Nagaraj Ashok
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Nagaraj Ashok has a total of 145 co-authors. Here are the top co-authors by number of shared publications:
Abhijit Bhowmik
Department of Additive Manufacturing, Mechanical Engineering, SIMATS, Saveetha Institute of Medical and Technical Sciences, Thandalam, Chennai, India
8 shared publicationsAnkush Mehta
School of Engineering and Technology, K. R. Mangalam University, Gurugram, India
4 shared publicationsJeewan Singh
University Center for Research & Development, Chandigarh University, Mohali, India
4 shared publicationsRaman Kumar
Department of Mechanical Engineering, Gokul Advanced Research & Innovation Laboratory (GARIL), Gokul Global University, Sidhpur, India
4 shared publicationsA. Bhowmik
Department of Additive Manufacturing, Mechanical Engineering, SIMATS, Saveetha Institute of Medical and Technical Sciences, Thandalam-602105, Chennai, India
3 shared publicationsPravat Ranjan Pati
Department of Mechanical Engineering, Graphic Era (Deemed To be University), Dehradun, India
3 shared publications
Latest Publications
- Open Access
- 4 November 2026
- Published by Springer Nature in Scientific Reports
Predicted enhanced wear resistance and mechanical integrity in AA8011 composites via dual-ceramic ZrB2 and B4C reinforcement
- 4 November 2026
- Published by Springer Nature in Scientific Reports
Open AccessPredicted enhanced wear resistance and mechanical integrity in AA8011 composites via dual-ceramic ZrB2 and B4C reinforcement
- Open Access
- 3 November 2026
- Published by Springer Nature in Journal of Materials Science: Materials in Engineering
Hybrid machine learning strategies for predicting for jute/ flax/ZnO reinforced composites
This study proposes an integrated experimental and machine-learning framework for the modeling and prediction of the properties of sustainable hybrid polymer nanocomposites reinforced with natural resource jute and flax fibers and Zinc Oxide (ZnO) nanoparticles. The effects of three key processing parameters fiber orientation, fiber content, and ZnO concentration on the tensile and flexural properties of the composites were systematically investigated. Response Surface Methodology (RSM) was utilized to establish quadratic predictive models for both mechanical responses, demonstrating strong in-sample agreement with experimental observations (R² > 0.98) and providing valuable insights into the interactions among the governing variables. To further enhance predictive capability, four machine-learning algorithms, namely Decision Tree (DT), Support Vector Machine (SVM), Extreme Gradient Boosting (XGBoost), and Random Forest (RF), were developed and evaluated alongside RSM using a single, leakage-free leave-one-design-point-out nested cross-validation protocol grouped by the 15 replicated Central Composite Design points. Model performance was assessed through the coefficient of determination (R²), mean absolute error (MAE), and root mean square error (RMSE). Under this protocol, RSM and XGBoost gave the most accurate held-out predictions for both responses (pooled R² ≈ 0.90) and were not significantly different from one another (paired tests, p > 0.8), while Decision Tree and Random Forest showed materially lower held-out accuracy (pooled R² ≈ 0.72–0.75) and SVM was the weakest model evaluated (pooled R² ≈ 0.51–0.53). Paired tests and bootstrap confidence intervals over design points showed that Decision Tree, Random Forest and SVM were significantly less accurate than RSM ( p < 0.05). Random splitting that places replicate specimens of one design point in both training and test sets was avoided because it inflates apparent accuracy. The results revealed that fiber orientation is the most influential parameter affecting composite mechanical behavior, followed by fiber loading and ZnO nanoparticle content. The combined use of experimental design, statistical modeling, and leakage-free machine-learning validation provides a transparent framework for comparing prediction models for natural fiber-reinforced polymer nanocomposites, within the scope of the factors, dataset size, and material system examined here. Within the studied factor ranges, RSM and XGBoost are candidate prediction tools. All replicates of each design point came from a single panel, and no independent external validation was performed; the quadratic RSM model shows a significant lack of fit, and the results should not be extrapolated beyond the tested ranges or to other material systems.
