ملخص البحث :

We present a novel and simple approach to incorporate the kernel function method to a recently proposed autonomous learning system (ALS). An ALS can learn online from data streams without any need to offline batch training and it is both memory and computational power efficient. We have codenamed our approach: KALMMo for Kernelized Autonomous Learning Multi Model system. Using the Radial Basis Function (RBF) kernel, we have tested the performance of KALMMo using four well-known and challenging datasets and compared the results to other well established algorithms. Our results have shown that KALMMo performed at least as good as other competitive approaches or even better. Its training time is linearly proportional to the number of instances of a dataset and that the training time is better by an order of magnitude to the nearest competitor. KALMMo shows interesting feature to several applications including big data and machine learning classification. The performance of the proposed systems should be tested with other types of kernel functions.

ملخص البحث :

Image classification and feature extraction have been studied extensively and used efficiently in several applications. This paper suggests a novel method by combining three main methods for texture feature extraction. The proposed method is based on Local Ternary Pattern (LTP), Texture Feature Coding Method (TFCM), and Gray Level Cooccurrence Matrix (GLCM). We have entitled our method as GCLTP which is stand for Gray Coding Local Ternary Pattern. The combination of LTP, TFCM, and GLCM is assigned a unique value used to extract the features of an image. GCLTP is tested using images are taken from the Brodatz database. A set of 22 features were extracted from images. GCLTP is experimentally accomplished a high accuracy in classification by using the most known classifiers.

ملخص البحث :

In this search, an important methodology has been presented for communicated information rectification utilizing advanced channel windowing approach. The modern data communication technologies are ensured with numerous challenges because of their unpredictability and arrangement. Various digital transmission topologies in 4G can't fulfill the requirements in future arrangements, therefore, alternative multicarrier modulation (MCM) becoming the nominated approaches among all other data transmission techniques. Wherein prototype filter configuration is a fundamental system based on which the synthesis and analysis filters are derived. This paper presents a complete review on the ongoing advances of finite impulse response (FIR) filter plan procedures in MCM based correspondence frameworks. Initially, the essential issues are tried, taking into consideration the presentation of available data signal applicants and the FIR filter design concept. At that point the techniques for FIR filter configuration are summed up in subtleties and are center around the accompanying three group’s recurrence testing strategies, windowing based strategies and advancement-based techniques. At last, the exhibitions of different FIR structure strategies are assessed and measured by power spectral density (PSD) and bit error rate (BER), and variable MCM plots as well as their potential prototype filters are examined.

ملخص البحث :

An edge is where an image’s intensity values rapidly change from low to high-intensity values or vice versa. The edge itself is at the midpoint of this change. Edge detection remains a challenge in computer vision despite recent advances. It cannot be applied to an image with excessive brightness and contrast. This paper produces a new method based on the standard deviation histogram feature to reduce the onerousness. The proposed method aims to prepare the input image for the edge detection approaches by performing a histogram feature extraction. The main characteristics of the proposed approach are simplicity and functionality. The authors utilize twenty MATLAB standard images as well as ADNI brain images. The authors use the Canny edge detection method to defect edges from the proposed method. The authors use edge detection evaluation metrics such as Figure of Merit (FOM), Structural Similarity Index Metric (SSIM), Peak Signal to Noise Ratio (PSNR), and Mean Square Error (MSE) measures for evaluating and justifying edge quality. The experimental results show that the proposed method performs better in visual and statistical edge quality than both classical and fractional-order edge detection methods.

ملخص البحث :

One of the most common image operation analyses is the edge detection technique. Edge detection is used for shaping the edge of an image. Also, it is used for enhancing images. This paper presents a new approach to detecting the edge of color image using the Mamdani fuzzy inference classifier based on the Fuzzy Set Membership Function (FSMF). Here, Gaussian Curve Membership Function (GCMF) is used as a FSMF. GCMF is used for each class to assign that class to each pixel. In this approach, two windows/filters are used in size (1x2) and (2x1). Several standard color images are used to test our proposed algorithm (City, Jelly_cc11, Baboon, Lena, and Peppers). In order to parametric evaluation of selected images, Peak Signal Noise Ratio (PSNR) and Mean Square Error (MSE) are considered. However, the performance of our proposed algorithm compared with other well-known approaches (Canny, Prewitt, and Sobel) is somehow very similar but significantly faster.

