Multi Layers Research Articles

Thermal features and its effect on the properties of AISI 4140 fabricated by conventional and extreme high-speed laser material deposition

The extreme high-speed laser material deposition (EHLA) process has the potential to enable additive manufacturing for mass production by overcoming the limitations of slow scanning speed in conventional laser material deposition (LMD) processes. Thermal features are the key factors to link process and properties. A sound understanding of process-thermal-property relationships is essential for performance control and process optimization of a deposited component. In this study, we studied the thermal characteristics within a single layer and among layers for continuous processing using the numerical method, and reveal the mechanism of microstructure and hardness changes of AISI 4140 material formed by EHLA and LMD processes through the analysis of thermal properties and temperature history results. The grain size and hardness evolution for both processes during single-layer cladding and continuous forming processes were investigated. The results revealed that the grain refinement effect in continuous LMD processing is stronger than that in EHLA process (from 30.0 μm for single layer to 3.2 μm for multi layers vs. from 18.6 μm for single layer to 2.2 μm for multi layers). Similar hardness values were obtained by LMD and EHLA processes, with mean values of 511 HV and 472 HV, respectively. The yield and tensile strengths of EHLA were superior to the conventional cast material, but inferior to those of the conventional material quenched and tempered at lower temperatures. The enhanced tensile results of EHLA process were found similar to those prepared through conventional method with quench and tempering at 600 °C.

A study on the multi layers of automotive interior trim parts to improve the acoustic performance with microfiber applied to the surface layer

As the world joins environmental regulations, there is an increasing demand for the production of eco-friendly cars. As a result, the driving method of the vehicle was changed from the engine to the electric motor, and the main noise source was changed. In case of existing internal combustion engines (ICE), the low-frequency sound range, which is the engine's main noise, is the main source of sound. As it is converted into an eco-friendly car, the noise that was hidden by the engine combustion sound and the high-frequency noise of the motor are being highlightened. PP meltblown generally has a lower denier than other fibers, so it is effective in improving sound absorption performance because the surfaces of the fibers are large compared to the same weight of another fibers. In conclusion, by applying this PP meltblown fibers to the structure of Dash Insulation, sound absorption performance is improved and resulting in lightweighten effect of Dash Insulation

MGPPI: multiscale graph neural networks for explainable protein-protein interaction prediction.

Protein-Protein Interactions (PPIs) involves in various biological processes, which are of significant importance in cancer diagnosis and drug development. Computational based PPI prediction methods are more preferred due to their low cost and high accuracy. However, existing protein structure based methods are insufficient in the extraction of protein structural information. Furthermore, most methods are less interpretable, which hinder their practical application in the biomedical field. In this paper, we propose MGPPI, which is a Multiscale graph convolutional neural network model for PPI prediction. By incorporating multiscale module into the Graph Neural Network (GNN) and constructing multi convolutional layers, MGPPI can effectively capture both local and global protein structure information. For model interpretability, we introduce a novel visual explanation method named Gradient Weighted interaction Activation Mapping (Grad-WAM), which can highlight key binding residue sites. We evaluate the performance of MGPPI by comparing with state-of-the-arts methods on various datasets. Results shows that MGPPI outperforms other methods significantly and exhibits strong generalization capabilities on the multi-species dataset. As a practical case study, we predicted the binding affinity between the spike (S) protein of SARS-COV-2 and the human ACE2 receptor protein, and successfully identified key binding sites with known binding functions. Key binding sites mutation in PPIs can affect cancer patient survival statues. Therefore, we further verified Grad-WAM highlighted residue sites in separating patients survival groups in several different cancer type datasets. According to our results, some of the highlighted residues can be used as biomarkers in predicting patients survival probability. All these results together demonstrate the high accuracy and practical application value of MGPPI. Our method not only addresses the limitations of existing approaches but also can assists researchers in identifying crucial drug targets and help guide personalized cancer treatment.

