Figure - available from: Soft Computing
This content is subject to copyright. Terms and conditions apply.
Source publication
The development of automated morphological classification schemes for galaxies is important to study the formation and subsequent evolution of galaxies in our universe. This paper proposed a new machine learning method for classifying three types of galaxies image (Hubble types) namely elliptical, lenticulars, and spirals. The proposed approach con...
Similar publications
Early diagnosis of cerebral infarction is essential since many patients cannot be cured where the diagnosis is made at an advanced stage. In case an infarct occurs, the tissue in the brain die and stop the circulation of blood, which carries oxygen and nutrients to the body. Therefore, this study uses a machine learning Support Vector Machine (SVM)...
Citations
... The visible universe constitutes of nearly 2 × 10 12 galaxies [1], which are the primary structural components of the universe [2]. Galaxies are not precisely evenly spread all through the universe [3].The cosmic web has been composed of voids and also filaments throughout the universe. ...
Photometric and spectroscopic approaches were utilized to examine the two galaxies, PGC 165324 and PGC 977941. Data releases (DR7 and DR17) from "The Sloan Digital Sky Survey (SDSS)” were employed to acquire the observed data. Then, ellipsoids were fitted via employing the Image Reduction and Analysis Facility (IRAF) with utilising STSDAS Library, the ELLIPS task. Along with the astrometric characteristics, the surfaces’ brightness of the galaxies PGC 165324 and PGC 977941, as well as their magnitudes, cumulative flux, central axis position angles, ellipticities, vertical and horizontal shifts, isophotal shape variables (B4), and also the star-forming rates (SFRs), were analysed and evaluated. It was indicated that the two galaxies, are members of a close pair galaxy system; in addition, they are considered a physical system; the PGC 165324 galaxy was a merging galaxy with a higher SFR. It was likely that the PGC 977941 had separated itself from the galaxy collision and drifted away.
... Then in the years that followed, Hosny (2011) used the high computational requirements of Gegenbauer moments to propose novel methods for image analysis and recognition, which in these studies, fractional-order shifted Gegenbauer moments (Hosny et al. 2020) and Gegenbauer moment Invariants (Hosny 2014) are seen. Also in 2014, Abd Elaziz et al. (2019) used artificial bee colony based on orthogonal Gegenbauer moments to be able to classify galaxies images with the help of support vector machines. In 2009, with the help of the orthogonality property of the Gegenbauer polynomial, Langley and Zhao (2009) introduced a new 3D phase unwrapping algorithm for the analysis of magnetic resonance imaging (MRI). ...
Because of the usage of many functions as a kernel, the support vector machine method has demonstrated remarkable versatility in tackling numerous machine learning issues. Gegenbauer polynomials, like the Chebyshev and Legender polynomials which are introduced in previous chapters, are among the most commonly utilized orthogonal polynomials that have produced outstanding results in the support vector machine method. In this chapter, some essential properties of Gegenbauer and fractional Gegenbauer functions are presented and reviewed, followed by the kernels of these functions, which are introduced and validated. Finally, the performance of these functions in addressing two issues (two example datasets) is evaluated.KeywordsGegenbauer polynomialFractional Gegenbauer functionsKernel trickOrthogonal functionsMercer’s theorem
... In recent years, one-dimensional and two-dimensional discrete orthogonal moments have been gaining importance because of their ability to represent signals and images well in various fields. The applications of discrete orthogonal moments include signal and image reconstruction [17,19,31], face recognition [46], image classification [2,12], image watermarking [57], image encryption [56], images compression [24,33,55], signals compression [3,21,32]. Charlier moment (CMs) represents one type of discrete orthogonal moment [18,38]. ...
Remote Healthcare Monitoring Systems (RHMs) that employ fetal phonocardiography (fPCG) signals are highly efficient technologies for monitoring continuous and long-term fetal heart rate. Wearable devices used in RHMs still face a challenge that decreases their efficacy in terms of energy consumption because these devices have limited storage and are powered by batteries. This paper proposes an effective fPCG compression algorithm to reduce RHM energy consumption. In the proposed algorithm, the Discrete Orthogonal Charlier Moment (DOCMs) is used to extract features of the signal. The householder orthonormalization method (HOM) is used with the Charlier Moment to overcome the propagation of numerical errors that occur when computing high-order Charlier polynomials. The proposed algorithm’s performance is evaluated in terms of CR, PRD, SNR, PSNR, and QS and provides the average values 18.33, 0.21, 48.85, 68.86, and 90.88, respectively. The results of the comparison demonstrate the proposed compression algorithm’s superiority over other algorithms. It also tested in terms of compression speed and computational efficiency. The results indicate that the proposed algorithm has a high Compression speed (218.672 bps) and high computational efficiency (21.33). Additionally, the results reveal that the proposed algorithm decreases the energy consumption of a wearable device due to the transmission time decreasing for data by 3.68 s.
