Search

This scientific paper explores the use of correlation coefficients of vibration signals and machine learning algorithms for structural damage assessment in beams under moving loads. The paper discusses the challenges of maintaining structural integrity and the importance of automated, nondestructive monitoring techniques. Preprocessing techniques, such as the random decrement technique (RDT), are highlighted for improving data analysis. Machine learning algorithms are identified as valuable tools for structural damage assessment. The paper concludes by emphasizing the potential of machine learning in safeguarding critical infrastructures. The text also discusses trigger points and the vibration response of a slender beam under a moving load. An artificial neural network (ANN) is proposed as a computational model for identifying non-linear features. Experimental testing on a simulated bridge girder using accelerometers collected data to identify and locate damage in the beam. The ANN achieved high accuracy in detecting damage appearance and location, but further research is needed to improve accuracy in real-world situations. [Extracted from the article]

Recent artificial neural networks that process natural language achieve unprecedented performance in tasks requiring sentence-level understanding. As such, they could be interesting models of the integration of linguistic information in the human brain. We review works that compare these artificial language models with human brain activity and we assess the extent to which this approach has improved our understanding of the neural processes involved in natural language comprehension. Two main results emerge. First, the neural representation of word meaning aligns with the context-dependent, dense word vectors used by the artificial neural networks. Second, the processing hierarchy that emerges within artificial neural networks broadly matches the brain, but is surprisingly inconsistent across studies. We discuss current challenges in establishing artificial neural networks as process models of natural language comprehension. We suggest exploiting the highly structured representational geometry of artificial neural networks when mapping representations to brain data. [ABSTRACT FROM AUTHOR]

The article focuses on predicting rolling force (RF) in the hot rolling process by incorporating nano-lubrication conditions through strategies available in finite element method (FEM) software. Additional work includes RF prediction by artificial neural network (ANN) modelling. The experimental RF were collected from an experimental rolling mill (ERM) for hot rolling IS 2062 E250 steel. The simulations were performed using SIMUFACT and the results were validated by experimental data. The prediction was made accurately by adjusting the lubrication panel available in the software. Then, FEM and ANN were performed to predict RF at various combinations of process parameters. FEA simulated hot rolling of IS 2062 E250 with varying process parameters. It incorporates changing 5 process parameters for FEA as roll speed, reduction%, nano-lubrication condition, billet size (thickness), and rolling temperature. Then, the accumulation of data for further application in ANN modelling. The validation of FEM software was successful with an error of less than 5%. According to the validation, the lubrication corresponding to the nano-lubrication setup was fixed in the software. The mesh was optimised and detected the least RF deviation at 1.8 mm mesh. The ANN was performed from the simulation data. The ANN performed better for a single hidden layer model for 8 neurons. The training, validating, and testing of the model resulted in an R-square value of 0.991, 0.987, and 0.994, respectively. The root mean square error (RMSE) value obtained was 0.985. Therefore, the ANN model developed was performing better. The article uses the combined strategy of FEM and ANN, with available lubrication panels in FEM software for accurate RF predictions. [ABSTRACT FROM AUTHOR]

Submerged arc welding (SAW), renowned for its high deposition rate and superior weld quality, is the go-to method for joining thick metals in heavy structures. However, industry beams and columns welded with SAW can exhibit detrimental defects like undercut, porosity, and burn-through, significantly impacting weld properties. This study addresses this challenge by presenting a multi-objective optimization approach for SAW parameters on AISI 1020 mild steel. Aiming to optimize tensile strength, hardness, and bead width, the study employs Taguchi's design of experiments and couples the multi-objective Jaya algorithm with an artificial neural network (ANN). This synergistic combination yielded optimal process parameters: 417 A welding current, 20.7 mm electrode stick-out, 33.7 V voltage, and 505.8 mm/min transverse speed. These settings translated into exceptional weld characteristics, with ultimate tensile strength reaching 427 MPa, hardness of 73.9 HRB, and bead width of 14.29 mm. Confirmation tests further validated these findings, demonstrating minimal error and solidifying the effectiveness of the optimization approach. This research paves the way for enhanced weld quality and process control in heavy structural applications. [ABSTRACT FROM AUTHOR]

This study investigated the mechanical properties of a low-plasticity clay soil reinforced with polypropylene (PP) fiber in various contents (0.05%, 0.10%, 0.15%, and 0.20%) and lengths (6, 12, and 19 mm). The reinforced specimens were subjected to unconsolidated-undrained (UU) triaxial compression tests under three different confining pressures (50, 100, and 200 kPa). The optimum fiber contents in specimens reinforced with 6-, 12-, and 19-mm PP fiber were determined as 0.15%, 0.15%, and 0.20%, respectively. As a result, the highest values regarding deviator stress at failure (σdev), energy absorption capacity (EAC), and shear strength parameters occurred in specimens containing 0.20% PP (19 mm). As a result of the reinforcement process, the most remarkable improvements in the σdev, cohesion, internal friction angle, and EAC values of the natural soil are 59.95%, 21.80%, 63%, and 34.70%, respectively. Linear and nonlinear relationships between σdev and fiber length, fiber content, and confining pressure were investigated by multiple linear regression and artificial neural network methods. Equations were generated to predict σdev of a low-plasticity clay soil reinforced with PP fiber and were made available to geotechnical researchers. [ABSTRACT FROM AUTHOR]

The significance of soil in agriculture and human survival cannot be overstated. Given its limited supply, improving soil properties is imperative. This study addresses this challenge by predicting five major soil properties—organic carbon, pH values, Mehlich-3 extractable calcium, Mehlich-3 extractable phosphorus, and sand content—utilizing mid-infrared absorbance measurements from the African Soil Information Service (AfSIS) dataset, covering non-desert regions of Africa. With a pressing need for a reliable and efficient model to predict African soil properties using spectral measurements, this study fills a crucial gap, addressing the scarcity of functional soil property databases in Africa. The developed model eliminates costly soil sample preparation and lengthy chemical analysis, applicable in both onsite and laboratory settings for determining soil functional properties. By employing stacked autoencoders for feature dimensionality reduction and combining discrete wavelet transform with two feature selection methods (stepwise regression and random forest) to build robust multi-layer perceptron (MLP) models, the study offers a comprehensive approach. Evaluation metrics including root mean square error (RMSE), scatter index (SI), Variance Accounted For (VAF), Nash-Sutcliffe Model Efficiency (NSE), and Correlation Coefficient (R) demonstrate the superior performance of the MLP model informed by stacked autoencoder-selected features, outperforming models informed by wavelet-transformed features and partial least square regression. This best-performing autoencoder-based model presents a valuable tool for soil scientists tasked with modeling African soil properties. [ABSTRACT FROM AUTHOR]

Increasing consumers demand for natural and additive -free foods and high volumes of food industry wastes, are stimulating the use of these resources in other food industries. Tomato pomace is one of the food factory wastes is the resulting by -product of tomato paste and sauce factories. The aim of this study was to evaluate the effect extraction method and microwave pretreatment of tomato seeds on the physicochemical characteristics of their extracted oil. The seeds were treated with microwaves using various power levels (0, 200 and 500 W) and different process times (0, 1, 3 and 5 min) and their oil was extracted by Soxhlet and press methods. Fatty acids composition of oils was determined by gas chromatography. Some physicochemical characteristics of extracted seed oil including oil yield, viscosity, acid value, peroxide value, and color index (L, b, a values) were evaluated. Data was analyzed with factorial treatment structure in a Completely Randomized Design in three replications. The experimental data was modeled by artificial neural network with 3 inputs (extraction method, microwave power and pretreatment time) and 7 outputs (oil yield, acid value, peroxide value, viscosity, L value, b value and a value). The results of artificial neural network modeling showed that the network with a 3 - 8 -7 structure and using the Hyperbolic tangent activation function can predict the oil yield, acid value, peroxide value, viscosity, L value, b value and a value of tomato seed oil with high correlation coefficient and low error. Based on the results of the sensitivity analysis, the extraction method compared to the power and time of microwave assisted pretreatment of seeds was determined as the main factor. [ABSTRACT FROM AUTHOR]

