The process involved in the local scour below pipelines is so complex that it makes it difficult to establish a general empirical model to provide accurate estimation for scour. This paper describes the use of artificial neural networks (ANN) to estimate the pipeline scour depth. The data sets of laboratory measurements were collected from published works and used to train the network or evolve the program. The developed networks were validated by using the observations that were not involved in training. The performance of ANN was found to be more effective when compared with the results of regression equations in predicting the scour depth around pipelines.
The removal of Reactive Black 5 dye in an aqueous solution by electrocoagulation (EC) as well as addition of flocculant was investigated. The effect of operational parameters, i.e. current density, treatment time, solution conductivity and polymer dosage, was investigated. Two models, namely the artificial neural network (ANN) and the response surface method (RSM), were used to model the effect of independent variables on percentage of dye removal. The findings of this work showed that current density, treatment time and dosage of polymer had the most significant effect on percentage of dye removal (p<0.001). In addition, interaction between time and current density, time and dosage of polymer, current density and dosage of polymer also significantly affected the percentage of dye removal (p=0.034, 0.003 and 0.024, respectively). It was shown that both the ANN and RSM models were able to predict well the experimental results (R(2)>0.8).
The main challenge in the lead removal simulation is the behaviour of non-linearity relationships between the process parameters. The conventional modelling technique usually deals with this problem by a linear method. The substitute modelling technique is an artificial neural network (ANN) system, and it is selected to reflect the non-linearity in the interaction among the variables in the function. Herein, synthesized deep eutectic solvents were used as a functionalized agent with carbon nanotubes as adsorbents of Pb2+. Different parameters were used in the adsorption study including pH (2.7 to 7), adsorbent dosage (5 to 20 mg), contact time (3 to 900 min) and Pb2+ initial concentration (3 to 60 mg/l). The number of experimental trials to feed and train the system was 158 runs conveyed in laboratory scale. Two ANN types were designed in this work, the feed-forward back-propagation and layer recurrent; both methods are compared based on their predictive proficiency in terms of the mean square error (MSE), root mean square error, relative root mean square error, mean absolute percentage error and determination coefficient (R2) based on the testing dataset. The ANN model of lead removal was subjected to accuracy determination and the results showed R2 of 0.9956 with MSE of 1.66 × 10-4. The maximum relative error is 14.93% for the feed-forward back-propagation neural network model.
Hyperparameter tuning is an important process to maximize the performance of any neural network model. This present study proposed the factorial design of experiment for screening and response surface methodology to optimize the hyperparameter of two artificial neural network algorithms. Feed-forward neural network (FFNN) and radial basis function neural network (RBFNN) are applied to predict the permeate flux of palm oil mill effluent. Permeate pump and transmembrane pressure of the submerge membrane bioreactor system are the input variables. Six hyperparameters of the FFNN model including four numerical factors (neuron numbers, learning rate, momentum, and epoch numbers) and two categorical factors (training and activation function) are used in hyperparameter optimization. RBFNN includes two numerical factors such as a number of neurons and spreads. The conventional method (one-variable-at-a-time) is compared in terms of optimization processing time and the accuracy of the model. The result indicates that the optimal hyperparameters obtained by the proposed approach produce good accuracy with a smaller generalization error. The simulation results show an improvement of more than 65% of training performance, with less repetition and processing time. This proposed methodology can be utilized for any type of neural network application to find the optimum levels of different parameters.
Groundwater, the world's most abundant source of freshwater, is rapidly depleting in many regions due to a variety of factors. Accurate forecasting of groundwater level (GWL) is essential for effective management of this vital resource, but it remains a complex and challenging task. In recent years, there has been a notable increase in the use of machine learning (ML) techniques to model GWL, with many studies reporting exceptional results. In this paper, we present a comprehensive review of 142 relevant articles indexed by the Web of Science from 2017 to 2023, focusing on key ML models, including artificial neural networks (ANN), adaptive neuro-fuzzy inference systems (ANFIS), support vector regression (SVR), evolutionary computing (EC), deep learning (DL), ensemble learning (EN), and hybrid-modeling (HM). We also discussed key modeling concepts such as dataset size, data splitting, input variable selection, forecasting time-step, performance metrics (PM), study zones, and aquifers, highlighting best practices for optimal GWL forecasting with ML. This review provides valuable insights and recommendations for researchers and water management agencies working in the field of groundwater management and hydrology.
