Conventional Artificial Neural Network Models Research Articles

Modeling of a hybrid stirling engine/desalination system using an advanced machine learning approach

In this study, the performance of a hybrid power/freshwater generation system is modeled using a coupled artificial neural network (ANN) model with a pelican algorithm (PA). The proposed system is composed of a Stirling engine fixed to a solar dish, a desalination unit, and a thermoelectric cooler. The Stirling engine is used to generate the electricity required to operate the electrical-powered components of the system as well as to preheat the saline water. The thermoelectric cooler is used to supply the saline water with additional heat as well as to cool the condensation surface of the desalination unit. The performance of the proposed system in terms of water yield, generated power, and system efficiency was considered as the model's output; while the solar irradiance and dish diameter were considered as the model's inputs. In addition to the pelican algorithm, a conventional gradient descent optimizer was employed as an internal optimizer of the ANN model. The prediction accuracy of the two models was compared based on different accuracy measures. The ANN-PA outperformed the conventional ANN model in predicting the water yield, generated power, and system efficiency. The computed root mean square errors of the ANN and ANN-PA models were (1.982 L, 104.863 W, and 1.227 %) and (0.019 L, 1.673 W, and 0.047 %) for water yield, generated power, and system efficiency, respectively.

Daily scale streamflow forecasting in multiple stream orders of Cauvery River, India: Application of advanced ensemble and deep learning models

Accurate forecasts of streamflow (Qflow) are crucial for optimal management of water reservoir systems and preparing for catastrophic events such as floods. Although several machine learning (ML) techniques have been documented to forecast Qflow with notable accuracy, no model could do so with the utmost certainty since Qflow data can be noisy and sometimes incomplete. Despite these challenges, there has been significant progress in the field of Qflow forecasting. Hence, novel techniques need to be explored or applied to forecast Qflow with improved accuracy and reduced data dependency. Recently, optimized input selection techniques were shown to increase the performance of forecast models, although they have yet to be thoroughly investigated in Qflow forecasting applications. This study aims at the application of deep-learning and advanced ML techniques, namely the (i) Convolutional Neural Network (CNN), (ii) Random Forest (RF), and (iii) Gradient Tree Boosting (GTB), to forecast daily Qflow in multiple stream orders of the Cauvery River, India. The performance of these models was compared with that of conventional multilayer perceptron (MLP), a class of feedforward artificial neural network (ANN). Antecedent daily Qflow time series were used as model inputs, with input selection guided by Akaike’s Information Criteria (AIC) and Bayesian Information Criteria (BIC). The models were also calibrated using inputs selected from commonly used cross-correlation function for comparative evaluation with those models developed using AIC and BIC. The results show that applying AIC and BIC to select the ideal model input parameters marginally increase the model’s performance. The deep-learning and advanced ML techniques clearly outperformed the conventional ANN models in forecasting one- and three-day lead daily Qflow at multiple gauging stations considered along the Cauvery River. It was found that the deep learning (CNN) model had superior forecasting accuracy with respect to all 3 stations for the 1st Input-Output (I/O) combination. An NNSE, WI and KGE indices of 0.85 or higher indicates that the forecast is highly efficient.

The Prediction of Cu(II) Adsorption Capacity of Modified Pomelo Peels Using the PSO-ANN Model.

It is very well known that traditional artificial neural networks (ANNs) are prone to falling into local extremes when optimizing model parameters. Herein, to enhance the prediction performance of Cu(II) adsorption capacity, a particle swarm optimized artificial neural network (PSO-ANN) model was developed. Prior to predicting the Cu(II) adsorption capacity of modified pomelo peels (MPP), experimental data collected by our research group were used to build a consistent database. Then, a PSO-ANN model was established to enhance the model performance by optimizing the ANN's weights and biases. Finally, the performances of the developed ANN and PSO-ANN models were deeply evaluated. The results of this investigation revealed that the proposed hybrid method did increase both the generalization ability and the accuracy of the predicted data of the Cu(II) adsorption capacity of MPPs when compared to the conventional ANN model. This PSO-ANN model thus offers an alternative methodology for optimizing the adsorption capacity prediction of heavy metals using agricultural waste biosorbents.

Application of Hybrid ANN Techniques for Drought Forecasting in the Semi-Arid Region of India.

