Hybrid Artificial Neural Network Research Articles

Terahertz Nondestructive Measurement of Heat Radiation Performance of Thermal Barrier Coatings Based on Hybrid Artificial Neural Network

Effective control of the micro- and nanostructure of thermal barrier coatings is essential to enhance the thermal radiation performance of the coating, which helps to determine the remaining service life of the coating. This paper proposed a method to measure the radiation properties of thermal barrier coatings by terahertz nondestructive testing technique, using APS-prepared thermal barrier coatings as the object of study. Radiative properties were a comprehensive set of properties characterized by the diffuse reflectance, transmittance, and absorptance of the thermal barrier coating. The coating data in actual service were obtained by scanning electron microscopy and metallographic experiments, and the data were used as the simulation model critical value. The terahertz time-domain simulation data of coatings with different microstructural features were obtained using the finite-different time-domain (FDTD) method. In simulating the real test signals, white noise with a signal-to-noise ratio of 20 dB was added, and fast Fourier transform (FFT), short-time Fourier transform (STFT), and wavelet transform (WT) were used to reduce the noise and compare their noise reduction effects. Different machine learning methods were used to build the model, including support vector machine algorithm (SVM) and k-nearest neighbor algorithm (KNN). The principal component algorithm (PCA) was used to reduce the dimensionality of terahertz time-domain data, and the SVM algorithm and KNN algorithm were optimized using the particle swarm optimization algorithm (PSO) and the ant colony optimization algorithm (ACO), respectively, to improve the robustness of the system. The K-fold cross-validation method was used to construct the model to improve the adaptability of the model. It could be clearly seen that the novel hybrid PCA-ACO-SVM model had superior prediction performance. Finally, this work proposed a novel, convenient, nondestructive, online, safe and highly accurate method for measuring the radiation performance of thermal barrier coatings, which could be used for the judgment of the service life of thermal barrier coatings.

Enhancement of Power Quality through the Implementation of a Hybrid Artificial Intelligence Model within Solar-Wind Energy Systems

The generation of electricity is significantly assisted by hybrid solar-wind power systems, which also play a crucial role in the advancement of intelligent grids. Furthermore, the integration of wind and solar energy storage control systems, in conjunction with energy markets, has rendered the electricity grid more economically feasible. To meet the growing demand for electricity, hybrid renewable energy systems connected to microgrids consist of substantial identifying elements. The issue of harmonic distortion in microgrids arising from nonlinear loads is a fundamental area of research. Understanding the impact of microgrids on power quality is also of great importance. This study focuses on enhancing power quality in solar-wind hybrid systems by incorporating emerging Artificial Intelligence (AI) methodologies. The proposed approach comprises two main components: (i) detection of distortions caused by voltage fluctuations and (ii) improvement of power quality through an AI-based control system. Initially, power distortions are identified and eliminated using the Enhanced Kalman Filter (EKF) algorithm. A Hybrid Artificial Neural Network with Fuzzy Intelligence (HANFI) model is then developed based on this power data. This model integrates two prominent neural network architectures with fuzzy systems. Experimental validation of the system is conducted using MATLAB, which facilitates the simulation of hybrid energy systems.

Superior decomposition of xenobiotic RB5 dye using three-dimensional electrochemical treatment: Response surface methodology modelling, artificial intelligence, and machine learning-based optimisation approaches

