter adapting to properties of the noise. The criterion to achieve this is based on measuring the eigenvalue spread based on the autocorrelation of the input noise. The proposed noise canceller (INC) applies an adaptive algorithm according to the characteristics of the input signal. Various experiments based on this technique using real-world signals are conducted to gauge the effectiveness of the approach. Initial results illustrated the system capabilities in executing noise cancellation under different types of environmental noise. The results based on the INC technique indicate fast convergence rates; improvements up to 30 dB in signal-to-noise ratio and at the same time shows 65% reduction of computational power compared to conventional method.     

Estimation of soil dispersivity using soft computing approaches

The accurate estimation of soil dispersivity (α) is required for characterizing the transport of contaminants in soil. The in situ measurement of α is costly and time-consuming. Hence, in this study, three soft computing methods, namely adaptive neuro-fuzzy inference system (ANFIS), artificial neural network (ANN), and gene expression programming (GEP), are used to estimate α from more readily measurable physical soil variables, including travel distance from source of pollutant (L), mean grain size (D ₅₀), soil bulk density (ρ _b), and contaminant velocity (V _c). Based on three statistical metrics [i.e., mean absolute error, root-mean-square error (RMSE), and coefficient of determination (R ²)], it is found that all approaches (ANN, ANFIS, and GEP) can accurately estimate α. Results also show that the ANN model (with RMSE = 0.00050 m and R ² = 0.977) performs better than the ANFIS model (with RMSE = 0.00062 m and R ² = 0.956), and the estimates from GEP are almost as accurate as those from ANFIS. The performance of ANN, ANFIS, and GEP models is also compared with the traditional multiple linear regression (MLR) method. The comparison indicates that all of the soft computing methods outperform the MLR model. Finally, the sensitivity analysis shows that the travel distance from source of pollution (L) and bulk density (ρ _b) have, respectively, the most and the least effect on the soil dispersivity.

     

A comprehensive study of clustering ensemble weighting based on cluster quality and diversity

Pattern Analysis and Applications - Clustering as a major task in data mining is responsible for discovering hidden patterns in unlabeled datasets. Finding the best clustering is also considered as...     

Optical properties of graphene based annular photonic crystals

The optical properties of a graphene based annular photonic crystal (APC) are theoretically investigated. The proposed structure is a hollow core cylindrical shell consists of the alternate dielectric layer and graphene monolayer immersed in free space. In order to study the photonic band structures of the APC, we obtained the optical spectra of the graphene based APC by employing the transfer matrix method in the cylindrical waves for both TE and TM polarizations. In this work we study the effect of different geometrical and optical parameters of the structure on the low loss high reflectance graphene induced band gap. It is found that the graphene induced band gap which appeared in the frequency below 10 THz is polarization independent and remains almost invariant with the change in the period number, the radius of the inner core region and the refractive indices of the inner core region and the surrounding medium. However, its width increases by increasing the azimuthal mode number and the chemical potential of the graphene monolayers and decreases by increasing the refractive index and the thickness of the dielectric layers.     

Ranking proposed models for attaining surface free energy of powders using contact angle measurements

This study is an attempt to evaluate the applicability of various proposed mathematical models to calculate the surface free energy of commercially available powders. The capillary rise experiments were employed to achieve the contact angle between 15 powders and seven corresponding liquids by means of the modified Lucas–Washburn's equation. The surface free energy of powders was then calculated using different models inclusive of Owens/Wendt, harmonic mean, van Oss et al., combined mean (i.e. the combination of Owens/Wendt and harmonic mean models) and Li/Neumann models. Mathematical approaches were used to assess the accuracy of the calculated surface free energy and its components for different powders. A series of first-, second- and third-order functions as well as an exponential one were developed and put to test for one-, two- and three-parameter variables of liquid surface tension. Unfortunately, all such functions did not perform well in correctly estimating the contact angles of the liquid/powder systems (i.e. r² range being 0.48–0.68 and PF/3 range being 114–312). On the other hand, a series of trained artificial neural networks (ANNs) comparatively gave good correlations, predicting with unsurpassed accuracy the contact angles of the same corresponding liquid/powder systems (i.e. r² range being 0.93–0.94 and PF/3 range being 30–55). Therefore, the attained and tested ANNs were used further to provide the surface free energy of the 15 powders. In addition, the ANNs were also employed to rank the surface free energies of powders as well as their corresponding components as calculated by other models. The results showed that the geometric mean model was able to calculate the surface free energy of powders with more accuracy than all the other models.