Metallurgical and Materials Engineering (E-Journal)
Not a member yet
915 research outputs found
Sort by
Smart Solar Cells: Harnessing Nanotechnology And Iot For Enhanced Transmission Capabilities By Using PI Controller
Full text linkThis research attempts to investigate new ways to enhance the effectiveness of solar cells by integrating cutting-edge technologies such as nanotechnology and the Internet of Things (IoT) to augment transmission capabilities. To maintain stability in voltage and current and to keep the power supplied to an AC load constant, the research utilizes a Proportional-Integral (PI) controller. Both experimental and simulated data indicated that the application of nanotechnology, in particular, the use of Fe₃O₄ magnetite nanoparticles, improves the effectiveness of solar cells by diminishing recombination losses and increasing charge carrier mobilities, thus increasing the overall efficacy of the solar panel. The data indicated that there was a solar panel efficiency increase of 2-3% during peak sunlight hours. In addition, the PI controller was better at controlling power output, especially with solar cells that used nanotechnology. The use of advanced nanotechnology and IoT demonstrate a big potential in improving and optimizing solar powered systems to provide efficient and dependable power generation
Interpretable Machine Learning For Concrete Compressive Strength Prediction: A Neural Network Model With SHAP-Based Explainability And Robust Multi-Metric Validation
Full text linkAccurate prediction of concrete compressive strength is crucial for efficient structural design, sustainable material optimization, and reliable quality control. While data-driven models, particularly artificial neural networks (ANNs), have shown superior predictive capability over traditional empirical methods, their widespread adoption in engineering practice is often hindered by their "black-box" nature and a lack of comprehensive, interpretable validation. This study develops a robust, fully connected neural network model to predict the 28-day compressive strength of concrete from eight key mix design parameters. The model, trained on a dataset of 1,133 mixtures, demonstrates excellent performance, achieving a test set coefficient of determination (R²) of 0.865, a root mean squared error (RMSE) of 5.91 MPa, and a mean absolute error (MAE) of 4.49 MPa. Crucially, the work transcends standard predictive analytics by integrating advanced model-agnostic interpretability techniques. Shapley Additive exPlanations (SHAP) and permutation importance analyses are employed to quantify and visualize feature contributions, revealing that the model's logic aligns with established concrete science: cement content and curing age are identified as the dominant positive factors, while water content exhibits a strong negative influence. The role of supplementary cementitious materials (slag and fly ash) is shown to be complex and context-dependent. A suite of six statistical metrics (MSE, RMSE, MAE, MAPE, R², CVRMSE) and detailed error distribution analysis provide a transparent, multi-faceted assessment of model accuracy and generalization. The results confirm that the proposed ANN is not only a high-fidelity predictive tool but also an interpretable model whose learned relationships validate domain knowledge, thereby bridging the gap between computational power and engineering trust for advanced concrete mix design
Breaking The Bottleneck: Automating Health Risk Assessment To Empower Care Teams Using Agentic Artificial Intelligence
Full text linkThe conventional approaches to health risk assessment used in healthcare organizations are increasingly becoming a burden to these organizations, with questionnaires, infrequent reviews by clinicians, and data systems that hold only isolated pieces of information about the health journey of patients. Care managers waste too much time in manual data collection and redundancy in questioning, instead of concentrating on therapeutic relationships with patients and the coordination of care. The solution of agentic artificial intelligence is disruptive as it will interact autonomously with patients by means of conversational interfaces, combine real-time data from various sources (wearables and health applications), and continuously update risk profiles. These smart systems liberate care team workloads, collect dynamic health indicators like sleep behaviors and heart rate variability, personalized measurements, and provide proactive notifications if a risk threshold has been met. The implementation offers a lot of benefits, such as an increased capacity of care managers, earlier identification of health decline, enhanced comprehensiveness of assessment, patient burden, and proactive risk management, which can be scaled. Nonetheless, to be deployed successfully, data privacy and security, mitigating algorithmic bias, encouraging an uninterrupted clinical workflow, preserving human oversight, overcoming the digital divide by hybrid solutions, and strict regulatory adherence are to be taken into account. The merging of artificial and human intelligence in health risk assessment is sure to radically remodel the care delivery, enabling it to intervene earlier, with more personalized care plans, and even better outcomes at a reduced cost in the value-based healthcare setting