The intensity and frequency of diverse hydro-meteorological disasters viz., extreme droughts, severe floods, and cyclones have increasing trends due to unsustainable management of land and water resources, coupled with increasing industrialization, urbanization and climate change. This study focuses on the forecasting of drought using selected Artificial Neural Network (ANN)-based models to enable decision-makers to improve regional water management plans and disaster mitigation/reduction plans. Four ANN models were developed in this study, viz., one conventional ANN model and three hybrid ANN models: (a) Wavelet based-ANN (WANN), (b) Bootstrap based-ANN (BANN), and (c) Wavelet-Bootstrap based-ANN (WBANN). The Standardized Precipitation Evapotranspiration Index (SPEI), the best drought index identified for the study area, was used as a variable for drought forecasting. Three drought indices, such as SPEI-3, SPEI-6 and SPEI-12 respectively representing "short-term", "intermediate-term", and "long-term" drought conditions, were forecasted for 1-month to 3-month lead times for six weather stations over the study area. Both statistical and graphical indicators were considered to assess the performance of the developed models. For the hybrid wavelet model, the performance was evaluated for different vanishing moments of Daubechies wavelets and decomposition levels. The best-performing bootstrap-based model was further used for analysing the uncertainty associated with different drought forecasts. Among the models developed for drought forecasting for 1 to 3 months, the performances of the WANN and WBANN models are superior to the simple ANN and BANN models for the SPEI-3, SPEI-6, and SPEI-12 up to the 3-month lead time. The performance of the WANN and WBANN models is the best for SPEI-12 (MAE = 0.091-0.347, NSE = 0.873-0.982) followed by SPEI-6 (MAE = 0.258-0.593; NSE = 0.487-0.848) and SPEI-3 (MAE = 0.332-0.787, NSE = 0.196-0.825) for all the stations up to 3-month lead time. This finding is supported by the WBANN analyze uncertainties as narrower band width for SPEI-12 (0.240-0.898) as compared to SPEI-6 (0.402-1.62) and SPEI-3 (0.474-2.304). Therefore, the WBANN model is recommended for the early warning of drought events as it facilitates the uncertainty analysis of drought forecasting results.

Performance prediction of aluminum and polycarbonate solar stills with air cavity using an optimized neural network model by golden jackal optimizer

Solar stills (SS) are simple eco-friendly desalination devices that exploit solar energy to obtain freshwater from seawater. In this study, a hybrid artificial intelligence model is proposed to predict the thermal behavior of two designs of SSs. Two SSs with a basin and absorber plate made of aluminum for the first SS (ALSS)and polycarbonate for the second SS (PCSS) were established and tested. Both SSs have a modified absorber plate with an air cavity. The hybrid model was composed of an optimized Artificial Neural Network (ANN) model by Golden Jackal Optimizer (GJO). To prove the capability of the proposed model to predict the SSs performance, it was compared with the conventional ANN model as well as two other optimized models with Genetic Algorithm (GA) or Particle Swarm Optimizer (PSO). The results showed that ANN-GJO had better accuracy than ANN, ANN-GA, and ANN-PSO to predict overall heat transfer coefficient, energy efficiency, exergy efficiency, and distillate output. Moreover, ALSS showed better thermal performance compared with PCSS regarding water productivity, exergy efficiency, and energy efficiency. The average exergy efficiency and energy efficiency of PCSS and ALSS were 2.30%, 42.40%, and 3.44%, 48.80%, respectively. The maximum distillate output for PCSS and ALSS were 3.40 l/m2/day and 3.80 l/m2/day, respectively.

Improving accuracy of SVM for monthly sediment load prediction using Harris hawks optimization

One of the most significant concerns for water resource projects is estimating sediment load (SL). In last three decades, the application of soft computing models for SL. prediction has broadly increased and provided effective outcomes. Present study applies a support vector machine (SVM) for estimating SL. at two stations of Baitarani river basin, Odisha, India. A meta-heuristic algorithm called Harris hawks optimization (HHO) is utilized for enhancing accuracy of SVM model in monthly SL prediction. Lagged rainfall, temperature, stage, runoff are considered different inputs for developing all models. The ability of SVM-HHO is benchmarked with SVM-PSO (particle swarm optimization), SVM-GWO (Grey wolves optimization), along with conventional SVM and ANN (artificial neural network) models. Collected data is divided into two subgroups (training and testing), and SL is estimated. Performance of applied methodologies is evaluated by quantitative statistical measures, such as coefficient of determination (R2), root mean square error (RMSE), and Nash-Sutcliffe efficiency (NSE). Obtained results revealed that highest value of NSE (0.9898), R2 (0.988), and a minimum of RMSE (0.6682) was generated by SVM-HHO in testing phase compared to other studied techniques. This leads to a conclusion regarding superiority of HHO evolutionary algorithm in enhancing accuracy of conventional SVM for monthly SL prediction. Ability of HHO algorithm to escape local optima marks SVM-HHO as a potential method in SL estimation. Findings of this study tend to ascertain the suitability of employed approach for precisely modelling SL in rivers.