Enhancing PV solar panel efficiency through integration with a passive Multi-layered PCMs cooling system: A numerical study

Photovoltaic (PV) solar cells are at the forefront of sustainable electricity generation technologies, yet they exhibit relatively low efficiency. Typically, less than 20 % of the solar energy absorbed is converted into electrical energy, with the remainder converts into heat. This heat increases the PV panel's operating temperature, negatively impacting its efficiency and life expectancy. To mitigate this, a novel approach using multi-layered phase change materials (PCMs) has been examined in this study. The approach involves integrating organic PCMs (OPCMs) with metallic PCMs (MPCMs), enhancing PV panel cooling efficiency by attaching the multi-layer PCM to the panel's rear. This study, employing ANSYS FLUENT software's solidification and melting model, explores the impact of multi PCM layers thickness and total multi layers thickness on PV cell temperature and electrical efficiency. The analysis reveals that a multi-layered PCMs configuration with a thickness ratio of 15:85 between MPCM (CERROLOW-117® alloy) and OPCM (RT44) significantly decreases temperature rise in PV cells, resulting in a temperature drop of 59.6 °C. This improvement boosts PV panel performance by an average of 35.8 % compared to panels lacking cooling systems during peak sun hours under hot climate conditions characterized by ambient temperatures of 40 °C and high solar radiation exceeding 1000 W/m². This suggests that a carefully optimized PCM layering approach could markedly improve PV system efficiency, offering a practical solution to the overheating problem and extending the operational life of PV installations.

Two comparative novel facile synthesis of Prussian blue/polyaniline bilayer films for supercapacitor electrode

A nanocomposite films of Prussian Blue/Polyaniline were prepared on ITO without binder, by two procedures: The first by forming thin multi layers of films of Prussian blue and Polyaniline alternatively, up to seven utilizing “layer by layer” technique. To prepare another film, a thick layer of Prussian Yellow was made under a Polyaniline layer with almost the same load of materials.PB successive layers were fabricated by dipping the ITO in a mixture of (Fe (NO3)3 + K3Fe(CN)6) solution, for a few minutes. next Pani layers were overlayed by electropolymerizing of aniline solution on the ITO/PY electrode. PY instantly was reduced by aniline as soon as dipped in solution, resulting in a nano Prussian Blue film on ITO.Uv-vis and FT-IR spectroscopy were used to characterize the fabricated films. AFM and SEM were utilized to study its morphology. The capacitive behavior of the two types of films was studied utilizing CVs and GCD techniques. The resistance of the electrode/electrolyte interface was studied by EIS. The electrochemical analysis confirmed that the multi-layer by layer thin film has much-improved specific capacitance of 255.6 F/g at 1 A/g current density and superior stability of 96.4 % of its initial value after 500 cycles.

88‐2: The Characteristics Analysis for Laser Cutting Process of Multilayers Display Panels

In this study, we analyzed the laser cutting characteristics of pulse transverse electrical discharge in gas at atmospheric pressure (TEA) CO2 and ultraviolet (UV) pulse laser processing in a multilayer display panels. First, the numerical calculation for was performed to confirm the thermal characteristics of each materials and optical field distribution at the interface of different material layers. Also, processing characteristics were experimentally confirmed by measuring cutting profile and adhesion characteristics of layer interface. Experimental results show that the characteristics of multi layers polymer cutting have different trend from those in a single‐layer because of the optical and thermal properties of each layer. In particular, the interface of layers had a substantial affect due to optical field distributions and thermal characteristic difference. Also, the optical absorbance of layers affect adhesion at the interface. The result suggests proper processing condition to enhance the laser ablation processing quality of multilayer display panel. In conclusion, understanding the characteristics of multilayer laser cutting processing is important for determining the optimal conditions for display panel micromachining and enhancing the quality of laser cutting for the cutting edge technology.

