Category Archives: Uncategorized

Enhancing News Verification System Using Blockchain and Text Analysis

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

Learning System for Tree Traversal Algorithms: An Enhanced Algorithm Visualization Tool

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

State-of-the-Art Machine Learning Paradigms And Explainable Artificial Intelligence (XAI) Frameworks For Intelligent Network Intrusion Detection: A Comprehensive Literature Survey

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

An Explainable Transformer Based Framework For Detecting Misinformation In Social Media

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

Explainable Artificial Intelligence For Early Disease Prediction: A Multi-Modal Healthcare Analytics Framework For Precision Medicine

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

Strategic Decision-Making Framework Using Business Analytics for Sustainable Organizational Growth

Authors: Assistant Professor Dr.S.Sujatha, Assistant Professor Dr Sayantani Chakraborty

Abstract: In times when organizations face a high level of challenges, they need sophisticated models that help them to reconcile conflicting goals and maintain sustainable development. In this paper, we propose an analytical strategic decision-making model combining the use of business analytics with multi-objective optimization and sustainability principles. We base our research on Multi-Objective Optimization (MOO) concept, Pareto frontier theory, and Triple Bottom Line (TBL) framework. As a result, we have developed a model that allows organizations to deal with conflicting goals concerning profitability and risk level and maintain sustainable development at the same time. The analysis of quantitative data from different industries shows that application of the proposed model significantly increases the efficiency of decision making and strategic planning in organizations.

DOI: https://doi.org/10.5281/zenodo.21350647

Real-Time IoT Environmental Monitoring: Unmasking Diurnal Thermodynamic Transitions, Inverse Humidity Relations, and Atmospheric Scrubbing Effects

Authors: Prince Pawar, Sujal Sisodiya, Associate Professor Pradeep Patel

Abstract: Rapid microclimatic fluctuations often evade detection by sparse, conventional meteorological networks, necessitating hyper-local, real-time monitoring solutions. This paper presents an analysis of an 8-hour diurnal environmental dataset (10:00 AM to 5:00 PM) captured via an Internet of Things (IoT)-based monitoring node. The system integrates low-cost sensors to continuously log ambient temperature, relative humidity, air quality (particulate/gas concentrations in ppm), light intensity, and precipitation. The empirical data reveals distinct thermodynamic transitions and strong inter-parameter correlations. Specifically, the dataset captures a textbook meteorological shift: midday solar heating—evidenced by a peak temperature of 34∘C, peak light intensity (100%), and a concurrent relative humidity drop to 45%—followed by a sudden convective afternoon rain shower. The onset of precipitation at 3:00 PM triggered an immediate environmental inversion, characterized by a 3∘C drop in temperature, a sharp moisture surge to 68% relative humidity by 5:00 PM, and a significant reduction in airborne pollutants (from a peak of 180 ppm down to 125 ppm) due to the atmospheric scrubbing effect of the rain. These findings demonstrate that high-frequency IoT sensor networks provide highly reliable, granular data essential for unmasking the velocity and impact of localized weather fronts. The proposed approach offers scalable, actionable insights applicable to urban climate mapping, smart agriculture, and industrial environmental compliance.

DOI: https://doi.org/10.5281/zenodo.21353849

Hybrid Deep Learning Approach for Enhancing Security and Disease Detection in Healthcare Systems

Authors: Ms. Nibha kumari, Associate Professor Dr. Pramod K

Abstract: The rapid growth of digital technologies in healthcare has led to the generation and storage of vast amounts of sensitive medical data, making security and efficient data processing critical concerns. Deep learning, a powerful subset of artificial intelligence, has shown significant potential in addressing these challenges by enabling accurate analysis of complex healthcare data and enhancing system security. This study examines the application of deep learning models in healthcare systems with a focus on improving security, disease detection, and data reliability. The research reviews existing studies related to artificial intelligence and deep learning techniques used in medical image analysis, disease prediction, and healthcare data protection.

DOI: https://doi.org/10.5281/zenodo.21355298

Ethical Artificial Intelligence: Bridging Innovation and Social Responsibility

Authors: Ms. Neha Yadav, Dr. Nitin Kumar

Abstract: Smartphone addiction has become a growing concern due to excessive dependence on mobile devices for communication, entertainment, and social interaction. This research focuses on a data-centric machine learning framework for detecting smartphone addiction by analyzing user behavioral patterns such as screen time, unlock frequency, app usage, and night-time activity. Unlike traditional model-focused approaches, the proposed framework emphasizes data quality, preprocessing, feature engineering, and reliable labeling to improve prediction performance. The study aims to support early identification of addiction risk and contribute to the development of intelligent digital well-being systems for healthier smartphone usage habits.