The highly efficient electrochemical treatment technology for dye-polluted wastewater is one of hot research topics in industrial wastewater treatment. This study reported a three-dimensional electrochemical treatment process integrating graphite intercalation compound (GIC) adsorption, direct anodic oxidation, and ∙OH oxidation for decolourising Reactive Black 5 (RB5) from aqueous solutions. The electrochemical process was optimised using the novel progressive central composite design–response surface methodology (CCD–NPRSM), hybrid artificial neural network–extreme gradient boosting (hybrid ANN–XGBoost), and classification and regression trees (CART). CCD–NPRSM and hybrid ANN–XGBoost were employed to minimise errors in evaluating the electrochemical process involving three manipulated operational parameters: current density, electrolysis (treatment) time, and initial dye concentration. The optimised decolourisation efficiencies were 99.30%, 96.63%, and 99.14% for CCD–NPRSM, hybrid ANN–XGBoost, and CART, respectively, compared to the 98.46% RB5 removal rate observed experimentally under optimum conditions: approximately 20 mA/cm2 of current density, 20 min of electrolysis time, and 65 mg/L of RB5. The optimised mineralisation efficiencies ranged between 89% and 92% for different models based on total organic carbon (TOC). Experimental studies confirmed that the predictive efficiency of optimised models ranked in the descending order of hybrid ANN–XGBoost, CCD–NPRSM, and CART. Model validation using analysis of variance (ANOVA) revealed that hybrid ANN–XGBoost had a mean square error (MSE) and a coefficient of determination (R2) of approximately 0.014 and 0.998 respectively, for the RB5 removal efficiency, outperforming CCD–NPRSM with MSE and R2 of 0.518 and 0.998, respectively. Overall, the hybrid ANN–XGBoost approach is the most feasible technique for assessing the electrochemical treatment efficiency in RB5 dye wastewater decolourisation.

Spiking NeRF: Representing the Real-World Geometry by a Discontinuous Representation

A crucial reason for the success of existing NeRF-based methods is to build a neural density field for the geometry representation via multiple perceptron layers (MLPs). MLPs are continuous functions, however, real geometry or density field is frequently discontinuous at the interface between the air and the surface. Such a contrary brings the problem of unfaithful geometry representation. To this end, this paper proposes spiking NeRF, which leverages spiking neurons and a hybrid Artificial Neural Network (ANN)-Spiking Neural Network (SNN) framework to build a discontinuous density field for faithful geometry representation. Specifically, we first demonstrate the reason why continuous density fields will bring inaccuracy. Then, we propose to use the spiking neurons to build a discontinuous density field. We conduct a comprehensive analysis for the problem of existing spiking neuron models and then provide the numerical relationship between the parameter of the spiking neuron and the theoretical accuracy of geometry. Based on this, we propose a bounded spiking neuron to build the discontinuous density field. Our method achieves SOTA performance. The source code and the supplementary material are available at https://github.com/liaozhanfeng/Spiking-NeRF.

Solar desalination system for fresh water production performance estimation in net-zero energy consumption building: A comparative study on various machine learning models.

This study employs diverse machine learning models, including classic artificial neural network (ANN), hybrid ANN models, and the imperialist competitive algorithm and emotional artificial neural network (EANN), to predict crucial parameters such as fresh water production and vapor temperatures. Evaluation metrics reveal the integrated ANN-ICA model outperforms the classic ANN, achieving a remarkable 20% reduction in mean squared error (MSE). The emotional artificial neural network (EANN) demonstrates superior accuracy, attaining an impressive 99% coefficient of determination (R2) in predicting freshwater production and vapor temperatures. The comprehensive comparative analysis extends to environmental assessments, displaying the solar desalination system's compatibility with renewable energy sources. Results highlight the potential for the proposed system to conserve water resources and reduce environmental impact, with a substantial decrease in total dissolved solids (TDS) from over 6,000 ppm to below 50 ppm. The findings underscore the efficacy of machine learning models in optimizing solar-driven desalination systems, providing valuable insights into their capabilities for addressing water scarcity challenges and contributing to the global shift toward sustainable and environmentally friendly water production methods.

