N. Saranya
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
N. Saranya has a total of 17 co-authors. Here are the top co-authors by number of shared publications:
- Archudha Arjunasamy
Department of Artificial Intelligence and Machine Learning, Dayananda Sagar College of Engineering, Shavigemalleshwara hills, Kumarasamy Layout, Bengaluru, Karnataka, India
1 shared publication - Biswadip Basu Mallik
Institute of Engineering and Management (School of University of Engineering and Management)
1 shared publication - F. Jessy Nirmala
Department of Information Technology, Nandha College of Technology, Perundurai, TN, India
1 shared publication - Ganesh Babu Loganathan
Rajalakshmi Engineering College
1 shared publication J. Kamalakumari
Department of BCA, SRMIST, Chennai, Tamil Nadu, India
1 shared publication- Pavithra. G.
Dept. of Electronics & Communication Engg., Dayananda Sagar College of Engg., Bengaluru, Karnataka, India
1 shared publication
Latest Publications
- Open Access
- 30 September 2026
- Published by Journal of Environmental Nanotechnology in Journal of Environmental Nanotechnology
- Vol. 15 (3) , 275-291
Green Synthesis of MgO Nanoparticles Using Mimusops elengi Leaf Extract: Multi-response Optimization, Machine Learning Prediction and Physicochemical Characterization
The green production of metal oxide nanoparticles has emerged as an environmentally sustainable alternative to conventional chemical synthesis because of its simplicity, reduced chemical consumption, and lower environmental impact. Data-driven optimization techniques and machine learning algorithms have become effective tools for minimizing experimental effort while improving process efficiency. In the present study, MgO nanoparticles were synthesized using Mimusops elengi leaf extract, and the synthesis process was optimized by considering magnesium nitrate hexahydrate concentration, plant extract concentration, reaction temperature, and reaction time as the input variables, whereas MgO nanoparticle yield and UV–Vis absorbance were selected as the response variables. A Taguchi L27 design and ANOVA were employed to evaluate the effects of the synthesis variables, while multi-criteria decision-making and machine-learning approaches were used for optimization and predictive modelling. The tuned SVR model showed strong predictive performance, with cross-validated R² values of 0.9841 for MgO nanoparticle yield and 0.9955 for UV–Vis absorbance. The optimized synthesis conditions were identified as 0.14698 M magnesium nitrate hexahydrate, 4.5638% (w/v) Mimusops elengi leaf extract, a reaction temperature of 87.735 °C, and a reaction time of 85.905 min. Under these conditions, the predicted MgO nanoparticle yield and UV–Vis absorbance were 86.10% and 0.8332 a.u., respectively. Characterization by UV–Vis spectroscopy, XRD, and SEM confirmed the formation and crystalline nature of the synthesized MgO nanoparticles. The integrated optimization framework demonstrated that combining statistical design, multi-criteria decision-making, and machine learning provides an efficient strategy for enhancing the green synthesis of MgO nanoparticles while reducing experimental effort.
- 30 September 2026
- Published by Journal of Environmental Nanotechnology in Journal of Environmental Nanotechnology
- Vol. 15 (3) , 275-291
Open AccessGreen Synthesis of MgO Nanoparticles Using Mimusops elengi Leaf Extract: Multi-response Optimization, Machine Learning Prediction and Physicochemical Characterization
The green production of metal oxide nanoparticles has emerged as an environmentally sustainable alternative to conventional chemical synthesis because of its simplicity, reduced chemical consumption, and lower environmental impact. Data-driven optimization techniques and machine learning algorithms have become effective tools for minimizing experimental effort while improving process efficiency. In the present study, MgO nanoparticles were synthesized using Mimusops elengi leaf extract, and the synthesis process was optimized by considering magnesium nitrate hexahydrate concentration, plant extract concentration, reaction temperature, and reaction time as the input variables, whereas MgO nanoparticle yield and UV–Vis absorbance were selected as the response variables. A Taguchi L27 design and ANOVA were employed to evaluate the effects of the synthesis variables, while multi-criteria decision-making and machine-learning approaches were used for optimization and predictive modelling. The tuned SVR model showed strong predictive performance, with cross-validated R² values of 0.9841 for MgO nanoparticle yield and 0.9955 for UV–Vis absorbance. The optimized synthesis conditions were identified as 0.14698 M magnesium nitrate hexahydrate, 4.5638% (w/v) Mimusops elengi leaf extract, a reaction temperature of 87.735 °C, and a reaction time of 85.905 min. Under these conditions, the predicted MgO nanoparticle yield and UV–Vis absorbance were 86.10% and 0.8332 a.u., respectively. Characterization by UV–Vis spectroscopy, XRD, and SEM confirmed the formation and crystalline nature of the synthesized MgO nanoparticles. The integrated optimization framework demonstrated that combining statistical design, multi-criteria decision-making, and machine learning provides an efficient strategy for enhancing the green synthesis of MgO nanoparticles while reducing experimental effort.
- 1 January 2024
- Published by AIP Publishing in AIP Conference Proceedings
- Vol. 3203 (1) , 140038
AI-ML-Powered IoT approach for designing a smart wheelchair for individuals with disabilities
Intelligent Wheelchairs represent mechanical devices designed to empower individuals with the ability to move independently. This results in a reduction of the Intelligent Wheelchairs represent mechanical devices designed to empower individuals with the ability to move independently. This results in a reduction of the
- 1 January 2024
- Published by AIP Publishing in AIP Conference Proceedings
- Vol. 3203 (1) , 140038
AI-ML-Powered IoT approach for designing a smart wheelchair for individuals with disabilities
Intelligent Wheelchairs represent mechanical devices designed to empower individuals with the ability to move independently. This results in a reduction of the Intelligent Wheelchairs represent mechanical devices designed to empower individuals with the ability to move independently. This results in a reduction of the