scholarly journals Application of feed-forward and recurrent neural network in modelling the adsorption of boron by amidoxime-modified poly(Acrylonitrile-co-Acrylic Acid)

2019 ◽  
Vol 25 (6) ◽  
pp. 830-840 ◽  
Author(s):  
Lau Kia Li ◽  
Siti Nurul Ain Md Jamil ◽  
Luqman Chuah Abdullah ◽  
Nik Nor Liyana Nik Ibrahim ◽  
Adeyi Abel Adekanm ◽  
...  
Keyword(s):  
Neural Network ◽  
Acrylic Acid ◽  
Adsorption Capacity ◽  
Prediction Models ◽  
Least Square ◽  
Maximum Adsorption Capacity ◽  
Good Prediction ◽  
Feed Forward ◽  
Poly Acrylonitrile ◽  
Boron Adsorption

This research reports application of artificial neural network (ANN) in investigation and optimisation of boron adsorption capacity in aqueous solution using amidoxime-modified poly(acrylonitrile-<i>co</i>-acrylic acid) (AO-modified poly(AN-<i>co</i>-AA)). Both feed-forward and recurrent ANN have been utilized to predict the adsorption potential of synthesised polymer. Three operational parameters, which are adsorbent dosage, initial pH and initial boron concentration during adsorption process were designed to study their effects on the removal capacity. The ANN was trained from experimental data and serviced to optimize, develop and create various prediction models in the process of boron adsorption by AO-modified poly(AN-<i>co</i>-AA). Among several models, radial basis function (RBF) with orthogonal least square (OLS) algorithm displayed good prediction on boron adsorption capacity with mean square error (MSE) and coefficient of determination (R<sup>2</sup>) at 0.000209 and 0.9985, respectively. With desirable the MSE and R<sup>2</sup> values, ANN worked as a promising prediction tool that was able to generate good estimate. The simulated maximum adsorption capacity of the synthesized polymer is 15.23 ± 1.05 mg boron/g adsorbent. Besides, from the results of ANN, the AO-modified poly(AN-<i>co</i>-AA) was proven to be a potential adsorbent for the removal of boron in wastewater treatment.

Removal of crystal violet from water by poly acrylonitrile-co-sodium methallyl sulfonate (AN69) and poly acrylic acid (PAA) synthetic membranes

2021 ◽  
Vol 0 (0) ◽  
Author(s):  
Ely Cheikh S’Id ◽  
Mohamed Degué ◽  
Chlouma Khalifa ◽  
Chamekh M’Bareck
Keyword(s):  
Acrylic Acid ◽  
Adsorption Capacity ◽  
Crystal Violet ◽  
Electrostatic Interactions ◽  
Adsorption Process ◽  
Maximum Adsorption Capacity ◽  
Dye Molecules ◽  
Membrane Composition ◽  
Poly Acrylonitrile ◽  
Poly Acrylic Acid

Abstract The current investigation is focused on the removal of crystal violet (CV) from water by adsorption process (bach method). To achieve this purpose, specific membranes were prepared from poly acrylonitrile-co-sodium methallyl sulfonate (AN69) and poly acrylic acid (PAA) blends. The adsorption of CV onto AN69/PAA membranes was studied under various conditions: membrane composition, pH, contact time, initial concentration and temperature. To understand the effect of membrane morphology on adsorption process, scanning electronic microscopy (SEM) was employed to determine the features of section and membrane’s surface. From isotherm results, it was found that: the maximum adsorption capacity Q m was 1250 mg g−1, the Langmuir separation factor R L was lying between 0.33 and 0.76, the Freundlich intensity was higher than Unit (n = 1.25) and the adsorption process follows preferentially the Langmuir model (correlation constant R 2 = 0.99). The mechanism of adsorption is perfectly fitted by pseudo second order. The obtained results tend to confirm that the removal of dye molecules is due to the establishment of strong electrostatic interactions between cationic dye molecules and anionic membrane groups. The high adsorption capacity (1250 mg g−1) for the small dye molecules may open wide opportunities to apply these membranes in the removal of various hazardous pollutants commonly present in water.