P‐4.30: Integral compressive light field display based on multi layers and micro lens array

P‐4.30: Integral compressive light field display based on multi layers and micro lens array

Mechanical and energy absorption properties of multilayered ultra-light sandwich panels produced by 3D-printing and electroforming

This investigation aims to assess the mechanical and energy absorption properties of the light sandwich panel portions made of open-cell polymer and metal/polymer foam cores. These multi-layered sandwich panels were produced by additive manufacturing of polymeric resin and electrodeposition of three layers of metals, Ni/Ni−Cu/Ni, with 4,5, and 6 pores per inch (PPI). The yield strength, energy absorption density, complementary energy, and specific energy absorption (SEA)were measured during uniaxial compression deformation. The results indicate that compared with pure Ni and Cu sandwich panel portions with the same thickness, the abovementioned properties of the sandwich panels had a noteworthy improvement. Mechanical and energy absorption properties were improved by increasing the PPI and the presence of metallic layers. In a sandwich panel with 6 PPI, the yield strength (energy absorption density)wasimproved from 0.12 MPa (0.12 MJ/m3) for the polymeric sandwich panel to 1.83 MPa (0.67 MJ/m3)for the metallic sandwich panel. Investigations on normalized energies of these structures show a predictable behavior for these sandwich panels during plastic deformations. The results show that the multi metallic layers improved the mechanical behavior of these novel sandwich panels. Noticeable enhancement of the calculated properties of these advanced materials guarantees their unique application in variable industries.

A NEW INTELLIGENT MODEL FOR PHISHING WEB SITES DETECTION

In this paper, we propose a new version of neural network algorithm to enhance the accuracy of detecting website phishing attacks. The proposed algorithm is presented to update weights on multi layers network. The updated algorithm initially started by collecting and storing data in phishing website dataset. We compare the performance of neural network with several machine learning algorithms. The feature selection method applied by the improved neural network algorithms is effective for characteristic capturing with reasonable results. The neural network techniques involve innovative phishing detection model to extract the significant phishing features and patterns. The evaluation of the proposed method accuracy. Accuracy measures the phishing websites correctly detected as trusted websites among all instances. The main conclusion gained from this research is the effectiveness of neural network in detecting website phishing attacks. In addition, the incremental method used for combination of different datasets provided a good insight. We can conclude that the accuracy rate is dependent to the feature counts and dataset size. In addition, the proposed model helps to avoid loss of cumulative knowledge over time and even with the change of characteristics of phishing websites with respect to the designers and developers of these websites.

Expediting High‐Yield Mxene Carbides and Nitrides Synthesis for Next‐Generation 2D Materials

AbstractThis research aims to enhance MXene (Ti3C2Tx) synthesis from MAX phases (Ti3AlC2) through a hydro‐solvothermal exfoliation process, with a focus on reducing time and temperature requirements. Prior hydrothermal studies have encountered challenges due to high reaction temperatures. In comparison to previous research, this work achieves superior results at lower temperatures. Two optimized MXene preparation routes are investigated and the etchant's impact on MXene surface chemistry is analyzed. Comprehensive X‐ray Diffraction (XRD), Scanning Electron Microscopy (SEM), Energy Dispersive X‐ray Spectroscopy (EDS), X‐ray Photoelectron Spectroscopy (XPS), Fourier transform infrared (FTIR), Raman spectroscopy, and Atomic Force Microscopy (AFM) analyses provide insights into hydrosolvothermal synthesis (H‐Ti3C2Tx ) multilayers(ML), confirming/challenging recent spectroscopic assignments. Remarkably, hydro‐solvothermal treatment induces significant changes in surface composition, increasing hydroxyl (─OH) groups without oxidation and reducing fluorine (─F) groups on the H‐ Ti3C2Tx surface. These study's results hold promise for applications in energy storage and electromagnetic wave shielding. This research accomplishes three main objectives: i) secures hydrothermal synthesis of two‐ dimensional (2D) MXenes, ii) efficiently utilizes lithium fluroide‐ hydrochloric acid (LiF−HCl) etching for high‐quality MXene flakes with minimal defects, and iii) understands hydro‐solvothermal kinetics. This approach advances MXene synthesis with enhanced material quality and production efficiency (>98%), in a more eco‐friendly and safer manner. This eco‐conscious synthesis underscores MXene's versatility and eco‐friendly methods' significance, reshaping MXene exploration and sustainable material synthesis, with potential implications for future electrochemical applications.