ملخص البحث :

Image segmentation is a critical step in computer-aided diagnosis that could speed up Leukemia detection. Leukemia is a cancer of the blood that has a reputation for being particularly lethal. Based on the immunohistochemical method, the leukocytes can be manually counted in a stained peripheral blood smear image to detect Acute Lymphoblastic Leukemia (ALL). Regrettably, the manual diagnosis process takes about 3 to 24 hours to complete, which is insufficient. This paper introduced a new and straightforward ALL image segmentation approach based on color image transformation. First, Leukemia, ALL-IDB1, ALL-IDB2, and ALL image datasets were used in this paper. The Leukemia dataset includes 208 ALL-IDB1 and ALL-IDB2 images, while The ALL dataset has 3256 images. Next, we use the HSV model to transform ALL images. In addition, we modified the HSV model by pre-processing the saturation channel for better results. Then, the pre-processed images were segmented based on a fixed threshold. After that, various metrics are utilized to measure the output of the proposed method. Finally, the proposed methodology is compared to currently used benchmarks. The proposed method outperforms previous approaches regarding accuracy, specificity, sensitivity, and time. In addition, results show that the proposed technique improves performance measures significantly.

ملخص البحث :

Medical images are a specific type of image that can be used to diagnose disease in patients. Critical uses for medical images can be found in many different areas of medicine and healthcare technology. Generally, the medical images produced by these imaging methods have low contrast. As a result, such types of images need immediate and fast enhancement. This paper introduced a novel image enhancement methodology based on the Laplacian filter, contrast limited adaptive histogram equalization, and an adjustment algorithm. Two image datasets were used to test the proposed method: The DRIVE dataset, forty images from the COVID-19 Radiography Database, endometrioma-11, normal-brain-MRI-6, and simple-breast-cyst-2. In addition, we used the robust MATLAB package to evaluate our proposed algorithm's efficacy. The results are compared quantitatively, and their efficacy is assessed using four metrics: Peak Signal to Noise Ratio (PSNR), Mean Squared Error (MSE), Contrast to Noise Ratio (CNR), and Entropy (Ent). The experiments show that the proposed method yields improved images of higher quality than those obtained from state-of-the-art techniques regarding MSE, CNR, PSNR, and Ent metrics.

ملخص البحث :

Among the most pressing issues in the field of illness diagnostics is identifying and diagnosing leukemia at its earliest stages, which requires accurate distinction of malignant leukocytes at a low cost. Leukemia is quite common, yet laboratory diagnostic centres often lack the necessary technology to diagnose the disease properly, and the available procedures take a long time. They are considering the efficacy of machine learning (ML) in illness diagnostics and that deep learning as a machine learning method is becoming critical. This study proposes a convolutional neural network (CNN) deep learning model for leukemia diagnosis utilizing the AML (acute myeloid leukemia) dataset. The classification using the proposed method achieved results that exceeded 98% accuracy, the sensitivity of 94.73% and specificity of 98.87%.

ملخص البحث :

Melanoma, the deadliest form of skin cancer, is on the rise. The goal of this study is to present a deep learning system implementation for the detection of melanoma lesions on a server equipped with a graphics processing unit (GPU). When applied by a dermatologist, the recommended method might aid in the early detection of this kind of skin cancer. Evidence shows that deep learning may be used in a variety of settings to successfully extract patterns from data such as signals and images. This research presents a convolution neural network–based strategy for identifying early-stage melanoma skin cancer. Images are input into a deep learning model known as a convolutional neural network (CNN) that has already been pre-trained. The CNN classifier, which is trained with large amounts of data, can discriminate between malignant and nonmalignant melanoma. The method's success in the lab bodes well for its potential to aid dermatologists in the early detection of melanoma. However, the experimental results show that the proposed technique excels beyond the state-of-the-art methods in terms of diagnostic accuracy.

