A Framework of Deep Optimal Features Selection for Apple Leaf Diseases Recognition

Identifying fruit disease manually is time-consuming, expert-required, and expensive; thus, a computer-based automated system is widely required. Fruit diseases affect not only the quality but also the quantity. As a result, it is possible to detect the disease early on and cure the fruits using computer-based techniques. However, computer-based methods face several challenges, including low contrast, a lack of dataset for training a model, and inappropriate feature extraction for final classification. In this paper, we proposed an automated framework for detecting apple fruit leaf diseases using CNN and a hybrid optimization algorithm. Data augmentation is performed initially to balance the selected apple dataset. After that, two pre-trained deep models are fine-tuning and trained using transfer learning. Then, a fusion technique is proposed named Parallel Correlation Threshold (PCT). The fused feature vector is optimized in the next step using a hybrid optimization algorithm. The selected features are finally classified using machine learning algorithms. Four different experiments have been carried out on the augmented Plant Village dataset and yielded the best accuracy of 99.8%. The accuracy of the proposed framework is also compared to that of several neural nets, and it outperforms them all.     

Fusion of thermal infrared and visible spectra for robust moving object detection

The detection of moving objects is a crucial step for many video surveillance applications whether using a visible camera (VIS) or an infrared (IR) one. In order to profit from both types, several fusion methods were proposed in the literature: low-level fusion, medium-level fusion and high-level fusion. The first one is the most used for moving objects’ detection in IR and VIS spectra. In this paper, we present an overview of the different moving object detection methods in IR and VIS spectra and a state of the art of the low-level fusion techniques. Moreover, we propose a new method for moving object detection using low-level fusion of IR and VIS spectra. In order to evaluate quantitatively and qualitatively our proposed method, three series of experiments were carried out using two well-known datasets namely “OSU Color-Thermal Database” and “INO-Database”; the results of these evaluations show promising results and demonstrate the effectiveness of the proposed method.     

TMT-HCC: A tool for text mining the biomedical literature for hepatocellular carcinoma (HCC) biomarkers identification

Hepatocellular carcinoma (HCC) is the third leading cause of cancer-related mortality worldwide. New insights into the pathogenesis of this lethal disease are urgently needed. Chromosomal copy number alterations (CNAs) can lead to activation of oncogenes and inactivation of tumor suppressors in human cancers. Thus, identification of cancer-specific CNAs will not only provide new insight into understanding the molecular basis of tumor genesis but also facilitate the identification of HCC biomarkers using CNA.     

Multi-breath dry powder inhaler for delivery of cohesive powders in the treatment of bronchiectasis

A series of co-engineered macrolide–mannitol particles were successfully prepared using azithromycin (AZ) as a model drug. The formulation was designed to target local inflammation and bacterial colonization, via the macrolide component, while the mannitol acted as mucolytic and taste-masking agent. The engineered particles were evaluated in terms of their physico-chemical properties and aerosol performance when delivered via a novel high-payload dry powder Orbital^? inhaler device that operates via multiple inhalation manoeuvres. All formulations prepared were of suitable size for inhalation drug delivery and contained a mixture of amorphous AZ with crystalline mannitol. A co-spray dried formulation containing 200?mg of 50:50?w/w AZ: mannitol had 57.6%?±?7.6% delivery efficiency with a fine particle fraction (≤6.8?µm) of the emitted aerosol cloud being 80.4%?±?1.1%, with minimal throat deposition (5.3?±?0.9%). Subsequently, it can be concluded that the use of this device in combination with the co-engineered macrolide–mannitol therapy may provide a means of treating bronchiectasis.     

Complex structural contribution of the morphotropic phase boundary in Na0.5Bi0.5TiO3 - CaTiO3 system

The correlation between structure and dielectric properties of lead-free (1-x)Na_0.5Bi_0.5TiO₃ - xCaTiO₃ ((1-x)NBT - xCT) polycrystalline ceramics was investigated systematically by X-ray diffraction, combined with impedance spectroscopy for dielectric characterizations. The system shows high miscibility in the entire composition range. A morphotropic phase boundary (MPB), at 0.09?≤?x?<?0.15 was identified where rhombohedral and orthorhombic symmetries coexist at room temperature. The fraction of orthorhombic phase increases gradually with x in the MPB region. Dielectric measurements reveal that the relative permittivity increase with addition of Ca²⁺. This behavior is unusual with this kind of doping. A thermal hysteresis occurred only in the MPB composition which varies in a non-monotonically manner with x, detected by dielectric properties. This phenomenon is related to the crystalline microstructure by a linear relationship between the fraction of each phase and dielectric properties, and, more precisely, to the strong interaction between rhombohedral and orthorhombic phases.     

Multivariate Analysis of the Stability of Spray-Dried Eupenicillium javanicum Peptidases

Peptidases occupy a central position in the enzyme market because of their importance in many areas, such as for physiological processes, foods, and detergents, as well as in the pharmaceutical, leather, and biotechnology industries. Microbial production is among the major sources of peptidases because it presents many advantages when compared with other methods. In this study, the metallopeptidases produced by the fungus Eupenicillium javanicum under a solid-state fermentation bioprocess were spray-dried. The enzymatic extract was dried using drying adjuvants, and optimal conditions for preserving enzymatic activity were studied following a Box-Behnken experimental design. The spray process factors studied were the air-drying temperature, enzyme feed flow rate, and the proportion of enzyme/additive. The responses analyzed were the dry extract yield and enzymatic activity after spray drying. Additionally, the stability of the dry extracts was assessed during 180 days at 4°C and 25°C. The results revealed extract yields of up to 66.12% and good enzymatic activity for intermediate values of temperature and adjuvant proportions. Furthermore, the dried enzymatic extracts showed potential for future commercial applications because of their stability at 25°C for 180 days.     