Multiple SiGe/Si layers epitaxy and SiGe selective etching for vertically stacked DRAM

Fifteen periods of Si/Si0.7Ge0.3 multilayers (MLs) with various SiGe thicknesses are grown on a 200 mm Si substrate using reduced pressure chemical vapor deposition (RPCVD). Several methods were utilized to characterize and analyze the ML structures. The high resolution transmission electron microscopy (HRTEM) results show that the ML structure with 20 nm Si0.7Ge0.3 features the best crystal quality and no defects are observed. Stacked Si0.7Ge0.3 ML structures etched by three different methods were carried out and compared, and the results show that they have different selectivities and morphologies. In this work, the fabrication process influences on Si/SiGe MLs are studied and there are no significant effects on the Si layers, which are the channels in lateral gate all around field effect transistor (L-GAAFET) devices. For vertically-stacked dynamic random access memory (VS-DRAM), it is necessary to consider the dislocation caused by strain accumulation and stress release after the number of stacked layers exceeds the critical thickness. These results pave the way for the manufacture of high-performance multivertical-stacked Si nanowires, nanosheet L-GAAFETs, and DRAM devices.

Modelisation of desorption isotherms and estimation of the thermophysic and thermodynamic properties of tropical woods in Cameroon: The case of Ayous and Ebony woods

A review at various models illustrates the necessary of choosing a model that can best describe each wood in relation to its isotherms of desorption. The theoretical models enable us to deduce several thermo physical parameters. The models of Dent and G.A.B are quite appropriate in the evaluation of the isotherms of desorption of Ayous and Ebony woods taking the humidity of the atmosphere air into consideration. The parameters of Dent’s model vary favourably with regard to the theoretical precisions. The level of humidity at fiber saturation points are at 0.2944 for Ayous wood and 0.19141 for Ebony wood. The specific surface area occupied by the woods under study decreases when there is a consequent increase in temperature. The specific surface area of Ayous wood ranges between 295 and 162 m2/g whereas that of Ebony ranges between 183 and 96 m2/g, while the wood temperatures vary between 20 and 60°C. It is realised that, there is a powerful relationship existing between the primary hydrophiles of Ebony and the first layer of mater molecules. The desorption heat of multi layers of our woods are superior to latent heat condensation of pure water. The heat condensation of water vapour constitutes a specific given which is superior to the heat isosteric adsorption of the woods in question. The soret effect is more important in the drying of Ayous wood than that of Ebony. However, temperature does not influence the soret effect for Ebony wood, relative air humidity is less than 0.85. This limits Ayous wood at 0.9. Above these limits soret effect increases when there is an increase in atmospheric air temperature.

Unveiling the effects of the surface and in-depth nanostructure on the far-UV optical reflectance of thin fluoride multilayer coatings

Developing high-quality optical components for far ultraviolet (FUV) spectrum is gaining significance in space observations. Optical elements designed for a narrowband FUV response rely on coatings made of thin multilayers (MLs), alternating between two materials with low optical absorption and significantly contrasting refractive indices. Recent research shows that (AlF3/LaF3) systems outperform (MgF2/LaF3) coatings in FUV optical reflectance due to two critical factors: 1) AlF3′s lower refractive index compared to MgF2, and 2) structural properties resulting from a trade-off between the number of bilayers, contributing to higher reflectance, and the tendency for roughness to increase with the total coating thickness, limiting FUV optical performance. This study conducts a comprehensive examination of the nano-microstructure of these MLs, using three techniques: AFM for surface characterization, cross-sectional SEM micrographs with backscattered electrons, and Rutherford Backscattering Spectrometry (RBS) for in-depth structural and compositional analysis. A strong correlation is observed between roughness, grain size, composition, and intermixing, impacting the optical response in the FUV range. Nanometer-scale intermixing between layers is estimated using RBS. These findings provide a foundation for modeling FUV optical reflectance in MLs, enabling the optimization of their design through materials engineering to achieve more efficient optical devices for FUV applications in space observations.