Predicting rock displacement in underground mines using improved machine learning-based models

Displacement of rock mass in tunnels and underground mines is considered one of the most hazardous phenomena that can cause the collapse of the structures. In this study, the rock properties, such as the depth of the tunnels (H), the angle of rock layers (α), anti-bending moment (Wc), the width of the tunnels (b), the tensile strength of rock layers (Rn), and monitoring distance (Lb), and observation time (t), were investigated to predict rock displacement in tunnels and underground mines. Two novel soft computing models, namely Harris Hawks optimization algorithm (HHOA)-based support vector machine (SVM) model (i.e., HHOA-SVM) and Grasshopper optimization algorithm (GOA)-based SVM model (i.e., GOA-SVM), were developed for this aim based on the field measurements. A total of 12 measurement stations and 63 observations of vertical rock mass displacement, rock properties, and observation time in some underground coal mines in the Donbas region (Ukraine) were compiled as the dataset for developing soft computing models. In addition, a constraint was also added to the proposed HHOA-SVM and GOA-SVM models to prevent the model from offering negative results in predicting rock displacement. The conventional models, such as SVM (without optimization) and artificial neural network (ANN), were also investigated to compare favorably with the two proposed HHOA-SVM and GOA-SVM models. Furthermore, linear and nonlinear equations were also established to predict rock displacement and compared to the soft computing models. The results showed that the novel HHOA-SVM and GOA-SVM models provided better performances than conventional SVM and ANN models. Besides, the sensitivity of the input variables was also analyzed to discover the certain characteristics of the rock displacement phenomenon through the properties of rock and observation time. The findings show that H, Lb, t, and α are the most influential parameters for predicting rock displacement in tunnels and underground mines. In contrast, the contribution of b in rock displacement is tiny, and Wc did not relate to the rock displacement in tunnels and underground mines.

Bond strength prediction of concrete-encased steel structures using hybrid machine learning method

The mechanical behavior of concrete-encased steel (CES) structures is crucially linked to the bond strength between steel section and concrete which should be predicted with ease and accuracy. In this paper, an efficient and robust soft computing strategy was proposed, where the artificial neural networks (ANN) are hybridized with genetic algorithm (GA) or particle swarm optimization (PSO) to predict the bond strength in CES structures. Seven features were extracted from push-out tests in the available literature, and a database containing 191 records was established for model training and testing. Then, the performance of three machine learning models ANN, GA-ANN, and PSO-ANN was thoroughly compared. The results showed that the developed GA-ANN and PSO-ANN models exhibit superior performance to both conventional ANN model and existing empirical equations. The PSO-ANN outperforms the GA-ANN in terms of convergence speed and prediction error owing to its unique information-sharing mechanism. Further, sensitivity analysis of main contributing factors was conducted on PSO-ANN model. It is quantitatively confirmed that the relative concrete cover has the most significant effect on bond strength while the influence of relative bonded length is relatively minimal. Eventually, an explicit formula was directly derived from the PSO-ANN model and a practical tool with a graphical user interface was created for design practice. The outcome of this study could be employed to intelligently estimate the bond strength in CES without costly and time-consuming tests.

Comparison of Artificial and Spiking Neural Networks on Digital Hardware.

Despite the success of Deep Neural Networks—a type of Artificial Neural Network (ANN)—in problem domains such as image recognition and speech processing, the energy and processing demands during both training and deployment are growing at an unsustainable rate in the push for greater accuracy. There is a temptation to look for radical new approaches to these applications, and one such approach is the notion that replacing the abstract neuron used in most deep networks with a more biologically-plausible spiking neuron might lead to savings in both energy and resource cost. The most common spiking networks use rate-coded neurons for which a simple translation from a pre-trained ANN to an equivalent spike-based network (SNN) is readily achievable. But does the spike-based network offer an improvement of energy efficiency over the original deep network? In this work, we consider the digital implementations of the core steps in an ANN and the equivalent steps in a rate-coded spiking neural network. We establish a simple method of assessing the relative advantages of rate-based spike encoding over a conventional ANN model. Assuming identical underlying silicon technology we show that most rate-coded spiking network implementations will not be more energy or resource efficient than the original ANN, concluding that more imaginative uses of spikes are required to displace conventional ANNs as the dominant computing framework for neural computation.

