Growth of MWCNTs from Azadirachta indica oil for optimization of chromium(VI) removal efficiency using machine learning approach

Uthayakumar, Haripriyan; Radhakrishnan, P.G.; Kalaiselvan, S.; Kushwaha, Omkar S.

doi:10.1007/s11356-021-17873-w

Cited by 18 publications

(6 citation statements)

References 78 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The output layer is where the prediction results are obtained. In order to imitate the learning mechanisms of biological systems, certain training algorithms such Levenberg‐Marquardt Algorithm (trainlm), Bayaerisian Regularisation (trainbr) and scalient conjugate gradient (trainscg) were employed in accordance with the learning rules that are used in artificial neural networks (ANNs) (Uthayakumar et al., 2022). The ANN networking predominantly works on the basis of the three important transfer functions, that is, exponential sigmoid, tangent sigmoid, and linear functions.…”

Section: Methodsmentioning

confidence: 99%

“…and scalient conjugate gradient (trainscg) were employed in accordance with the learning rules that are used in artificial neural networks (ANNs) (Uthayakumar et al, 2022). The ANN networking predominantly works on the basis of the three important transfer functions, that is, exponential sigmoid, tangent sigmoid, and linear functions.…”

Section: Artificial Neural Networkmentioning

confidence: 99%

See 1 more Smart Citation

Modeling and optimization of the yield of pyrolytic oil from waste face masks using RSM‐ANN‐LM hybrid approach

Abu Huraira,

Saravanathamizhan,

Israel

et al. 2023

Environmental Quality Mgmt

View full text Add to dashboard Cite

Pyrolysis is one of the most widely practiced thermochemical conversion technique to convert biomass into bio fuel. In this investigation, waste surgical masks were taken for pyrolysis process and the pyrolysis oil yield was determined experimentally. The experiments were designed and optimized based on Box Behnken Design (BBD) with operating parameters (feed size, temperature, and time) to study the effect on the yield of the pyrolysis oil and char. Experiments were conducted by varying the feed size (10–50 mm), pyrolysis temperature (400–600°C), and time (30–90 min). A hybrid Response Surface Methodology –Artificial Neural Network‐ Levenberg–Marquardt algorithm (RSM‐ANN‐LM) modelling approach has been to optimize the process parameters for the prediction of pyrolysis oil yield. The optimized network architecture was found to be 3‐10‐1 and the authenticity of the developed model has been evaluated using Regression Co‐efficient (R2) and Mean Squared Error (MSE). The developed RSM‐ANN‐LM model has outperformed the RSM model on predicting the pyrolytic oil yield. For the optimized conditions of 10 mm size, 600°C of pyrolysis temperature and 90 min pyrolysis time, 85.30% oil yield was obtained.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Artificial Neural Networkmentioning

confidence: 99%

Modeling and optimization of the yield of pyrolytic oil from waste face masks using RSM‐ANN‐LM hybrid approach

Abu Huraira,

Saravanathamizhan,

Israel

et al. 2023

Environmental Quality Mgmt

View full text Add to dashboard Cite

show abstract

“…A recent study [45] monitors gas emissions from urban traffic, applying artificial intelligence and the IoT, aiming to reduce greenhouse gas emissions in urban environments. Buragohain and Mahanta [25] evaluated artificial intelligence methods (adaptive neurofuzzy inference systems and artificial neural networks, ANNs) for modeling and predicting energy production and greenhouse gas emissions from farms in Iran, and the results showed that both models have benefits, but due to the use of fuzzy rules, adaptive neurofuzzy inference systems could model energy production and greenhouse gas emissions more accurately than the ANN model.…”

Section: Literature Reviewmentioning

confidence: 99%

“…However, in recent years, various artificial intelligence (AI) methods have been used to establish the relationship between energy input, energy production, and greenhouse gas (GHG) emissions for various products [24]. To this end, various known artificial intelligence methods for modeling and forecasting energy production and GHG emissions include fuzzy inference systems, adaptive neuro-fuzzy systems, genetic algorithms (GAs), and artificial neural networks (ANNs) [25,26]. Fuzzy logic is used to handle the fundamental concept of partial truth, where truth values can vary between completely true and completely false [27].…”

