Metallurgical and Materials Engineering (E-Journal)
Not a member yet
915 research outputs found
Sort by
Secure Federated Learning In Healthcare Using Blockchain And Smpc
Get PDFIn the World of AI in Healthcare, coupling Federated Learning (FL) with Blockchain is a changing paradigm in building secure and privacy upholding AI systems. However, FL potentially can be subject to model poisoning attacks and has no mechanisms for integrity verification of local models. This paper presents a blockchain-based federated learning framework with Secure Multi-Party Computation for the verification of encrypted models. Prior to aggregation, local model validation takes place under privacy preservation to ensure no malicious updates are counted. Verified models are then stored and SMPC aggregation on the blockchain to enable tamperproof decentralized training. The updated global model is shared among participants via the blockchain ledger. Experimental evaluations using Convolutional Neural Networks (CNNs) on medical datasets show that the proposed system can eliminate all poisoned models, improving global model accuracy from 0 to potentially 25%, while the verification speed is still close to normal inference. This framework promotes trust, data privacy, and model integrity in collaborative healthcare AI
Accelerometer-Based Dynamic Health Monitoring Of The Swarnamukhi River Bridge With Seasonal Vibration Evaluation
Get PDFEnsuring the structural integrity of bridges is critical for public safety and cost-effective infrastructure management. This study proposes a real-time structural health monitoring system for the Swarnamukhi River Bridge using accelerometer-based vibration analysis. Accelerometers were strategically installed across the bridge to continuously capture dynamic responses under varying traffic loads and environmental influences.The collected data was analyzed through key performance indicators: Frequency vs. Load, Acceleration vs. Time, and Stress Distribution heat map. These graphical analyses revealed the bridge's dynamic behavior and helped identify zones with elevated stress or abnormal vibration patterns. Special emphasis was placed on seasonal variation, with a detailed analysis of vibration characteristics recorded during December. This temporal assessment provided insight into how environmental conditions affect structural performance over time.The system effectively detected early signs of potential structural anomalies related to traffic-induced vibrations, climatic factors, and possible seismic effects. By enabling timely and informed maintenance decisions, the approach enhances bridge longevity and operational reliability.The results confirm the viability of using low-cost, accelerometer-based monitoring systems for accurate, real-time structural health assessment. This method offers a scalable and replicable solution for monitoring other critical infrastructure assets, contributing to broader efforts in sustainable infrastructure management and disaster resilience
Smart Grid Technologies: AI and ML for Enhanced Energy Management
Get PDFThe growing complexity of power systems necessitates intelligent solutions for efficient energy management. The various smart grid technologies integrate the artificial intelligence (AI) and machine learning (ML) to optimize energy distribution, predict the demand and provide the grid with enhanced resilience. Predictive analytics, demand response and fault detection are some of the main aspects that are discussed in this paper regarding the intelligent use of AI and ML in the modern smart grids. In doing this for recent advancements and case studies, we bring up the advantages of AI driven energy management in the forms of improved efficiency, reduced costs, and reduced environmental impact
Mathematical Modeling of Turbulent Flows Using Advanced Computational Fluid Dynamics
Get PDFVarious engineering projects depend on turbulent flow dynamics for operations in aerodynamics and energy systems as well as environmental fluid dynamics purposes. This research evaluates state-of-the-art CFD methods for simulating turbulence by studying RANS, LES, and DNS approaches. The research demonstrates both strengths and drawbacks and accuracy and efficiency comparison of different models as it evaluates computational methods. Better predictive modeling can be attained by implementing hybrid models together with machine learning assistance for turbulence modeling according to the findings presented
Optimizing Edge Computing for Big Data Processing in Smart Cities
Get PDFThe surge of big data and IoT in smart cities requires effective computational models to process massive amounts of real-time data. Edge computing emerges as an innovative solution by minimizing latency, improving security, and maximizing energy efficiency. This paper investigates the convergence of AI-based edge computing for big data processing through a study of four sophisticated algorithms: Federated Learning, TinyML, Edge-Optimized CNNs, and Adaptive Data Compression. Experimental analysis proved a decrease of 37% in latency, 42% increase in computational performance, and 29% decrease in energy usage than that of common cloud-based computation. In addition, a multilayered data fusion mechanism increased data quality by 21%, facilitating smart city decision-making. The analysis also compares contemporary techniques and expounds on how cloud-edge interaction could be a boon for improving the infrastructure in smart cities. Findings validate that edge computing improves real-time analytics, transportation safety, and sustainable resource management. Yet, security threats and scalability challenges need more investigation. Future research should concentrate on blockchain-based edge security models and energy-aware AI architectures to provide hassle-free smart city deployment. This research concludes that edge computing is the key to the next generation of smart urban infrastructure, encouraging efficiency, sustainability, and intelligent automation
The Rise of Artificial Intelligence in Intellectual Property Law: Patentability and Copyright Issues