Prediction of Recurrence in Pyogenic Vertebral Osteomyelitis by Artificial Neural Network Using Time-series Data of C-Reactive Protein

Study Design. A retrospective cohort study. Objective. The aim of this study was to develop recurrence-prediction models of pyogenic vertebral osteomyelitis (PVO). Summary of Background Data. Prediction of recurrence in PVO is crucial to avoid additional prolonged antibiotic therapy and aggressive spinal surgery and to reduce mortality. However, prediction of PVO recurrence by previously identified, initial risk factors is limited in PVO patients who exceptionally require prolonged antibiotic therapy and experience various clinical events during the treatment. We hypothesized that time-series analysis of sequential C-reactive protein (CRP) routinely measured to estimate the response to the antibiotics in PVO patients could reflect such long treatment process and increase the power of the recurrence-prediction model. Methods. A retrospective study was performed to develop a PVO recurrence-prediction model, including initial risk factors and time-series data of CRP. Of 704 PVO patients, 493 and 211 were divided into training and test cohorts, respectively. Conventional stepwise logistic regression and artificial neural network (ANN) models were created from the training cohort, and the predictions of recurrence in the test cohort were compared. Results. Prediction models using initial risk factors showed poor sensitivity (4.7%) in both conventional logistic model and ANN models. However, baseline ANN models using time-series CRP data showed remarkably increased sensitivity (55.8%–60.5%). Ensemble ANN model using both initial risk factors and time-series CRP data showed additional benefit in prediction power. Conclusion. The recurrence-prediction models for PVO created only using the initial risk factors showed low sensitivity, regardless of statistical method. However, ANN models using time-series data of CRP values and their ensemble model showed considerably increased prediction power. Therefore, clinicians treating PVO patients should pay attention to the treatment response including changes of CRP levels to identify high-risk patients for recurrence, and further studies to develop recurrence-prediction model for PVO should focus on the treatment response rather than initial risk factors. Level of Evidence: 4

An ensemble‐driven long short‐term memory model based on mode decomposition for carbon price forecasting of all eight carbon trading pilots in China

AbstractThe carbon trading market has become a powerful weapon in alleviating carbon emissions in China, and the carbon price is at the core of its operation. Hence, the carbon trading market serves as an indispensable component in forecasting the carbon price accurately in advance. This paper innovatively explores an ensemble‐driven long short‐term memory network (LSTM) model based on complementary ensemble empirical mode decomposition (CEEMD) for carbon price forecasting, applying it to all eight carbon trading pilots in China. The CEEMD was initially implemented for mode transformation in order to decompose the original complicated mode into a set of simple modes. Then, the partial autocorrelation function selected time‐lagged features as inputs for each mode. Subsequently, the LSTM was used to model the mapping between time‐lagged factors as well as each mode's target values, constructing multiple LSTM models for ensemble learning. Finally, the inverse CEEMD computation was introduced to integrate the anticipated results of the multi‐mode into the final results. Its practical application simultaneously embraced all eight carbon pilots in China, covering their corresponding carbon price data over a considerably long period. The obtained results illustrated that the proposed model driven by ensemble learning possessed sufficient accuracy in carbon price forecasting in China compared with the single LSTM model as well as other conventional artificial neural network models. Furthermore, according to the scope of its application, the innovative model exhibited strong stability and universality.

Refurbishing ANN with the aid of adaptive crow search optimisation for effectively diagnosing railway wheel condition

The research intends to diagnosis the railway wheel condition with the aid of artificial neural network (ANN). In diagnosing, ANN has been proven its convenience over manual computation in various applications. The research utilises optimisation techniques for identifying appropriate hidden layers and their associated neurons to enhance the performance of ANN techniques. This configuration process includes optimisation techniques like evolutionary algorithm (EA), genetic algorithm (GA), particle swarm optimisation (PSO), and crow search optimisation (CSO). Also, this research includes modified and improved conventional strategy in CSO, which urge incorporating novel strategy called adaptive crow search optimisation (ACSO) to enhance the performance. The proposed strategy unveils proficient performance of 99.2% accuracy, which is 1.7% greater than the conventional ANN model and an average of 0.9% greater than other contest techniques consider for configuration. The credibility of the ANN model gets increased while employs the optimisation techniques in diagnosing the railway wheel condition.