Experimental analysis of forming forces in incremental forming and its prediction by AI-based methods

Single point incremental forming (SPIF) is an emerging approach to manufacture the user-specific parts of greater strength economically without involving dedicated tools and dies. In this study, peak deforming loads have been measured and estimated in order to determine the size and capacity of forming machinery for manufacturing components, using the SPIF process, for designed process conditions on AA7075-O sheets. Estimation of maximum deforming loads has been accomplished with the help of hybrid artificial neural network (HANN) approach by taking experimental load values as the input dataset. The load values, estimated by HANN approach, have been compared with the load values estimated by two state-of-art regression approaches, that is, Support Vector Machine (SVM) and Gaussian Process Regression (GPR). Results show that the regression methods (SVM and GPR) are outperformed by the HANN model with an accuracy of 99.80%. HANN model estimated force values very close to experimental results. The forming forces were found to be greater when the flat-end tools were used as a forming agent in place of hemispherical-end tool. The proposed study would help the researchers and scientists to assess the capacity the machines used in SPIF process to prepare a particular sheet-part and to prevent the failure of hardware during the SPIF process.

Leveraging hybrid ANN–AHP to optimize cement industry average inventory levels

In recent years, inventory has been critical due to the production cost and overstock risk related to the expiration date and the fluctuation price risk. This study's minimization of overstock and price fluctuation in the warehouse used a hybridized artificial neural network (ANN) and analytical hierarchy process (AHP) to produce an optimum model. The variables, such as average demand, reorder point, order quantity, factor service level, safety stock, and average inventory level, were used to obtain the optimal condition of the average inventory levels to maximize the profit. Then, the type of inventory system that guarantees the minimum risks in managing the inventory would be selected. The result shows that the data has a mean of 39.2 units, and the standard deviation (SD) was 12.9. This means that the order quantity is 20.2 units, the average inventory level is 57.3, and the average demand is 39. These conditions used the factor z, which is 97% service level. This study concludes that the optimum average inventory level is 91 units, the order quantity is 11 units with the maximum average profit is $1098, and the peak fluctuation condition maximum profit is $1463 when the average inventory level is 7.3, and the inventory policy system used to minimize the risk is the continuous review policy type. The study could be beneficial to reduce production costs and enhance overall profitability and operational efficiency in the sector by mitigating the risks associated with excessive inventory and price volatility while also minimizing the potential for expired inventory.

Functional link hybrid artificial neural network for predicting continuous biohydrogen production in dynamic membrane bioreactor

Conventional machine learning approaches have shown limited predictive power when applied to continuous biohydrogen production due to nonlinearity and instability. This study was aimed at forecasting the dynamic membrane reactor performance in terms of the hydrogen production rate (HPR) and hydrogen yield (HY) using laboratory-based daily operation datapoints for twelve input variables. Hybrid algorithms were developed by integrating particle swarm optimized with functional link artificial neural network (PSO-FLN) which outperformed other hybrid algorithms for both HPR and HY, with determination coefficients (R2) of 0.97 and 0.80 and mean absolute percentage errors of 0.014 % and 0.023 %, respectively. Shapley additive explanations (SHAP) explained the two positive-influencing parameters, OLR_added (1.1–1.3 mol/L/d) and butyric acid (7.5–16.5 g COD/L) supports the highest HPR (40–60 L/L/d). This research indicates that PSO-FLN model are capable of handling complicated datasets with high precision in less computational timeat 9.8 sec for HPR and 10.0 sec for HY prediction.

Formation mechanism of user stickiness in live e-commerce: the hybrid PLS-SEM and ANN approach

PurposeAlthough user stickiness has been studied for several years in the field of live e-commerce, little attention has been paid to the effects of streamer attributes on user stickiness in this field. Rooted in the stimulus-organism-response (S-O-R) theory, this study investigated how streamer attributes influence user stickiness.Design/methodology/approachThe authors obtained 496 valid samples from Chinese live e-commerce users and explored the formation of user stickiness using partial least squares-structural equation modeling (PLS-SEM). Artificial neural network (ANN) was used to capture linear and non-linear relationships and analyze the normalized importance ranking of significant variables, supplementing the PLS-SEM results.FindingsThe authors found that attractiveness and similarity positively impacted parasocial interaction (PSI). Expertise and trustworthiness positively impacted perceived information quality. Moreover, streamer-brand preference mediated the relationship between PSI and user stickiness, as well as the relationship between perceived information quality and user stickiness. Compared to PLS-SEM, the predictive ability of ANN was more robust. Further, the results of PLS-SEM and ANN both showed that attractiveness was the strongest predictor of user stickiness.Originality/valueThis study explained how streamer attributes affect user stickiness and provided a reference value for future research on user behavior in live e-commerce. The exploration of the linear and non-linear relationships between variables based on ANN supplements existing research. Moreover, the results of this study have implications for practitioners on how to improve user stickiness and contribute to the development of the livestreaming industry.