Weight embedding autoencoder as feature representation learning in an intrusion detection systems

The increasing need for safe internet access that withstands against various malicious attacks has gained much attention, especially in this abundant information age. Network intrusion detection systems have been proposed to tackle these kinds of attacks. Various machine learning algorithms, including deep learning, have been utilized in network intrusion detection systems. However, the limitations of current feature extraction methods for feature representation learning result in low detection accuracy. Our method utilizes an autoencoder to extract the low-level features in order to provide the necessary information for the classifier. We propose a weight embedding autoencoder to share feature representations between the autoencoder and the classifier. We apply our proposed method to improve two types of networks, a weight embedding autoencoder with a multi layers neural network (WE-AE DNN) and a weight embedding autoencoder with a convolutional neural network (WE-AE CNN) as the classifier. Experiments on two demanding benchmark datasets, such as NSL-KDD and UNSW-NB15 show the effectiveness and superiority of our proposed algorithm in terms of accuracy. The WE-AE DNN and WE-AE CNN improve the accuracy by 0.4% and 0.5% on NSL-KDD, respectively. Meanwhile, on the UNSW-NB15 dataset, the WE-AE DNN and WE-AE CNN improve the accuracy by 2.8% and 0.5%, respectively.

Efficient automated car parking system based modified internet of spatial things in smart cities

The technological advances of smart cities have been progressively increasing to improve the quality of life to humans, especially in urban mobility. Parking appears to be a major issue, with residents needing to find a suitable parking space among many parking areas, resulting in time and fuel waste as well as environmental pollution. We propose in this paper a new automated system model that integrates reinforcement learning (RL), Q-learning, and image processing algorithms based on modified Internet of Spatial Things (IoST) architecture to optimize automated parking in smart cities. For demonstrating the efficiency of the proposed model, iFogSim simulation is used to reduce network usage and latency. Moreover, it deploys heterogeneous devices in multi layers and different scenarios. The experimental results show that the suggested system for automated car parking in fog-based placement-IoST network is feasible and effective. it minimizes latency and the total network usage compared to the cloud-based placement of the implemented system.

Sediment thickness in the eastern part of Kalimantan from high-frequency receiver functions

We analyze high-frequency receiver functions from two seismic stations to characterize the sediment properties around the eastern coast of Kalimantan. First, we compute high-frequency receiver functions from teleseismic events using the time-domain deconvolution method. The obtained receiver functions are then stacked using the H-κ stacking approach to determine the sediment properties. The computed receiver functions show the complicated waveforms for the seismic station located near Kutai Basin. These waveforms may indicate the presence of multi sedimentary layers. The H-κ stacking results suggest that the sediment is thinner in the northern part of the area (∼1.34 km depth) than in the southern part of the region (∼3.0 km depth). These results are consistent with the previous geological and geophysical studies conducted in this region. The previous works suggested that the sediment thickness around the study area can reach up to 9 km.