scholarly journals EFFECT OF IONIC STRENGTH FROM DIFFERENT SALT RESOURCES ON BORON ADSORPTION IN CALCAREOUS SOIL

2019 ◽  
Vol 50 (6) ◽  
Author(s):  
K. M. Nasser
Keyword(s):  
Ionic Strength ◽  
Adsorption Capacity ◽  
Calcareous Soil ◽  
Bonding Energy ◽  
Maximum Adsorption Capacity ◽  
Silty Clay ◽  
Three Solutions ◽  
College Of Agriculture ◽  
Adsorbed Quantity ◽  
Boron Adsorption

This study was conducted in the laboratories of Soil and water resources Department, College of Agricultural Sciences Engineering, University of Baghdad for the purpose of disclosing the effect of ionic strength from different salt mixtures on the adsorption of Boron in a silty clay loam calcareous soil taken from the prior location of the college of Agriculture in Abu Ghraib, after a quite equilibrium of Boron solution prepared from Boric acid at( 0, 1, 5, 7.5, 10 and 20) μmole B.ml-1 at 298 Kalvin. Three solutions with different ionic strength were used( 0.1, 0.2, 0.3) mole.L-1 of four different salts CaCl2, MgCl2, NaCl and composed salt of the three salts at 3:1:1 ratios respectively. Langmuir single surface line equation was used for better description of the reactions of Boron adsorption in soil.Results showed a significant increase in Boron adsorbed quantity in soil with the increase of the applied Boron. The increase in ionic strength led to a significant increase in adsorbed Boron for all salts with different rates. These different salts showed significant differences in adsorbed quantity of Boron, where CaCl2 treatment was exceeded followed by MgCl2, mixture salt, then NaCl treatments as an averages of the three ionic strengths where it reached (68.95, 65.26, 58.38 and 44.37) μmole B.gm-1 soil respectively and at maximum adsorption capacity (Xm) at (58.26, 55.92, 47.90, 46.17) mg B. Kg-1 soil, while bonding energy to soil particles (K) was  (0.279, 0.244, 0.244 and 0.125) ml μ B for the mentioned salts respectively. In general, soil is considered to have a high maximum adsorption capacity (42.88 mg B.Kg-1 soil) and low bonding energy (0.216 ml μ-1 B) .

scholarly journals Adsorptive Removal of Methylene Blue from Aquatic Environments Using Thiourea-Modified Poly(Acrylonitrile-co-Acrylic Acid)

Materials ◽  
2019 ◽  
Vol 12 (11) ◽  
pp. 1734 ◽  
Author(s):  
Abel Adekanmi Adeyi ◽  
Siti Nurul Ain Md Jamil ◽  
Luqman Chuah Abdullah ◽  
Thomas Shean Yaw Choong ◽  
Kia Li Lau ◽  
...  
Keyword(s):  
Methylene Blue ◽  
Acrylic Acid ◽  
Morphological Properties ◽  
Aquatic Environments ◽  
Maximum Adsorption Capacity ◽  
Freundlich Model ◽  
Physico Chemical ◽  
Pseudo Second Order ◽  
Ft Ir ◽  
Poly Acrylonitrile