DOI: https://doi.org/10.5281/zenodo.21355847

Dual-Transporter Targeted Lectin-Omega-3 Nanoparticles For Enhanced Neuronal Resilience In Neurodegenerative Disease Models

Authors: Hammed, Hammidat D, Enoma, Samuel, Donkoh, Christian J. K, Kikeh, Emric N, Agboola, Anthonia O, Benin, Sandra

Abstract: Neurodegenerative illnesses pose a significant problem, partly due to the challenge of getting therapeutic drugs across the blood-brain barrier (BBB), as well as the complex interactions between neuroinflammation and metabolic dysregulation. As a way to address these issues, we have created a lipid nanoparticle (LNP) system. It combines two different types of transporters with the intended goal of delivering omega-3 fatty acids through the use of plant lectins to help facilitate the movement of DHA and EPA across the BBB. As a special feature of this created LNP system, when utilizing the GLUT1 and LAT1 transporters located on the endothelium of the BBB in order to move the LNPs across the BBB from the circulation to the brain, both GLUT1 and LAT1 are used simultaneously, allowing a more efficient means of delivering the LNP system across the BBB without being limited by saturation kinetics when both GLUT1 and LAT1 are engaged. Within the LNP, both DHA and EPA are contained in an optimized ratio for both optimal delivery and maximal effect, supporting the activation of neuroprotective pathways (NF-κB suppression) and the promotion of mitochondrial biogenesis. The use of lectin (a binding agent derived from plant sources) as a means by which to reduce inflammation and provide a pathway to help the LNP system penetrate the BBB and provide an inflammatory reduction via helping to change microglial polarity towards an anti-inflammatory phenotype was also demonstrated. The experimental validations done with this LNP system, using human induced pluripotent stem cell (iPSC) derived human BBB models, clearly showed significantly greater levels of transcytosis flow than what is typically expected. As well, in transgenic Alzheimer's mouse models, the oxidative stress levels were significantly decreased and the synaptic structure was maintained. The novel nature of this work is due to the ability of each of the transporters, GLUT1 and LAT1, to target neurodegenerative disorders while also utilizing immunomodulatory and metabolic pathways in tandem. The strategy applied here provides an innovative and effective platform to enhance neuronal resiliency through the combination of neuroprotection and directional/neural specific drug delivery with applicability across a broad range of neurodegenerative diseases.

DOI: http://doi.org/10.5281/zenodo.21357715

A Review On Solar Energy Based Electricity Production

Authors: Dr Hari Gangadhar Kale

Abstract: The solar energy is generated by the Sunlight is a sustainable renewable energy source that doesn't harm the environment. The earth receives enough solar energy per hour to cover all of the world's energy needs for a full year. In the modern era we require electricity on a daily basis. This solar energy is produced for commercial, residential and industrial uses. It can readily absorb energy from direct sunshine. As a result it is highly effective and pollution free. We have analyzed solar energy from sunlight and spoken about its future developments and characteristics in this essay. Additionally, the page attempts to clarify how different types of solar panels operate and highlights the numerous uses and strategies for promoting the advantages of solar energy.

A Versatile Approach to Design Thinking Applied in Educational Contexts

Authors: Jereen Susan John

Abstract: Design thinking has emerged as an innovative, human-centered approach to addressing complex challenges in education by fostering creativity, collaboration, critical thinking, and problem-solving. This paper explores the versatility of design thinking and its application across diverse educational contexts, including school, higher, and professional education. It examines the core stages of the design thinking process—empathize, define, ideate, prototype, and test—and their role in promoting learner-centered, experiential, and inquiry-based learning. The study highlights how design thinking enables educators to develop inclusive teaching strategies, redesign curricula, enhance student engagement, and encourage interdisciplinary collaboration. Furthermore, it discusses the integration of digital technologies and real-world problem-solving activities that prepare learners with essential 21st-century skills. The paper argues that adopting design thinking as both a pedagogical framework and an institutional innovation strategy can transform teaching and learning environments by encouraging adaptability, empathy, and continuous improvement. It concludes that the widespread implementation of design thinking can contribute significantly to educational quality, innovation, and lifelong learning.

Magnetohydrodynamic Blood-Based Nanofluid Transport In Cardiovascular Prosthetics: A Numerical Study Of Coupled Heat And Mass Transfer With Nanoparticle Dynamics

Authors: Sheid, Avidime Momohjimoh, Sheidu Omeiza Momoh, Oyem Onyekachi Anslem, Shuaibu, Muhib Amoto

Abstract: This study presents a comprehensive numerical investigation of magnetohydrody-namic (MHD) blood-based nanofluid flow with coupled heat and mass transfer for cardiovascular prosthetic applications. The research addresses critical gaps in thermal regulation and targeted drug delivery modeling by developing a physiolog-ically realistic mathematical framework that incorporates electromagnetic effects, nanoparticle dynamics, and the non-Newtonian rheology of blood. The govern-ing conservation equations for mass, momentum, energy, and species concentration are formulated within a boundary layer framework, incorporating Lorentz forces, variable thermal conductivity, viscous dissipation, Joule heating, Brownian motion, thermophoresis, and chemical reactions. Through similarity transformations, the nonlinear partial differential equations are reduced to a system of coupled ordinary differential equations, which are solved numerically using a collocation method im-plemented in Python (scipy.integrate.solve_bvp). A comprehensive parametric analysis reveals that thermal and solutal buoyancy significantly enhance momentum transport, while the Prandtl number governs thermal boundary layer characteristics. Nanoparticle transport is predominantly controlled by thermophoresis and Brown-ian motion, with thermophoresis promoting nanoparticle accumulation and Brown-ian motion enhancing diffusion. The Schmidt number suppresses species diffusion, while the Casson parameter exhibits minimal influence on velocity but significantly affects thermal distribution. The magnetic parameter introduces resistive Lorentz forces that modify both momentum and thermal fields. These findings provide valu-able insights for the design of cardiovascular prosthetics, thermal therapy systems, and targeted drug delivery platforms.

DOI: http://doi.org/10.5281/zenodo.21407708