The main reaction parameters examined were the amount of blast furnace slag, the hydration duration, ammonium acetate concentration, and temperature. The Response surface methodology was employed to quantify their impact on the sorbent's surface area. Using a central composite design, the surface area of the resulting sorbent corresponding to Brunauer-Emmett-Teller (BET) was investigated. The sorbents produced range in surface area from 49.89 to 155.33 m2/g. Additionally, the effectiveness and response prediction capacities of the Response Surface Methodology (RSM) and Artificial Neural Network (ANN) modeling methodologies were investigated. The models were assessed using various statistical metrics, including (MSE) mean squared error, (ARE) average relative errors, the (SSE) sum of squared errors, (HYBRID) Hybrid fractional error function, (SAE) Sum of the absolute errors, (R2)coefficient of determination, and Root means square. According to statistical evidence, the ANN approach surpassed the RSM-CCD model approach. The surface area of the sorbent was shown to be significantly influenced by interactions between variables in addition to all the individual variables examined. The sorbent was made from a material with substantial structural porosity based on SEM. The functional groups were identified using FTIR. The XRF determined the elemental composition of BFS-based sorbents. [ABSTRACT FROM AUTHOR]

Estimation of the reservoir parameters such as porosity, lithology and saturation from well logs and seismic data would require the shear wave velocity data. The high cost of shear wave well logging and subsequently the lack of the shear velocity log in most wells are the main reasons to estimate the shear velocity log. The routine methods for estimating the shear velocity are empirical relations, regression analysis, intelligent methods and rock physics models. Most of these methods do not include the impact of geometry of pore spaces and minerals (aspect ratio). Excluding geometry of pore spaces and minerals from the estimation procedure would create considerable estimation error in the oil and gas reservoirs, particularly in the carbonates. In the first step, shear velocity log is estimated using empirical relations, regression analysis and neural network methods. The estimated shear velocity log using neural network is better than empirical and regression methods. Subsequently, a new simple equation utilizing rock physics models is developed to estimate the shear velocity log. The Xu–White (Geophys Prospect 43: 91–118, 1995) and as reported by Gassmann (Elasticity of porous media, Vierteljahrsschrde Naturforchenden, Gesellschaft, 1951) relations were employed to include the impact of lithology, fluid, minerals and pore spaces. The estimated shear velocity log using new equation compares well with the original as reported by Gassmann (Elasticity of porous media, Vierteljahrsschrde Naturforchenden, Gesellschaft, 1951) and Xu–White (Geophys Prospect 43: 91–118, 1995) rock physics methods. The average difference between the measured and estimated velocity logs using new method is 12.6 m/s (or 0.41%). This equation includes the impact of major parameters in the rock physics model in the simple form; thus, it would be applicable in the carbonate and clastic reservoirs. [ABSTRACT FROM AUTHOR]

A new method for the generation of axial power distributions using artificial neural network (ANN) technique and real-time measured planar radial peaking factor, Fxy (hereinafter 'Live Fxy') method for digital core protection system of pressurized water reactors is presented. ANN with Simulated Annealing (SA) technique to find global optimum solution was used to calculate core average axial power distribution. In Live Fxy method, axial node-wise Fxys were calculated by multiplying pin/box factors to the measured assembly powers inferred from in-core detector signals without calculating detailed 3D power distributions. The hot pin power distribution for DNBR and LPD was then obtained by multiplying the core average axial power distribution and Fxys at axial nodes. The validation of the method was performed for various core conditions (e.g. core power levels, control rod positions, etc.) of Korean OPR1000 power plant. The result showed a decrease in RMS errors by 2.2% ~ 7.0% (3.6% on average), and the minimum thermal margins for DNBR and LPD were increased by 6.4% and 15.6%, respectively. The application of the method would improve the accuracy of axial power distribution and thermal margin, contributing to the operability and safety of digital core protection system. [ABSTRACT FROM AUTHOR]

Excessive sodium consumption is a worldwide problem, prompting the industry to develop sodium-reduced products and substitute salts. High sodium consumption is a significant risk factor for high blood pressure, cardiovascular disease and kidney disease. Excessive sodium intake also impairs the immune system in the gastrointestinal tract. Potassium chloride (KCl) is the most commonly used mineral salt due to its similarity to sodium chloride (NaCl), and its consumption has been shown to lower blood pressure when consumed in adequate amounts. The aim of this study was to partially replace NaCl with KCl at levels of 25%, 50% and 75% in the brine used to make white brined cheese. Parameters such as acidity, total dissolved solids, salinity, conductivity, colour, texture and sensory properties were evaluated during a 28-day refrigerated storage period. KCl can replace NaCl by 50%, and no significant differences in physicochemical and sensory parameters were observed during cheese storage compared to the control sample. In addition, the study investigates the use of Artificial Neural Network (ANN) models to predict certain brine and cheese properties. The study successfully developed four different ANN models to accurately predict various properties such as brine pH, cheese colour and hardness over a 28-day storage period. [ABSTRACT FROM AUTHOR]

The main objective of this study is to assess and contrast the efficacy of distinct spatial prediction methods in a simulation aimed at optimizing the embodied energy during the construction of prestressed slab bridge decks. A literature review and cross-sectional analysis have identified crucial design parameters that directly affect the design and construction of bridge decks. This analysis determines the critical design variables to improve the deck's energy efficiency, providing practical guidance for engineers and professionals in the field. The methods analyzed in this study are ordinary Kriging and a multilayer perceptron neural network. The methodology involves analyzing the predictive performance of both models through error analysis and assessing their ability to identify local optima on the response surface. The results show that both models generally overestimate the observed values. The Kriging model with second-order polynomials yields a 4% relative error at the local optimum, while the neural network achieves lower root mean square errors (RMSEs). Neither the Kriging model nor the neural network provides precise predictions but point to promising solution regions. Optimizing the response surface to find a local minimum is crucial. High slenderness ratios (around 1/28) and 40 MPa concrete grade are recommended to improve energy efficiency. [ABSTRACT FROM AUTHOR]

The development of alternative environmentally friendly modes of transportation is becoming an increasingly promising solution in traffic-congested and polluted urban areas. E-bikes, as one of them, are recognized as an ecologically sustainable means of transportation that has significant potential to replace motorized modes of transportation that can improve urban mobility. Relying on artificial intelligence and considering an ecological approach when considering the acceptability of e-bikes by setting a direct question for users influences the development of an innovative way of understanding and evaluating the use of more sustainable modes of transportation. In this regard, this study aims to elucidate the main variables influencing the acceptability of e-bike use using artificial neural network (ANN) models—multilayer perceptron (MLP) and radial basis function (RBF). For training and testing the models, data from a random sample obtained through an online questionnaire, which was answered by 626 residents of Belgrade (Serbia), were used. A multilayer perceptron with nine and seven neurons in two hidden layers, respectively, hyperbolic tangent activation function in the hidden layer and identity function in the output layer, gave better results than the radial basis function model. With an accuracy of 89%, a precision of 83%, a recall of 79%, and an area under the receiver operating characteristic (ROC) curve of 0.927, the multilayer perceptron model recognized the influential variables in predicting acceptability. The results of the model indicate that the mileage traveled, the frequency of motorcycle use, the respondents' awareness of the pollution in Belgrade, and the age of the respondents have the greatest influence on the acceptability of using e-bikes. In addition to majority acceptability (69.8%), the results obtained by the model can represent a useful basis for decision-makers when defining strategies for the development and application of e-bikes while reducing traffic congestion and environmental pollution in Belgrade. [ABSTRACT FROM AUTHOR]

Aroma essential oils contain ingredients that are beneficial to the human body. A gas sensor array is required to monitor the concentration of these essential oil components to regulate their concentration by air conditioning systems. Therefore, we investigated the discrimination ability and concentration measurement accuracy of 14 effective components, including four aroma essential oils (lavender, melissa, tea tree, and eucalyptus), from a single gas sample and mixtures of two gases using sensor arrays. To obtain our data, we used two sensor arrays comprising commercially available semiconductor sensors and our developed semiconductor sensors. For machine learning, principal component analysis was used to visualize the dataset obtained from the sensor signals, and an artificial neural network was used for a detailed analysis. Our developed sensor array, which included sensors that possessed excellent sensor responses to 14 effective components and combined different semiconductive sensor principles, showed a better discrimination and prediction accuracy than the commercially available sensors investigated in this study. [ABSTRACT FROM AUTHOR]