Refurbishing ANN with the aid of adaptive crow search optimisation for effectively diagnosing railway wheel condition

The research intends to diagnosis the railway wheel condition with the aid of artificial neural network (ANN). In diagnosing, ANN has been proven its convenience over manual computation in various applications. The research utilises optimisation techniques for identifying appropriate hidden layers and their associated neurons to enhance the performance of ANN techniques. This configuration process includes optimisation techniques like evolutionary algorithm (EA), genetic algorithm (GA), particle swarm optimisation (PSO), and crow search optimisation (CSO). Also, this research includes modified and improved conventional strategy in CSO, which urge incorporating novel strategy called adaptive crow search optimisation (ACSO) to enhance the performance. The proposed strategy unveils proficient performance of 99.2% accuracy, which is 1.7% greater than the conventional ANN model and an average of 0.9% greater than other contest techniques consider for configuration. The credibility of the ANN model gets increased while employs the optimisation techniques in diagnosing the railway wheel condition.

Machine Learning-Enabled Competitive Grain Growth Behavior Study in Directed Energy Deposition Fabricated Ti6Al4V

Directed energy deposition (DED) of titanium alloys is a rapidly developing technology because of its flexibility in freeform fabrication and remanufacturing. However, the uncertainties of a solidification microstructure during the deposition process are limiting its development. This article presents an artificial neural network (ANN) to investigate the relation between the grain boundary tilt angle and three causative factors, namely the thermal gradient, crystal orientation and Marangoni effect. A series of wire feedstock DED, optical microscope and electron backscatter diffraction experiments was carried out under the Taguchi experimental design to gather the training and testing data for the ANN. Compared with conventional microstructure simulation methods, the strategy and ANN model developed in this work were demonstrated to be a valid way to describe the competitive grain growth behavior in DED fabricated Ti6Al4V. They can be deployed to achieve a quantitative microstructure simulation and extended to other polycrystal material solidification processes.

Prediction of suspended sediment loading by means of hybrid artificial intelligence approaches

The main aim of the research is to use the artificial neural network (ANN) model with the artificial bee colony (ABC) and teaching–learning-based optimization (TLBO) algorithms for estimating suspended sediment loading. The stream flow per month and SSL data obtained from two stations, Inanli and Altinsu, in Coruh River Basin of Turkey were taken as precedent. While stream flow and previous SSL were used as input parameters, only SSL data were used as output parameters for all models. The successes of the ANN-ABC and ANN-TLBO models that were developed in the research were contrasted with performance of conventional ANN model trained by BP (back-propagation). In addition to these algorithms, linear regression method was applied and compared with others. Root-mean-square and mean absolute error were used as success assessing criteria for model accuracy. When the overall situation is evaluated according to errors of the testing datasets, it was found that ANN-ABC and ANN-TLBO algorithms are more outstanding than conventional ANN model trained by BP.

Real-time Intraday Traffic Volume Forecasting – A Hybrid Application Using Singular Spectrum Analysis and Artificial Neural Networks

The present paper provides a comparative evaluation of hybrid Singular Spectrum Analysis (SSA) and Artificial Neural Networks (ANN) against conventional ANN, applied on real time intraday traffic volume forecasting. The main research objective was to assess the applicability and functionality of intraday traffic volume forecasting, based on toll station measurements. The proposed methodology was implemented and evaluated upon a custom developed forecasting software toolbox, based on the software Mathworks MatLab, by using real data from Iasmos-Greece toll station. Experimental results demonstrated a superior ex post forecasting accuracy of the proposed hybrid forecasting methodology against conventional ANN, when compared to performance of usual statistical criteria (Mean Absolute Error, Mean Squared Error, Root Mean Squared Error, Coefficient of Determination R2, Theil's inequality coefficient). The obtained results revealed that the hybrid model could advance forecasting accuracy of a conventional ANN model in intraday traffic volume forecasting, while embedding hybrid forecasting algorithm in an Intelligent Transport System could provide an advanced decision support module for transportation system maintenance, operation and management.

