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.
In this article, the research presents a general overview of deep learning-based AVSS (audio-visual source separation) systems. AVSS has achieved exceptional results in a number of areas, including decreasing noise levels, boosting speech recognition, and improving audio quality. The advantages and disadvantages of each deep learning model are discussed throughout the research as it reviews various current experiments on AVSS. The TCD TIMIT dataset (which contains top-notch audio and video recordings created especially for speech recognition tasks) and the Voxceleb dataset (a sizable collection of brief audio-visual clips with human speech) are just a couple of the useful datasets summarized in the paper that can be used to test A
... Show MoreThe social contract represents a set of laws and determinants agreed upon by a group of individuals in order to organize society for the better.This agreement guarantees them to live in peace according to the pre-agreed laws, and on the basis of that, it represents the key to resolving the crisis relations between the state and society, and this is what prompted Iraqi society to move towards the formulation of a new social contract through popular protest movements in 2019.To overcome the old social contract that shook the trust between the state and society as a result of its negative outputs at various political, economic and social levels, and many problems emerged that hindered the process of building the social contra
... Show MoreSignature verification involves vague situations in which a signature could resemble many reference samples or might differ because of handwriting variances. By presenting the features and similarity score of signatures from the matching algorithm as fuzzy sets and capturing the degrees of membership, non-membership, and indeterminacy, a neutrosophic engine can significantly contribute to signature verification by addressing the inherent uncertainties and ambiguities present in signatures. But type-1 neutrosophic logic gives these membership functions fixed values, which could not adequately capture the various degrees of uncertainty in the characteristics of signatures. Type-1 neutrosophic representation is also unable to adjust to various
... Show MoreMany purposes require communicating audio files between the users using different applications of social media. The security level of these applications is limited; at the same time many audio files are secured and must be accessed by authorized persons only, while, most present works attempt to hide single audio file in certain cover media. In this paper, a new approach of hiding three audio signals with unequal sizes in single color digital image has been proposed using the frequencies transform of this image. In the proposed approach, the Fast Fourier Transform was adopted where each audio signal is embedded in specific region with high frequencies in the frequency spectrum of the cover image to sa
... Show MoreThe aim of the work is synthesis and characterization of bidentate ligand [3-(3-acetylphenylamino)-5,5-dimethylcyclohex-3-enone][HL], from the reaction of dimedone with 3-amino acetophenone to produce the ligand [HL], the reaction was carried out in dry benzene as a solvent under reflux. The prepared ligand [HL] was characterized by FT-IR, UV-Vis spectroscopy, 1H, 13C-NMR spectra, Mass spectra, (C.H.N) and melting point. The mixed ligand complexes were prepared from ligand [HL] was used as a primary ligand while 8-hydroxy quinoline [HQ] was used as a secondary ligand with metal ion M(Π).Where M(Π) = (Mn ,Co ,Ni ,Cu ,Zn ,Cd and Pd) at reflux ,using ethanol as a solvent, KOH as a base. Complexes of the composition [M(L)(Q)] with (1
... Show More