The scope of the present study is the estimation of key operational parameters of a drinking water treatment plant (DWTP), particularly the dosages of treatment chemicals, using artificial neural networks (ANNs) based on measurable in situ data. The case study consists of the Aposelemis DWTP, where the plant operator had an estimation of the ANN output parameters for the required dosages of water treatment chemicals based on observed water quality and other operational parameters at the time. The estimated DWTP main operational parameters included residual ozone (O3) and dosages of the chemicals used: anionic polyelectrolyte (ANPE), poly-aluminum chloride hydroxide sulfate (PACl), and chlorine gas (Cl2(g)). Daily measurable results of water sample analysis and recordings from the DWTP Supervisory Control and Data Acquisition System (SCADA), covering a period of 38 months, were used as input parameters for the artificial neural network (1188 values for each of the 14 measurable parameters). These input parameters included: raw water supply (Q), raw water turbidity (T1), treated water turbidity (T2), treated water residual free chlorine (Cl2), treated water concentration of residual aluminum (Al), filtration bed inlet water turbidity (T3), daily difference in water height in reservoir (∆H), raw water pH (pH1), treated water pH (pH2), and daily consumption of DWTP electricity (El). Output/target parameters were: residual O3 after ozonation (O3), anionic polyelectrolyte (ANPE), poly-aluminum chloride hydroxide sulfate (PACl), and chlorine gas supply (Cl2(g)). A total of 304 different ANN models were tested, based on the best test performance (tperf) indicator. The one with the optimum performance indicator was selected. The scenario finally chosen was the one with 100 neural networks, 100 nodes, 42 hidden nodes, 10 inputs, and 4 outputs. This ANN model achieved excellent simulation results based on the best testing performance indicator, which suggests that ANNs are potentially useful tools for the prediction of a DWTP's main operational parameters. Further research could explore the prediction of water chemicals used in a DWTP by using ANNs with a smaller number of operational parameters to ensure greater flexibility, without prohibitively reducing the reliability of the prediction model. This could prove useful in cases with a much higher sample size, given the data-demanding nature of ANNs. [ABSTRACT FROM AUTHOR]

Integrating small and large-scale photovoltaic (PV) solar systems into electrical distribution systems has become mandatory due to increased electricity bills and the concern for limiting greenhouse gases. However, the reliable and efficient operation of PV-based distribution systems can be confronted by the intermittence and high variability of solar sources and their consequential faults. In this regard, this article suggests a moderated fault-clearing strategy based on the incremental conductance–maximum power point tracking (IC–MPPT) technique and artificial neural networks (ANNs) to enhance fault detection, localization, and restoration processes in PV-based distribution systems. The proposed strategy leverages IC–MPPT to ensure optimal power generation from the PV solar system, even in the presence of faults. By tracking the maximum power point, the algorithm maintains the performance of the system and mitigates against the impact of faults on the output power. Furthermore, an ANN is employed to improve fault detection and localization accuracy. The developed ANN-based moderated fault-clearing strategy is trained using historical data and fault scenarios, enabling it to recognize fault patterns and make informed decisions through extensive simulations and comparisons with traditional fault-clearing methods. To accomplish this study, benchmarks in PV-based distribution systems are constructed and employed using the MATLAB®/Simulink® software package. Moreover, to validate the efficacy of the developed ANN-based moderated fault-clearing strategy, a real case study of a 1-MW PV-based distribution system in an industrial field located in Giza governorate, Egypt, is tested and investigated. The obtained results demonstrate the effectiveness of the IC–MPPT and ANN-based moderated fault-clearing strategy in achieving faster fault detection, precise fault localization, and efficient restoration in PV solar-based distribution systems while preserving maximum power extraction under small and large system disturbances. Furthermore, IC–MPPT based on an ANN achieves an average power of 98.556 kW and 299.632 kWh energy availability, whereas the IC–MPPT based on a proportional–integral controller achieves 95.7996 kW and 283.4036 kWh, and the classic perturb-and-observe MPPT algorithm achieves 92.2657 kW and 276.8014 kWh. [ABSTRACT FROM AUTHOR]

Myelin damage and a wide range of symptoms are caused by the immune system targeting the central nervous system in Multiple Sclerosis (MS), a chronic autoimmune neurological condition. It disrupts signals between the brain and body, causing symptoms including tiredness, muscle weakness, and difficulty with memory and balance. Traditional methods for detecting MS are less precise and time-consuming, which is a major gap in addressing this problem. This gap has motivated the investigation of new methods to improve MS detection consistency and accuracy. This paper proposed a novel approach named FAD consisting of Deep Neural Network (DNN) fused with an Artificial Neural Network (ANN) to detect MS with more efficiency and accuracy, utilizing regularization and combat over-fitting. We use gene expression data for MS research in the GEO GSE17048 dataset. The dataset is preprocessed by performing encoding, standardization using min-max-scaler, and feature selection using Recursive Feature Elimination with Cross-Validation (RFECV) to optimize and refine the dataset. Meanwhile, for experimenting with the dataset, another deep-learning hybrid model is integrated with different ML models, including Random Forest (RF), Gradient Boosting (GB), XGBoost (XGB), K-Nearest Neighbors (KNN) and Decision Tree (DT). Results reveal that FAD performed exceptionally well on the dataset, which was evident with an accuracy of 96.55% and an F1-score of 96.71%. The use of the proposed FAD approach helps in achieving remarkable results with better accuracy than previous studies. [ABSTRACT FROM AUTHOR]

Efficient and accurate acquisition of slope shear strength parameters is the key to slope stability analysis and landslide prevention engineering design. This paper establishes a back analysis method based on uniform design, artificial neural network, and genetic algorithm. It can obtain the shear strength parameters of slopes based on information such as the radius and center coordinates of the slip surface obtained from on‐site investigations. This method has been applied to engineering practice. The research results indicate that the stability of the waste dump slope is most sensitive to the response of the internal friction angle of the loose body, followed by cohesion, and least sensitive to the response of the soil volume weight. This method can effectively reduce the number of network training samples and efficiently and quickly determine the initial weights of the BP (abbreviation for back‐propagation) neural network. This method can efficiently and quickly conduct back analysis to obtain the shear strength parameters of slopes. Using the obtained shear strength parameters for slope stability calculation, the most dangerous slip surface abscissa error, ordinate error, and slip surface radius error are only 3.59%, 0.95%, and 1.83%. It is recommended to promote the back analysis method of shear strength parameters in engineering practice in the future. [ABSTRACT FROM AUTHOR]

In this study, we present a novel voice recognition service developed on the Raspberry Pi 4 model B platform, leveraging the fast Fourier transform (FFT) for efficient speech-to-digital signal conversion. By integrating the hidden Markov model (HMM) and artificial neural network (ANN), our system accurately reconstructs speech input. We further fortify this service with dual-layer encryption using the Rivest-Shamir-Adleman (RSA) and advanced encryption standard (AES) methods, achieving encryption and decryption times well suited for real-time applications. Our results demonstrate the system's robustness and efficiency: speech processing within 1.2 to 1.9 seconds, RSA 2048-bit encryption in 2 to 6 milliseconds, RSA decryption in 6 to 10 milliseconds, and AES-GCM 256-bit encryption and decryption in approximately 2.6 to 3 seconds. [ABSTRACT FROM AUTHOR]

This study examines the generation of irreversibility and the behavior of stagnation point hybrid nanofluid flow on a Riga plate. The effects of nonlinear thermally convective and solar radiation are incorporated in the modeled equations. The nanoparticles of (Cu) and (Al2O3) are mixed with Glycol (C3H8O2) to hybridized it. The leading equations have been changed to dimension-free form by using the set of appropriate variables and then have been evaluated by Artificial Neural Network (ANN) approach. It is revealed in this work that, the velocity panels are amplified with expansion in Grashof number and electromagnetic factor while declined with escalation in magnet/electrode factor and nanoparticles concentration. Upsurge, in Eckert number for both the scenarios (Ec < 0) and (Ec > 0), the radiation factor and nanoparticles concentration cause augmentation in thermal characteristics. Radiation factor has positive impacts on Bejan number and generation of Entropy. Moreover, Bejan number is retarded while entropy is augmented with growth in Brinkman number. It is also established in this work that the principle of entropy generation for hybrid nanoparticles supports the efficient delivery of drug in cancer treatment. [ABSTRACT FROM AUTHOR]