Get PDFThe rise of Artificial Intelligence (AI) is transforming and posing important challenges in the field of Intellectual Property (IP) law regarding patentability and copyright. As AI systems increasingly produce inventions and creative works without human involvement, doubts arise on how suitable the present framework of intellectual property rights-invented to protect human-made innovations-is for such a confused state of AI. This paper develops its line of analysis around the AI implications for patent and copyright laws, checking out if current legal structures are such that they can address outputs from AI systems. While current laws in the patent regime recognize only a human inventor, an AI system can produce novel and non- obvious inventions. Should AI be viewed as an inventor, or would patent laws be transformed to recognize that AI is merely a tool in the invention process? The paper discusses various in-applicable case law and decisions such as the 2019 ruling of the USPTO that in certain inventions, the inventor could only be a human being, which manifests the fact that patentability frameworks remain unfit for AI-generated inventions. Moreover, in relation to copyright, it can be noted that the contingent works executed by AI challenge and suspend the necessity for human authorship. When AI generates such works on its way, the alternative arises and must be critically analysed who is to be considered the actual owner of copyright over the work? Current copyright frameworks in various jurisdictions, such as the U.S., do not extend protection to AI-generated works without incorporation of some human involvement in their creation. Possible suggestions of reform like placing authorship over X work under the AIs developer or user, or a New IP category addressing the input of AI in creation, formulations were discussed in the paper. Ultimately, innovations in both patent and copyright laws ought to grow in a balanced way that, while producing adequate protective layers over human creators, prepares itself to come into terms with rising Aid creativity and invention. For maintaining justice and fairness, reform in legal constructs for tracking with AI-generated creations is inevitable
Context-Aware Anomaly Detection In Smart Cities Using Multi-Modal Machine Learning Approaches
Get PDFAnomaly detection in smart cities is crucial for identifying unusual patterns in real-time data streams generated by diverse urban systems, such as traffic flow, energy consumption, air quality, and public safety. This study proposes a multi-modal machine learning framework for context-aware anomaly detection, integrating Convolutional Neural Networks (CNNs) for spatial feature extraction, Long Short-Term Memory (LSTM) networks for temporal pattern recognition, and contextual data (e.g., weather, public events) to improve detection accuracy. The hybrid CNN-LSTM model captures both spatial and temporal dependencies. At the same time, the inclusion of contextual information enables the model to adapt to changing conditions, improving the detection of anomalies such as traffic accidents or pollution spikes. Experimental results demonstrate that the proposed framework outperforms traditional anomaly detection methods in terms of accuracy, precision, and recall. The hybrid model's superior performance highlights its potential for real-time applications in smart cities, including sustainable urban management, fraud detection, and public safety monitoring
Estimation Of Binary Logistic Regression Parameters In Sensitive Surveys For A Two-Stage Randomized Response Technique
Get PDFWhen collecting data on sensitive topics such as abortion, harassment, tax evasion, and income, respondents often provide untruthful answers, leading to biased results. To address this issue, Warner introduced the Randomized Response Technique (RRT) to obtain sensitive information while ensuring respondent privacy. Building on this, Narjis and Shabbir proposed a two-stage RRT to estimate the prevalence of a sensitive attribute. This study extends their two-stage RRT by incorporating covariates through logistic regression to analyze their effect on the sensitive characteristic. Parameters of the logistic regression model are estimated under simple random sampling, and the performance of maximum likelihood estimators is evaluated through simulation
Beyond Illumination: Stakeholders Perspectives and Preferences on Eco-Friendly Lighting for Sustainable Cities
Get PDFThis study explores integrating eco-friendly lighting technologies as crucial components in advancing sustainable smart city infrastructure. As cities strive to reduce their carbon footprint and enhance energy efficiency, lighting systems like LEDs and OLEDs have emerged as critical components. This research aimed to assess industry stakeholders' awareness, adoption drivers, and challenges associated with these technologies. The survey, with a 73% response rate was conducted among key stakeholders in the construction, architecture, and real estate sectors, and the data was analyzed statistically (ANOVA and independent T-test) to capture differences in perceptions. Results indicate that over 70% of respondents are familiar with eco-friendly lighting, with key adoption drivers being energy savings, cost efficiency, and regulatory compliance. Similar perceptions between male and female respondents were observed, while more experienced professionals showed a greater preference for energy-saving innovations. However, significant barriers to widespread adoption include high upfront costs and installation complexity. The study concludes that financial incentives and targeted education are essential to overcoming the barriers and accelerating the adoption of sustainable lighting technologies. These findings align with Sustainable Development Goals (SDGs) 7, 11, and 13, supporting clean energy and resilient cities. These findings underscore the critical role that eco-friendly lighting technologies can play in advancing sustainable urban environments
Blockchain For Higher Education Reform: A Strategic Model For Formalizing Knowledge, Advancement, And Governance Systems
Get PDFUniversities across post-transition and semi-formal education systems face a persistent paradox: while knowledge production lies at the heart of their mission, the structures guiding staff advancement, knowledge use, and internal governance remain informal, politicized, and resistant to change. This paper presents a strategic reform model that uses blockchain not as a digital overhaul, but as a trust-enabling backbone to support cultural and institutional formalization. Grounded in prior field research and lived insight into Eastern European academic environments, the model integrates blockchain infrastructure with knowledge management formalization and performance accountability. It offers a layered blueprint to address deep-rooted challenges such as misaligned strategic plans, opaque staff progression, fragmented budgeting, and siloed information systems. Each layer maps onto essential university functions—rectorate governance, HR, finance, research, international relations, and IT—while allowing phased, modular implementation rooted in organizational realism. Rather than replacing the culture, the design respects it, while offering scalable tools for traceable decisions, transparent recognition, and shared institutional memory. By linking strategy, governance, and knowledge in practical and culturally aware ways, this model offers a path toward universities that are not only better managed—but more transparent, future-ready, and self-aware