Dates Fruit Recognition: From Classical Fusion to Deep Learning

There are over 200 different varieties of dates fruit in the world. Interestingly, every single type has some very specific features that differ from the others. In recent years, sorting, separating, and arranging in automated industries, in fruits businesses, and more specifically in dates businesses have inspired many research dimensions. In this regard, this paper focuses on the detection and recognition of dates using computer vision and machine learning. Our experimental setup is based on the classical machine learning approach and the deep learning approach for nine classes of dates fruit. Classical machine learning includes the Bayesian network, Support Vector Machine, Random Forest, and Multi-Layer Perceptron (MLP), while the Convolutional Neural Network is used for the deep learning set. The feature set includes Color Layout features, Fuzzy Color and Texture Histogram, Gabor filtering, and the Pyramid Histogram of the Oriented Gradients. The fusion of various features is also extensively explored in this paper. The MLP achieves the highest detection performance with an F-measure of 0.938. Moreover, deep learning shows better accuracy than the classical machine learning algorithms. In fact, deep learning got 2% more accurate results as compared to the MLP and the Random forest. We also show that classical machine learning could give increased classification performance which could get close to that provided by deep learning through the use of optimized tuning and a good feature set.     

Conserved Imprinted Genes between Intra-Subspecies and Inter-Subspecies Are Involved in Energy Metabolism and Seed Development in Rice

Genomic imprinting is an epigenetic phenomenon in which a subset of genes express dependent on the origin of their parents. In plants, it is unclear whether imprinted genes are conserved between subspecies in rice. Here we identified imprinted genes from embryo and endosperm 5–7 days after pollination from three pairs of reciprocal hybrids, including inter-subspecies, japonica intra-subspecies, and indica intra-subspecies reciprocal hybrids. A total of 914 imprinted genes, including 546 in inter-subspecies hybrids, 211 in japonica intra-subspecies hybrids, and 286 in indica intra-subspecies hybrids. In general, the number of maternally expressed genes (MEGs) is more than paternally expressed genes (PEGs). Moreover, imprinted genes tend to be in mini clusters. The number of shared genes by R9N (reciprocal crosses between 9311 and Nipponbare) and R9Z (reciprocal crosses between 9311 and Zhenshan 97), R9N and RZN (reciprocal crosses between Zhonghua11 and Nipponbare), R9Z and RZN was 72, 46, and 16. These genes frequently involved in energy metabolism and seed development. Five imprinted genes (Os01g0151700, Os07g0103100, Os10g0340600, Os11g0679700, and Os12g0632800) are commonly detected in all three pairs of reciprocal hybrids and were validated by RT-PCR sequencing. Gene editing of two imprinted genes revealed that both genes conferred grain filling. Moreover, 15 and 27 imprinted genes with diverse functions in rice were shared with Arabidopsis and maize, respectively. This study provided valuable resources for identification of imprinting genes in rice or even in cereals.     

Enrichment of antibacterial compound from the stem bark of Stereospermum fimbriatum using supercritical carbon dioxide extraction

ABSTRACT

Supercritical carbon dioxide (sc-CO₂) extraction was carried out on Stereospermum fimbriatum’s stem bark in order to obtain an enriched extract containing the targeted active compound. The recovery of its active compound, C1, was compared with the most active Soxhlet’s extract of dichloromethane. A minimum inhibitory concentration (MIC) assay was done to examine the antibacterial activity of extracts against methicillin-resistant Staphylococcus aureus. The optimum condition for an enriched extract of sc-CO₂ to have a maximum recovery of C1 at MIC value of 400 µg/mL was suggested to be operated at 40°C and pressure at 30 MPa, with addition of 6% co-solvent.     

The space time CE/SE method for solving one-dimensional batch crystallization model with fines dissolution

This article is concerned with the numerical investigation of one-dimensional population balance models for batch crystallization process with fines dissolution. In batch crystal ization, dissolution o...     