This paper introduces a novel hybrid approach for predicting the rainfall-runoff (r-r) phenomenon across different data division scenarios (50%-50%, 60%-40%, and 75%-25%) within two distinct watersheds, encompassing both monthly and daily scales. Additionally, the effectiveness of this newly proposed hybrid method is evaluated in multi-step ahead prediction (MSAP) scenarios. The proposed method comprises three primary steps. Initially, to address the non-stationarity of the runoff and rainfall time series, these series are decomposed into multiple sub-time series using the wavelet (WT) decomposition method. Subsequently, in the second step, the decomposed sub-series are utilized as input data for the M5 model tree, a decision tree-based model. The M5 model tree classifies the samples of decomposed runoff and rainfall time series into distinct classes. Finally, each class is modeled using an artificial neural network (ANN). The results demonstrate the superior efficiency of the proposed WT-M5-ANN method compared to other available hybrid methods. Specifically, the calculated R2 was 0.93 for the proposed WT-M5-ANN method, whereas it was 0.89 and 0.81 for the WT-ANN (WANN) and WT-M5 methods, respectively, for the Lobbs Hole Creek watershed at the daily scale. [ABSTRACT FROM AUTHOR]

In recent times, the efficacy of machine learning (ML) algorithms as tools for forecasting structural damage has become increasingly evident. However, input data in structural health monitoring predominantly comprises normal operational states or states with minor deviations from the initial condition, lacking potentially hazardous states. Consequently, creating a realistic dataset for machine learning models to identify structural damage poses a challenge. If such data were obtainable, it might involve parameters like stress intensity factor range and stress ratio, which are often difficult to measure within real structures. In this paper, ML models, including Artificial Neural Network (ANN), Extreme Gradient Boosting (XGB), and Random Forest (RF), were constructed to predict the locations, widths, and depths of saw-cuts in steel beams. The prognostications were based on fluctuations in natural frequencies. The natural frequencies under various damage scenarios were identified using the Finite Element Method (FEM). The natural frequencies in the absence of saw-cuts, obtained from the two methods, Finite Element Method (FEM) and Frequency Domain Decomposition (FDD), were compared to validate their agreement. Conclusions regarding the selection of appropriate machine learning models, as well as the combination of FEM, FDD, and machine learning methods, will be drawn upon completion. [ABSTRACT FROM AUTHOR]

Glass-ceramic is difficult to be ultra precision machined due to its high hardness and brittleness. Laser-assisted fast tool servo machining (LAFTSM) of glass-ceramic optical free-form surface was carried out with tool wear as the characteristic value to study the machining quality of glass-ceramic. Orthogonal experiments on LAFTSM were conducted using the Taguchi method (TM). The range of tool wear reduction obtained by comparing laser-assisted machining (LAM) with fast tool servo (FTS) machining is 48.83%–64.12%. The order of contribution of each machining parameter obtained through variance analysis to the reduction of tool wear is: spindle speed > laser power > feed rate > piezoelectric frequency. The optimal combination of machining parameters that can minimize tool wear obtained through signal-to-noise ratio (S/N) analysis is: spindle speed 55 rpm, feed rate 0.01 mm/rev, piezoelectric frequency 8 Hz, laser power 75 W. Artificial neural network (ANN) and genetic algorithm (GA) were used to fit and optimize the machining parameters and experimental results in TM orthogonal experiments. The fitting values of ANN are highly consistent with the orthogonal experimental results. The optimal combination of machining parameters obtained after GA optimization analysis is: spindle speed 50 rpm, feed rate 0.015 mm/rev, piezoelectric frequency 4 Hz, laser power 75 W. Experiments were conducted using the optimal combination of machining parameters of TM and ANN, the results showed that ANN performs better than TM in predicting minimum tool wear and optimizing machining parameters. This study provides a reference for LAFTSM and the research methods of tool wear. [ABSTRACT FROM AUTHOR]

Alkali-activated materials/geopolymer (AAMs), due to their low carbon emission content, have been the focus of recent studies on ecological concrete. In terms of performance, fly ash and slag are preferred materials for precursors for developing a one-part geopolymer. However, determining the optimum content of the input parameters to obtain adequate performance is quite challenging and scarcely reported. Therefore, in this study, machine learning methods such as artificial neural networks (ANN) and gene expression programming (GEP) models were developed using MATLAB and GeneXprotools, respectively, for the prediction of compressive strength under variable input materials and content for fly ash and slag-based one-part geopolymer. The database for this study contains 171 points extracted from literature with input parameters: fly ash concentration, slag content, calcium hydroxide content, sodium oxide dose, water binder ratio, and curing temperature. The performance of the two models was evaluated under various statistical indices, namely correlation coefficient (R), mean absolute error (MAE), and root mean square error (RMSE). In terms of the strength prediction efficacy of a one-part geopolymer, ANN outperformed GEP. Sensitivity and parametric analysis were also performed to identify the significant contributor to strength. According to a sensitivity analysis, the activator and slag contents had the most effects on the compressive strength at 28 days. The water binder ratio was shown to be directly connected to activator percentage, slag percentage, and calcium hydroxide percentage and inversely related to compressive strength at 28 days and curing temperature. [ABSTRACT FROM AUTHOR]

The challenge of predicting time series with limited data has evolved over time due to nonlinearity, complexity, and limited information. It can be perceived as a mapping of dynamical systems in one-dimensional space. This article proposes a neural grey system to tackle this challenge. The system enhances its ability to fit nonlinearity by employing polynomials, captures complexity through a fractional-order cumulant operator, and resolves information-poor uncertainty by utilizing grey system modeling techniques. The model effectively integrates research findings from neural computing, uncertainty theory, and complexity theory at a theoretical level. It accurately describes dynamic processes of complex systems. Additionally, we have reduced the complexity of calculations in the algorithm design. We selected a dataset of total retail sales of consumer goods to test the model's validity and applicability. Our experiments demonstrate that the newly proposed grey forecasting model can effectively forecast time series with small samples, offering good forecasting outcomes and generalization ability. [ABSTRACT FROM AUTHOR]

Hydrothermal carbonization (HTC) emerges as a promising avenue for converting food waste into valuable resources while addressing environmental concerns. This study investigated the optimization of HTC parameters, utilizing landfill leachate as a sustainable moisture source and exploring methane recovery from process water. Employing the response surface methodology (RSM) and artificial neural networks (ANN), the influence of key process variables on HTC efficiency was meticulously analyzed. Notably, the superior predictive capability of ANN over RSM was demonstrated, with a lower mean-squared error and a higher correlation coefficient. The identified optimal HTC conditions were 193°C for 175 min at a solid/liquid ratio of 0.2; under these conditions, RSM and ANN predicted mass yields of 66.37 ± 1.15% and 65.68 ± 0.11%, respectively. Furthermore, under these conditions, process water exhibited a remarkable biomethane production rate of approximately 283.11 ± 13.5 mL/g COD, fitting well with the modified Gompertz model. This study advances HTC optimization strategies and underscores the potential of integrating landfill leachate and methane recovery into food waste valorization processes, thereby paving the way for sustainable resource management practices. [ABSTRACT FROM AUTHOR]

A novel process and its optimization using bioinspired artificial intelligence techniques is described for the generation of energy precursors in the form of volatile fatty acids (VFAs) from date palm waste (DPW). The work was undertaken in view of the fact that about 4 million metric tons of DPW is produced every year, and the bulk of it is left untreated and unutilized. This makes DPW as one of the biggest solid waste streams of which the quantities are slated to rise with the projected increase in date palm cultivation. Dried and powdered DPW was pre-treated with aqueous NaOH solution and VFAs were extracted from it in an acid-phase bioreactor. The highest VFA yield (57 g/kg) was obtained from the reactor run on DPW of particle size ≥ 0.3– < 0.4 mm, and soaked for 12 h in once-used NaOH solution. The process was modeled using artificial neural networks (ANNs) to predict the VFA yield. Genetic algorithms were then deployed in conjunction with the ANN model to arrive at the optimal value of the input variables that will give the maximum VFA yield. It led to the prediction that the maximum VFA yield attainable would be 65.7 g/kg if the optimum process parameters of particle size 0.44 mm, 13 h of soaking in once-used NaOH solution, and at 4.3 days of reactor operation were invoked. The prediction was then tested experimentally. The VFA yield actually obtained agreed with the predicted yield within a margin of 9%. This extent of agreement between the model prediction and the actual process performance can be deemed excellent, indicating that the modeling approach of this report can be used to greatly reduce the experimental time and costs involved in running the process. [ABSTRACT FROM AUTHOR]

