Daily Archives: July 13, 2026

Authors: N Jeevana Jyothi, M. Priyatharshini

Abstract: Combination of multimodal healthcare data such as genomic profiles, EHRs, medical imaging, and wearable sensor data brings in new opportunities for early disease prediction and precision medicine. Nevertheless, the complexity and black-box nature of state-of-the-art machine learning models bring many challenges towards their clinical deployment. This paper introduces a novel explainable artificial intelligence (XAI) architecture for early disease prediction using multi-modal healthcare analytics. The proposed framework combines various data streams using cross-modal generative transformers, interprets results by means of feature attribution and attention heatmaps computed using SHAP values, and utilizes federated learning techniques to preserve the privacy of the participating institutions. Evaluation using real-world multimodal datasets confirms high effectiveness of our solution with accuracy of 97% and AUC of 0.971, which is much better compared to unimodal and black box models.

DOI: http://doi.org/10.5281/zenodo.21338356

Published by: vikaspatanker

Authors: Dr. Prakash Kammam, Mukkapati Venu, K. Ashwini

Abstract: The fast spread of misinformation on social media platforms is causing serious issues with regards to public trust, democracy, and making sound decisions. The following paper provides a comprehensive overview of transformer-based systems for explainable misinformation detection, considering the latest research in the field of multimodal fusion, large language models implementation, and explainable AI. As can be seen from the systematic analysis, transformers surpass traditional methods in performance, with the multimodal system providing an accuracy of up to 94.5% and 81.1% on benchmark datasets. Moreover, large language models are very useful when generating background knowledge and enriching context, whereas explainability methods such as SHAP and LIME offer human-interpretable rationales for decisions made by the model. It was found that hierarchical progressive transformers successfully incorporate multimodality, combining different types of data such as text, images, background knowledge, and user comments, resulting in better performance than current methods.

DOI: http://doi.org/10.5281/zenodo.21338113

Published by: vikaspatanker

Authors: Aravind Chagantipati

Abstract: The deployment of high-throughput deep neural networks within modern enterprise multi-cloud backbones has significantly advanced the accuracy of automated anomaly tracking. However, their highly complex, multi-layered topologies operate as opaque black boxes, creating substantial validation and trust barriers for security operations teams. This paper provides a comprehensive literature survey analyzing the structural shift from traditional shallow machine learning classifiers to deep temporal topologies using benchmark corpuses (NSL-KDD, CICIDS, and UNSW-NB15). Furthermore, it reviews contemporary post-hoc Explainable AI (XAI) integration paradigms, focusing on SHAP and LIME architectures designed to manage the performance-trust trade-off across production boundaries. We provide a rigorous analysis of classification metrics, mathematical foundations of feature attribution, and practical implications for next-generation security operations centers.

DOI: http://doi.org/10.5281/zenodo.21336418

Published by: vikaspatanker

Authors: Samir Yau Nuhu, Jamilu Awwalu, Zaharaddeen Salele Iro, Zaharaddeen Sufyanu

Abstract: Tree traversal algorithms form a major part of undergraduate computer science education because they teach important concepts about how data is organized and processed in trees. However, students find these algorithms difficult to understand since they are abstract and involve following specific rules to visit each node in a particular sequence. Existing visualization tools fail to help students fully because they do not clearly separate or explain the differences between the three main Depth-First Search variants, and they do not show the step-by-step order of visited nodes in a simple and structured format. To solve these problems, this thesis presents a new interactive learning tool that runs directly in a web browser and is built using HTML, CSS, JavaScript and SVG. The tool allows students to create their own binary trees by adding nodes, gives them full control to move through each step of any traversal method, and includes a table-generation feature that automatically builds and displays a clear list showing exactly which nodes are visited and in what order. We carried out an analysis of the system’s algorithms and showed that it remains efficient and scalable even when working with larger tree. In addition, we tested the tool in a real classroom setting with 100 undergraduate computer science students. Before using the tool, their average score on a test about tree traversals was only 40%. After use of the tool their average score increased to 68%. These results clearly demonstrate that the new system overcomes the main weaknesses of earlier visualization tools and helps students gain a better understanding of tree traversal algorithms.

DOI: http://doi.org/10.5281/zenodo.21334804

Published by: vikaspatanker

Authors: Durga Prasad, Dr. Avadhesh Kumar Dixit

Abstract: The spread of fake news and misinformation on the internet has becoming the very serious problem, which making it difficult for the people to know what to trust. The current methods for verifying news often have the limitations: they can be too slow, lack transparency, or fail to confirm that the original source of story. This paper is proposing a new system that is combining two powerful technologies to addressing these challenges. Where first, we use the text analysis techniques from the field of Natural Language Processing (NLP) to scan news contents and identifying linguistic patterns often associated with the false and misleading information. Second, we leveraging the blockchain technology which is used to create a tamper-proof record of a news article’s origin and any changes made to it over time. By storing a digital footprint of the verified content on the blockchain, our system which allowing the readers to check if the news they are viewing matches the original version published by a trusted source. This dual-prolonged approach not only helps flag the potentially deceptive content through analysis but also builds a trustworthy chain of provenance. In the proposed system offers a more reliable and transparent way to verify digital news, empowering users to make informed judgments about the information they will consume.

DOI: http://doi.org/10.5281/zenodo.21333813

Published by: vikaspatanker