ملخص البحث :

The Internet of Things (IoT) is a cutting-edge innovation that facilitates the cost-effective development of smart system architectures. Although current regulations necessitate installing an analog fire alarm system, such a system lacks the intelligence to instantly notify the appropriate parties in a timely fashion. In addition, since people are not always present, an analog fire alarm will not be able to prevent immediate danger or damage in the event of a fire. Therefore, the incident must be reported as soon as possible to the appropriate party in order to lessen the impact of a fire. In this study, we suggest a smart fire-alarm system made of a fire sensor and a sound sensor that can both detect fire and noise as well as the status of the analog fire alarm system to ascertain whether the analog fire alarm system is operational. We first tested our proposed smart fire alarm system to determine its effectiveness before putting it into use. From there, we ran experiments to determine how well it worked. The outcomes show that the system is trustworthy in a range of scenarios.

ملخص البحث :

In light of the fact that the global pandemic of Coronavirus Disease 2019 (COVID-19) is still having a significant impact on the health of people all over the world, there is a growing need for testing diagnosis and treatment that can be completed quickly. The primary imaging modalities used in the respiratory disease diagnostic process are the Chest X-ray (CXR) and the computed tomography scan. In this context, this paper aims to design a new Convolutional Neural Network (CNN) to diagnose COVID-19 in patients based on CXR images and determine whether they are COVID or healthy. We have tested the performance of our CNN on the COVID-19 Radiography Database with three classes (COVID, Pneumonia, and Normal). Also, we proposed a new enhancement technique to enhance the CXR image using the Laplacian kernel with Delta Function and Contrast-Limited Adaptive Histogram Equalization. The proposed CNN has been trained and tested on 15153 enhanced and original images, COVID (3616), Pneumonia (1345), and Normal (10192). Our enhancement technique increased the performance metrics scores of the proposed CNN. Hence, the proposed method obtained better results than the state-of-the-art methods in accuracy, sensitivity, precision, specificity, and F measure.

ملخص البحث :

As the world continues to battle the devastating effects of the COVID-19 pandemic, it has become increasingly crucial to screen patients for contamination accurately and effectively. One of the primary screening methods is chest radiography, utilizing radiological imaging to detect the presence of the virus in the lungs. This study presents a cutting-edge solution to classify COVID-19 infections in chest X-ray images by utilizing the Gray-Level Co-occurrence Matrix (GLCM) and machine learning algorithms. The proposed method analyzes each X-ray image using the GLCM to extract 22 statistical texture features and then trains two machine learning classifiers - K-Nearest Neighbor and Support Vector Machine - on these features. The method was tested on the COVID-19 Radiography Database and was compared to a state-of-the-art method, delivering highly efficient results with impressive sensitivity, accuracy, precision, F1-score, specificity, and Matthew's correlation coefficient. The proposed approach offers a promising new way to classify COVID-19 infections in chest X-ray images and has the potential to play a crucial role in the ongoing fight against the pandemic.

ملخص البحث :

Coronavirus is considered the first virus to sweep the world in the twenty-first century, it appeared by the end of 2019. It started in the Chinese city of Wuhan and began to spread in different regions around the world too quickly and uncontrollable due to the lack of medical examinations and their inefficiency. So, the process of detecting the disease needs an accurate and quickly detection techniques and tools. The X-Ray images are good and quick in diagnosing the disease, but an automatic and accurate diagnosis is needed. Therefore, this paper presents an automated methodology based on deep learning in diagnosing COVID-19. In this paper, the proposed system is using a convolutional neural network, which is considered one of the mostly prominent techniques used today for its reliability and ability to generate rapid results. The system was trained on a set of X-Ray images taken of the chest area of infected and uninfected people. The CNN structure gave accuracy, Precision, Recall and F-Measure 98%. This model is characterized by its ability to distinguish efficiently and adapt to different cases.