The paper presents a study on the erosion performance of stainless steel SS316L grade. The micron layers of Ni-20Al2O3 powder were sprayed on the surface SS316L by utilizing a high-velocity oxygen–fuel (HVOF) thermal spraying process. Wear experiments were performed in a slurry pot tester (Ducom TR-41) at different speeds varying from 600 to 1500 rpm. During the experiments, the sand was used to erode the coated surface of SS316L. Multi-sized slurry having a solid concentration lies in the range of 30–60% (by weight) was prepared to perform the wear experiments. A neural network technique was implemented to predict the erosion data by training 75% of the total data. Results show that the microhardness of bare and Ni-20Al2O3 HVOF coated SS316L was tested as 196 ± 21 and 393.32 ± 17 VHN respectively. The current ANN model yielded an R-value that was 0.98871 for training, 0.97209 for validation, and 0.96264 for testing accordingly. It was determined that the total R-value of the model was 0.98153. The ANN's performance evaluated based on the mean squared error (MSE) was determined as 0.0176, 0.00265, and 0.00334 respectively for the training, validation, and testing. [ABSTRACT FROM AUTHOR]

Environmental hurdles, in the form of climatic crises, have taken a toll on prevalence of medicinal plants, which served as the foundation for traditional medicine from time immemorial. Drying preserves medicinal plants, and analyzing drying kinetics enhances resource efficiency, including energy and time utilization. This study is the first to examine the drying kinetics of insulin plant leaves. In this study, insulin plant leaves were dried at different temperatures ("40 °C," "50 °C," and "60 °C") to determine optimal drying temperature and assess its mass transfer characteristics. Higher temperatures led to shorter drying times: 530 min at 40 °C, 290 min at 50 °C, and 155 min at 60 °C. Both mathematical models and artificial neural networks (ANN) were used to model drying characteristics, with the logarithmic model showing superior predictive performance among the mathematical models. ANN with the "Levenberg-Marquardt algorithm" and "TANSIGMOID transfer function" gave the best model with better prediction. Comparative analysis confirmed that ANN exhibited superior predictive capabilities. Effective moisture diffusivity followed an upward trend with temperature and 60 °C revealed a diffusivity of 2.4352 × 10−7 m2/s. Activation energy, at 42.124 kJ/mol, underscored utilization of a moderate level of energy to enhance moisture diffusivity within the sample. Color and microstructural analysis also revealed that 60 °C had better color attributes and agglomerative structures. Drying leaves at 60 °C expedited the drying process, enhanced mass transfer, and improved color characteristics. These results provided vital insights for utilizing dried insulin plant leaves in various nutraceutical products. [ABSTRACT FROM AUTHOR]

Artificial neural networks are amongst the artificial intelligence techniques with their ability to provide machines with some functionalities such as decision making, comparison, and forecasting. They are known for having the capability of forecasting issues in real-world problems. Their acquired knowledge is stored in the interconnection strengths or weights of neurons through an optimization system known as learning. Several limitations have been identified with commonly used gradient-based optimization algorithms, including the risk of premature convergence, the sensitivity of initial parameters and positions, and the potential for getting trapped in local optima. Various meta-heuristics are proposed in the literature as alternative training algorithms to mitigate these limitations. Therefore, the primary aim of this study is to combine a feed-forward artificial neural network (ANN) with a cultural algorithm (CA) as a meta-heuristic, aiming to establish an efficient and dependable training system in comparison to existing methods. The proposed artificial neural network system (ANN-CA) evaluated its performance on classification tasks over nine benchmark datasets: Iris, Pima Indians Diabetes, Thyroid Disease, Breast Cancer Wisconsin, Credit Approval, Glass Identification, SPECT Heart, Wine and Balloon. The overall experimental results indicate that the proposed method outperforms other methods included in the comparative analysis by approximately 12% in terms of classification error and approximately 7% in terms of accuracy. [ABSTRACT FROM AUTHOR]

An effort has been made to develop statistical and ANN models for estimation of sodium concentration in pre-monsoon and post-monsoon seasons using routinely monitored water quality parameters of ground water wells in Jaipur district, Rajasthan (India). The Best Subset procedure based on R2 (coefficient of determination) and F (Fishers test) values was used in model dissemination. It was found that electrical conductivity, hardness, chloride, and sulphate could be used as surrogate parameters for the prediction of sodium. The model values of Na when compared with actual values (validation) showed a reasonably good matching. Further it was noticed that there was not a single model which could be used to predict the Na levels. It is primarily attributed to the fact that sodium concentration not only varies from site to site but also varies from season to season. Secondly, Principal component analysis was used to predict the dominating water quality constituents and it was revealed that four principal components are accounted for the total chemical variability in the ground water quality for pre-monsoon season and three principal components for post-monsoon season, respectively. The common factors conductivity, fluoride, nitrate, alkalinity, and phosphate have perceptible influence on the quality of groundwater of Jaipur district, Rajasthan. Finally, Back Propagation, three layered ANN models for both pre-monsoon and post-monsoon season was developed for estimation of sodium using the steepest descent optimization technique. ANN models were developed considering a fixed number of iterations as 1000 and the developed models were verified on the data not considered in calibration. The input variables considered for different model structures were identified through correlation analysis. Based on the statistical performance evaluation criteria such as root mean square error (RMSE), correlation coefficient (CC), and coefficient of efficiency (CE), the results indicated satisfactory performance of ANN based model. [ABSTRACT FROM AUTHOR]

The weight of livestock is a crucial metric for evaluating management efficacy, informing policy decisions, and determining the market value of animals. In certain scenarios, conventional methods such as physical weighing and measurement calculations can prove challenging, including the absence of livestock health records or weighing equipment. This research aims to develop a predictive model for estimating the live weight of cattle through visual assessments and metadata, including age and pixel count, utilizing a combination of convolutional neural network (CNN) and artificial neural network (ANN) methodologies. A total of 223 data were obtained from a local farm before augmentation. The model's predictive capability was successfully demonstrated, with its performance quantified by an average mean absolute percentage error (MAPE) of 10% on test data. This study demonstrates that through the combination of CNN and ANN, as well as optimal parameter tuning, efficient prediction of cattle weight can be achieved. [ABSTRACT FROM AUTHOR]

Accurate forecasting of global horizontal irradiance (GHI) is critical for optimizing solar power plant (SPP) output, particularly in tropical locales where solar potential is high yet underutilized due to forecasting challenges. This research aims to enhance GHI prediction in one of the major cities of Indonesia, where existing models struggle with the area's natural climate unpredictability. Our analysis harnesses a decade of data 2011-2020, including GHI, temperature, and the Sky Insolation Clearness Index, to calibrate and compare these methodologies. We evaluate and contrast the exponential smoothing method versus the more complicated artificial neural network (ANN). Our findings reveal that the ANN method, notably its fourth iteration model with 12 input and hidden layers, substantially outperforms exponential smoothing with a low error rate of 1.12%. The use of these methodologies forecasts an average energy output of 252,405 Watt for a solar panel with specification 15.3% efficiency and 1.31 m2 surface area throughout the 2021 to 2025 timeframe. The work offers the ANN method as a strong prediction tool for SPP development and urges a further exploration into more advanced forecasting methodologies to better harness solar energy. [ABSTRACT FROM AUTHOR]

