Search

The conventional K‐Means clustering algorithm is widely used for grouping similar data points by initially selecting random centroids. However, the accuracy of clustering results is significantly influenced by the initial centroid selection. Despite different approaches, including various K‐Means versions, suboptimal outcomes persist due to inadequate initial centroid choices and reliance on common normalization techniques like min‐max normalization. In this study, we propose an improved algorithm that selects initial centroids more effectively by utilizing a novel formula to differentiate between instance attributes, creating a single weight for differentiation. We introduce a preprocessing phase for dataset normalization without forcing values into a specific range, yielding significantly improved results compared to unnormalized datasets and those normalized using min‐max techniques. For our experiments, we used five real datasets and five simulated datasets. The proposed algorithm is evaluated using various metrics and an external benchmark measure, such as the Adjusted Rand Index (ARI), and compared with the traditional K‐Means algorithm and 11 other modified K‐Means algorithms. Experimental evaluations on these datasets demonstrate the superiority of our proposed methodologies, achieving an impressive average accuracy rate of up to 95.47% and an average ARI score of 0.95. Additionally, the number of iterations required is reduced compared to the conventional K‐Means algorithm. By introducing innovative techniques, this research provides significant contributions to the field of data clustering, particularly in addressing modern data‐driven clustering challenges. [ABSTRACT FROM AUTHOR]

The proliferation of photorealistic images synthesized by generative adversarial networks (GANs) has posed serious threats to society. Therefore a new challenge task, named image attribution, is arising to attribute fake images to a specific GAN. However, existing approaches focus on model‐specific features but neglect the misguidance of semantic‐relevant features in image attribution, which leads to a significant performance decrease in cross‐dataset evaluation. To tackle the above problem, we propose a semantic‐agnostic fake image attribution (SFIA) method, which effectively distinguishes fake images by disentangling the GANs fingerprint and semantic‐relevant features in latent space. Specifically, we design a semantic eliminator based on residual block with skip connections that take images as input and outputs GAN fingerprint features. A classifier with an attention module for feature refinement is introduced to make the final decision. In addition, we develop a well‐trained reconstructor and classifier which supervise the semantic eliminator to achieve semantic‐agnostic feature extraction. Moreover, we propose an improved data augmentation combined with meta‐learning to enhance the model's generalization in detecting unseen image categories. Comprehensive experiments on various datasets, namely, CelebA, LSUN‐church, and LSUN‐bedroom, demonstrate the effectiveness of our proposed SFIA. It achieves over 95% accuracy on three datasets and exhibits superior performance in terms of generalization to unseen data. [ABSTRACT FROM AUTHOR]

Mobile ad hoc networks (MANETs) have revolutionized wireless communications by enabling dynamic, infrastructure-free connectivity across various applications, from disaster recovery to military operations. However, these networks are highly vulnerable to security threats, particularly black hole and gray hole attacks, which can severely disrupt network performance and reliability. This study addresses the critical challenge of detecting and mitigating these attacks within the framework of the dynamic source routing (DSR) protocol. To tackle this issue, we propose a robust hybrid detection method that significantly enhances the identification and mitigation of black hole and gray hole attacks. Our approach integrates anomaly detection, advanced data mining techniques, and cryptographic verification to establish a multi-layered defense mechanism. Extensive simulations demonstrate that the proposed hybrid method achieves superior detection accuracy, reduces false positives, and maintains high packet delivery ratios even under attack conditions. Compared to existing solutions, this method provides more reliable and resilient network performance, dynamically adapting to evolving threats. This research represents a significant advancement in MANET security, offering a scalable and effective solution for safeguarding critical MANET applications against sophisticated cyber-attacks. [ABSTRACT FROM AUTHOR]

Apical hypertrophic cardiomyopathy (ApHCM) is an HCM variant, affecting frequently males in midlife. It is characterized by apical obliteration and persistent diastolic contraction, often resulting in microvascular ischaemia. We report five cases of ApHCM, with evidence of intramyocardial calcification on echocardiogram. On cardiac magnetic imaging (MRI), a hypointense component at early gadolinium enhancement (EGE) sequences, compatible with calcium, and a deep layer, with hyperintensity at late gadolinium enhancement (LGE) sequences, referable to fibrosis, suggest an endomyocardial fibrosis (EMF) diagnosis. EMF pathologic hallmark is endocardium and myocardium scarring, evolving to dystrophic calcification. It is found only in few ApHCM patients. Our series is the largest one described until now. Analysing patients' history, coexistent inflammatory triggers were evident in all of them, so their co‐morbidities could represent a further cause of small vessel disease, in the context of ischaemic microvascular stress due to hypertrophy, leading to fibrosis and dystrophic calcification. This series could demonstrate the relation between apical fibrosis/calcification and microvascular ischaemia due to hypertrophy and inflammatory triggers. [ABSTRACT FROM AUTHOR]

The phenomenon of man's abuse of his partner requires a complex analysis of both the marital relationship and the personalities of the two protagonists and the children who witness the violence. In addition to the necessary interventions for the protection of the victim, individual (not couple-based) treatment of both the woman struggling to get out of the abusive relationship and the man perpetrator of violence must be planned, without neglecting specific programs for children. [ABSTRACT FROM AUTHOR]

Background: Recurrence, even after years from the last treatment, characterizes lymphoproliferative disorders. Therefore, patients in complete remission from the disease should be followed up with periodic clinical checks. There is not a consensus on the role of imaging for this aim, because the radiological techniques used at the time of diagnosis expose patients to a risk of ionizing radiation damage. Whole-body magnetic resonance imaging with diffusion-weighted imaging (WB-MRI-DWI) has given similar results to gold standard techniques in detecting lymphoma in the involved sites without ionizing radiation. In this retrospective real-life study, we aimed to assess the accuracy of WB-MRI-DWI during follow-ups of lymphoma patients in terms of sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV). Methods: Lymphoma patients who were subject to at least one WB-MRI-DWI during follow-up between February 2010 and February 2022 were enrolled. Results: Based on our investigation, the calculated sensitivity of WB-MRI-DWI was 100% (95% CI: 99.4–100.0), the specificity was 98.6% (95% CI: 97.4–99.3), PPV was 79% (95% CI: 75.9–81.9), and NPV was 100% (95% CI: 99.4–100.0). Conclusions: Despite the possibility of poor patient compliance and the identification of false positives, WB-MRI-DWI examination demonstrated an excellent sensitivity in ruling out the disease relapse. [ABSTRACT FROM AUTHOR]