Assessment and Comparison of Satellite-Based Rainfall Products: Validation by Hydrological Modeling Using ANN in a Semi-Arid Zone

Several satellite precipitation estimates are becoming available globally, offering new possibilities for modeling water resources, especially in regions where data are scarce. This work provides the first validation of four satellite precipitation products, CHIRPS v2, Tamsat, Persiann CDR and TerraClimate data, in a semi-arid region of Essaouira city (Morocco). The precipitation data from different satellites are first compared with the ground observations from 4 rain gauges measurement stations using the different comparison methods, namely: Pearson correlation coefficient (r), Bias, mean square error (RMSE), Nash-Sutcliffe efficiency coefficient and mean absolute error (MAE). Secondly, a rainfall-runoff modeling for a basin of the study area (Ksob Basin S = 1483 km2) was carried out based on artificial neural networks type MLP (Multi Layers Perceptron). This model was -then used to evaluate the best satellite products for estimating the discharge. The results indicate that TerraClimate is the most appropriate product for estimating precipitation (R2 = 0.77 and 0.62 for the training and validation phase, respectively). By using this product in combination with hydrological modeling based on ANN (Artificial Neural Network) approach, the simulations of the monthly flow in the watershed were not very satisfactory. However, a clear improvement of the flow estimations occurred when the ESA-CCI (European Space Agency’s (ESA) Climate Change Initiative (CCI)) soil moisture was added (training phase: R2 = 0.88, validation phase: R2 = 0.69 and Nash ≥ 92%). The results offer interesting prospects for modeling the water resources of the coastal zone watersheds with this data.

Magnetization dynamics in layered systems with coexisting bilinear and biquadratic interlayer exchange coupling

Important aspects of exchange-coupled magnetic layered structures are related to the noncollinear arrangement of sublayer magnetizations which can arise from competition between bilinear (BL) and biquadratic (BQ) interlayer exchange coupling (IEC). In this work, the influence of coexisting BL and BQ IEC of different strengths on magnetization precession in layered systems is investigated both experimentally and theoretically. Laser-induced magnetization precession has been studied in the $\text{Fe/Si}({d}_{\text{Si}}$) multilayers (MLS) as a function of the amplitude ($H$) and orientation angle (${\ensuremath{\theta}}_{H}$) of external magnetic field using time-resolved magneto-optical Kerr (TRMOKE) effect. Strongly changing characters of precession frequency dependencies $\ensuremath{\omega}(H,{\ensuremath{\theta}}_{H})$ for Fe sublayer thickness ${d}_{\text{Fe}}=3$ nm and Si spacer-layer thicknesses (${d}_{\text{Si}}$) varying in the range of 0.9--2.4 nm have been observed. Analytical formulas for acoustic and optic mode dispersion relations with coexisting BL and BQ IEC, scaled by ${J}_{1}$ and ${J}_{2}$ parameters, respectively, for the in-plane effective magnetic anisotropy and arbitrary magnetic field direction were derived, and very good agreement with the experimentally observed frequency dependencies has been obtained. It is shown that BQ coexisting with BL IEC significantly influences on the magnitude and form of dispersion relations. From analytical formula derived, it follows that zero-field optical mode frequency tends to zero as $|{J}_{1}|$ approaches $2{J}_{2}$. The acoustic and optic mode-crossing effect has been observed and it is found that values of crossing fields and frequency gaps strongly increase as ${\ensuremath{\theta}}_{H}$ angles decrease and depend on relative BL and BQ IEC strengths. The BL IEC is of ferromagnetic type with ${J}_{1}\ensuremath{\approx}1.6$ mJ/${\mathrm{m}}^{2}$ for the MLS with ${d}_{\text{Si}}=0.9$ nm, and changes to antiferromagnetic one with ${J}_{1}\ensuremath{\approx}\ensuremath{-}0.9$ mJ/${\mathrm{m}}^{2}$ for the MLS with ${d}_{\text{Si}}=1.4$ nm, while the ${J}_{2}$ parameter of BQ IEC decreases from 1.8 to 1.0 mJ/${\mathrm{m}}^{2}$. The coupling strengths decrease by one to two orders of magnitude for the sample with ${d}_{\text{Si}}=2.4$ nm, but both mode frequencies are still observed and well reproduced by the theory. It is shown that ${J}_{1}$ and ${J}_{2}$ parameters obtained in the TRMOKE experiment coincide within the estimated error bars with the determined from independent measurements of magnetization processes in the static magneto-optical Kerr effect and interpreted with the use of analytical formulas derived. Numerical solutions of coupled Landau-Lifshitz-Gilbert (LLG) equations for acoustic and optic modes, with inclusion of BL IEC, intrinsic Gilbert damping, and spin-pumping damping terms, and extended to include BQ IEC, were performed and fitted to experimental data. It is shown that determined effective damping coefficients on $H$ and ${\ensuremath{\theta}}_{H}$ dependencies for acoustic and optic modes are very well simulated with the use of LLG equation solutions with Gilbert damping, spin-pumping-damping--related effective spin-mixing conductance, and spin-diffusion length parameters included. The dependencies of the parameters on ${d}_{\text{Si}}$ spacer-layer thickness are discussed and compared with available data for other systems.