This study investigated relationships of a water quality index (WQI) with multiple water quality variables (WQVs), explored variability in water quality over time and space, and established linear and non-linear models predictive of WQI from raw WQVs. Data were processed using Spearman's rank correlation analysis, multiple linear regression, and artificial neural network modeling. Correlation analysis indicated that from a temporal perspective, the WQI, temperature, and zinc, arsenic, chemical oxygen demand, sodium, and dissolved oxygen concentrations increased, whereas turbidity and suspended solids, total solids, nitrate nitrogen (NO3-N), and biochemical oxygen demand concentrations decreased with year. From a spatial perspective, an increase with distance of the sampling station from the headwater was exhibited by 10 WQVs: magnesium, calcium, dissolved solids, electrical conductivity, temperature, NO3-N, arsenic, chloride, potassium, and sodium. At the same time, the WQI; Escherichia coli bacteria counts; and suspended solids, total solids, and dissolved oxygen concentrations decreased with distance from the headwater. Lastly, regression and artificial neural network models with high prediction powers (81.2% and 91.4%, respectively) were developed and are discussed.
This paper describes the design of an artificial neural network (ANN) model to predict the water quality index (WQI) using land use areas as predictors. Ten-year records of land use statistics and water quality data for Kinta River (Malaysia) were employed in the modeling process. The most accurate WQI predictions were obtained with the network architecture 7-23-1; the back propagation training algorithm; and a learning rate of 0.02. The WQI forecasts of this model had significant (p < 0.01), positive, very high correlation (ρs = 0.882) with the measured WQI values. Sensitivity analysis revealed that the relative importance of the land use classes to WQI predictions followed the order: mining > rubber > forest > logging > urban areas > agriculture > oil palm. These findings show that the ANNs are highly reliable means of relating water quality to land use, thus integrating land use development with river water quality management.
The SARS-CoV-2 virus is responsible for the rapid global spread of the COVID-19 disease. As a result, it is critical to understand and collect primary data on the virus, infection epidemiology, and treatment. Despite the speed with which the virus was detected, studies of its cell biology and architecture at the ultrastructural level are still in their infancy. Therefore, we investigated and analyzed the viral morphometry of SARS-CoV-2 to extract important key points of the virus's characteristics. Then, we proposed a prediction model to identify the real virus levels based on the optimization of a full recurrent neural network (RNN) using transmission electron microscopy (TEM) images. Consequently, identification of virus levels depends on the size of the morphometry of the area (width, height, circularity, roundness, aspect ratio, and solidity). The results of our model were an error score of training network performance 3.216 × 10-11 at 639 epoch, regression of -1.6 × 10-9, momentum gain (Mu) 1 × 10-9, and gradient value of 9.6852 × 10-8, which represent a network with a high ability to predict virus levels. The fully automated system enables virologists to take a high-accuracy approach to virus diagnosis, prevention of mutations, and life cycle and improvement of diagnostic reagents and drugs, adding a point of view to the advancement of medical virology.
The most important targets for vaccine development are the proteins that are highly expressed by the microorganisms during infection in-vivo. A number of Mycobacterium tuberculosis (Mtb) proteins are also reported to be expressed in-vivo at different phases of infection. In the present study, we analyzed multiple published databases of gene expression profiles of Mtb in-vivo at different phases of infection in animals and humans and selected 38 proteins that are highly expressed in the active, latent and reactivation phases. We predicted T- and B-cell epitopes from the selected proteins using HLAPred for T-cell epitope prediction and BCEPred combined with ABCPred for B-cell epitope prediction. For each selected proteins, regions containing both T- and B-cell epitopes were identified which might be considered as important candidates for vaccine design against tuberculosis.
Time series modelling and forecasting plays an important role in various domains. The objective of this paper is to construct a simple average ensemble method to forecast the number of cases for infectious diseases like dengue and typhoid and compare it by applying models for forecasting. In this paper we have also evaluated the correlation between the number of typhoid and dengue cases with the ecological variables. The monthly data of dengue and typhoid cases from 2014 to 2017 were taken from integrated diseases surveillance programme, Government of India. This data was analysed by three models namely support vector regression, neural network and linear regression. The proposed simple average ensemble model was constructed by ensemble of three applied regression models i.e. SVR, NN and LR. We combine the regression models based upon the error metrics such as Mean Square Error, Root Mean Square Error and Mean Absolute Error. It was found that proposed ensemble method performed better in terms of forecast measures. The finding demonstrates that the proposed model outperforms as compared to already available applied models on the basis of forecast accuracy.