... Abd Elaziz et al., classified galaxies into three groups of elliptical, lenticulars, and spirals using a hybrid approach [12]. At first, they performed feature extraction using the Gegenbauer moment method. ...
... However, the deciding the architecture of the CNN is not easy. Abd Elaziz et al. [12] used a meta-heuristic optimization algorithm for feature selection. This study uses a metaheuristic optimization algorithm to obtain the optimum CNN architecture. ...
... The Precision, Recall and F1 Score formulas are given in Eqs. (11), (12) and (13), respectively. Here, TP, FP and FN represent True Positives, False Positives and False Negatives, respectively. ...
In this study, the morphological galaxy classification process was carried out with a hybrid approach. Since the Galaxy classification process may contain detailed information about the universe’s formation, it remains the current research topic. Researchers divided more than 100 billion galaxies into ten different classes. It is not always possible to understand which class the galaxy types belong. However, Artificial Intelligence (AI) can be used for successful classification. There are studies on the automatic classification of galaxies into a small number of classes. As the number of classes increases, the success of the used methods decreases. Based on the literature, the classification using Convolutional Neural Network (CNN) is better. Three meta-heuristic algorithms are used to obtain the optimum architecture of CNN. These are Grey Wolf Optimizer (GWO), Particle Swarm Optimization (PSO) and Artificial Bee Colony (ABC) algorithms. A CNN architecture with nine hidden layers and two full connected layers was used. The number of neurons in the hidden layers and the fully connected layers, the learning coefficient and the batch size values were optimized. The classification accuracy of my model was 85%. The best results were obtained using GWO. Manual optimization of CNN is difficult. It was carried out with the help of the GWO meta-heuristic algorithm.
... The study of the literature on image analysis techniques indicates that the method of orthogonal moments plays a significant role in each of its important fields. These fields include image reconstruction [1, 2], face recognition [3], image classification [4,5], image watermarking [6], image encryption [7], image compression [8,9], color stereo image analysis [10]. Orthogonal moments are classified as continuous or discrete depending on whether ...
... Experimental results and discussion are presented in Sect. 5. Discussions are shown in Sect. ...
Bio-signals are extensively used in diagnosing many diseases in wearable devices. In signal processing, signal reconstruction is one of the essential applications. Discrete orthogonal moments (DOMs) are effective analysis tools for signals that can extract digital information without redundancy. The propagation of numerical errors is a significant challenge for the computation of DOMs at high orders. This problem damages the orthogonality property of these moments, which restricts the ability to recover the signal's distinct and unique components with no redundant information. This paper proposes a stable computation of DOMs based on QR decomposition methods: the Gram–Schmidt, Householder, and Given Rotations methods. It also presents a comparative study on the performance of the types of moments: Tchebichef, Krawtchouk, Charlier, Hahn, and Meixner moments. The proposed algorithm's evaluation is done using the MIT-BIH arrhythmia dataset in terms of mean square error and peak signal to noise ratio. The results demonstrate the superiority of the proposed method in computing DOMs, especially at high moment orders. Moreover, the results indicate that the Householder method outperforms Gram–Schmidt and Given Rotations methods in execution time and reconstruction quality. The comparative results show that Tchebichef, Krawtchouk, and Charlier moments have superior reconstruction quality than Hahn and Meixner moments, and Tchebichef generally has the highest performance in signal reconstruction.
... Astronomers used shape and general visual semblance of galaxies to know more information about their development and their structure, [2]. The first step towards a super perception understanding of the origin and formation process of galaxies is study the shape and structure of galaxies which is an important role in the large scale to understanding the provenance and developments in the universe, [3]. Astronomers deduce that bar detection is a trouble because it is often considered as a suitable way to differentiate between two kinds of spiral galaxies that have different physical properties. ...
... Specifically, many researchers have applied deep learning (DL) techniques in classifying the severity of COVID-19 in accordance with CT scans [11][12][13][14] attributed to their remarkable ability in image processing tasks. The images are classified by using a descriptor to extract the images' import features (e.g., SIFT [15] and image moment [16], which is followed by the application of classifiers such as SVM for the final image classification [17]. Techniques that are based on deep neural networks are characterised by high performance as the images are classified based on the extracted features, thereby reflecting their difference compared to handcrafted features [18]. ...
The COVID-19 pandemic has resulted in a global health crisis. The rapid spread of the virus has led to the infection of a significant population and millions of deaths worldwide. Therefore, the world is in urgent need of a fast and accurate COVID-19 screening. Numerous researchers have performed exceptionally well to design pioneering deep learning (DL) models for the automatic screening of COVID-19 based on computerised tomography (CT) scans; however, there is still a concern regarding the performance stability affected by tiny perturbations and structural changes in CT images. This paper proposes a fusion of a moment invariant (MI) method and a DL algorithm for feature extraction to address the instabilities in the existing COVID-19 classification models. The proposed method incorporates the MI-based features into the DL models using the cascade fusion method. It was found that the fusion of MI features with DL features has the potential to improve the sensitivity and accuracy of the COVID-19 classification. Based on the evaluation using the SARS-CoV-2 dataset, the fusion of VGG16 and Hu moments shows the best result with 90% sensitivity and 93% accuracy.