Comparison of decision tree with common machine learning models for prediction of biguanide and sulfonylurea poisoning in the United States: an analysis of the National Poison Data System

BackgroundBiguanides and sulfonylurea are two classes of anti-diabetic medications that have commonly been prescribed all around the world. Diagnosis of biguanide and sulfonylurea exposures is based on history taking and physical examination; thus, physicians might misdiagnose these two different clinical settings. We aimed to conduct a study to develop a model based on decision tree analysis to help physicians better diagnose these poisoning cases.MethodsThe National Poison Data System was used for this six-year retrospective cohort study.The decision tree model, common machine learning models multi layers perceptron, stochastic gradient descent (SGD), Adaboosting classiefier, linear support vector machine and ensembling methods including bagging, voting and stacking methods were used. The confusion matrix, precision, recall, specificity, f1-score, and accuracy were reported to evaluate the model’s performance.ResultsOf 6183 participants, 3336 patients (54.0%) were identified as biguanides exposures, and the remaining were those with sulfonylureas exposures. The decision tree model showed that the most important clinical findings defining biguanide and sulfonylurea exposures were hypoglycemia, abdominal pain, acidosis, diaphoresis, tremor, vomiting, diarrhea, age, and reasons for exposure. The specificity, precision, recall, f1-score, and accuracy of all models were greater than 86%, 89%, 88%, and 88%, respectively. The lowest values belong to SGD model. The decision tree model has a sensitivity (recall) of 93.3%, specificity of 92.8%, precision of 93.4%, f1_score of 93.3%, and accuracy of 93.3%.ConclusionOur results indicated that machine learning methods including decision tree and ensembling methods provide a precise prediction model to diagnose biguanides and sulfonylureas exposure.

Graphene oxide based regenerated carbon waste tyre (rCB): Synthesis by modified Hummers method and characterization

Graphene oxide (GO) has attracted attention in the study of the creation novel material and mainly synthesized from exfoliation of graphite. However, the expensive market price of graphite lead to the high-cost production of GO beside the resource exhaustion due to rising demands from research and industry worsen the situation. Consequently, a cheaper and recycle alternative to graphite as possible raw material for producing GO is from carbon of waste tyre through modified Hummers method. The obtained GO was confirmed by using Raman spectroscopy, XRD, FTIR and FESEM. The Raman spectroscopy obtained for ID of ∼1375cm-1and IG of ∼1602cm-1with ID/IG ratio of 0.82 with 2D multi layers. The XRD spectroscopy showed the diffraction peak at (2θ = 25.39°) with interlayer spacing of 3.51 Å and FTIR spectra revealed the functional groups of hydroxyl (OH), carboxyl (COOH), alcohol (COH), and epoxy (CO) at 3392 cm-1, 1706 cm-1, 1615 cm-1, and 1108 cm-1 respectively that resembles the FTIR result of GO from graphite by previous study. FESEM pictures revealed that the surface morphology of the carbon black structure changed, resulting in an increase in the presence of pores on the GO structure. The establishment of GO from carbon waste tyre was successfully supported by all the above characterizations thus indicate that it can be suitable alternative of graphite for the synthesis of GO.