Metallurgical and Materials Engineering (E-Journal)
Not a member yet
915 research outputs found
Sort by
Metaverse-Based Career Counseling and Networking for College Students
Get PDFThe digital landscape is growing at an unparalleled rate and has transformed career counseling and professional networking, leading to the metaverse serving as a transformative platform for the collegiates. In this conceptual paper, we aim to discuss how metaverse-based career counseling and networking can leverage on potential in mitigating traditional challenges like access, engagement, and personalization in career counseling. Metaverse career counseling aims to bridge the gap between students' skills and industry demands through immersive experience and data-driven insights.
In addition, virtual-form or 3d form interaction in other to have physical activity give students a sense of lively in-school networking within the metaverse enables students to network with industry professionals, recruiters, and peers in realistic environments, circumventing geographical constraints to develop significant work-based links. This study addresses the theoretical foundation forming the basis of metaverse applications in relation to career development and the impact of those applications on student career readiness. Based on existing literature and emerging trends, this paper explores the opportunities, challenges, and future directions for career interventions in the metaverse.
In this way, findings have implications for the societal movement toward integrating metaverse technologies into career counseling frameworks and potentially eliciting substantial benefits for students in the form of engagement, self-efficacy, and better choices in their career decision-making. To start, some aspects of digital literacy, accessibility, and ethical considerations need to be considered for successful implementation. This paper is a step forward in the discussion of the role of virtual environments in preparing the future labor market and presents a framework for effective metaverse-based professional guidance and networking
Smart Healthcare Systems: Wireless Body Area Network Design and Analysis
Get PDFThe Wireless Body Area Networks (WBANs) have revolutionized healthcare by enabling continuous remote monitoring and enhancing diagnostic capabilities. This study introduces the Hierarchical Temperature and Energy Protocol (HTTEP), a novel, energy-efficient protocol designed to address the security and efficiency challenges of WBANs. Traditional WBANs struggle with issues related to secure communication, power management, and performance optimization due to energy constraints and network stability concerns. To secure digital-human body communication transceivers and sophisticated intrusion detection systems to improve data protection and network reliability. HTTEP enhances WBAN performance through a weighted function that considers residual energy, temperature, data rate, and energy expenditure. This protocol aims to optimize network stability and extend the network's lifetime while effectively managing node temperature and energy consumption. The development of a new WBAN architecture, extensive simulations and real-world testing. The results reveal that HTTEP outperforms existing protocols such as SIMPLE and ATTEMPT by maintaining superior network stability, extending network lifetime, and improving energy and temperature management. The HTTEP protocol showcases significant advancements in healthcare applications by providing a robust and efficient WBAN system that supports continuous health monitoring and management, offering enhancements in energy efficiency, data integrity, and system scalability compared to conventional solutions
Dynamic Orchestration of Data Pipelines via Agentic AI: Adaptive Resource Allocation and Workflow Optimization in Cloud-Native Analytics Platforms
Get PDFThe move towards more dynamic machine learning (ML) is present in all sorts of areas within the field, creating a tantalizing possibility to use such methods to not only create models that are more in tune with the constantly changing world we live in and the data which is being generated from it but also a world where the automated pipeline processes behind the ML modeling are severely underutilized. One area that has received little attention in this burgeoning area is most of the work being done under the umbrella of agentic AI, or methods aimed at creating agents that are semi-autonomously able to do complex tasks with little human interaction. This paper aims to summarize some of the work, both in terms of completed tasks as well as the technologies that will allow us to create a new paradigm for an automated data ML pipeline, both in terms of how data is consumed for ML tasks as well as how tasks are set up, monitored, and completed. Using an agent-centric approach we seek to allow agents to both have different expertise levels with regards to different types of ML tasks, be able to learn over time by themselves which are the most competent agents for certain tasks, as well as having users not need to worry about piping together a complex set of steps for a complicated task. Rather the user will simply provide a high-level description of what they need accomplished, as well as any constraints, and the agent system will find the best pathway for accomplishing the task and either execute the pathway itself or coordinate with other agents to complete the task. Such a paradigm will allow for the automated orchestration of very complicated tasks as well as the execution and monitoring of larger, often cumbersome and fragile task pathways, and allow domain specialists for any field to be able to utilize ML pipelines to accomplish their goals while the technical details are handled by specialized ML agents
