Minimum redundancy maximum relevance (mRMR) based feature selection from endoscopic images for automatic gastrointestinal polyp detection

Multimedia Tools and Applications - In this paper, a computer based system has been proposed as a support to gastrointestinal polyp detection. It can detect and classify gastrointestinal polyps...     

A new nonparametric double exponentially weighted moving average control chart

There are many practical situations where the underlying distribution of the quality characteristic either deviates from normality or it is unknown. In such cases, practitioners often make use of the nonparametric control charts. In this paper, a new nonparametric double exponentially weighted moving average control chart on the basis of the signed-rank statistic is proposed for monitoring the process location. Monte Carlo simulations are carried out to obtain the run length characteristics of the proposed chart. The performance comparison of the proposed chart with the existing parametric and nonparametric control charts is made by using various performance metrics of the run length distribution. The comparison showed the superiority of the suggested chart over its existing parametric and nonparametric counterparts. An illustrative example for the practical implementation of the proposed chart is also provided by using the industrial data set.     

A Coordinated Navigation Strategy for Multi-Robots to Capture a Target Moving with Unknown Speed

The paper proposes an algorithm for multi-robot coordination and navigation in order to intercept a target at a long distance. For this purpose, a limit cycle based algorithm using a neural oscillator with phase differences is proposed. The state of target is unknown, under the assumption that it is stationary or in motion with constant unknown speed along a straight line. Using the proposed algorithm, a group of robots is intended to move towards the target in such a way that the robots surround it. While moving to the target, self-collision between the robots is avoided. Moreover, a collision avoidance with static obstacles as well as dynamic target is realized. The robots reach the target at a desired distance, keeping uniformly distributed angles around the target. The algorithm is further extended so that a static interception point for the target can be estimated in place of pursuing a dynamic target, which is referred to as a virtual target in this paper. In other words, the robots move towards the virtual target instead of the actual target. The robots ultimately encircle the actual target when they arrive at the virtual target. The effectiveness of the proposed method is verified through simulation results.     

Saliency-weighted graphs for efficient visual content description and their applications in real-time image retrieval systems

The exponential growth in the volume of digital image databases is making it increasingly difficult to retrieve relevant information from them. Efficient retrieval systems require distinctive features extracted from visually rich contents, represented semantically in a human perception-oriented manner. This paper presents an efficient framework to model image contents as an undirected attributed relational graph, exploiting color, texture, layout, and saliency information. The proposed method encodes salient features into this rich representative model without requiring any segmentation or clustering procedures, reducing the computational complexity. In addition, an efficient graph-matching procedure implemented on specialized hardware makes it more suitable for real-time retrieval applications. The proposed framework has been tested on three publicly available datasets, and the results prove its superiority in terms of both effectiveness and efficiency in comparison with other state-of-the-art schemes.     

Magneto-resistance and Excess Conductivity Studies of Tl(Ba2−y Mg y )Ca 2 Cu 3 O 10−δ Samples

The flux pinning characteristics of T l(B a _2?y M g _y )C a ₂ C u ₃ O _10?δ(0.0≤y≤ 1.5) samples have been studied under the influence of various dc magnetic fields in the light of thermally activated flux flow model. It was observed form the magneto resistivity measurements that the activation energy U has been increased in the sample with Mg incorporation of y=0.5, however, it is decreased in the samples with higher Mg doping. This shows that lower Mg doping concentration promotes enhancement, whereas its higher concentration suppresses the flux pinning characteristics of Tl(Ba _2?yMg _y )Ca ₂Cu ₃ O _10?δ (0.0 ≤y≤1.5) samples. The excess conductivity analysis of Tl(Ba _2?yMg _y )Ca ₂Cu ₃ O _10?δ (0.0 ≤ y ≤ 1.5) samples has shown that the coherence length along the c-axis ξ _c(0), the interlayer coupling J, the phase relaxation time of the carriers τ _? , and the Fermi velocity v _F of the carriers are suppressed with Mg doping. However, the values of B _c0(T), B _c1(T), and J _c(0) are enhanced which complement the magnetoresistivity analysis. These results showed that the flux pinning characteristics are enhanced for lower doping concentration of Mg at the charge reservoir layer sites.     

Development of Al356/SiCp cast composites by injection of SiCp containing composite powders

One of the great challenges of producing cast metal matrix composites is the agglomeration tendency of the reinforcements. This would normally result in poor distribution of the particles, high porosity content, and low mechanical properties. In the present work, a new method for uniform distribution of very fine SiC particles with average size of less than 3 μm was employed. The key idea was to allow for gradual in situ release of properly wetted SiC particles in the liquid metal. For this purpose, SiC particles were injected into the melt in three different forms, i.e., untreated SiC_p, milled particulate Al–SiC_p composite powder, and milled particulate Al–SiC_p–Mg composite powder. The resultant composite slurries were then cast from either fully liquid (stir casting) or semisolid (compocasting) state. Consequently, the effects of the casting method and the type of the injected powder on the microstructural characteristics as well as the mechanical properties of the cast composites were investigated. The results showed that the distribution of SiC particles in the matrix and the porosity content of the composites were greatly improved by injecting milled composite powders instead of untreated-SiC particles into the melt. Casting from semisolid state instead of fully liquid state had similar effects. The average size of SiC particles incorporated into the matrix was also significantly reduced from about 8 to 3 μm by injecting milled composite powders. The ultimate tensile strength, yield strength and elongation of Al356/5 vol.%SiC_p composite manufactured by compocasting of the (Al–SiC_p–Mg)_cp injected melt were increased by 90%, 103% and 135%, respectively, compared to those of the composite manufactured by stir casting of the untreated-SiC_p injected melt.     

Modeling the free convection heat transfer in a partitioned cavity using ANFIS

In this paper, an adaptive neuro-fuzzy inference system (ANFIS) is used to predict the free convection in a partitioned cavity consisting of an adiabatic partition. The main focus of the present paper is to consider the effects of partition angle and Rayleigh number variation on average heat transfer in the partitioned cavity. The training data for optimizing the ANFIS structure is obtained experimentally. For the best ANFIS structure obtained in this study, the mean relative errors of the train and test data were found to be 0.055% and 1.735% respectively, which shows that ANFIS can predict the experimental results precisely.     

The Effect of Methylcellulose,Temperature, and Microwave Pretreatment on Kinetic of Mass Transfer During Deep Fat Frying of Chicken Nuggets

The aim of this study was to determine the effect of microwave pretreatment, usage of methylcellulose, oil temperature, and frying time on mass transfer during deep fat frying of chicken nuggets. Methylcellulose was used in batter and as a coating on product. Microwave with two power densities namely 3.7 and 7.4 W/g was used for reduction of initial moisture content of samples before frying. Frying was performed at three temperatures (150 °C, 170 °C, and 190 °C) and five intervals (0.5, 1, 2, 3, and 4 min) in the sunflower oil. The least oil content was observed when MC was used as a coating layer on non-precooked samples fried at 190 °C. Oil absorption of samples with MC in batter was partially higher compared to control samples. This could be attributed to the rheology of batters. The first-order kinetic model was fitted to moisture and oil content. For determining the correlation between temperature and moisture diffusivity, Arrhenius equation was used. The constant rate for moisture and oil transfer was in the range of 2.2–5 and 0.023–2.67 s^?1, respectively. Effective moisture diffusivity values were between 1.43?×?10^?8 and 3.24?×?10^?8 m²/s. Activation energy ranged between 0.71 and 1.71 kJ/mol.