The paper evaluates the adsorptive potential of thiourea-modified poly(acrylonitrile-co-acrylic acid), (TA-poly(AN-co-AA)) for the uptake of cationic methylene blue (MB) from aquatic environments via a batch system. TA-poly(AN-co-AA) polymer was synthesized through redox polymerization and modified with thiourea (TA) where thioamide groups were introduced to the surface. Fourier transform infrared (FT-IR) spectroscopy, scanning electron microscopy (SEM), CHNS and Zetasizer were used to characterize the physico-chemical and morphological properties of prepared TA-poly(AN-co-AA). Afterwards, it was confirmed that incorporation of thioamide groups was successful. The adsorption kinetics and equilibrium adsorption data were best described, respectively, by a pseudo-second-order model and Freundlich model. Thermodynamic analysis showed the exothermic and spontaneous nature of MB uptake by TA-poly(AN-co-AA). The developed TA-poly(AN-co-AA) polymer demonstrated efficient separation of MB dye from the aqueous solution and maintained maximum adsorption capacity after five regeneration cycles. The findings of this study suggested that synthesized TA-poly(AN-co-AA) can be applied successfully to remove cationic dyes from aquatic environments.

scholarly journals Hydrothermal Synthesis of Cellulose Nanocrystal-Grafted-Acrylic Acid Aerogels with Superabsorbent Properties

Polymers ◽  
2018 ◽  
Vol 10 (10) ◽  
pp. 1168 ◽  
Author(s):  
Xuehua Liu ◽  
Rue Yang ◽  
Mincong Xu ◽  
Chunhui Ma ◽  
Wei Li ◽  
...  
Keyword(s):  
Acrylic Acid ◽  
Adsorption Capacity ◽  
Environmental Remediation ◽  
Freeze Drying ◽  
Treatment Time ◽  
Hydrothermal Process ◽  
Cellulose Nanocrystal ◽  
Maximum Adsorption Capacity ◽  
Simple Method ◽  
Hydrothermal Treatment Time

In this work, we applied a fast and simple method to synthesize cellulose nanocrystal (CNC) aerogels, via a hydrothermal strategy followed by freeze drying. The characteristics and morphology of the obtained CNC-g-AA aerogels were affected by the hydrothermal treatment time, volume of added AA (acrylic acid), and the mass fraction of the CNCs. The formation mechanism of the aerogels involved free radical graft copolymerization of AA and CNCs with the cross-linker N,N′-methylene bis(acrylamide) (MBA) during the hydrothermal process. The swelling ratio of the CNC-g-AA aerogels was as high as 495:1, which is considerably greater than that of other polysaccharide-g-AA aerogels systems. Moreover, the CNC-g-AA aerogels exhibited an excellent methyl blue (MB) adsorption capacity and the ability to undergo rapid desorption/regeneration. The maximum adsorption capacity of the CNC-g-AA aerogels for MB was greater than 400 mg/g. Excellent regeneration performance further indicates the promise of our CNC-g-AA aerogels as an adsorbent for applications in environmental remediation.

scholarly journals Preparation of Poly (Acrylic Acid-Acrylamide/Starch) Composite and Its Adsorption Properties for Mercury (II)

Materials ◽  
2021 ◽  
Vol 14 (12) ◽  
pp. 3277
Author(s):  
Wenjuan Zhu ◽  
Zhiyong Yang ◽  
Akram Yasin ◽  
Yanxia Liu ◽  
Letao Zhang
Keyword(s):  
Particle Size ◽  
Acrylic Acid ◽  
Adsorption Capacity ◽  
Graft Copolymer ◽  
Ph Value ◽  
Adsorption Properties ◽  
Size Exclusion ◽  
Narrow Particle Size Distribution ◽  
Maximum Adsorption Capacity ◽  
Poly Acrylic Acid