Slug liquid holdup (SLH) is a critical requirement for accurate pressure drop prediction during multiphase pipe flows and by extension optimal gas lift design and production optimization in wellbores. Existing empirical correlations provide inaccurate predictions because they were developed with regression analysis and data measured for limited ranges of flow conditions. Existing SLH machine learning models provide accurate predictions but are published without any equations making their use by other researchers difficult. The only existing ML model published with actual equations cannot be considered optimum because it was selected by considering artificial neural network (ANN) structures with only one hidden layer. In this study, an ANN-based model for SLH prediction with actual equations is presented. A total of 2699 data points randomly divided into 70%, 15%, and 15% for training, validation, and testing was used in constructing 71 different network structures with 1, 2, and 3 hidden layers respectively. Sensitivity analysis revealed that the optimum network structure has 3 hidden layers with 20, 5, and 15 neurons in the first, second, and third hidden layers, respectively. The optimum network structure was translated into actual equations with the aid of the weights, biases, and activation functions. Trend analysis revealed that this study's model reproduced the expected effects of inputs on SLH. Test against measured data revealed that this study's model is in agreement with measured data with coefficient of determinations of 0.9791, 0.9727, 0.9756, and 0.9776 for training, testing, validation, and entire datasets, respectively. Comparative study revealed that this study's model outperformed existing models with a relative performance factor of 0.002. The present model is presented with visible mathematical equations making its implementation by any user easy and without the need for any ML framework. Unlike existing ANN-based models developed with one hidden layered ANN structures, the present model was developed by considering ANN structures with one, two, and three hidden layers, respectively. [ABSTRACT FROM AUTHOR]

Wind energy is being integrated into the grid as a renewable energy source to meet the world's electricity needs. Grid-connected wind turbines are often disrupted by grid fault problems. Fault ride-through (FRT) ability has become the most important grid connection necessity for wind energy conversion systems (WECS). In the event of a voltage dip fault, the low voltage ride-through (LVRT) capacity is an imperative key to successful grid integration. This paper proposes a dynamic voltage restorer (DVR) controlled through an artificial neural network (ANN) to improve the LVRT capability of a grid-connected wind turbine (WT) based permanent magnet synchronous generator (PMSG). The DVR injects series voltage into the system through a series-connected transformer. The DVR can then restore the voltage to the pre-fault value. The injection transformer is connected to the line linking the PMSG-based wind turbine output to the utility grid. Design and simulation of the low voltage ride-through applied to symmetrical and asymmetrical fault conditions were performed in MATLAB/Simulink software. Simulation results approve that the performance of the technique fully demonstrates its effectiveness and practicality. [ABSTRACT FROM AUTHOR]

The use of externally bonded composite systems is recognized as an effective solution for strengthening existing reinforced concrete (RC) structures. Steel-reinforced grout (SRG) is an attractive option, because of its compatibility with the concrete substrate and mechanical properties. However, a critical aspect is the delamination that might affect the steel textile–mortar and the mortar–concrete substrate interfaces. An experimental and theoretical investigation of the SRG–concrete bond is reported in this paper. In particular, the bond performances of SRG-to-concrete joints, which varies the width of the SRG fabric, the displacement rate, and the applied load eccentricity, are analyzed for the stress that is associated with the bond capacity, slip, and failure modes based on the results that are obtained by direct single-lap shear tests. To assess a data set for model calibration, the findings of this paper and those in the technical literature are collected. Therefore, a machine learning (ML) approach that is based on an artificial neural networks (ANN) algorithm is implemented, and a new analytical formulation for the prediction of the SRG-to-concrete bond capacity is proposed. [ABSTRACT FROM AUTHOR]

Aerodynamic modeling and control law design methods are crucial foundational technologies that enable efficient maneuvering flight of aircraft. Hence, this study focuses on how to construct the aerodynamic model and design control law using machine learning, as well as their differences from classical methods. To conduct this, a modified NACA0012 airfoil with a tail functioning as an elevator is employed as the geometry model. Through the utilization of the rigid dynamic grid method and overlapping grid technology, the pitch of the airfoil and the deflection of the elevator are efficient to execute. Firstly, the pitching moment coefficient is sampled through both steady and unsteady computations. Then, multivariate nonlinear regression (MNR) models and artificial neural network (ANN) models are established based on steady and unsteady sampling data, respectively. Additionally, the obtained model is evaluated using open‐loop control laws. Based on the evaluation, the proportional‐integral‐derivative (PID) control algorithm is used to design the airfoil pitching control law using the MNR model. Meanwhile, deep reinforcement learning (DRL) is used to design the pitching control law using the ANN model. Finally, the PID and DRL controllers are implemented in a CFD environment for airfoil pitching control to verify their effectiveness in application scenarios. The results suggest that models based on both steady and unsteady data can reflect dynamic aerodynamic characteristics. However, using unsteady computation for data sampling significantly reduces time consumption compared to steady computation. Furthermore, the model constructed by ANN may have unexpected excellent characteristics. Both the PID and DRL control laws, designed based on the models, perfectly complete the control process in the CFD environment. This study provides valuable insights for the implementation of controllable maneuvering flight in aircraft. [ABSTRACT FROM AUTHOR]

The enormous amount of solar power and its state-of-the-art capturing technology that produces electricity, increases the grid interconnection rate of photovoltaic (PV) plants. Prior knowledge of the aperiodic characteristics of solar energy received by the Earth’s surface is essential for PV plants to ensure reliable operation and stable, secure grid connections. Power generation under diffused sunlight by PV plants with the most widely used first-generation solar cells has significant limitations. A dye-sensitized solar plant (DSSP), utilizes dye-sensitized solar cell (DSSC) technology, remains active in low light conditions. Though the activeness enables such plants to generate electricity throughout the year while receiving diffuse sunlight, unlike conventional solar technologies the plants have a requirement of knowledge of future power generation. This could be the first paper to report on the generated power forecast for such plants. The study has utilized a machine learning approach with a proposed DSSP model for the forecast. Spyder, an open-source integrated development environment, is the test workbench for the experimentation. The results show the robustness and reliability of the method, regardless of the weather conditions in the test area. The DSSP, along with the prediction model, will moderately overcome the shortcomings of power generation under diffuse daylight with intermittent solar radiation and grid connections. [ABSTRACT FROM AUTHOR]

Introduction: Developing somatic embryogenesis is one of the main steps in successful in vitro propagation and gene transformation in the carrot. However, somatic embryogenesis is influenced by different intrinsic (genetics, genotype, and explant) and extrinsic (e.g., plant growth regulators (PGRs), medium composition, and gelling agent) factors which cause challenges in developing the somatic embryogenesis protocol. Therefore, optimizing somatic embryogenesis is a tedious, time-consuming, and costly process. Novel data mining approaches through a hybrid of artificial neural networks (ANNs) and optimization algorithms can facilitate modeling and optimizing in vitro culture processes and thereby reduce large experimental treatments and combinations. Carrot is a model plant in genetic engineering works and recombinant drugs, and therefore it is an important plant in research works. Also, in this research, for the first time, embryogenesis in carrot (Daucus carota L.) using Genetic algorithm (GA) and data mining technology has been reviewed and analyzed. Materials and methods: In the current study, data mining approach through multilayer perceptron (MLP) and radial basis function (RBF) as two well-known ANNs were employed to model and predict embryogenic callus production in carrot based on eight input variables including carrot cultivars, agar, magnesium sulfate (MgSO4), calcium dichloride (CaCl2), manganese (II) sulfate (MnSO4), 2,4-dichlorophenoxyacetic acid (2,4-D), 6-benzylaminopurine (BAP), and kinetin (KIN). To confirm the reliability and accuracy of the developed model, the result obtained from RBF-GA model were tested in the laboratory. Results: The results showed that RBF had better prediction efficiency than MLP. Then, the developed model was linked to a genetic algorithm (GA) to optimize the system. To confirm the reliability and accuracy of the developed model, the result of RBF-GA was experimentally tested in the lab as a validation experiment. The result showed that there was no significant difference between the predicted optimized result and the experimental result. Conclutions: Generally, the results of this study suggest that data mining through RBF-GA can be considered as a robust approach, besides experimental methods, to model and optimize in vitro culture systems. According to the RBF-GA result, the highest somatic embryogenesis rate (62.5%) can be obtained from Nantes improved cultivar cultured on medium containing 195.23 mg/l MgSO4, 330.07 mg/l CaCl2, 18.3 mg/l MnSO4, 0.46 mg/l 2,4- D, 0.03 mg/l BAP, and 0.88 mg/l KIN. These results were also confirmed in the laboratory [ABSTRACT FROM AUTHOR]