... Machine Learning has established excellent performance for various applications of image processing like image classification [15], image analysis [16,17], also image segmentation [18]. Image classification was obtained by removing the significant characteristics from the descriptive images like image moment [19] or SIFT [20]. Afterward, these characteristics can be applied in the organizing task by organizers like SVM [21]. ...
A novel coronavirus, also known as SARS-CoV-2, first spread in Wuhan city China in late 2019 from a seafood market and is spreading worldwide. WHO, i.e., World Health Organization, on January 30th, 2020, mentioned and declared this novel coronavirus outbreak as an emergency of public health at the international level. In the current situation, scientists, researchers, medical experts, and clinicians find an alternative technology to handle the pandemic situation due to COVID-19. ML or Machine Learning had an essential impact on previous epidemic situations; therefore, the researchers are looking forward to overcoming the COVID-19 crisis. This chapter thoroughly discusses how the modern Machine Learning process involves the COVID-19 pandemic and helps fight against it. The constant growth in Machine Learning has a significant improvement in prediction, forecasting, screening, contact tracing, treatment, medication, and drug or vaccine invention process for COVID-19 and decreasing human interference in the healthcare system. The ongoing developments in Machine Learning have significantly improved treatment, medication, screening, prediction, forecasting, contact tracing, and drug/vaccine development process for the Covid-19 pandemic and reduce the human intervention in medical practice.
... Understanding galaxies, their formation, and evolution are at the center of modern cosmology [2]. Galaxy visual appearance, morphology, general form, and shape allow for the estimation of their composition and their billions of years of evolution [3]. Galaxy age and past life could also be estimated from their star motion and shapes as well as their chemical composition. ...
... Abd el aziz et al. (2018) [3], proposed a new machine learning technique for galaxy classification. The technique has three stages. ...
... Number of points of circle c (n c ) are evaluated as equal to circle c perimeter, measured in pixels, according to equation (2). Accordingly, the angular displacement between these points is calculated according to equation (3). Finally the Â, y location of the circle pixel point i is calculated according to Eqs. (5) and (6). ...
Clues and traces of the universe's origin and its developmental process are deeply buried in galaxy shapes and formations. Automated galaxies classification from their images is complicated due to the faintness of the galaxy images, conflicting bright background stars, and image noise. For this purpose, the current work proposes a novel logically structured modular algorithm that analyses galaxy morphological raw brightness data to automatically detect galaxy visual center, region, and classification. First, a novel selective brightness threshold is employed to eliminate the effect of bright background stars on detecting galaxy visual centers. Second, a galaxy region detection technique is developed. Finally, a novel technique based on galaxy brightness variation patterns is employed for galaxies classification. The current work has been tested with a run on a collection of 1000 galaxies from the EFIGI catalog. Results demonstrated a success rate of 97.2% in galaxies classification with an average processing time of 0.37 s per galaxy. The high success rates and the low processing time proved the efficiency of the proposed work.
... Due to the noise sensitivity and the redundant information of geometric moments, Teague [34] proposed the utilization of orthogonal moments, Legendre & Zernike, to construct orthogonal image moments. For more than four decades, moments invariant of gray-scale images has been successfully used in pattern recognition applications [11], invariant image watermarking [12,35], copy-move forgery detection [17], image classification [1,26], image retrieval [2,19], rotation estimation [28,41], texture segmentation [36], texture analysis and classification [32,38]. Lakshmi et al. [37] proposed Texture analysis based on exact Legendre moment features [9] for CT liver scan images. ...
The texture is an essential characteristic of the image. So, recognition of texture is increasingly becoming a major topic in many image processing applications such as image retrieving, image classification, similarity, object recognition, and detection. The recognition of texture tries to allocate an unidentified image to one of the identified class of textures. This paper proposes a novel feature extraction technique for classification and recognition of color texture. The significant advantage of the introduced method is that it combines the extraction of local and global features of the color texture by using Local Binary Pattern (LBP) and multi-channel orthogonal radial substituted Chebyshev moments, respectively. Relevant features (local or global) provides discriminatory information that used to differentiate one object from another. Global features represent the image as a whole, while local features represent a specific part of the image. We performed experiments using challenging datasets: (Outex, ALOT) to test the efficacy of our image classification descriptors. The result of this approach has said that our descriptor is valid, competitive, discriminatory, and exceeds the current state-of-art methods.
