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.
Emotion recognition has important applications in human-computer interaction. Various sources such as facial expressions and speech have been considered for interpreting human emotions. The aim of this paper is to develop an emotion recognition system from facial expressions and speech using a hybrid of machine-learning algorithms in order to enhance the overall performance of human computer communication. For facial emotion recognition, a deep convolutional neural network is used for feature extraction and classification, whereas for speech emotion recognition, the zero-crossing rate, mean, standard deviation and mel frequency cepstral coefficient features are extracted. The extracted features are then fed to a random forest classifier. In
... Show MoreThis paper presents a hybrid energy resources (HER) system consisting of solar PV, storage, and utility grid. It is a challenge in real time to extract maximum power point (MPP) from the PV solar under variations of the irradiance strength. This work addresses challenges in identifying global MPP, dynamic algorithm behavior, tracking speed, adaptability to changing conditions, and accuracy. Shallow Neural Networks using the deep learning NARMA-L2 controller have been proposed. It is modeled to predict the reference voltage under different irradiance. The dynamic PV solar and nonlinearity have been trained to track the maximum power drawn from the PV solar systems in real time.
Moreover, the proposed controller i
... Show MoreThis study is due to insufficient development of the issues of initial training in tennis at youthful (student) age. Objective: development of a methodological and scientific-methodological base of students' tennis with current trends in tennis. Summing up the best practices of modern tennis, we came to the conclusion that the formation of the art of reflection backhands in teaching beginner students of sports specialization to achieve future success. In modern conditions in the development of Russian tennis student opens the possibility of using new technologies and programs. Using these approaches, we have developed a training program and tested students' tennis in the pedagogical experiment, which resulted in its effectiveness.
In this work, the(m-phenylenediamine) and (2-naphthol) have been used in the synthesis of tetradentate ligand [m-phenylenedi(azo-2-naphthol)][H2L] type (N2O2). The ligand was refluxed in the ethanol with the metal ions [Co(II), Cu(II) and Zn(II)] salts, using triethyleamine as a base in (2:2) molar ratio to give the binuclear complexes. These complexes were characterised by (A.A), F.T.I.R, (U.V-Vis) spectroscopies, along with conductivity, chloride content and melting point measurement. These studies revealed an octahedral geometries for Co(II), Cu(II) and Zn(II) complexes with the general structure [M2(L)2(H2O)4]. The ligand and its complexes exhibited biological activity against the Bacillus(G+) strain and the
... Show MoreIn this work the fabrication and characterization of poly(3-hexylthiophene) P3HT-metallic nanoparticles (Ag, Al). Pulsed Laser Ablation (PLA) technique was used to synthesis the nanoparticles in liquid. The Fourier Transformer Infrared (FTIR) for all samples indicate the chemical interaction between the polymer and the nanoparticles. Scanning Electron Microscopic (SEM) analysis showed the particle size for P3HT-AgNps samples between 44.50 nanometers as well the spherical structure. While for P3HT-AlNps samples was flakes shape. Energy Dispersive X-ray (EDX) spectra show the existing of amount of metallic nanoparticles.
Due to their attractive properties, silver nanowires (Ag-NWs) are newly used as nanoelectrodes in continuous wave (CW) THz photomixer. However, since these nanowires have small contact area, the nanowires fill factor in the photomixer active region is low, which leads to reduce the nanowires conductivity. In this work, we proposed to add graphene nanoantenna array as nanoelectrodes to the silver nanowires-based photomixer to improve the conductivity. In addition, the graphene nanoantenna array and the silver nanowires form new hybrid nanoelectrodes for the CW-THz photomixer leading to improve the device conversion efficiency by the plasmonic effect. Two types of graphene nanoantenna array are proposed in two separate photomixer conf
... Show MoreMetoclopramide HCl (MTB) is a potent antiemetic drug used for the treatment of nausea and vomiting. Many trials were made to prepare a satisfactory MTB orodispersible tablet using direct compression method.Various super disintegrants were used in this study which are croscarmellose sodium (CCS), sodium starch glycolate (SSG) and crospovidone (CP). The latter was the best in terms of showing the fastest disintegration time in the mouth.Among the different diluents utilized, it was found that a combination of microcrystalline cellulose PH101 (MCC 101), mannitol, dicalcium phosphate dihydrate (DPD) and Glycine was the best in preparing MTB orodispersible tablet with fastest disintegration time in the mouth.The physical parameters of the pre
... Show MoreThis work includes a detailed description of the Leucostoma nigricorpuris sp. nov. from
Iraq. Locality, host plants and data of collection were given.
Some new complexes of 4-(5-(1,5-dimethyl-3-oxo-2-phenyl pyrazolidin-4- ylimino)-3,3-dimethyl cyclohexylideneamino) -1,5- dimethyl-2- phenyl -1H- pyrazol -3(2H) –one (L) with Mn(II), Fe(III), Co(II), Ni(II), Cu(II), Pd(II), Re(V) and Pt(IV) were prepared. The ligand and its metal complexes were characterized by phisco- chemical spectroscopic techniques. The spectral data were suggested that the (L) as a neutral tetradentate ligand is coordinated with the metal ions through two nitrogen and two oxygen atoms. These studies revealed Octahedral geometries for all metal complexes, except square planar for Pd(II) complex. Moreover, the thermodynamic activation parameters, such as ?E*, ?H, ?S, ?G and K are calculated from the TGA curves using Coa
... Show More