ئەز   Abdulhakeem Othman Mohammed

Cardiovascular diseases, particularly cardiac arrhythmias, remain a leading cause of global mortality, necessitating efficient and accurate diagnostic tools. Despite advances in deep learning for ECG analysis, current models face challenges in cross-population performance, signal noise robustness, limited training data efficiency, and clinical result interpretability. Additionally, most current approaches struggle to generalize across different ECG databases and require extensive computational resources for real-time analysis. This paper presents a novel hybrid deep learning framework for automated ECG analysis, combining one-dimensional convolutional neural networks (1D-CNN) with a specialized attention mechanism. The proposed architecture implements a four-stage CNN backbone enhanced with a squeeze-and-excitation attention block, enabling adaptive feature selection across multiple scales. The model incorporates advanced regularization techniques, including focal loss, L2 regularization, and an ensemble approach with mixed precision training. We conducted extensive experiments across multiple datasets to evaluate generalization capabilities. This study utilizes two standard databases: the MIT-BIH Arrhythmia Database (48 half-hour recordings sampled at 360 Hz) and the PTB Diagnostic ECG Database (549 records from 290 subjects sampled at 1000 Hz). Through rigorous validation including five-fold cross-validation and statistical significance testing, our model attained remarkable performance, achieving 99.48% accuracy on MIT-BIH, 99.83% accuracy on PTB, and 99.64% accuracy on the combined dataset, with corresponding F1-scores of 0.99, 1.00, and 1.00 respectively. The findings demonstrate robust generalization across varied ECG morphologies and recording conditions, with particular effectiveness in handling class imbalance without data augmentation. The model’s reliable performance across multiple datasets indicates significant potential for clinical applications in automated cardiac diagnostics.

Graph databases have recently gained a lot of attention in areas where the relationships between data and the data itself are equally important, like the semantic web, social networks, and biological networks. A graph database is simply a database designed to store, query, and modify graphs. Recently, several graph database models have been developed. The goal of this research is to evaluate the performance of the two most popular graph databases, Neo4j and TigerGraph, for network centrality metrics including degree centrality, betweenness centrality, closeness centrality, eigenvector centrality, and PageRank. We applied those metrics to a set of real-world networks in both graph databases to see their performance. Experimental results show Neo4j outperforms TigerGraph for computing the centrality metrics used in this study, but TigerGraph performs better during the data loading phase.

Hundreds of millions of people worldwide have recently been infected by the novel Coronavirus disease (COVID-19), causing significant damage to the health, economy, and welfare of the world's population. Moreover, the unprecedented number of patients with COVID-19 has placed a massive burden on healthcare centers, making timely and rapid diagnosis challenging. A crucial step in minimizing the impact of such problems is to automatically detect infected patients and place them under special care as quickly as possible. Deep learning algorithms, such as Convolutional Neural Networks (CNN), can be used to meet this need. Despite the desired results, most of the existing deep learning-based models were built on millions of parameters (weights), which are not applicable to devices with limited resources. Inspired by such fact, in this research, we developed two new lightweight CNN-based diagnostic models for the automatic and early detection of COVID-19 subjects from chest X-ray images. The first model was built for binary classification (COVID-19 and Normal), whereas the second one was built for multiclass classification (COVID-19, viral pneumonia, or normal). The proposed models were tested on a relatively large dataset of chest X-ray images, and the results showed that the accuracy rates of the 2- and 3-class-based classification models are 98.55% and 96.83%, respectively. The results also revealed that our models achieved competitive performance compared with the existing heavyweight models while significantly reducing cost and memory requirements for computing resources. With these findings, we can indicate that our models are helpful to clinicians in making insightful diagnoses of COVID-19 and are potentially easily deployable on devices with limited computational power and resources.

In this paper, we study Gromov hyperbolicity and related parameters, that represent how close (locally) a metric space is to a tree from a metric point of view. The study of Gromov hyperbolicity for geodesic metric spaces can be reduced to the study of graph hyperbolicity. The main contribution of this paper is a new characterization of the hyperbolicity of graphs, via a new parameter which we call rooted insize. This characterization has algorithmic implications in the field of large-scale network analysis. A sharp estimate of graph hyperbolicity is useful, e.g., in embedding an undirected graph into hyperbolic space with minimum distortion (Verbeek and Suri, in Symposium on Computational Geometry, ACM, New York, 2014). The hyperbolicity of a graph can be computed in polynomial-time, however it is unlikely that it can be done in subcubic time. This makes this parameter difficult to compute or to approximate on large graphs. Using our new characterization of graph hyperbolicity, we provide a simple factor 8 approximation algorithm (with an additive constant 1) for computing the hyperbolicity of an n-vertex graph in optimal time (assuming that the input is the distance matrix of the graph). This algorithm leads to constant factor approximations of other graph-parameters related to hyperbolicity (thinness, slimness, and insize). We also present the first efficient algorithms for exact computation of these parameters. All of our algorithms can be used to approximate the hyperbolicity of a geodesic metric space. We also show that a similar characterization of hyperbolicity holds for all geodesic metric spaces endowed with a geodesic spanning tree. Along the way, we prove that any complete geodesic metric space (X, d) has such a geodesic spanning tree.

Slimness of a graph measures the local deviation of its metric from a tree metric. In a graph G = (V, E), a geodesic triangle 4(x, y, z) with x, y, z ∈ V is the union P (x, y) ∪ P (x, z) ∪ P (y, z) of three shortest paths connecting these vertices. A geodesic triangle 4(x, y, z) is called δ-slim if for any vertex u ∈ V on any side P (x, y) the distance from u to P (x, z) ∪ P (y, z) is at most δ, i.e. each path is contained in the union of the δ-neighborhoods of two others. A graph G is called δ-slim, if all geodesic triangles in G are δ-slim. The smallest value δ for which G is δ-slim is called the slimness of G. In this paper, using the layering partition technique, we obtain sharp bounds on slimness of such families of graphs as (1) graphs with cluster-diameter ∆(G) of a layering partition of G, (2) graphs with tree-length λ, (3) graphs with tree-breadth ρ, (4) k-chordal graphs, AT-free graphs and HHD-free graphs. Additionally, we show that the slimness of every 4-chordal graph is at most 2 and characterize those 4-chordal graphs for which the slimness of every of its induced subgraph is at most 1.

ElGamal cryptosystem is one of the well-known public-key algorithms for its ability to generate different ciphertexts for the same plaintext on successive runs. However, this algorithm results in a ciphertext occupying a larger memory space than its plaintext due to its encryption nature. As a result, it is pretty infeasible to use data that require their encrypted form to have the same size, such as image data. To overcome this issue, we propose an enhanced ElGamal cryptosystem that can be used for any given digital data message, including image, text, and video. The proposed approach mainly tests image data, consisting of three stages: key pair generation, image encryption, and image decryption. First, we generate as many random bytes as required for encrypting or decrypting images using the sender or receiver's public key information. Then, we use an XOR operation between each pixel in the image and each randomly generated byte to obtain the encrypted or decrypted image. Experimental results revealed that the proposed approach gives excellent results in various evaluation metrics tested on four different color images.

We investigate a metric parameter “Leanness” of graphs which is a formalization of a well-known Fellow Travelers Property present in some metric spaces. Given a graph G = (V,E), the leanness of G is the smallest λ such that, for every pair of vertices x, y ∈ V , all shortest (x, y)-paths stay within distance λ from each other. We show that this parameter is bounded for many structured graph classes and is small for many real-world networks. We present efficient algorithms to compute or estimate this parameter and evaluate the performance of our algorithms on a number of real-world networks.