Road traffic forecasting — A hybrid approach combining Artificial Neural Network with Singular Spectrum Analysis

The paper presents a comparison of a hybrid methodology which combines Singular Spectrum Analysis (SSA) with Artificial Neural Networks (ANN) against conventional ANN, applied on time series analysis and forecasting of road traffic volume. The main research objective was to develop a short-term forecast of daily traffic volume at toll stations across the Greek National Highway Network. The proposed methodology was implemented and evaluated upon a custom developed integrated forecasting software, based on the Mathworks MatLab platform. Experimental outcomes on daily data, from specific toll stations, demonstrate a superior prediction accuracy of hybrid SSA–ANN forecasting methodology against conventional ANN, when compared to performances of statistical criteria such as Root Mean Squared Error (RMSE), Mean Absolute Error (MAE) and Coefficient of Determination (R2). A comparison of results revealed that the SSA–ANN hybrid model could improve the forecasting accuracy of the conventional ANN model in the case of daily traffic volume forecasting. An Intelligent Transport System with embedded hybrid SSA–ANN forecasting algorithm could manage and analyze big data traffic volume time series in real time, providing an advanced decision support system for transportation system management and maintenance, while it would enable proactive decisions to mitigate the economic and environmental impacts of traffic congestion.

Electric Vehicle Charging Load Forecasting: A Comparative Study of Deep Learning Approaches

Load forecasting is one of the major challenges of power system operation and is crucial to the effective scheduling for economic dispatch at multiple time scales. Numerous load forecasting methods have been proposed for household and commercial demand, as well as for loads at various nodes in a power grid. However, compared with conventional loads, the uncoordinated charging of the large penetration of plug-in electric vehicles is different in terms of periodicity and fluctuation, which renders current load forecasting techniques ineffective. Deep learning methods, empowered by unprecedented learning ability from extensive data, provide novel approaches for solving challenging forecasting tasks. This research proposes a comparative study of deep learning approaches to forecast the super-short-term stochastic charging load of plug-in electric vehicles. Several popular and novel deep-learning based methods have been utilized in establishing the forecasting models using minute-level real-world data of a plug-in electric vehicle charging station to compare the forecasting performance. Numerical results of twelve cases on various time steps show that deep learning methods obtain high accuracy in super-short-term plug-in electric load forecasting. Among the various deep learning approaches, the long-short-term memory method performs the best by reducing over 30% forecasting error compared with the conventional artificial neural network model.

Feasibility of a novel predictive technique based on artificial neural network optimized with particle swarm optimization estimating pullout bearing capacity of helical piles

This study aimed to assess particle swarm optimization (PSO) enhanced with an artificial neural network (ANN) for the prediction of the Pul (pullout resistance of helical piles in pure cohesionless soils). To make data sets of training and testing as to the expanded predictive models, 36 laboratory experiments were performed. The database involved 27 experiments for the training data sets (e.g., 80% of the whole database) and 9 experiments for the testing data sets (e.g., a range of 20% of the whole database). In addition, variables of the ANN algorithm (e.g., neurons in each hidden layer) and PSO algorithm, such as population size, were optimized utilizing a series of trial-and-error processes. The input parameters that were used in the analysis include density, embedment ratio, shaft base diameter, and shaft diameter, where the output was taken and the laboratory Pul determined. The selection of these parameters is because the Pul is affected by the geologic conditions, helical pile’s configuration, and penetration depth. After performing the sensitivity analysis, the optimized architecture, 4 × 8 × 1 is specified for the structure of ANN. As a result, both models, ANN and PSO–ANN, presented excellent prediction performance. Note that the PSO–ANN method can provide a more accurate network outputs in predicting measured values compared to the conventional ANN model. Based on R2, RMSE and VAF values of, 0.999, 0.0350 and 99.9978, as well as, 0.999, 0.0379 and 99.998, were determined for the normalized training and testing data sets in the optimized PSO–ANN network, respectively. However, in the ANN model with four neurons in each hidden layer, the R2 as well as RMSE for the non-normalized training and testing data sets were (0.99985 and 7.99007) and (0.99990 and 11.97427), respectively, which confirms the superiority of the proposed PSO–ANN model in predicting the Pul.

A wavelet neural network approach to predict daily river discharge using meteorological data

This paper reports some part of modelling and data analysis work carried out within the frame of a comprehensive project on the web-based development of watershed information system. This work basically aims to present the daily discharge predictions from the actual discharge along with the meteorological data using a wavelet neural network approach, which combines two methods: discrete wavelet transform and artificial neural networks. The wavelet–artificial neural network model developed provides a good fit with the measured data, in particular with zero discharge in the summer months and also with the peaks and sudden changes in discharge on the test data collected throughout the year. The results indicate that the wavelet–artificial neural network model based predictions are distinctly superior to that of conventional artificial neural network model that corresponds up to an 80% reduction in the mean-squared error between the artificial neural network model and measured data.