The poly (acrylic acid-acrylamide/starch) composite was synthesized by solution polymerization, aiming to adsorb mercury (II) in water. The resulted copolymer was characterized by particle size exclusion chromatography (SEC), Fourier transform infrared spectroscopy (FTIR), thermogravimetry (TG), scanning electron microscopy (SEM) and dynamic light scattering particle size analyzer (DLS). It turned out that starch was successfully incorporated with the macromolecular polymer matrix and played a key role for improving the performance of the composites. These characterization results showed that the graft copolymer exhibited narrow molecular weight distribution, rough but uniform morphology, good thermal stability and narrow particle size distribution. The graft copolymer was used to remove Hg(II) ions from aqueous solution. The effects of contact time, pH value, initial mercury (II) concentration and temperature on the adsorption capacity of Hg(II) ions were researched. It was found that after 120 min of interaction, poly (acrylic acid-acrylamide/starch) composite achieved the maximum adsorption capacity of 19.23 mg·g−1 to Hg(II) ions with initial concentration of 15 mg·L−1, pH of 5.5 at 45 °C. Compared with other studies with the same purpose, the composites synthesized in this study present high adsorption properties for Hg(II) ion in dilute solution. The adsorption kinetics of Hg(II) on the poly (acrylic acid-acrylamide/starch) composite fits well with the pseudo second order model.

scholarly journals A Survey and Analysis of Extreme Machine Learning Models and Its Techniques

2021 ◽  
Author(s):  
Shubhangi Pande ◽  
Neeraj Kumar Rathore ◽  
Anuradha Purohit
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Support Vector Machine ◽  
Learning Algorithm ◽  
Feature Learning ◽  
Global Optimum ◽  
Least Square ◽  
Support Vector ◽  
Feed Forward Neural Network ◽  
Feed Forward

Abstract Machine learning applications employ FFNN (Feed Forward Neural Network) in their discipline enormously. But, it has been observed that the FFNN requisite speed is not up the mark. The fundamental causes of this problem are: 1) for training neural networks, slow gradient descent methods are broadly used and 2) for such methods, there is a need for iteratively tuning hidden layer parameters including biases and weights. To resolve these problems, a new emanant machine learning algorithm, which is a substitution of the feed-forward neural network, entitled as Extreme Learning Machine (ELM) introduced in this paper. ELM also come up with a general learning scheme for the immense diversity of different networks (SLFNs and multilayer networks). According to ELM originators, the learning capacity of networks trained using backpropagation is a thousand times slower than the networks trained using ELM, along with this, ELM models exhibit good generalization performance. ELM is more efficient in contradiction of Least Square Support Vector Machine (LS-SVM), Support Vector Machine (SVM), and rest of the precocious approaches. ELM’s eccentric outline has three main targets: 1) high learning accuracy 2) less human intervention 3) fast learning speed. ELM consider as a greater capacity to achieve global optimum. The distribution of application of ELM incorporates: feature learning, clustering, regression, compression, and classification. With this paper, our goal is to familiarize various ELM variants, their applications, ELM strengths, ELM researches and comparison with other learning algorithms, and many more concepts related to ELM.

scholarly journals An Analysis of Extreme Machine Learning Models

2021 ◽  
Author(s):  
Shubhangi Pande ◽  
Neeraj Rathore ◽  
Anuradha Purohit
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Support Vector Machine ◽  
Learning Algorithm ◽  
Feature Learning ◽  
Global Optimum ◽  
Least Square ◽  
Support Vector ◽  
Feed Forward Neural Network ◽  
Feed Forward

Abstract Machine learning applications employ FFNN (Feed Forward Neural Network) in their discipline enormously. But, it has been observed that the FFNN requisite speed is not up the mark. The fundamental causes of this problem are: 1) for training neural networks, slow gradient descent methods are broadly used and 2) for such methods, there is a need for iteratively tuning hidden layer parameters including biases and weights. To resolve these problems, a new emanant machine learning algorithm, which is a substitution of the feed-forward neural network, entitled as Extreme Learning Machine (ELM) introduced in this paper. ELM also come up with a general learning scheme for the immense diversity of different networks (SLFNs and multilayer networks). According to ELM originators, the learning capacity of networks trained using backpropagation is a thousand times slower than the networks trained using ELM, along with this, ELM models exhibit good generalization performance. ELM is more efficient in contradiction of Least Square Support Vector Machine (LS-SVM), Support Vector Machine (SVM), and rest of the precocious approaches. ELM’s eccentric outline has three main targets: 1) high learning accuracy 2) less human intervention 3) fast learning speed. ELM consider as a greater capacity to achieve global optimum. The distribution of application of ELM incorporates: feature learning, clustering, regression, compression, and classification. With this paper, our goal is to familiarize various ELM variants, their applications, ELM strengths, ELM researches and comparison with other learning algorithms, and many more concepts related to ELM.