- 3 November 2026
- Published by Springer Nature in Journal of Materials Science: Materials in Engineering
Open AccessHybrid machine learning strategies for predicting for jute/ flax/ZnO reinforced composites
This study proposes an integrated experimental and machine-learning framework for the modeling and prediction of the properties of sustainable hybrid polymer nanocomposites reinforced with natural resource jute and flax fibers and Zinc Oxide (ZnO) nanoparticles. The effects of three key processing parameters fiber orientation, fiber content, and ZnO concentration on the tensile and flexural properties of the composites were systematically investigated. Response Surface Methodology (RSM) was utilized to establish quadratic predictive models for both mechanical responses, demonstrating strong in-sample agreement with experimental observations (R² > 0.98) and providing valuable insights into the interactions among the governing variables. To further enhance predictive capability, four machine-learning algorithms, namely Decision Tree (DT), Support Vector Machine (SVM), Extreme Gradient Boosting (XGBoost), and Random Forest (RF), were developed and evaluated alongside RSM using a single, leakage-free leave-one-design-point-out nested cross-validation protocol grouped by the 15 replicated Central Composite Design points. Model performance was assessed through the coefficient of determination (R²), mean absolute error (MAE), and root mean square error (RMSE). Under this protocol, RSM and XGBoost gave the most accurate held-out predictions for both responses (pooled R² ≈ 0.90) and were not significantly different from one another (paired tests, p > 0.8), while Decision Tree and Random Forest showed materially lower held-out accuracy (pooled R² ≈ 0.72–0.75) and SVM was the weakest model evaluated (pooled R² ≈ 0.51–0.53). Paired tests and bootstrap confidence intervals over design points showed that Decision Tree, Random Forest and SVM were significantly less accurate than RSM ( p < 0.05). Random splitting that places replicate specimens of one design point in both training and test sets was avoided because it inflates apparent accuracy. The results revealed that fiber orientation is the most influential parameter affecting composite mechanical behavior, followed by fiber loading and ZnO nanoparticle content. The combined use of experimental design, statistical modeling, and leakage-free machine-learning validation provides a transparent framework for comparing prediction models for natural fiber-reinforced polymer nanocomposites, within the scope of the factors, dataset size, and material system examined here. Within the studied factor ranges, RSM and XGBoost are candidate prediction tools. All replicates of each design point came from a single panel, and no independent external validation was performed; the quadratic RSM model shows a significant lack of fit, and the results should not be extrapolated beyond the tested ranges or to other material systems.
- Open Access
- 9 October 2026
- Published by Springer Nature in Discover Applied Sciences
Early disease detection using multiscale EEG graph fusion and bioinspired deep ensemble learning
Early detection of Alzheimer’s disease (AD) is essential for timely clinical intervention, yet remains challenging due to subtle neural changes in its initial stages. This study proposes a non-invasive EEG-based framework that integrates multiscale signal processing, dynamic brain connectivity analysis, nonlinear feature learning, and ensemble classification for improved diagnosis. Empirical Wavelet Transform (EWT) is employed to decompose nonstationary EEG signals into informative frequency subbands. Dynamic Functional Connectivity Graph Fusion (DFCG) is then used to model time-varying inter-channel synchronization patterns across multiple EEG rhythms. Discriminative representations are extracted using Nonlinear Manifold Statistical Feature Encoding (NMSFE), which preserves the intrinsic geometric structure of connectivity features. Finally, a Bio-Inspired Deep Ensemble Neural Network (BIDENN) performs classification by adaptively combining multiple deep learners to enhance robustness and generalization. Experimental evaluation on publicly available EEG datasets, using cross-validation and external validation protocols, demonstrates consistent performance with an accuracy of 96.2%, precision of 95.8%, recall of 96.5%, and F1-score of 96.1%. The results, supported by confusion matrix and ROC analysis, indicate that the proposed approach provides a reliable and efficient tool for early-stage Alzheimer’s disease detection.
- 9 October 2026
- Published by Springer Nature in Discover Applied Sciences
Open AccessEarly disease detection using multiscale EEG graph fusion and bioinspired deep ensemble learning
Early detection of Alzheimer’s disease (AD) is essential for timely clinical intervention, yet remains challenging due to subtle neural changes in its initial stages. This study proposes a non-invasive EEG-based framework that integrates multiscale signal processing, dynamic brain connectivity analysis, nonlinear feature learning, and ensemble classification for improved diagnosis. Empirical Wavelet Transform (EWT) is employed to decompose nonstationary EEG signals into informative frequency subbands. Dynamic Functional Connectivity Graph Fusion (DFCG) is then used to model time-varying inter-channel synchronization patterns across multiple EEG rhythms. Discriminative representations are extracted using Nonlinear Manifold Statistical Feature Encoding (NMSFE), which preserves the intrinsic geometric structure of connectivity features. Finally, a Bio-Inspired Deep Ensemble Neural Network (BIDENN) performs classification by adaptively combining multiple deep learners to enhance robustness and generalization. Experimental evaluation on publicly available EEG datasets, using cross-validation and external validation protocols, demonstrates consistent performance with an accuracy of 96.2%, precision of 95.8%, recall of 96.5%, and F1-score of 96.1%. The results, supported by confusion matrix and ROC analysis, indicate that the proposed approach provides a reliable and efficient tool for early-stage Alzheimer’s disease detection.