Modeling and Forecasting of Water Demand in the City of Istanbul Using Artificial Neural Networks Optimized with Rao Algorithms

AbstractIn this study, a hybrid artificial neural network (ANN)-Rao series (Rao_1, Rao_2, and Rao_3) algorithm model was developed to analyze water consumption in Istanbul province, Turkey. A multiple linear regression (MLR) model was developed and an ANN was also trained with back-propagation (BP) artificial bee colony (ABC) algorithms for comparison. Gross domestic product and population data were treated as independent variables. To test the accuracy of the presently developed hybrid model, its outputs were compared with those of ANN-BP, ANN-ABC, and MLR models. Error values calculated for the test set indicated that the ANN-Rao_3 algorithm outperformed the MLR, ANN-BP, and ANN-ABC reference models as well as ANN-Rao_1 and ANN-Rao_2 algorithms. Therefore, using the ANN-Rao_3 model, water consumption forecasts for Istanbul province were generated out to 2035 for low-, expected-, and high-water demand conditions. The model-generated forecasts indicate that the water requirements of Istanbul in 2035 will be between 1182.95 and 1399.54 million m3, with the upper-range estimates outpacing supplies. According to low and expected scenarios, there will be no problem in providing the water needs of Istanbul until 2035. However, according to high scenario, water needs of Istanbul will not be provided as of 2033.Therefore, water conservation policies should be enacted to ensure provision of the water needs of Istanbul province from 2033 onward.

Hybrid Artificial Neural Network-based Grasshopper Optimization Algorithm for Anomaly Detection in Wireless Body Area Networks

Recent technological advances in sensor networks show rapid growth in healthcare monitoring systems based on Wireless Body Area Networks (WBANs). A small sensor attached to the body can record various psychological parameters. WBAN sensors frequently fail due to noise, misalignment of the hardware, and patient perspiration. It is difficult for healthcare professionals to determine whether the data collected by these sensing devices is defected or influenced by a malicious attacker. Even inaccurate information can result in a wrong diagnosis, and the physiological parameters are categorized as normal or abnormal. This research focuses on reading anomaly detection for wireless body sensors and proposes a novel method based on hybrid machine-learning algorithms. A hybrid Artificial Neural Network – Grasshopper Optimization Algorithm (ANN-GOA) is proposed to find anomalous records in the dataset. Each anomalous record’s predicted value determines whether the recognized form is anomalous. The suggested hybrid ANN-GOA method results are compared with the parameters like recall, accuracy, F1 score, loss, and precision. The simulation results of the proposed hybrid ANN-GOA algorithm provide better accuracy of 98.8%, recall of 99.9%, F-score of 97.9% and precision of 99.8% when compared with other conventional algorithms.

Soil temperature forecasting using a hybrid artificial neural network in Florida subtropical grazinglands agro-ecosystems

Soil temperature is a key meteorological parameter that plays an important role in determining rates of physical, chemical and biological reactions in the soil. Ground temperature can vary substantially under different land cover types and climatic conditions. Proper prediction of soil temperature is thus essential for the accurate simulation of land surface processes. In this study, two intelligent neural models—artificial neural networks (ANNs) and Sperm Swarm Optimization (SSO) were used for estimating of soil temperatures at four depths (5, 10, 20, 50 cm) using seven-year meteorological data acquired from Archbold Biological Station in South Florida. The results of this study in subtropical grazinglands of Florida showed that the integrated artificial neural network and SSO models (MLP-SSO) were more accurate tools than the original structure of artificial neural network methods for soil temperature forecasting. In conclusion, this study recommends the hybrid MLP-SSO model as a suitable tool for soil temperature prediction at different soil depths.