Syngas (CO + H 2) production through biomass gasification offers a promising and sustainable alternative to conventional fuels. This study investigates the co-gasification of palm oil decanter cake (PODC) and Alum Sludge (AS), utilizing response surface methodology (RSM) and artificial neural network (ANN) techniques to optimize and predict syngas production. Conducted in a fixed bed horizontal reactor, the experiment investigates temperature, airflow rate, and particle size as input parameters. Results revealed that optimal condition of 900 °C temperature, 10 mL/min airflow rate, and 2 mm particle size yielded the highest syngas production at 39.48 vol%. The RSM showed an R2 value of 0.9896, whereas ANN network revealed an overall R2 value of 0.971. Both models demonstrated strong alignment with experimental data and the modelled equation. This research demonstrates the effective use of statistical modelling to enhance the efficiency and effectiveness of syngas production, thereby fostering advancements in sustainable energy production. [Display omitted] • PODC and AS co-gasification was carried out in fixed bed horizontal tube furnace reactor. • RSM and ANN were applied for optimization and prediction of syngas production. • At optimal condition of 900 °C, 10 mL/min, and 2 mm, 39.48 vol% syngas was produced. • RSM and ANN model prediction accuracy were 98.96% and 97.1%, respectively. • Both RSM and ANN satisfactory validate and predict the response. [ABSTRACT FROM AUTHOR]

This study investigated the pyrolysis of oil sand bitumen as an alternative energy source in response to the global energy crisis. Thermogravimetric analysis was performed at different heating rates in a nitrogen atmosphere. Low moisture and ash content and high volatile matter content were found by proximate analysis, indicating the possibility for effective pyrolysis and ignition. Fourier-transform infrared spectroscopy identified functional groups, and X-ray diffraction confirmed the absence of problematic expandable clay minerals. The Friedman, Flynn–Wall–Ozawa, and Kissinger–Akahira–Sunose models were used to calculate the kinetic parameters. The activation energies of the models were primarily between 100 and 200 kJ/mol, with the Friedman model having higher values. It was discovered that the process was non-spontaneous and endothermic. An artificial neural network model demonstrated the potential for future energy applications by accurately predicting the behaviour of pyrolysis. [ABSTRACT FROM AUTHOR]

Reliable information plays a pivotal role in sustainable urban planning. With advancements in computer technology, geoinformatics tools enable accurate identification of land use and land cover (LULC) in both spatial and temporal dimensions. Given the need for precise information to enhance decision-making, it is imperative to assess the performance and reliability of classification algorithms in detecting LULC changes. While research on the application of machine learning algorithms in LULC evaluation is widespread in many countries, it remains limited in Zambia and Sri Lanka. Hence, we aimed to assess the reliability and performance of support vector machine (SVM), random forest (RF), and artificial neural network (ANN) algorithms for detecting changes in land use and land cover taking Lusaka and Colombo City as the study area from 1995 to 2023 using Landsat Thematic Mapper (TM), and Operational Land Imager (OLI). The results reveal that the RF and ANN models exhibited superior performance, both achieving Mean Overall Accuracy (MOA) of 96% for Colombo and 96% and 94% for Lusaka, respectively. Meanwhile, the SVM model yielded Overall Accuracy (OA) ranging between 77% and 94% for the years 1995 and 2023. Further, RF algorithm notably produced slightly higher OA and kappa coefficients, ranging between 0.92 and 0.97, when compared to both the ANN and SVM models, across both study areas. A predominant land use change was observed as the expansion of vegetation by 11,990 ha (60.4%), primarily through the conversion of 1,926 ha of bare lands into vegetation in Lusaka during 1995-2005. However, a noteworthy shift was observed as built-up areas experienced significant growth from 2005 to 2023, with a total increase of 25,110 ha (71%). However, despite the conversion of vegetation to built-up areas during the entire period from 1995 to 2023, there was still a net gain of over 11,000 ha (53.4%) in vegetation cover. In case of Colombo, built-up areas expanded by 1,779 ha (81.5%), while vegetation land decreased by 1,519 ha (62.3%) during concerned period. LULC simulation also indicated a 160-ha expansion of built-up areas during the 2023-2035 period in Lusaka. Likewise, Colombo saw a rise in built-up areas by 337 ha within the same period. Overall, the RF algorithm outperformed the ANN and SVM algorithms. Additionally, the prediction and simulation results indicate an upward trend in built-up areas in both scenarios. The resultant land cover maps provide a crucial baseline that will be invaluable for urban planning and policy development agencies in both countries. [ABSTRACT FROM AUTHOR]

AbstractThrough the increasing use of supplementary cementitious materials, the properties of concrete have taken on increased significance in a design code. Using reliable prediction models based on a small data set for the mechanical properties and durability of concrete can reduce the number of trial batches and experiments needed to produce useful design data in the laboratory, reducing time as well as resources. In this study, we investigate how the properties of water penetration, chlorine resistance, and compressive strength can be predicted by polynomial regression (PR), random forest (RF) regression, and artificial neural networks (ANNs) based on the input values of density, workability, and the constituent amount of rice husk ash, cement, and nano SiO2. We vary the training data used and test the coefficient of determination (R2 score) on the remaining data as a test set to measure predictive capability. We show that RFs and ANNs outperform PR in all settings and have unambiguously extrapolating properties when hyperparameter optimization is designed for this purpose. Remarkably, we obtain R2 scores on the test data of 0.858 − 0.990 for RFs and 0.825 − 0.985 for ANNs. [ABSTRACT FROM AUTHOR]

In this study, it is aimed to predict the performance of concretes obtained by using supplementary cementitious materials (SCM) before and after high temperature using artificial neural network. Thus, in addition to contributing to sustainable development and circular economy by using waste materials in concrete production, predicting concrete strength using artificial neural network without the need for experimental studies will provide a great advantage in practice. In addition, it will also contribute to the literature in terms of determining the optimum amount of metakaolin to be used with fly ash in concrete production. Metakaolin, silica fume and fly ash were used as SCM in different proportions in concrete mixes. Accordingly, a total of 22 concrete series were prepared, one of which was the control series. Porosity, ultrasonic pulse velocity, pressure and tensile strength tests were applied to the series at the end of 7th, 28th and 90th curing periods before high temperature. In order to determine the strength losses after elevated temperature, porosity and compressive strength tests were applied at temperatures of 400, 600 and 800 °C. Mineral additive series showed positive mechanical properties up to 20%. However, it has been observed that the use of fly ash after a certain rate causes a decrease in strength. After elevated temperature, strength loss was observed in all series due to the increase in temperature, while it was observed that the rate of being affected by elevated temperature decreased as the percentage of metakaolin increased. Optimum mineral additive usage percentages were determined as 10% fly ash and 15% metakaolin. On the other hand, the use of mineral additives above the optimum level caused the performance of the concrete to decrease. Then, the concrete compression strengths obtained at 7th, 28th, and 90th days and at 400, 600 and 800 °C temperatures are taken as the outputs of the ANN. The artificial neural network provided the closest results to experimental data. Moreover, to prove the predictive performance of ANN, a comparative analysis was made with GPR, SVM and LR and the smallest value of the RMSE value is obtained with the ANN model. Finally, a fivefold cross-validation criteria was used to objectively present the performance of the model. [ABSTRACT FROM AUTHOR]

ABSTRACT This study employs advanced data mining techniques to investigate the DASS‐42 questionnaire, a widely used psychological assessment tool. Administered to 680 students at Necmettin Erbakan University's Ahmet Kelesoglu Faculty of Education, the DASS‐42 comprises three distinct subscales—depression, anxiety and stress—each consisting of 14 items. Departing from traditional statistical methodologies, the study harnesses the power of the WEKA data mining program to analyse the dataset. Employing Naive Bayes (NB), Artificial Neural Network (ANN), Logistic Regression (LR), Support Vector Machine (SVM) and Random Forest (RF) algorithms, the research unveils novel insights. The ANN method emerges as a standout performer, achieving remarkable distinctiveness scores for all subscales: depression (99.26%), anxiety (98.67%) and stress (97.35%). The study highlights the potential of data mining in enhancing psychological assessment and showcases the ANN's prowess in capturing intricate patterns within complex psychological dimensions. By charting a course beyond conventional statistical methods, this research pioneers a new frontier for employing data mining within the realm of social sciences. As a result of the study, it is recommended that teacher candidates in the teacher education process should have knowledge about depression, anxiety and stress, and relevant courses on these topics should be added to the curriculum of teacher education programs. [ABSTRACT FROM AUTHOR]