Computed tomography (CT) is used in a wide range of medical imaging diagnoses. However, the reconstruction of CT images from raw projection data is inherently complex and is subject to artifacts and noise, which compromises image quality and accuracy. In order to address these challenges, deep learning developments have the potential to improve the reconstruction of computed tomography images. In this regard, our research aim is to determine the techniques that are used for 3D deep learning in CT reconstruction and to identify the training and validation datasets that are accessible. This research was performed on five databases. After a careful assessment of each record based on the objective and scope of the study, we selected 60 research articles for this review. This systematic literature review revealed that convolutional neural networks (CNNs), 3D convolutional neural networks (3D CNNs), and deep learning reconstruction (DLR) were the most suitable deep learning algorithms for CT reconstruction. Additionally, two major datasets appropriate for training and developing deep learning systems were identified: 2016 NIH-AAPM-Mayo and MSCT. These datasets are important resources for the creation and assessment of CT reconstruction models. According to the results, 3D deep learning may increase the effectiveness of CT image reconstruction, boost image quality, and lower radiation exposure. By using these deep learning approaches, CT image reconstruction may be made more precise and effective, improving patient outcomes, diagnostic accuracy, and healthcare system productivity.
The artificial neural network (ANN) modeling of m-cresol photodegradation was carried out for determination of the optimum and importance values of the effective variables to achieve the maximum efficiency. The photodegradation was carried out in the suspension of synthesized manganese doped ZnO nanoparticles under visible-light irradiation. The input considered effective variables of the photodegradation were irradiation time, pH, photocatalyst amount, and concentration of m-cresol while the efficiency was the only response as output. The performed experiments were designed into three data sets such as training, testing, and validation that were randomly splitted by the software's option. To obtain the optimum topologies, ANN was trained by quick propagation (QP), Incremental Back Propagation (IBP), Batch Back Propagation (BBP), and Levenberg-Marquardt (LM) algorithms for testing data set. The topologies were determined by the indicator of minimized root mean squared error (RMSE) for each algorithm. According to the indicator, the QP-4-8-1, IBP-4-15-1, BBP-4-6-1, and LM-4-10-1 were selected as the optimized topologies. Among the topologies, QP-4-8-1 has presented the minimum RMSE and absolute average deviation as well as maximum R-squared. Therefore, QP-4-8-1 was selected as final model for validation test and navigation of the process. The model was used for determination of the optimum values of the effective variables by a few three-dimensional plots. The optimum points of the variables were confirmed by further validated experiments. Moreover, the model predicted the relative importance of the variables which showed none of them was neglectable in this work.
The stability of clusters is a serious issue in mobile ad hoc networks. Low stability of clusters may lead to rapid failure of clusters, high energy consumption for reclustering, and decrease in the overall network stability in mobile ad hoc network. In order to improve the stability of clusters, weight-based clustering algorithms are utilized. However, these algorithms only use limited features of the nodes. Thus, they decrease the weight accuracy in determining node's competency and lead to incorrect selection of cluster heads. A new weight-based algorithm presented in this paper not only determines node's weight using its own features, but also considers the direct effect of feature of adjacent nodes. It determines the weight of virtual links between nodes and the effect of the weights on determining node's final weight. By using this strategy, the highest weight is assigned to the best choices for being the cluster heads and the accuracy of nodes selection increases. The performance of new algorithm is analyzed by using computer simulation. The results show that produced clusters have longer lifetime and higher stability. Mathematical simulation shows that this algorithm has high availability in case of failure.
Radial basis function neural networks are used in a variety of applications such as pattern recognition, nonlinear identification, control and time series prediction. In this paper, the learning algorithm of radial basis function neural networks is analyzed in a feedback structure. The robustness of the learning algorithm is discussed in the presence of uncertainties that might be due to noisy perturbations at the input or to modeling mismatch. An intelligent adaptation rule is developed for the learning rate of RBFNN which gives faster convergence via an estimate of error energy while giving guarantee to the l 2 stability governed by the upper bounding via small gain theorem. Simulation results are presented to support our theoretical development.
One of the main difficulties in designing online signature verification (OSV) system is to find the most distinctive features with high discriminating capabilities for the verification, particularly, with regard to the high variability which is inherent in genuine handwritten signatures, coupled with the possibility of skilled forgeries having close resemblance to the original counterparts. In this paper, we proposed a systematic approach to online signature verification through the use of multilayer perceptron (MLP) on a subset of principal component analysis (PCA) features. The proposed approach illustrates a feature selection technique on the usually discarded information from PCA computation, which can be significant in attaining reduced error rates. The experiment is performed using 4000 signature samples from SIGMA database, which yielded a false acceptance rate (FAR) of 7.4% and a false rejection rate (FRR) of 6.4%.