Section: Introductionmentioning

confidence: 99%

Greening Automation: Policy Recommendations for Sustainable Development in AI-Driven Industries

Doran,

Badareu,

Doran

et al. 2024

Sustainability

View full text Add to dashboard Cite

This study delves into the dynamic relationship between artificial intelligence (AI) and environmental performance, with a specific focus on greenhouse gas (GHG) emissions across European countries from 2012 to 2022. Utilizing data on industrial robots, AI companies, and AI investments, we examine how AI adoption influences GHG emissions. Preliminary analyses, including ordinary least squares (OLS) regression and diagnostic assessments, were conducted to ensure data adequacy and model readiness. Subsequently, the Elastic Net (ENET) regression model was employed to mitigate overfitting issues and enhance model robustness. Our findings reveal intriguing trends, such as a downward trajectory in GHG emissions correlating with increased AI investment levels and industrial robot deployment. Graphical representations further elucidate the evolution of coefficients and cross-validation errors, providing valuable insights into the relationship between AI and environmental sustainability. These findings offer policymakers actionable insights for leveraging AI technologies to foster sustainable development strategies.

show abstract

“…The kinetic different models, such as pseudo-first-order, pseudo-second-order, and Weber-Morris models (Figures A1-A3), were fitted to the experimental data to investigate the sorption mechanism of Pb (II) and Cr (VI) onto PANI/MIL-100(Fe). Table 1 summarizes the mathematical expression of the kinetic parameters used in this study [40,41].…”

Section: Study Of Kinetic Modelsmentioning

confidence: 99%

Adsorptive Removal Behavior of Pb (II) and Cr (VI) Pollutants from an Aqueous Environment onto Polyaniline-Modified MIL100(Fe)

et al. 2023

View full text Add to dashboard Cite

The present work introduces a new sorbent, so-called PANI/MIL100(Fe), for removing Pb (II) and Cr (VI) from wastewater. The successful preparation of PANI/MIL100(Fe) was verified via Fourier-transform infrared spectroscopy (FT-IR), X-ray powder diffraction (XRD), scanning electron microscopy (SEM), and Brunauer–Emmett–Teller (BET) characterizations. This adsorptive material showed a microporous structure with surface area magnitudes of up to 261.29 m2/g, a total pore volume of 0.2124 cm3/g, and a pore size distribution of around 1.2 nm. The maximum adsorption capacities of PANI/MIL100(Fe) for Cr (VI) (pH = 2) and Pb (II) (pH = 6) were obtained as 72.37 and 81.76 mg/g, respectively. The isotherm modeling assessments illustrated that the sorption of Pb (II) and Cr (VI) was consistent with the Sips model (R2 > 0.99), while the adsorption kinetics were suited to a pseudo-second-order model (R2 > 0.95). Thermodynamic studies of both metal ions demonstrated the spontaneous and endothermic nature of the process. The reusability of the PANI/MIL100(Fe) indicated promising adsorption properties for Pb (II) and Cr (VI) up to three cycles. Moreover, the XRD and FT-IR spectroscopy results after adsorption/desorption showed excellent stability of the adsorbent and physisorption mechanism, wherein electrons were exchanged between the PANI/MIL-100(Fe) and Pb (II) and Cr (VI). Finally, the findings suggested that PANI/MIL100(Fe) can be considered an efficient and environmentally friendly adsorbent to remove Pb (II) and Cr (VI) from wastewater.

show abstract

Growth of MWCNTs from Azadirachta indica oil for optimization of chromium(VI) removal efficiency using machine learning approach

Cited by 18 publications

References 78 publications

Modeling and optimization of the yield of pyrolytic oil from waste face masks using RSM‐ANN‐LM hybrid approach

Modeling and optimization of the yield of pyrolytic oil from waste face masks using RSM‐ANN‐LM hybrid approach

Greening Automation: Policy Recommendations for Sustainable Development in AI-Driven Industries

Adsorptive Removal Behavior of Pb (II) and Cr (VI) Pollutants from an Aqueous Environment onto Polyaniline-Modified MIL100(Fe)

Contact Info

Product

Resources

About