New deep recurrent hybrid artificial neural network for forecasting seasonal time series

New deep recurrent hybrid artificial neural network for forecasting seasonal time series

A novel COVID-19 infection-forecasting model based on artificial neural networks

The COVID-19 surge has mostly affected people and wreaked havoc on multiple sectors of the global economy. This study uses artificial neural networks (ANN) to develop COVID-19 prediction models to minimize the perilous situation. With positive infection data, these hybrid artificial neural network models looked at COVID-19 cases in Andhra Pradesh, India. Then, COVID-19 data were divided into training and testing for simulation. The developed model that takes the previous 14 days into account outperforms the others, depending on the results. According to the developed ANN models for Andhra Pradesh districts, the prediction model that works well and yields positive results is the one that receives lower values of error metrics like MSE, RMSE, MAE, and MAPE and higher values of R2. The hybrid neural network model that considers the previous 14 days for prophecy has suggested anticipating daily positive suffering, notably in areas of Andhra Pradesh, as a result of the collected data. Linear regression, ARIMA, and LSTM have been used for model assessment. The proposed 14-day model statistically surpasses all metrics in RMSE, MAE, MAPE, and R2. This study showed that an ANN-based model can predict the COVID-19 outbreak as well as other epidemics.

Performance evaluation of artificial neural network and hybrid artificial neural network based genetic algorithm models for global horizontal irradiance forecasting

The output of photovoltaic (PV) systems is highly dependent on Global Horizontal Irradiance (GHI). Thus, accurate prediction of GHI is essential to meet increasing energy demands, stabilise the electric grid system and mitigate climate change. The main objective of this study is to accurately model and forecast GHI at Albion, Mauritius for a time step of every 15 min using the Artificial Neural Network (ANN) and hybrid Artificial Neural Network based Genetic Algorithm (ANN-GA) techniques. Ground-based measurement (GBM) data, collected every 15 min for a winter month was checked for stationarity and normalised to enhance its quality. Only strongly correlated input variables were selected to minimise uncertainties in forecasts. Special emphasis is given to short-term forecasting with a relatively small dataset size. This work is repeated for 30 min and 1 h time scales. The study is further validated using satellite data for a different location (Curepipe) in Mauritius. The performance evaluation over different statistical metrics indicated that the ANN model has the best capabilities for GHI forecasting, regardless of the location. The highest quality forecasts from the ANN technique resulted in values of 0.9999 for correlation coefficient (r), 0.9999 for coefficient of determination (R2), 0.1537 W/m2 for Mean Absolute Error (MAE), 0.0641 W/m2 for Mean Square Error (MSE) and 0.2532 W/m2 for Root Mean Square Error (RMSE). The best ANN technique outperformed the strongest hybrid ANN-GA technique for every measured performance indicator.

Enhanced Daily Global Solar Radiation Prediction Through Hybrid Artificial Neural Network and Adaptive Neuro-Fuzzy Inference System with Meta-Heuristic Algorithm Integration

Enhanced Daily Global Solar Radiation Prediction Through Hybrid Artificial Neural Network and Adaptive Neuro-Fuzzy Inference System with Meta-Heuristic Algorithm Integration

A new deep recurrent hybrid artificial neural network of gated recurrent units and simple seasonal exponential smoothing

A new deep recurrent hybrid artificial neural network of gated recurrent units and simple seasonal exponential smoothing

Optimized neural network-based state-of-the-art soft computing models for the bearing capacity of strip footings subjected to inclined loading