ملخص البحث :

Image enhancement is vital in computer vision and image processing applications. This study introduces an innovative approach combining HSV color space, Discrete Wavelet Transforms (DWT), and Bi Histogram Equalization (BiHE) techniques. By converting the image from RGB to HSV, we separate color and intensity information, allowing us to enhance the intensity component for improved visual quality. The DWT is then applied to decompose the image into frequency sub bands, enabling targeted manipulation of specific frequency components to enhance image details and overall appearance. Additionally, the BiHE technique enhances contrast while preserving local image details. The proposed method was evaluated on various images, including tissue, football, Lena, and yellow lily. The results show that the proposed method achieved high Peak Signal-to-Noise Ratio (PSNR) values, with tissue achieving 32.1853 dB, football achieving 30.5452 dB, Lena achieving 27.1462 dB, and yellow lily achieving 25.2015 dB. The Mean Squared Error (MSE) values were also low, with tissue having an MSE of 0.0006, football having an MSE of 0.0009, Lena having an MSE of 0.0022, and yellow lily having an MSE of 0.0031. These results demonstrate the effectiveness of the proposed method in enhancing the visual quality, details, and contrast of the images while maintaining naturalness and avoiding artifacts. Experimental results demonstrate that our method outperforms traditional techniques, significantly enhancing visual quality, details, and contrast while maintaining naturalness and avoiding artifacts.

ملخص البحث :

The field of image classification in medical diagnosis presents several challenges and problems that motivated our research and led us to propose a novel method. These challenges include the need for accurate and efficient diagnosis, extracting relevant features from medical images, and integrating different classification algorithms for improved performance. Considering these challenges, we aimed to develop a robust and effective approach to address these issues and enhance the accuracy of medical image classification. This research proposes a hybrid feature extraction method for eye disease classification using a combination of Local Binary Pattern (LBP), Gray-Level Co-occurrence Matrix (GLCM), and Texture Feature Coding Method (TFCM). The dataset used for evaluation is obtained from Kaggle and consists of retinal images representing various eye diseases. Pre-processing involves ROI extraction and image resizing. Features are extracted using LBP, GLCM, and TFCM, totaling 37 features. These features are combined into a single vector. The classification task is performed using k-Nearest Neighbors (kNN) and Support Vector Machine (SVM) classifiers, with performance analysis conducted using five metrics. The experimental results demonstrated the effectiveness of the hybrid feature extraction method in accurately classifying eye diseases. The SVM and kNN classifiers achieved high accuracy, with SVM achieving an accuracy of 0.9988 and kNN achieving an accuracy of 0.9955.

ملخص البحث :

Retinal fundus images, specifically the morphology of blood vessels, are valuable diagnostic tools for diseases such as hypertension, diabetic retinopathy, and glaucoma. Modern ophthalmic diagnostic methods rely on the results of analyses of retinal images, and the quality of these analyses depends on the precision with which blood vessels in the retina are segmented. Retinal blood vessel segmentation methods all rely on a process known as contrast enhancement. Having uniform contrast throughout the image is crucial to the accuracy of the segmentation. An essential step in Computer-Aided Diagnosis (CAD) for many eye conditions is the automatic segmentation of retinal blood vessels. Medical analysis and disease diagnosis rely on segmenting thin and thick retinal vessels. This article proposes a new method for accurate vessel segmentation to overcome the difficulties already described in the literature. However, the proposed method is based on the Gabor filter and optimized top-hat morphology techniques. The proposed method is divided into three main stages, image pre-processing, segmentation, and post-processing. A common and public dataset, DRIVE, is employed to evaluate our proposed method. In addition, three metrics are utilized to evaluate the proposed method: accuracy, sensitivity, and specificity. As a result, compared to the state-of-the-art method, the proposed method resulted in significantly improved segmentation accuracy, achieving an accuracy of 96.55%, a sensitivity of 79.36%, and a specificity of 98.20% for the training set. Also, the final results of the proposed method achieved 95.95%, 74.24%, and 98.05% for the testing set’s accuracy, sensitivity, and specificity, respectively.