Prediction of Concrete Compressive Strength Using Support Vector Machine Regression: Statistical Characterization, Model Performance, and Feature Importance Analysis
Full text linkThis study presents the development and evaluation of a machine learning–based framework for predicting the compressive strength of concrete using a Support Vector Machine (SVM) regression model. A comprehensive dataset comprising 1,133 concrete mix designs was employed, incorporating key material composition parameters, including cement, blast-furnace slag, fly ash, water, super-plasticizer, fine aggregate, coarse aggregate, and curing age. Prior to model development, extensive descriptive and advanced statistical analyses were conducted to examine the distributional characteristics, variability, skewness, and robustness of the input variables, ensuring a sound understanding of the data structure. The analysis revealed substantial variability in cementitious materials and curing age, highlighting the nonlinear and heterogeneous nature of concrete strength development. An ε-SVM regression model with a radial basis function kernel was implemented to capture these complex relationships. Model performance was assessed using an 80:20 train–test split and multiple statistical metrics, including mean squared error, root mean squared error, mean absolute error, mean absolute percentage error, coefficient of determination, and coefficient of variation of RMSE. The results demonstrate that the SVM model achieved strong predictive accuracy, with an R² value of 0.89, RMSE of 5.32 MPa, and MAPE of 11.38%, indicating reliable generalization to unseen data. Error analysis confirmed stable prediction behavior for most samples, with only a limited number of isolated outliers. Feature importance evaluation using univariate regression and a Relief-based algorithm identified cement content and curing age as the most influential parameters, followed by super-plasticizer and water content, in agreement with established concrete technology principles. Overall, the study confirms the suitability of SVM regression for concrete compressive strength prediction while emphasizing the importance of thorough data characterization, multi-metric evaluation, and feature interpretability for robust and physically consistent machine learning applications in civil engineering
Microstructure and impression creep characteristics Al-9Si-xCu aluminum alloys
Full text linkThe effects of 1.5, 2.5 and 3.5 wt.% Cu additions on the microstructure and creep behavior of the as-cast Al-9Si alloy were investigated by impression tests. The tests were performed at temperature ranging from 493 to 553 K and under punching stresses in the range 300 to 414 MPa for dwell times up to 3000 seconds. The results showed that, for all loads and temperatures, the Al-9Si-3.5Cu alloy had the lowest creep rates and thus, the highest creep resistance among all materials tested. This is attributed to the formation of hard intermetallic compound of Al2Cu, and higher amount of α-Al2Cu eutectic phase. The stress exponent and activation energy are in the ranges of 5.2- 7.2 and 115 -150 kJ/ mol, respectively for all alloys. According to the stress exponent and creep activation energies, the lattice and pipe diffusion- climb controlled dislocation creep were the dominant creep mechanism
The effect of primary copper slag cooling rate on the copper valorization in the flotation process
No full textTechnological procedure of slow cooling slag from primary copper production is applied in the purpose of copper recovery in the level of 98.5% to blister. This technological procedure is divided into two phases, first slow cooling of slag on the air for 24 hours, and then accelerated cooling with water for 48 hours. Within the research following methods were used: calculation of nonstationary slag cooling, verification of the calculation using computer simulation of slag cooling in the software package COMSOL Multiphysics and experimental verification of simulation results. After testing of the experimentally gained samples of slowly cooled slag it was found that this technological procedure gives the best results in promoting growth or coagulation of dispersed particles of copper sulfide and copper in the slag, thereby increasing the utilization of the flotation process with a decrease of copper losses through very fine particles
Assessing Service Quality in Ayurveda Medical Tourism: Health Care Services of Kerala, India