scholarly journals Synthesis, characterization and adsorption studies of an acrylic acid-grafted sodium alginate-based TiO2 hydrogel nanocomposite

2017 ◽  
Vol 36 (1-2) ◽  
pp. 458-477 ◽  
Author(s):  
Sourbh Thakur ◽  
Omotayo Arotiba
Keyword(s):  
Acrylic Acid ◽  
Adsorption Capacity ◽  
Sodium Alginate ◽  
Methyl Violet ◽  
Maximum Adsorption Capacity ◽  
Nanocomposite Hydrogel ◽  
X Ray Diffraction ◽  
X Ray ◽  
Pseudo Second Order ◽  
Hydrogel Nanocomposite

Hydrogel nanocomposites were synthesized by solution polymerization of acrylic acid in the presence of sodium alginate biopolymer and TiO2 nanoparticle. TiO2 nanoparticle and N, N-methylene-bis-acrylamide was used as an inorganic and organic crosslinker, respectively. The structure and morphology of the nanocomposites were investigated using X-Ray Diffraction (XRD), Fourier Transform Infra-Red Spectroscopy (FTIR), Scanning Electron Microscopy (SEM), Brunauer-Emmett-Teller (BET) and thermogravimetric analysis techniques. The nanocomposites hydrogel was used for the adsorption of methyl violet dye from water. The influence of TiO2 nanoparticle, sodium alginate content and grafting on adsorption were studied. The results showed that a pseudo-second-order adsorption kinetic was predominant in the adsorption of methyl violet onto the nanocomposite hydrogel. The experimental equilibrated adsorption capacity of the nanocomposite hydrogel agrees with Langmuir isotherm. Maximum adsorption capacity of 1156.61 mg g−1 and adsorption efficiency of 99.6% towards methyl violet were obtained for the hydrogel nanocomposite.

scholarly journals PREDIKSI HARGA EMAS MENGGUNAKAN FEED FORWARD NEURAL NETWORK DENGAN METODE EXTREME LEARNING MACHINE

2019 ◽  
Vol 8 (2) ◽  
pp. 171-183
Author(s):  
Nisa Afida Izati ◽  
Budi Warsito ◽  
Tatik Widiharih
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Artificial Neural Networks ◽  
Extreme Learning Machine ◽  
Gold Price ◽  
Good Prediction ◽  
Feed Forward Neural Network ◽  
Feed Forward ◽  
Artificial Neural ◽  
Learning Machine

The prediction of gold price aims to find out the gold price in the future on the basis of historical data on gold prices in the past, so it can be used as a consideration by gold investors to investing in gold. Prediction methods that do not require assumptions, one of which is Artificial Neural Networks. In this study, using Artificial Neural Networks, Feed Forward Neural Network with Extreme Learning Machine (ELM). ELM is a non-iterative algorithm so ELM has advantages in process speed. The input weight and bias for this method are determined randomly. After that, to find the final weight using the Moore-Penrose Generalized Inverse calculation on the hidden layer output matrix. The best model selection criteria uses the Mean Absolute Percentage Error (MAPE). This study shows that the results of the training and testing process from the model 1 input neuron and 7 hidden neurons are very good, because it produces MAPE training = 0.6752% and MAPE testing = 0.8065%. Also gives a very good prediction result because it has MAPE = 0.5499% Keywords: gold price, Extreme Learning Machine, MAPE

Sign in / Sign up

Export Citation Format

Share Document