Structural Rietveld refinement and magnetic features of prosademium (Pr) doped Cu nanocrystalline spinel ferrites

Pr doped spinel nanoferrites having following composition Cu Pr_x Fe_2-xO₄ (x?=?0, 0.25, 0.50, 0.75, 1.00) were synthesized using sol-gel route. Prosademium (Pr) which is a rare earth metal was doped to tailor the properties of the Cu spinel nanoferrites. Characterization tools such as FTIR, XRD, FESEM and VSM were employed to investigate the phase, absorption bands, structure, microstructure and magnetic properties. FTIR was used to see the absorption bands and force constants of the Pr doped Cu spinel nanoferrites. Crystallite size, lattice parameters, cell volume and micro strains were determined from XRD data. Bulk density, X-ray density and porosity of the Pr doped Cu spinel nanoferrites were also calculated. Rietveld refinement was applied to investigate the detailed structural parameters of the Pr doped Cu spinel nanoferrites. Unit cell software based on regression diagnostics was also used to determine the structural factors of the prepared nanoferrites. It was noticed that Cu nanoferrite showed the single-phase cubic structure whereas the Pr doped Cu ferrite depicted the orthorhombic structure respectively. FESEM show large amount of agglomerations at x?=?0.00 whereas irregular shape of the particles confirms the nanosized of ferrites as well. Magnetic properties were determined from VSM which elaborated the remanence, coercivity, saturation magnetization, anisotropy constant (K), initial permeability, Bohr magneton and YK (Yafet and Kittel) angles. Magnetic saturation, coercivity, remanence and anisotropy constant were decreased with Pr concentration in Cu spinel ferrite. However, YK angles were increased with Pr doping in Cu spinel nanoferrites. Microwave frequency response was evaluated which confirm the use of these Pr doped Cu spinel nanoferrites in the range of 5.2?Ghz–9.5?GHz respectively. The properties of these Pr doped Cu spinel nanoferrites suggested their used for microwave devices, memory devices and recording media applications.     

Implication of scanning electron microscopy as a tool for identification of novel,nonedible oil seeds for biodiesel production

Biodiesel is a promising, bio-based, renewable, nontoxic, environment friendly, and alternative fuel for petroleum derived fuels which helps to reduce dependency on conventional fossil fuels. In this study, six novel, nonedible seed oil producing feedstock were explored for their potential for sustainable production of biodiesel. It is very important to correctly identify oil yielding plant species. Scanning electron microscopy (SEM) was used as reliable tool for authentic identification of oil yielding seeds. Macromorphological characters of seeds were studied with light microscopy (LM). Outcomes of LM of seeds exposed distinctive variation in seed size from 16.3 to 3.2 mm in length and 12.4 to 0.9 mm in width, shape varied from oval to triangular, and color from black to light brown. Oil content of nonedible seed ranged from 25 to 30% (w/w). Free fatty acid content of seed oil varied from 0.32 to 2.5 mg KOH/g. Moreover, ultra structural study of seeds via SEM showed variation in surface sculpturing, cell arrangement, cell shape, periclinal wall shape, margins, protuberances, and anticlinal wall shape. Surface sculpturing varied from rugged, reticulate, varrucose, papillate, and striate. Periclinal wall arrangements confirmed variation from rough, wavy, raised, depressed, smooth, and elevated whereas, anticlinal walls pattern showed variation from profuse undulating, smooth, raised, grooved, deep, curved, and depressed. It was concluded that SEM could be a latent and advanced technique in unveiling hidden micromorphological characters of nonedible oil yielding seeds which delivers valuable information to researchers and indigenous people for precise and authentic identification and recognition.     

URWF: user reputation based weightage framework for twitter micropost classification

Information Systems and e-Business Management - Sentiment analysis is an emerging field that helps in understanding the sentiments of users on microblogging sites. Many sentiment analysis...     

Controlling Chaos and Neimark–Sacker Bifurcation in a Host–Parasitoid Model

In this paper, a new density‐dependent host–parasitoid model is proposed. The modification is based on density‐dependent factor by introducing Hassell growth function in host population. Moreover, the permanence of solutions, existence and uniqueness of positive equilibrium, local asymptotic stability and global behavior of the positive equilibrium point are also investigated. It is demonstrated that system endures Neimark–Sacker bifurcation for wide range of bifurcation parameter. In order to control chaos due to emergence of Neimark–Sacker bifurcation, two feedback control strategies, that is, OGY and hybrid control methods are implemented. Finally, all mathematical analysis, particularly, Neimark–Sacker bifurcation, chaos control strategies, and global asymptotic stability of unique positive point are verified with the help of numerical simulations.