- Open Access
- 25 September 2026
- Published by Springer Nature in Discover Applied Sciences
Comprehensive review of substrate selection process conditions risk and industrial feasibility for sustainable lactic acid production
- 25 September 2026
- Published by Springer Nature in Discover Applied Sciences
Open AccessComprehensive review of substrate selection process conditions risk and industrial feasibility for sustainable lactic acid production
- Open Access
- 19 September 2026
- Published by Springer Nature in Scientific Reports
- Vol. 16 (1)
Comparative study of zero degree and ambient plate temperature of submerged arc welded IS 2062 grade B steel for application in cold region
- 19 September 2026
- Published by Springer Nature in Scientific Reports
- Vol. 16 (1)
Open AccessComparative study of zero degree and ambient plate temperature of submerged arc welded IS 2062 grade B steel for application in cold region
- Open Access
- 16 September 2026
- Published by Springer Nature in Scientific Reports
Modeling of wetting-state evolution in polypropylene-stearic acid functionalized nanostructured superhydrophobic coatings
- 16 September 2026
- Published by Springer Nature in Scientific Reports
Open AccessModeling of wetting-state evolution in polypropylene-stearic acid functionalized nanostructured superhydrophobic coatings
- Open Access
- 31 August 2026
- Published by Springer Nature in Scientific Reports
Predictive modeling of mechanical properties in CO₂ laser welding of hastelloy X using supervised machine learning
- 31 August 2026
- Published by Springer Nature in Scientific Reports
Open AccessPredictive modeling of mechanical properties in CO₂ laser welding of hastelloy X using supervised machine learning
- Open Access
- 1 August 2026
- Published by Springer Nature in Discover Applied Sciences
- Vol. 8 (11)
Application of multiple explainable machine learning models for predicting the mechanical properties of nanoparticle modified basalt and flax fiber composites
- 1 August 2026
- Published by Springer Nature in Discover Applied Sciences
- Vol. 8 (11)
Open AccessApplication of multiple explainable machine learning models for predicting the mechanical properties of nanoparticle modified basalt and flax fiber composites
- Open Access
- 29 July 2026
- Published by Springer Nature in Scientific Reports
- Vol. 16 (1)
Machine learning-based mechanical prediction and characterization of natural fiber hybrid polyester composites for structural and automotive applications
- 29 July 2026
- Published by Springer Nature in Scientific Reports
- Vol. 16 (1)
Open AccessMachine learning-based mechanical prediction and characterization of natural fiber hybrid polyester composites for structural and automotive applications
- Open Access
- 8 July 2026
- Published by Springer Nature in Journal of Materials Science: Materials in Engineering
- Vol. 21 (1)
Sustainable assessment of high-temperature solid particle erosion behaviour of Ti–6Al–5Zr–0.5Mo–0.2Si via experimental and data-driven approaches
High-temperature solid particle erosion (HTSPE) limits the operational life of titanium alloys used in aerospace and power generation systems. This study develops a machine learning–driven predictive framework for the Ti–6Al–5Zr–0.5Mo–0.2Si alloy to estimate and optimize its erosion rate under high-velocity particle impact. Experimental datasets were generated by varying particle velocity, impingement angle, and specimen surface temperature. Three ensemble learning models: Random Forest, Gradient Boosting, and XGBoost were trained to capture nonlinear interactions among these parameters. The Gradient Boosting model achieved the best performance with an R 2 of 0.9425 and an RMSE of 0.00012. Model predictions identified an optimal condition corresponding to a velocity of ~ 33 m/s, surface temperature of ~ 204 °C, and impact angle of 70°, yielding a minimum material removal rate of 0.000530 mg/g. The results demonstrate that data-driven modelling can effectively capture erosion trends within the investigated parameter range and provide useful predictive insights for identifying erosion-resistant operating conditions. This framework bridges data analytics and physical metallurgy, enabling predictive optimisation of titanium alloys subjected to combined thermal and mechanical loading.
- 8 July 2026
- Published by Springer Nature in Journal of Materials Science: Materials in Engineering
- Vol. 21 (1)
Open AccessSustainable assessment of high-temperature solid particle erosion behaviour of Ti–6Al–5Zr–0.5Mo–0.2Si via experimental and data-driven approaches
High-temperature solid particle erosion (HTSPE) limits the operational life of titanium alloys used in aerospace and power generation systems. This study develops a machine learning–driven predictive framework for the Ti–6Al–5Zr–0.5Mo–0.2Si alloy to estimate and optimize its erosion rate under high-velocity particle impact. Experimental datasets were generated by varying particle velocity, impingement angle, and specimen surface temperature. Three ensemble learning models: Random Forest, Gradient Boosting, and XGBoost were trained to capture nonlinear interactions among these parameters. The Gradient Boosting model achieved the best performance with an R 2 of 0.9425 and an RMSE of 0.00012. Model predictions identified an optimal condition corresponding to a velocity of ~ 33 m/s, surface temperature of ~ 204 °C, and impact angle of 70°, yielding a minimum material removal rate of 0.000530 mg/g. The results demonstrate that data-driven modelling can effectively capture erosion trends within the investigated parameter range and provide useful predictive insights for identifying erosion-resistant operating conditions. This framework bridges data analytics and physical metallurgy, enabling predictive optimisation of titanium alloys subjected to combined thermal and mechanical loading.