High-Temperature CO₂ Separation from Flue Gas Using Ceramic Membranes: Experimental Insights and Artificial Neural Network Modeling
Get PDFThe effective capturing of carbon dioxide (CO₂) from flue gases represents an important environmental and economic challenge, where such emissions are considered a major contributor to global climate issue. Traditional capturing techniques such as amine scrubbing are energy-intensive with high cost, due to the necessity of cooling high temperature flue gases before the separation process. In this study, we investigated the utilization of ceramic membranes fabricated from Saudi red clay which considered an available, cost-effective local material as a sustainable solution for high-temperature CO₂ capture. The research evaluates separation efficiency under high temperatures and different pressure values, which enable direct CO₂ capturing from hot flue streams without precooling processes. Experimental results demonstrate the membranes efficacy in separating CO₂ from flue gas, in which the presence of iron oxide (Fe₂O₃) constituents in the clay enhancing capture efficiency through weak chemisorption. In addition, the membranes showed robust structural integrity and consistent performance under high temperature conditions, compared to polymeric membranes that degrade thermally and offer advantages over metal-organic framework-enhanced ceramics, which incur higher costs and lower thermal tolerance. An ANN model is constructed to estimate the membrane performance (CO2 concentration (%) in permeate) using results obtained from the present experimental results and utilizing pressure and temperature as ANN input parameters. The process of training incorporates the analysis of the loss function on training and validation data for controlling the weights and biases using backpropagation while feed forward propagate the selected input parameters. A total of 8 hidden layers consisting of 12 neurons each has been used in constructing the ANN, and training process is optimized using the ADAM algorithm to minimize the loss function. The Final layer uses the linear activation function while all the hidden layers use the rectified Linear Units Activation function (ReLU). The ANN model demonstrates excellent predictive performance, yielding values close to 1 for R2 and r, along with extremely low values for MSE, MAPE, MSLE, and log-cosh loss (0.00033, 0.146%, 4.1×10⁻6, 0.00016 respectively), demonstrating the ANN model's high predictive accuracy
The Assessment of Water Quality Forecasting Using AI-Based ML Algorithms
Get PDFWater quality matters to people, animals, plants, ecosystems, and entities. Recent environmental damage and contamination have harmed water purity. Because they indicate water authenticity, the Water Quality Index (WQI) and Water Quality Classification (WQC) are difficult to predict. In this paper, KNN imputers improve many MLalgorithms for water quality prediction. The precision of current methods is not good enough. Additionally, there are missing values in the dataset that are currently accessible for study, and these missing values significantly impact the classifiers' performance. This paper proposes an automated water-quality prediction system that effectively handles missing data while achieving high forecast accuracy. Furthermore, the accuracy of the suggested approach is assessed in relation to that of four machine learning methods. BPNN, RBFNN, SVM, and K-Nearest Neighbours are these approaches. These approaches model and predict water quality parameters such as DO, pH, NH3, NO3, and NO2. For the purpose of evaluating the accuracy of the various approaches to prediction, published data were utilized and for DO prediction, BPNN, RBFNN, SVM, and KNN had Pearson correlation values of 0.60, 0.99, 0.99, and 0.99. BPNN, RBFNN, SVM, and LSSVM had Pearson correlation coefficients of 0.56, 0.84, 0.99, and 0.57 for pH prediction. For NH3-N forecasting, BPNN, RBFNN, SVM, and LSSVM had Pearson correlation coefficients of 0.28, 0.88, 0.99, and 0.25. For NO3-N prediction, BPNN, RBFNN, SVM, and LSSVM obtained coefficients of correlation of 0.96, 0.87, 0.99, and 0.87. With correlation ratings of 0.87, 0.08, 0.99, and 0.75, BPNN, RBFNN, SVM, and LSSVM projected NO2-Ncorrelated coefficients. SVM was used to forecast water quality for groundwater-based industrial aquaculture systems. Most precise and reliable predictions were made with SVM. Both published and commercial aqua farming system data showed that the support vector machine (SVM) had the highest prediction accuracy, with 99% accuracy. For commercial farming water quality modeling and forecasting, utilize the SVM model.est
Enhancing Web Browsing Experience Using User Perception Knowledge Through The Construction Of An Indigenous Occurrence Warehouse
Get PDFToday, users' information is increasingly converted into digital content. Personal information, knowledge extraction, advertisements, travel details, and more are all accessed through web extraction. Any knowledge available digitally today is based on users' personal searches, which vary from one user to another. Whenever a user attempts to extract information from the stored pool, the extraction is based on the content available on the World Wide Web and the specific search performed by the user. By combining these two types of extraction, users can retrieve the information they need. Based on users' search frequency, online examination procedures can identify their patterns. This enables the system to suggest relevant searches the next time a user performs a query, thereby improving the search process. The proposed research work demonstrates how this search process can be aligned with both global content and users' generalized content. The examination presented in this work introduces methods that enhance users' investigation functions effectively
