Fuzzy logic-based pre-classifier for tropical wood species recognition system

Classifying tropical wood species poses a considerable economic challenge and failure to classify the wood species accurately can have significant effects on timber industries. The problem of wood recognition is compounded with the nonlinearities of the features among the similar wood species. Besides that, large wood databases presented a problem of large processing time especially for online wood recognition system. In view of these problems, we propose the use of fuzzy logic-based pre-classifier as a means of treating uncertainty to improve the classification accuracy of tropical wood recognition system. The pre-classifier serve as a clustering mechanism for the large database simplifying the classification process making it more efficient. The use of the fuzzy logic-based pre-classifier has managed to increase the accuracy of the wood recognition system by 4 % and reduce the processing time for training and testing by more than 75 % and 26 % respectively.     

Hydrodynamics of gas fluidized beds with mixture of group D and B particles

The dynamics of a gas‐solid fluidized bed containing Geldart Group D particles mixed with a small proportion of Geldart Group B particles are investigated using pressure fluctuations data. Time series analysis, using a variety of nonlinear dynamics tools, shows that the slugging present with Group D particles can be suppressed by the addition of a small proportion of Group B particles. The power spectra and the auto‐correlation function are used for a preliminary evaluation of dominant slug frequencies. It is shown that the bed fluidized with the mixture of Group D and B particles behaves in a less periodic manner and is dominated by more random bubble motion. On the other hand, the correlation integral is used to analyze the chaotic behaviour of the flow, through evaluation of the fractal structure of the reconstructed attractors. It is shown that the bed fluidized with Group D particles is characterized by a combination of steady slug motion and irregular particles motion. The behaviour of the fluidized bed of Group D/B particles mixture is characterized by a single correlation dimension for a wide range of fluidization velocities.     

Brain tumor classification from multi-modality MRI using wavelets and machine learning

In this paper, we propose a brain tumor segmentation and classification method for multi-modality magnetic resonance imaging scans. The data from multi-modal brain tumor segmentation challenge (MICCAI BraTS 2013) are utilized which are co-registered and skull-stripped, and the histogram matching is performed with a reference volume of high contrast. From the preprocessed images, the following features are then extracted: intensity, intensity differences, local neighborhood and wavelet texture. The integrated features are subsequently provided to the random forest classifier to predict five classes: background, necrosis, edema, enhancing tumor and non-enhancing tumor, and then these class labels are used to hierarchically compute three different regions (complete tumor, active tumor and enhancing tumor). We performed a leave-one-out cross-validation and achieved 88% Dice overlap for the complete tumor region, 75% for the core tumor region and 95% for enhancing tumor region, which is higher than the Dice overlap reported from MICCAI BraTS challenge.     

Cryptanalysis of an embedded systems’ image encryption

Multimedia Tools and Applications - Recently, a new image encryption-scheme for embedded systems based on continuous third-order hyperbolic sine chaotic system, has been proposed. The...     

Silicon Application Enhances the Photosynthetic Pigments and Phenolic/Flavonoid Content by Modulating the Phenylpropanoid Pathway in Common Buckwheat under Aluminium Stress

Silicon - Silicon (Si) is very effective in the amelioration of heavy metal (HM) stress in different crop plants. This investigation was conducted to assess the protective role of Si in modulating...     

Microscopic Evaluation of Strain Distribution in Granular Materials during Shear

The evolution of local strains during shear of particles of a granular material is presented in this paper. A cylindrical specimen composed of 6.5-mm spherical plastic particles was loaded under an axisymmetric triaxial loading condition. Computed tomography (CT) was used to acquire three-dimensional images of the specimen at three shearing stages. The high-resolution CT images were used to identify the 3D coordinates of 400 particles. Nine strain components (normal, shear, and rotation), rotation angles, and local dilatancy angles for particle groups were calculated, and their frequency distribution histograms are presented and discussed. It was found that there is no preferred shear direction, and the standard deviation values for shear strain components (εxy, εxz, and εyz) were almost equal for the specific test shearing stage. Shear strains as high as 25.6% were recorded for some particle groups. Furthermore, granular particle groups rotated in the 3D space with almost equal amounts of rotation strains when loaded under axisymmetric triaxial condition. Rotation strain values are very close to the corresponding shear strains. Compared to particle sliding, rotation plays a major role in the shearing resistance of granular materials. The cumulative vertical rotation angles can be as high as 38° and the horizontal rotation angles have values as high as 60°. The statistical distributions of the local dilatancy angle (ψ1) of particle groups were calculated and found to be increasing as shearing continues. The “global” dilatancy angle value is very close to the mean local ψ1 during the first stage of shearing (i.e, when global εz = ?7.3%)     

Performance of PAM/PEI gel system for water shut‐off in high temperature reservoirs: Laboratory study

A polymer gel is one of the common remediate methods to either reduce or totally block excessive water production in oilfields. Some systems demonstrated an excellent performance in treating the problem like polyacrylamide tert‐butyl acrylate (PAtBA)/polyethylenimine (PEI). In this study, polyacrylamide (PAM) was introduced as a cheap alternative to PAtBA that can tolerate high salinity reservoirs. The thermal stability of the PAM/PEI polymeric gel in saline water was examined at 150°C (302F). Samples prepared in sea water showed better stability compared with distilled and field water. Dynamic rheology and core‐flooding experiments were used to evaluate the PAM / PEI gel system at high temperatures. NaCl and NH₄Cl were evaluated as a possible retarders for delaying the gelation time in order to achieve a successful placement. NH₄Cl was found to be more effective retarder. Core‐flooding tests were conducted in sandstone and carbonate cores. The subject polymer gel was injected at rates typical of those in field applications. The injectivity of PAM/PEI was tested in Berea sandstone cores with initial permeability of ～45 mD. The post‐treatment of the system showed a permeability reduction of ～94% for a period of two weeks. The injectivity in low permeability carbonate cores required more retardation compared with the injectivity in sandstone cores. The gel reduced the permeability to brine in Indiana limestone core by 99.8% for more than 5 months. Rheology of cured gel samples indicated that the gel strength needs about one day of curing in the core for the strength to stabilize. © 2015 Wiley Periodicals, Inc. J. Appl. Polym. Sci. 2015 , 132, 41869.