An artificial neural network (ANN) and affinity propagation (AP) algorithm based user categorization technique is presented. The proposed algorithm is designed for closed access femtocell network. ANN is used for user classification process and AP algorithm is used to optimize the ANN training process. AP selects the best possible training samples for faster ANN training cycle. The users are distinguished by using the difference of received signal strength in a multielement femtocell device. A previously developed directive microstrip antenna is used to configure the femtocell device. Simulation results show that, for a particular house pattern, the categorization technique without AP algorithm takes 5 indoor users and 10 outdoor users to attain an error-free operation. While integrating AP algorithm with ANN, the system takes 60% less training samples reducing the training time up to 50%. This procedure makes the femtocell more effective for closed access operation.
Flyrock is one of the major disturbances induced by blasting which may cause severe damage to nearby structures. This phenomenon has to be precisely predicted and subsequently controlled through the changing in the blast design to minimize potential risk of blasting. The scope of this study is to predict flyrock induced by blasting through a novel approach based on the combination of imperialist competitive algorithm (ICA) and artificial neural network (ANN). For this purpose, the parameters of 113 blasting operations were accurately recorded and flyrock distances were measured for each operation. By applying the sensitivity analysis, maximum charge per delay and powder factor were determined as the most influential parameters on flyrock. In the light of this analysis, two new empirical predictors were developed to predict flyrock distance. For a comparison purpose, a predeveloped backpropagation (BP) ANN was developed and the results were compared with those of the proposed ICA-ANN model and empirical predictors. The results clearly showed the superiority of the proposed ICA-ANN model in comparison with the proposed BP-ANN model and empirical approaches.
Research on psychophysics, neurophysiology, and functional imaging shows particular representation of biological movements which contains two pathways. The visual perception of biological movements formed through the visual system called dorsal and ventral processing streams. Ventral processing stream is associated with the form information extraction; on the other hand, dorsal processing stream provides motion information. Active basic model (ABM) as hierarchical representation of the human object had revealed novelty in form pathway due to applying Gabor based supervised object recognition method. It creates more biological plausibility along with similarity with original model. Fuzzy inference system is used for motion pattern information in motion pathway creating more robustness in recognition process. Besides, interaction of these paths is intriguing and many studies in various fields considered it. Here, the interaction of the pathways to get more appropriated results has been investigated. Extreme learning machine (ELM) has been implied for classification unit of this model, due to having the main properties of artificial neural networks, but crosses from the difficulty of training time substantially diminished in it. Here, there will be a comparison between two different configurations, interactions using synergetic neural network and ELM, in terms of accuracy and compatibility.
Following the study on computational neuroscience through functional magnetic resonance imaging claimed that human action recognition in the brain of mammalian pursues two separated streams, that is, dorsal and ventral streams. It follows up by two pathways in the bioinspired model, which are specialized for motion and form information analysis (Giese and Poggio 2003). Active basis model is used to form information which is different from orientations and scales of Gabor wavelets to form a dictionary regarding object recognition (human). Also biologically movement optic-flow patterns utilized. As motion information guides share sketch algorithm in form pathway for adjustment plus it helps to prevent wrong recognition. A synergetic neural network is utilized to generate prototype templates, representing general characteristic form of every class. Having predefined templates, classifying performs based on multitemplate matching. As every human action has one action prototype, there are some overlapping and consistency among these templates. Using fuzzy optical flow division scoring can prevent motivation for misrecognition. We successfully apply proposed model on the human action video obtained from KTH human action database. Proposed approach follows the interaction between dorsal and ventral processing streams in the original model of the biological movement recognition. The attained results indicate promising outcome and improvement in robustness using proposed approach.
Landslide is one of the natural disasters that occur in Malaysia. Topographic factors such as elevation, slope angle, slope aspect, general curvature, plan curvature, and profile curvature are considered as the main causes of landslides. In order to determine the dominant topographic factors in landslide mapping analysis, a study was conducted and presented in this paper. There are three main stages involved in this study. The first stage is the extraction of extra topographic factors. Previous landslide studies had identified mainly six topographic factors. Seven new additional factors have been proposed in this study. They are longitude curvature, tangential curvature, cross section curvature, surface area, diagonal line length, surface roughness, and rugosity. The second stage is the specification of the weight of each factor using two methods. The methods are multilayer perceptron (MLP) network classification accuracy and Zhou's algorithm. At the third stage, the factors with higher weights were used to improve the MLP performance. Out of the thirteen factors, eight factors were considered as important factors, which are surface area, longitude curvature, diagonal length, slope angle, elevation, slope aspect, rugosity, and profile curvature. The classification accuracy of multilayer perceptron neural network has increased by 3% after the elimination of five less important factors.