Edge Computing And NLP In AI -Enabled Vehicle Emergency Systems: Reducing Response Time And Saving Lives
Get PDFThis paper presents a novel AI-driven emergency response system for vehicles that significantly improves post-crash emergency assistance by enhancing accident detection accuracy and response time optimization. The proposed system integrates multi-modal sensor data with deep learning techniques to accurately detect accidents, assess injury severity, and optimize emergency resource allocation. Experimental results demonstrate a 94.7% accuracy in crash detection, 89.3% accuracy in injury severity prediction, and an average 8.2-minute reduction in emergency response time compared to traditional systems. The framework incorporates vehicle sensor networks, edge computing, and natural language processing to create a comprehensive emergency response ecosystem. Field tests conducted across diverse environmental conditions validate the system's robustness and reliability, suggesting significant potential for reducing road traffic fatalities through AI-enhanced emergency response mechanisms
The Influence Of Brand Reputation On Women’s Buying Decisions For Baby Products
Get PDFWhen it comes to parenthood, selecting baby products mirrors a mother's commitment and concern for her child's well-being and health. This decision, far from being inconsequential, is influenced by profound sociological and emotional factors, rendering it a subject worthy of comprehensive scrutiny. This study examines the effect of brand reputation on women's purchasing decisions regarding baby care products within the rapidly evolving baby product market. Using data collected from a specific sample in Chennai, the research employs factor analysis and multiple linear regression to reveal that brand reputation significantly influences women's buying choices in this domain, with a focus on product quality, customer service, and customer reviews. However, it is essential to acknowledge the study's limitations, including its sample specificity, potential regional and cultural variations, limited factors explored, and geographic scope. Despite these constraints, the findings contribute valuable insights for businesses seeking to enhance brand reputation and cater to shifting consumer preferences in the baby care product industry
Enhancing Sentiment Analysis With Emotion And Sarcasm Detection: A Transformer-Based Approach
Get PDFOur research focuses on analyzing the reviews generated on ecommerce sites like Amazon, which is complex due to the diverse ways in which the customers express themselves. They may be informal, sarcastic, and contain underlying and hidden sentiments making it difficult to analyze the sentiments meticulously. Traditional methods have been successful in training sentiment analysis models which predict whether a given statement or review is positive, negative or neutral. They fail to record deeper and underlying emotions like frustration, joy, anger and also, cannot detect sarcasm, where a positively shaped statement is actually negative. Therefore, our research puts forward an advanced sentiment analysis system that incorporates both Natural Language Processing (NLP) and Machine Learning techniques to bridge these gaps. Consequently, integrating sentiment analysis, emotion and sarcasm detection gives a better understanding of the product and customer feedback. To enhance the readability, the system also consists of visualizations of the sentiments and emotions through interactive pie charts and word clouds. This hence helps businesses to take data-centric decisions, and also help customers get a concise analysis of the product. This research emphasizes on the usage of VADER and BERT for sentiment analysis. Additionally, a neural network is used for sarcasm detection and Amazon reviews are scraped using Beautiful Soup
A Data-Driven Digital Twin Framework Using Long Short-Term Memory Networks For Intelligent Energy Optimization In Residential Buildings
Get PDFWith the increasing emphasis on sustainability and energy-conscious living, there is a growing demand for adaptive systems that can intelligently manage residential energy usage. This study proposes a data driven approach that combines Long Short-Term Memory (LSTM) neural networks with Digital Twin (DT) technology to support long-term energy forecasting and optimization in non-automated residential buildings. The LSTM model was trained using real-time data collected from multiple homes, focusing on variables such as indoor temperature, occupancy, humidity, and electricity consumption. Corresponding DT models were built to simulate the physical behavior of each building and validate the predictive performance under various operational scenarios. The hybrid system achieved high accuracy in forecasting, with a Mean Absolute Percentage Error (MAPE) under 7% and R² values consistently above 0.91. Additionally, simulation-based energy control using this model demonstrated annual savings between 19% and 21%. The study builds on prior ANN-based research and introduces an adaptable and scalable methodology suitable for conventional residential contexts