Full text linkThis study aims to explore the main dimensions of service quality and their impact on customer satisfaction in Ayurveda medical tourism in Kerala. The research seeks to identify the most important service quality attributes from the perspective of tourists to know various dimensions affect satisfaction and identify challenges and opportunities for improving service delivery in Ayurveda wellness centres. The approach adopted was quantitative research with an analytical and descriptive design. Data collection was through a structured questionnaire using a stratified random sampling method with a sample of 112 tourists. The data was analysed by use of SPSS software and statistical techniques, including the Friedman test, One-way ANOVA and One-sample t-test. Findings includes the service quality dimensions like Reliability, Responsiveness, Assurance, Empathy and Tangibles have significant influence on customer satisfaction. Improvement areas include infrastructure, cultural sensitivity and hygiene standards. Results of this study indicate Ayurveda service providers will need to work on reliability and responsiveness and personalization to drive customer satisfaction. It is concluded in the study that overcoming these challenges and exploiting the scope of improvement can help strengthen the competitiveness of Ayurveda wellness centres in Kerala's increasing medical tourism market
Enhanced Framework for Breast Cancer Detection in PET Images Using Hybrid Graph Convolutional Bidirectional LSTM and Hyperparameter Optimization
Full text linkBreast Cancer Detection (BCD) through Positron Emission Tomography (PET) images remains a crucial area of study for efficient treatment planning and early diagnosis. In combining innovative techniques for Noise Reduction (NR), segmentation, Feature Extraction (FE), Feature Selection (FS), classification, and hyperparameter (HP)tuning, this research offers a thorough framework for PET scans for BCD. First, a Hyper-Averaging Filter (HAF) is applied to PET images to effectively remove noise and enhance image clarity, ensuring more accurate analysis. Subsequently, the Improved BIRCH algorithm is utilized for segmentation, enabling the delineation of regions of interest within the images. Gray-level zone length matrix (GLZLM) features are taken from the segmented regions to present comprehensive texture information, providing important information on the textural characteristics of breast tissue. In addition, to maximize the effectiveness of ensuing classification tasks, the most useful features from the extracted feature set are selected with the FS method known as the minimum redundancy maximum relevance (mRMR). For breast cancer classification, a hybrid optimized Inspection Boosted Graph Convolutional Bidirectional LSTM (long short-term memory) units (O-IBGC-BiLSTM) model is developed. This innovative architecture improves PET image spatial and temporal feature processing by combining Graph Convolutional Networks (GCN) with Bi-LSTM memory units. To enhance model performance, hyperparameter tuning is performed using the improved sparrow search algorithm (ISSA), optimizing model parameters for improved accuracy and robustness. It uses the QIN-Breast Dataset to assess the suggested framework, demonstrating its effectiveness in accurately detecting Breast Cancer (BC) in PET images. Overall, this study presents a comprehensive and integrated approach for breast cancer detection, in clinical practice, may improve early diagnosis and treatment
Graph Theory: Modelling and Analyzing Complex System
Full text linkExhaustive data analysis becomes possible thanks to the implementation of graphs which combine nodes with edges since they let researchers study links and enhance networks alongside pattern identification. Researchers examine essential theories and applications of graphs as well as their analytic methods for analyzing complex systems in this study. Network centrality measures and shortest path algorithms and graph clustering methods constitute important analytical techniques which the study presents. These discoveries exhibit both effectiveness and necessity of graph-based models for addressing real-world difficulties through their optimization abilities in structure analysis
Statistical Modeling for COVID-19 Related Depression: Prediction, Classification, and Intervention
Full text linkThe globe has been in a chaos state since a corona-virus (SARSCoV2) first appeared in December 2019. It was helpful to utilize an isolation strategy with quarantine to slow down the spread of disease. As a result, individuals stayed indoors instead of engaging in their regular daily activities outside. The goal of this study is to examine the connections and potential mediatory pathways between mental health issues, how people perceive their illnesses, and disorders of anxiety and depression. This aim of this study is to use various machine learning approaches to predict, classify, and detect depression risk factors in two districs of Khyber Pukhtunkhwa (KPK), Pakistan. In this paper, machine learning methods i.e., Random Forest and LASSO have been used for feature selection. Random Forest (RF), Support Vector Machine (SVM), k-Nearest Neighbor (k-NN), Least Absolute Shrinkage Selection Operation (LASSO), and Random Projection ensembles (RP) have been used to assess the performance of the LASSO and Random Forest by identifying important features. The results show that LASSO has performed better than the other methods. Additionally, the clustering technique is also utilized to detect different hot spots in the population by considering the data as an unsupervised issue