BACKGROUND RESULTS CONCLUSION Strawberry is a rich source of antioxidants, including ascorbic acid (ASA) and polyphenols, which have numerous health benefits. Antioxidant content and activity are often determined manually using laboratory equipment, which is destructive and time‐consuming. This study constructs a prediction model for antioxidant compounds utilizing machine learning (ML) and multiple linear regression based on environmental, plant growth and agronomic fruit quality‐related parameters as well as antioxidant levels. These were studied in three farms at two‐week intervals during two years of cultivation.During the ML model screening, artificial neural network (ANN)‐boosted models displayed a moderate coefficient of determination (R2) at 0.68–0.78 and relative root mean square error (RRMSE) at 3.8–4.8% in polyphenols and total ASA levels, as well as a high R2 of 0.96 and low RRMSE at <3.0% in antioxidant activity. Additionally, we developed variable selection models regarding the antioxidant activity, and variables two and five (environmental parameters and leaf length, respectively) with high accuracy were selected. The linear regression analysis between the actual and predicted data of antioxidants in the ANN‐boosted models revealed high fitness with all parameters in almost all training, validation and test sets. Furthermore, environmental parameters are essential in developing such reliable models.We conclude that ANN‐boosted, stepwise and double‐Lasso regression models can predict antioxidant compounds with enhanced accuracy, and the relevant parameters can be easily acquired on‐site without the need for any specific equipment. © 2024 Society of Chemical Industry. [ABSTRACT FROM AUTHOR]

A comprehensive model based on CFD modelling as well as AI/ML based modelling for an alkaline water electrolysis (AWE) cell is presented. A single cell 2D multiphase CFD model is solved in COMSOL Multiphysics 6.1® and is successfully validated with the experimental results for different operating conditions. The CFD model accurately computes the concentration and flow profiles of produced oxygen and hydrogen gases, the movement of the bubbles, and turbulence within the cell as well as the impact of current density, electrolyte flow rate and electrode-diaphragm distance. Further, integrating the CFD model with a neural network model enhances its potential for better cell design and performance. Multiple inputs and single output (MISO) artificial neural network (ANN) models are developed to predict the performance of the AWE cell. The ANN models are trained using the Levenberg-Marquardt algorithm, which operates as a feed-forward back-propagation network. The trained ANN models accurately predicts the complex relationships between input parameters (temperature, initial current density, and electrolyte weight concentration) and output parameters (actual current density and cell voltage) with an R2 value of 0.999 for both the outputs. This integrative CFD and ANN approach provides a comprehensive understanding of the AWE cell's behavior, further optimizing its design for efficient hydrogen production, offering a robust process that minimizes both computational resources and time as well as contributes for the scale up of the process. [Display omitted] • A comprehensive model based on CFD and ANN modeling for an alkaline water electrolysis (AWE) cell is presented. • The 2D multiphase CFD model is successfully validated with the experimental results for different operating conditions. • MISO models are developed to predict the performance of the AWE cell. • The trained ANN model was able to predict the input/output relationship with high accuracy. [ABSTRACT FROM AUTHOR]

The solar-driven high-temperature steam electrolysis is promising for efficient large-scale H 2 production. In this study, a comprehensive component-to-system model and optimization framework is developed to investigate the performance of a zero-emission H 2 production system based on solar power plant and protonic ceramic electrolysis cell. Compared to previous system studies, the detailed description of cell internal operating characteristics is realized by integrating multi-physics simulation and artificial neural network. After parametric analyses, it is found that the system energy/exergy efficiency and co-generation performance are complicated by each subsystem. And the optimal system performance (η th = 50.63 %, Z = 179.63 $·h−1 and η ex = 33.03 %, Z = 178.94 $·h−1, with LCOE = 0.172 $·kWh−1 and Z H2 = 6.497 $·kg−1) is obtained considering cell operating features and system energy-exergy-economic factors through multi-objective optimizations. Besides, the tradeoff between system maximum H 2 production capacity and cell internal thermal conditions is revealed. This study can facilitate the development of zero-emission green H 2 production driven by renewable energy. • A novel SPT-PCEC based integrated system is proposed for green H 2 production. • Both PCEC state and system energy-exergy-economic performance are considered. • Effects of each subsystem parameters on system performance are analyzed. • Optimal system performance under different constraints is obtained. • The tradeoff between system H 2 capacity and PCEC thermal conditions is revealed. [ABSTRACT FROM AUTHOR]

The evaluation of uterine contraction offers significant information regarding the progression of labour. The occurrence of deliveries before the expected dates leads to undesirable consequences for the mother and fetus. Electrohysterography (EHG) is a non-invasive monitoring scheme generally preferred to detect preterm delivery and reduce the hostile consequences. This paper proposed a novel term and preterm prediction method for predicting preterm deliveries by employing EHG signals. The proposed scheme involves three phases: pre-processing, feature extraction and prediction. Initially, the acquired EHG signals are pre-processed using a band pass filter and wavelet transform to remove noise and artefacts from the EHG signal. The second stage is feature extraction, where the representative features, including Shannon energy, median frequency, time-varying centroid frequency, etc., are extracted. At last, the prediction is carried out using an enhanced sheep flock optimized hybrid extreme artificial neural learning network (ESFHEANL). ESFHEANL is the combination of a hybrid extreme artificial neural learning network (HEANL) and enhanced sheep flock optimization (ESFO) algorithm. It assists in diagnosing the term and preterm birth more accurately. The proposed scheme is implemented in the Python platform and assessed the performance in terms of accuracy, recall, specificity and f-measure using the term-preterm EHG (TPEHG) database. Finally, the experimental outcomes evidenced that the proposed scheme achieved better performance and was employed to diagnose term and preterm births accurately. [ABSTRACT FROM AUTHOR]

Salt marshes provide diverse habitats for a wide range of creatures and play a key defensive and buffering role in resisting extreme marine hazards for coastal communities. Accurately obtaining the terrains of salt marshes is crucial for the comprehensive management and conservation of coastal resources and ecology. However, dense vegetation coverage, periodic tide inundation, and pervasive ditch distribution create challenges for measuring or estimating salt marsh terrains. These environmental factors make most existing techniques and methods ineffective in terms of data acquisition resolution, accuracy, and efficiency. Drone multi-line light detection and ranging (LiDAR) has offered a fire-new perspective in the 3D point cloud data acquisition and potentially exhibited great superiority in accurately deriving salt marsh terrains. The prerequisite for terrain characterization from drone multi-line LiDAR data is point cloud filtering, which means that ground points must be discriminated from the non-ground points. Existing filtering methods typically rely on either LiDAR geometric or intensity features. These methods may not perform well in salt marshes with dense, diverse, and complex vegetation. This study proposes a new filtering method for drone multi-line LiDAR point clouds in salt marshes based on the artificial neural network (ANN) machine learning model. First, a series of spatial–spectral features at the individual (e.g., elevation, distance, and intensity) and neighborhood (e.g., eigenvalues, linearity, and sphericity) scales are derived from the original data. Then, the derived spatial–spectral features are selected to remove the related and redundant ones for optimizing the performance of the ANN model. Finally, the reserved features are integrated as input variables in the ANN model to characterize their nonlinear relationships with the point categories (ground or non-ground) at different perspectives. A case study of two typical salt marshes at the mouth of the Yangtze River, using a drone 6-line LiDAR, demonstrates the effectiveness and generalization of the proposed filtering method. The average G-mean and AUC achieved were 0.9441 and 0.9450, respectively, outperforming traditional geometric information-based methods and other advanced machine learning methods, as well as the deep learning model (RandLA-Net). Additionally, the integration of spatial–spectral features at individual–neighborhood scales results in better filtering outcomes than using either single-type or single-scale features. The proposed method offers an innovative strategy for drone LiDAR point cloud filtering and salt marsh terrain derivation under the novel solution of deeply integrating geometric and radiometric data. [ABSTRACT FROM AUTHOR]