Image classification is the process of finding common features in images from various classes and applying them to categorize and label them. The main problem of the image classification process is the abundance of images, the high complexity of the data, and the shortage of labeled data, presenting the key obstacles in image classification. The cornerstone of image classification is evaluating the convolutional features retrieved from deep learning models and training them with machine learning classifiers. This study proposes a new approach of “hybrid learning” by combining deep learning with machine learning for image classification based on convolutional feature extraction using the VGG-16 deep learning model and seven classifiers. A hybrid supervised learning system that takes advantage of rich intermediate features extracted from deep learning compared to traditional feature extraction to boost classification accuracy and parameters is suggested. They provide the same set of characteristics to discover and verify which classifier yields the best classification with our new proposed approach of “hybrid learning.” To achieve this, the performance of classifiers was assessed depending on a genuine dataset that was taken by our camera system. The simulation results show that the support vector machine (SVM) has a mean square error of 0.011, a total accuracy ratio of 98.80%, and an F1 score of 0.99. Moreover, the results show that the LR classifier has a mean square error of 0.035 and a total ratio of 96.42%, and an F1 score of 0.96 comes in the second place. The ANN classifier has a mean square error of 0.047 and a total ratio of 95.23%, and an F1 score of 0.94 comes in the third place. Furthermore, RF, WKNN, DT, and NB with a mean square error and an F1 score advance to the next stage with accuracy ratios of 91.66%, 90.47%, 79.76%, and 75%, respectively. As a result, the main contribution is the enhancement of the classification performance parameters with images of varying brightness and clarity using the proposed hybrid learning approach.
Multiple eliminations (de-multiple) are one of seismic processing steps to remove their effects and delineate the correct primary refractors. Using normal move out to flatten primaries is the way to eliminate multiples through transforming these data to frequency-wavenumber domain. The flatten primaries are aligned with zero axis of the frequency-wavenumber domain and any other reflection types (multiples and random noise) are distributed elsewhere. Dip-filter is applied to pass the aligned data and reject others will separate primaries from multiple after transforming the data back from frequency-wavenumber domain to time-distance domain. For that, a suggested name for this technique as normal move out- frequency-wavenumber domain
... Show MoreThe problem of the study was to identify the possibility of benefiting from the application of the target cost system as a modern cost system to activate the environmental cost management instead of the traditional systems used in the company due to the great transformations witnessed by the business environment in all fields, which have resulted in the search for modern systems to provide more accurate and more appropriate information to reduce Costs, because accurate information makes the company have a complete vision to achieve the company’s goals. To solve this problem, the research was based on the following hypothesis (that the role of the target cost system leads to the activation of environmental cost management). Target c
... Show MoreLaportea aestuans L. (Chew), Commelina virginica (L.) and Sida rhombifolia (L.) are common wild plants used in treating several ailments including diarrhea, dysentery, hernia, oedema, ulcers and many more in traditional African medicine especially, Nigeria. The potentials of Random Amplified polymorphic DNA (RAPD) primers in delimiting intra-specific variation in L. aestuans, C. virginica and S. rhombifolia was assessed using three RAPD primers. Plant and soil samples were collected from 19 local government areas in Lagos State and assessed for genetic and biochemical relationships. A total of 56 bands were produced of which 44 were polymorphic. Maximum number of bands (21) was produced by OPY
... Show MoreFrom September 2002 to August 2003 monthly samples of fish were collected from two stations at the area of study. The results of the present study showed that the sex-ratio (male: female) was 1:0.95. Sexual maturity was reached by all fishes above 28 cm in total length , the smallest mature male was 21.3 cm in total length and body weight 164 gm. While the smallest mature female was 21.5 cm in T.L. and body weight 155 gm. The mature male and female were in the second year of their ages. The breeding season extended from the end of February until the end of June and another season started from Se
... Show MoreIn wide range of chemical, petrochemical and energy processes, it is not possible to manage without slurry bubble column reactors. In this investigation, time average local gas holdup was recorded for three different height to diameter (H/D) ratios 3, 4 and 5 in 18" diameter slurry bubble column. Air-water-glass beads system was used with superficial velocity up to 0.24 m/s. the gas holdup was measured using 4-tips optical fiber probe technique. The results show that the axial gas holdup increases almost linearly with the superficial gas velocity in 0.08 m/s and levels off with a further increase of velocity. A comparison of the present data with those reported for other slurry bubble column having diameters larger than
... Show MoreThe present study was implemented in the period from January to December 2017, to assess the assemblage of fish, with the effects of some environmental factors and knowledge the impacts of annual periodic fluctuations between drowning and drought on the abundance and size-spectrum on the fish community in Al-Cibyaish marsh. Water temperature ranged between 13 ͦ C in January to 35 ͦ C in July, salinity from 2.90 PSU (Practical salinity unite) in February to 4.14 PSU in August. Hydrogen ion ranged between 7.60 in July to 8.30 in February. The present study appears contribution of environmental variables in the distribution, widespread and occurrence of fish assemblage in the Al-Chibyaish marsh. A total of 3294 specimens were collected re
... Show MoreThe aim of this work is to produce samples from Iraqi raw materials like Husyniat Bauxite (raw and burnt) and to study the effect of some additives like white Doekhla kaolin clays and alumina on that material properties were using sodium silica as a binding material. Five mixtures were prepared from Bauxite (raw and burnt) and kaolin clays, with an additive of (40) ml from sodium silica and alumina of (2.5, 5, 7.5,10 wt %) percentage as a binding material. the size grading was through sieving. The formation of all specimens was conducted by a measured gradually semi-dry pressing method under a compression force of (10) Tons and humidity ratio ranging from (5-10) % from mixture weight. Drying all specimens was done and then they were burn
... Show MoreAl-Qudis power plant was chosen, as one of the power stations of Baghdad, to investigate the effects of Cadmium that emitted from combustion of crude oil in that power plant on the workers' glutathione serum level. Air samples were taken seasonally during August 2011- July 2012 from four sites at Al- Qudis power plant which are oil treatment unit 1(site 1), oil treatment 2 (site2), pre –chimney 1(site 3) and pre-chimney 2 (site 4), to measure levels of heavy metal (cadmium) under study. Blood samples were collected from the workers to estimate the heavy metal Cadmium. Air cadmium levels during summer (August and September) were varied from 6.26 ± 0.6 μg/m3 at site 1 to 6.89 ± 0.67 μg/m3 at site 3, while in spring (end of March, and
... Show MoreAbstract: Background: Staphylococcus aureus is Gram-positive bacteria that lives as a normal flora in living organisms but can be pathogenic to humans. Although a relatively unspectacular, nonmotile coccoid bacterium, S. aureus is a dangerous human pathogen in both community-acquired and nosocomial infections. Due to the increasing emergence of new strains of this antibiotic-resistant bacteria, it has become essential to approach different methods to control this pathogen. One of these methods is the antimicrobial photodynamic inactivation process using a low-level laser, in this paper, the Photodynamic effects of Rose Bengal and LLLL on the virulence factors of S.aureus were evaluated.