Determining the bearing capacity of a strip footing under inclined loading is crucial in designing foundations. Due to the complex correlations, the subject area remains predominantly unexplored, or it has been simulated using only limited datasets. This paper presents the development of a prediction model based on machine learning (ML), leveraging advanced hybrid artificial neural network (ANN) models for estimating the bearing capacity of strip footings under inclined loading. The ANN models are hybridized with four different optimization algorithms, ant colony optimization (ACO), artificial lion optimization (ALO), the imperialist competitive algorithm (ICA), and shuffled complex evolution (SCE), which enhance the accuracy and efficiency of the predictive capabilities of ANN. The models are trained on a dataset of 920 records, and their performance is evaluated using a range of significant performance metrics. The ANN-ICA model achieved the highest rank in the score analysis (R2 =0.912, RMSE=0.165 in testing), followed by ANN-ALO and ANN-ACO. To reinforce the trustworthiness of the predictions, external validation is employed, and visual analysis is conducted using the Taylor diagram. The findings suggest that the proposed models are robust, and the incorporation of optimization techniques has improved the performance of traditional ANNs. The research findings have significant implications for the field of geotechnical engineering, providing engineers and researchers with valuable insights into the applicability of hybrid artificial neural network (ANN) models and alternative machine learning (ML)-based prediction models in assessing the bearing capacity of strip footings.

Short-term Electric Energy Load Forecasting of Ankara Region Using Artificial İntelligence Methods

While energy, which is an indispensable part of everyday life, maintains its importance and place in socio-economic structures of countries, importance of electricity energy, as an important component of energy, is increasing its gravity exponentially. Importance of electricity energy demand maintains its increasing trend in line with growing population, urbanization, industrialization, becoming widespread of technology and welfare. While meeting electricity energy demand, correct and effective load forecasting is needed in order to ensure operational safety without losing the stability of voltage, frequency and power flows within the limits determined under the real time conditions of electric power systems, operate and plan secure and low-cost electricity transmission systems and supply sustainable, reliable, high quality and affordable electricity to consumers. In recent years, use of the artificial intelligence models are quite common in many areas of the power system analysis and control, static and dynamic security analysis, dynamic load modelling and alarm processing and error diagnostics. Therefore, in this study, hybrid artificial neural network model optimized with genetic algorithm has been proposed to perform short-term load forecast since fairly good forecasting results are being obtained especially for non-linear complex problems. The proposed short-term load forecasting model has been tested by making 24 hours load forecasting using actual load data of Ankara Region in Turkey. The results obtained from the proposed model have been compared with classical ANN. In this study, for short-term electric load forecasting based on artificial neural networks and genetic algorithm an adaptive hybrid system has been proposed. Using artificial neural network based on Genetic Algorithm (GA) a new approach for short-term electric load forecasting has been developed. This proposed hybrid algorithm has been implemented for short-term load forecasting. In the proposed model, the actual forecast was made by ANN, Genetic Algorithm is used to select the most appropriate activation function for each node of ANN. Thus, it has been observed that network error decreased even more than classical ANN. The results show that hybrid ANN gives better result than classical ANN. So, the accuracy of the proposed model for short-term load forecasting has been increased. These results showed that the proposed model has a higher accuracy rate than the classical ANN in the short-term load forecasting.

Modelling and optimization of biodiesel production from waste fish oil using nano immobilized rPichiapastoris whole cell biocatalyst with response surface methodology and hybrid artificial neural network based approach

In this study, zinc oxide (ZnO) nano particle immobilized recombinant whole cell biocatalyst (rWCB) was used for bioconversion of waste fish oil in to biodiesel in a lab scale packed bed reactor (PBR). Central composite design and hybrid artificial neural network (ANN) models were explored to optimize the production of biodiesel. Developed rWCB exhibited maximum lipase activity at 15 % (v/v) of glutaraldehyde concentration and 6 % (w/v) of ZnO nanoparticles at pH of 7. Maximum biodiesel yield reached about 91.54 ± 1.86 % after 43 h in PBR using hybrid ANN model predicted process conditions of 13.2 % (w/v) of nano immobilized rWCB concentration and 4.7:1 of methanol to oil ratio at 33 °C. Importantly, developed nano immobilized rWCB was adequately stable for commercialization. Thus, production of biodiesel from waste fish oil using ZnO nano immobilized rWCB could become potential candidate for commercialization.