ملخص البحث :

Alzheimer's disease (AD) increasingly affects the elderly and is a major killer of those 65 and over. Different deep-learning methods are used for automatic diagnosis, yet they have some limitations. Deep Learning is one of the modern methods that were used to detect and classify a medical image because of the ability of deep Learning to extract the features of images automatically. However, there are still limitations to using deep learning to accurately classify medical images because extracting the fine edges of medical images is sometimes considered difficult, and some distortion in the images. Therefore, this research aims to develop A Computer-Aided Brain Diagnosis (CABD) system that can tell if a brain scan exhibits indications of Alzheimer's disease. The system employs MRI and feature extraction methods to categorize images. This paper adopts the Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset includes functional MRI and Positron-Version Tomography scans for Alzheimer's patient identification, which were produced for people with Alzheimer's as well as typical individuals. The proposed technique uses MRI brain scans to discover and categorize traits utilizing the Histogram Features Extraction (HFE) technique to be combined with the Canny edge to representing the input image of the Convolutional Neural Networks (CNN) classification. This strategy keeps track of their instances of gradient orientation in an image. The experimental result provided an accuracy of 97.7% for classifying ADNI images.

ملخص البحث :

Due to the importance of data security at present, an encryption algorithm based on the principle of non-commutative group, hash function, and E-fractal has been proposed. Key generation depends on the array values generated by the braid group and using them as input to the SHA-3 (256) which increases the strength of the key because it generates values in one direction only. The results of the hash function are determined by the Lorenz hyper-chaotic system initial values, and four image-size arrays are generated as the final image-encryption keys using the RC4 algorithm. Then the use of the E-fractal diffusion method. To bolster the security of the encryption, it is employed to disperse the pixel values., adopting the control word that increases the randomness of the data. The security analysis of the proposed encryption algorithm demonstrates that it is difficult to decipher due to the presence of the hash function in addition to its easy implementation within seconds, and the efficiency scale was calculated that showed its strength in effectively resisting attacks by others.

ملخص البحث :

Alzheimer’s disease emerges as a profoundly distressing neurological condition affecting older individuals, pre-ending itself as an insufficiently addressed and often overlooked ailment that poses a growing concern for public health. In the past decade, there has been a notable surge in endeavors aimed at unraveling the disease’s origins and devising pharmacological interventions. Recent advancements encompass enhanced clinical diagnostic criteria and refined approaches for managing cognitive impairments and behavioral challenges. The pursuit of symptomatic relief primarily centered on cholinergic therapy has been subject to rigorous scrutiny through randomized, double-blind, placebo-controlled studies assessing cognitive function, daily activities, and behavioral aspects. This research delves into the utilization of diverse algorithms for the classification of Alzheimer’s disease severity, employing CNN, DenseNet, VGG19, and ensemble learning approaches. The obtained accuracy scores underscore the supremacy of the Ensemble model, surpassing the performance of the other models with an impressive accuracy level of 94%.

ملخص البحث :

Alzheimer’s disease (AD) stands as a formidable global health challenge, impacting millions of lives. Timely detection and localization of affected brain regions are pivotal for understanding its progression and developing effective treatments. This research introduces a cutting-edge approach to address these critical concerns. Traditionally, exploring the influence of AD on the human brain has been a complex task. Existing methods often face limitations in accurately localizing the most affected brain regions, impeding our understanding of the disease's focal impact. Additionally, the need for efficient and precise cortical thickness analysis techniques has driven the quest for innovative solutions. In this paper, we proposed the DL+DiReCT method, a high-precision strategy that integrates deep learning-based neuroanatomy segmentations with Diffeomorphic Registration-based Cortical Thickness (DiReCT). This approach streamlines the measurement of cortical thickness, enabling rapid and precise localization of AD-affected regions within the brain. Our method significantly contributes to enhancing our understanding of the localized effects of Alzheimer’s disease. Our extensive study, involving 434 subjects from the ADNI dataset and rigorous data augmentation and optimization, has yielded remarkable outcomes. This approach has far-reaching implications for discerning the specific regions of the brain affected by AD, shedding light on their consequences for essential physiological factors.