Tunning the Physical Properties of PVDF/PVC/Zinc Ferrite Nanocomposites Films for More Efficient Adsorption of Cd (II)

This work deals with the synthesis of ZnFe₂O₄ NPs and studies the effect of addition on the physical properties PVDF/PVC blend. XRD affirmed the formation of ZnFe₂O₄ NPs and HRTEM shows that the size of the prepared ZnFe₂O₄ NPs ranged from 20 to 55 nm. The effect of ZnFe₂O₄ on the behavior of PVDF/PVC was studied through XRD, ATR-FTIR, FESEM and UV–Visible spectroscopy. XRD revealed that the addition of ZnFe₂O₄ NPs enhanced the crystallinity of PVDF/PVC blend system and also confirmed the incorporation of ZnFe₂O₄ NPs by appearing a diffraction peak at 2θ equals 35°. ATR-FTIR affirmed the interaction between blend sample and ZnFe₂O₄ NPs by appearing new bands 554 cm^?1 and 421 cm^?1 which are corresponded to ZnFe₂O₄ NPs functional group with appearing a new band at 603 cm^?1. FESEM showed that the addition of ZnFe₂O₄ to PVDF/PVC blend improved surface properties, for example, roughness average has been increased from 319 to 414 nm while maximum height increased from 260 to 473 nm for PVDF/PVC and PVDF/PVC/10% ZnFe₂O₄, respectively. Optical properties and band gap calculations revealed that addition of ZnFe₂O₄ NPs changes the structure of polyblend samples which results due to the formation of localized states. The removal efficiency of Cd (II) by using PVDF/PVC/10% ZnFe₂O₄ reached about 50% at pH 6 after 60 min. the absorption mechanism as well as kinetics isotherm have been studied. It is found that adsorption of Cd (II) occurred through the Langmuir mechanism and fellow pseudo-second order isotherm.

     

Gallium gradients in Cu(In,Ga)Se2 thin‐film solar cells

The gallium gradient in Cu(In,Ga)Se₂ (CIGS) layers, which forms during the two industrially relevant deposition routes, the sequential and co‐evaporation processes, plays a key role in the device performance of CIGS thin‐film modules. In this contribution, we present a comprehensive study on the formation, nature, and consequences of gallium gradients in CIGS solar cells. The formation of gallium gradients is analyzed in real time during a rapid selenization process by in situ X‐ray measurements. In addition, the gallium grading of a CIGS layer grown with an in‐line co‐evaporation process is analyzed by means of depth profiling with mass spectrometry. This gallium gradient of a real solar cell served as input data for device simulations. Depth‐dependent occurrence of lateral inhomogeneities on the µm scale in CIGS deposited by the co‐evaporation process was investigated by highly spatially resolved luminescence measurements on etched CIGS samples, which revealed a dependence of the optical bandgap, the quasi‐Fermi level splitting, transition levels, and the vertical gallium gradient. Transmission electron microscopy analyses of CIGS cross‐sections point to a difference in gallium content in the near surface region of neighboring grains. Migration barriers for a copper‐vacancy‐mediated indium and gallium diffusion in CuInSe₂ and CuGaSe₂ were calculated using density functional theory. The migration barrier for the In_Cu antisite in CuGaSe₂ is significantly lower compared with the Ga_Cu antisite in CuInSe₂, which is in accordance with the experimentally observed Ga gradients in CIGS layers grown by co‐evaporation and selenization processes. Copyright © 2014 John Wiley & Sons, Ltd.     

Synthesis of a novolac‐based 3‐aminopropylsiloxane resin and its application for the removal of Cu2+, Cr3+, and Ni2+ from electroplating wastewater

Novolac resin was modified with 3‐aminopropyltrimthoxysilane to obtain phenol‐formaldehyde‐aminopropylsiloxane resin (PF‐APS). Fourier transformation infra‐red spectra, thermogravimetric analysis, elemental analysis, and pH‐metric titration were used to characterize PF‐APS. Its chemical formula was suggested to be C₁₄H_12.49N_0.1O₂Si_0.1. The resin shows high experimental metal ions uptake capacity within short time of equilibration. The metal capacity was determined by atomic absorption spectrometry to be 0.787 mEq Cu/g. Maximum separation efficiencies of Cu²⁺, Cr³⁺, and Ni²⁺ from aqueous solutions on PF‐APS were at pH 8.0 and time of stirring 60 min; 94.0%, 90.8%, 83.2%, respectively. No significant interference from the background ions Na⁺, Cl^?, and was observed on the separation process. The heavy metal ions were eluted using 0.01 mol L^?1 EDTA at 65°C releasing >94% of the separated metal ions. The method of separation was applied successfully to remove the heavy metal ions Cu²⁺, Cr³⁺, and Ni²⁺ from electroplating wastewater from Dekirnis, Dakahlia Governorate, Egypt. © 2014 Wiley Periodicals, Inc. J. Appl. Polym. Sci. 2014 , 131, 40993.