Blockchain-based smart contracts, while transformative, pose privacy concerns due to Ethereum's transparency. To address this, we present Safe Smart Contracts (SafeSC), leveraging zk-SNARKs for privacy without com...
详细信息
The availability of large, high-quality annotated datasets in the medical domain poses a substantial challenge in segmentation tasks. To mitigate the reliance on annotated training data, self-supervised pre-training s...
详细信息
The availability of large, high-quality annotated datasets in the medical domain poses a substantial challenge in segmentation tasks. To mitigate the reliance on annotated training data, self-supervised pre-training strategies have emerged, particularly employing contrastive learning methods on dense pixel-level representations. In this work, we proposed to capitalize on intrinsic anatomical similarities within medical image data and develop a semantic segmentation framework through a self-supervised fusion network, where the availability of annotated volumes is limited. In a unified training phase, we combine segmentation loss with contrastive loss, enhancing the distinction between significant anatomical regions that adhere to the available annotations. To further improve the segmentation performance, we introduce an efficient parallel transformer module that leverages Multiview multiscale feature fusion and depth-wise features. The proposed transformer architecture, based on multiple encoders, is trained in a self-supervised manner using contrastive loss. Initially, the transformer is trained using an unlabeled dataset. We then fine-tune one encoder using data from the first stage and another encoder using a small set of annotated segmentation masks. These encoder features are subsequently concatenated for the purpose of brain tumor segmentation. The multiencoder-based transformer model yields significantly better outcomes across three medical image segmentation tasks. We validated our proposed solution by fusing images across diverse medical image segmentation challenge datasets, demonstrating its efficacy by outperforming state-of-the-art methodologies. IEEE
This project aims to help flash floods' victims and rescuers facilitate rescue efforts. By integrating Internet of Things (loT) and Global Positioning System (GPS) capabilities, flood victims can use a device (eme...
详细信息
This research explores the Jacobi elliptic expansion function method and a modified version of the Sardar sub-equation method to discover new exact solutions for the nonlinear Hamiltonian amplitude equation. By applyi...
详细信息
For a torsion-free affine connection on a given manifold, which does not necessarily arise as the Levi-Civita connection of any pseudo-Riemannian metric, it is still possible that it corresponds in a canonical way to ...
The project "Real-time data-driven maintenance logistics" was initiated with the purpose of bringing innovations in data-driven decision making to maintenance logistics, by bringing problem owners in the for...
详细信息
Specifically targeting Yemeni universities, the focus lies on their potential to enter these rankings and enhance their positions such as Quacquarelli Symonds (QS) World University Ranking (QS), Academic Ranking of Wo...
详细信息
ISBN:
(数字)9798331533557
ISBN:
(纸本)9798331533564
Specifically targeting Yemeni universities, the focus lies on their potential to enter these rankings and enhance their positions such as Quacquarelli Symonds (QS) World University Ranking (QS), Academic Ranking of World Universities (ARWU), Webometrics Ranking, Times Higher Education (THE) World University Ranking, and SCImago Institutions (SIR) Rankings. Its objective is to encourage Yemeni universities to prioritize the criteria outlined in these rankings and view them as a means to access other international rankings. The research tackles the challenge of comprehending the criteria and application process required for Yemeni universities to participate in these rankings, as well as the rankings they have achieved. The study underscores the importance of this research by providing Yemeni university administrators with valuable insights into the criteria used for international rankings and the rankings obtained by Yemeni universities. This understanding can facilitate efforts to enhance the quality of higher education within these institutions. The findings of the study reveal that there are two Yemeni universities listed in the QS. The University of science and Technology, ranks 151-170, while Thamar University, ranks 171-200 for 2023. While in 2024, the University of science and Technology ranked first locally and the University of Aden ranked second. This paper investigates the participation of Yemeni universities in global ranking systems such as ARWU, THE, QS, and SIR, with the aim of enhancing their international standing. It highlights the challenges and opportunities for Yemeni universities to meet ranking criteria, offering insights that can help improve the quality of higher education.
The k - Sum Problem, which is a generic member of the family of which 2 - Sum and 3 - Sum problems are the youngest siblings is one of the most interesting problems in the domain of Optimization Techniques. Many resea...
详细信息
The term Internet of Things (IoT) is used to refer as embedded devices or objects with internet access, allowing them to communicate globally, interacting with people and networks. IoT security issues are directly rel...
详细信息
The mining industry's continuous pursuit of sustainable practices and enhanced operational efficiency has led to an increasing interest in leveraging innovative technologies for process monitoring and optimization...
详细信息
暂无评论