Artificial Neural Network Parameters Research Articles

Electroelastic wave dispersion in the rotary piezoelectric NEMS sensors/actuators via nonlocal strain gradient theory

This article introduces a computational means for investigating the electroelastic nonlinear wave dispersion traits of the nano-dimension sandwich pipe, which is composed of a core formed of a bi-directional functionally graded (Bi-FG) material, together with a piezoelectric sensor/actuator. A combination of Hamilton’s principle, first-order shear deformation, along with Von-Karman nonlinearity, is used for modeling and obtaining the nonlinear governing equations of the nano-sized sandwich pipe connected to a piezoelectric part. The nonlinear governing equations to obtain the nonlinear phase velocity of the current system are determined using a combination of analytical and multiple scales approaches. Due to some computational cost for choosing the precise values of both the nonlocality factor and length scale of the nanopipe in the laboratory, for the first time in this research, with the aid of COMSOL multi-physics finite element simulation, the results are verified, and new outcomes for obtaining the exact functions for nonlocal and length scale factors is presented. In addition, an artificial neural network (ANN) is utilized in this study for the prediction of the results. The mathematical and finite element results were used to train the ANN. A newly presented optimization algorithm is exploited for the first time for optimizing the ANN parameters concluding higher accuracy of the ANN predictions. Consequently, to explore the influences of the location of the piezoelectric patch, nonlocality and length scale factors, and applied voltage parameter on the phase velocity characteristics of the nano-dimension sandwich pipe made of a Bi-FG core and electrically patch, an effort is performed. As an applicable result that can be useful in the related nano-industries, the current work presents exact nonlocal and length scale functions for different conditions.

Artificial neural networks to solve dynamic programming problems: A bias-corrected Monte Carlo operator

Artificial Neural Networks (ANNs) are powerful tools that can solve dynamic programming problems arising in economics. In this context, estimating ANN parameters involves minimizing a loss function based on the model's stochastic functional equations. In general, the expectations appearing in the loss function admit no closed-form solution, so numerical approximation techniques must be used. In this paper, I analyze a bias-corrected Monte Carlo operator (bc-MC) that approximates expectations by Monte Carlo. I show that the bc-MC operator is a generalization of the all-in-one expectation operator, already proposed in the literature. I demonstrate that, under some conditions on the primitives of the economic model, the bc-MC operator is the unbiased estimator of the loss function with the minimum variance. I propose a method to optimally set the hyperparameters defining the bc-MC operator, and illustrate the findings numerically with well-known economic models. I also demonstrate that the bc-MC operator can scale to high-dimensional models. With just approximately a minute of computing time, I find a global solution to an economic model with a kink in the decision function and more than 100 dimensions.

Performance investigation of an active free-piston Stirling engine using artificial neural network and firefly optimization algorithm

The aim of this study is to explore the characteristics of an active Free-Piston Stirling Engine (AFPSE) through the use of machine learning methods. Due to the time-intensive nature of extracting simulation results from complex thermal equations, an Artificial Neural Network (ANN) is utilized to expedite the process. To construct a nonlinear model, 5000 samples are extracted from simulation results. Input parameters included in the model are the hot and cold source temperatures, the voltage given to the DC motor, spring stiffness, and the mass of the power piston, while output parameters are the amplitude and frequency of power piston displacement. The proposed ANN model structure comprises two hidden layer with 10 and 20 neurons, respectively, indicating the applicability of the ANN model in estimating significant parameters of AFPSE in a shorter amount of time. The firefly optimization algorithm is utilized to determine the unknown input parameters of ANN and maximize the output power. Results indicate that a maximum output power of 23.07 W can be attained by applying 8.5 V voltage on the DC motor. This study highlights the potential of machine learning techniques to explore the primary features of AFPSE.

Abstract 2388: Artificial neural network based ensemble models for single-arm glioblastoma trials: A new historical control adjustment method

Abstract Background: Despite a long history of poor decision making leading to repeated failed phase 3 trials, phase 2 single-arm studies continue to be common in glioblastoma (GBM). With the drawback of inflated false positive rate in current adjustment method for historical control data as concurrent controls, the new statistical methods and validation approach will be needed for adequate covariate adjustment in the GBM single-arm trial data. Methods: The systematic review was performed to extract the summary-level external data of survival outcomes (mean progression-free survival, mPFS, and PFS at 6 months, PFS6) and prognostic factors (age, gender, extent of resection, KPS, methylation status, and treatment history) from published randomized clinical trials for the standard of care (SOC) treatment in GBM. Four models of the standard, bootstrap aggregating, random subspaces, and random patches models were developed to construct a powerful predictive tool by comprising a series of connections producing survival outputs as a function of prognostic inputs using (1) artificial neural network (ANN) method and (2) linear method (Fig1). The root mean square errors (RMSEs) were calculated to evaluate the model performance using the five-fold cross-validation approach with the effects of ensemble size. The predictive survival outcomes among prognostic factors were calculated to evaluate the relative importance of factors. Results: We identified 19 Phase 2 and 3 clinical trials in glioblastoma and two survival outcomes and seven prognostic factors (Table 1). ANN models have less prediction error and therefore better performance on the test set than linear models. Presumably, the relationships in the data are highly nonlinear, and thus linear models cannot capture these relationships (Table 2). Bagging models typically outperform their standard counterparts for both ANNs and linear models. Ensemble methods can capture many trends within the data by manipulation of the training set and are therefore less prone to biases of individual models exacerbated by the small sample size. The previous treatment history and methylation status were the top two influential prognostic factors for both mPFS and PFS6, followed by the extent of resection and mean age (Fig2). With the examination of the ANN parameters of sample size, learning rate, training hyperparameters, it could be observed that there is no clear change in error when increasing sample size beyond 10 (Fig3). Conclusions: High failure rate of phase 3 glioblastoma trials emphasizes the need for greater reliability of earlier studies in phase 2 single-arm trials. The proposed statistical and epidemiologic approach based on the ensemble-based ANN models will be an effective tool to lead to better decision with phase 2 single-arm trials, which may give better chance to appropriately advance to phase 3 trials with higher predictive power. Citation Format: Wonsuk Yoo, Tortsen Ullrich, Nader Sanai. Artificial neural network based ensemble models for single-arm glioblastoma trials: A new historical control adjustment method [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2024; Part 1 (Regular Abstracts); 2024 Apr 5-10; San Diego, CA. Philadelphia (PA): AACR; Cancer Res 2024;84(6_Suppl):Abstract nr 2388.

Optimasi Parameter Artificial Neural Network (ANN) Menggunakan Particle Swarm Optimization (PSO) Untuk Pengkategorian Nasabah Bank

Artificial Neural Network (ANN), also known as Jaringan Saraf Tiruan, is one of the methods commonly used for pattern recognition, classification, forecasting, and regression, depending on the problem or data used. While the results obtained are generally good, there are often issues with determining the initial parameters as the initial weights, which can lead to non-convergence of results. This is why a method is needed to optimize the ANN parameters to achieve better outcomes. Particle Swarm Optimization (PSO) was chosen as the method to optimize the ANN parameters (PSO-ANN). The best parameter values for PSO were predefined, with w (inertia weight) set to 0.8 and c1 and c2 (acceleration coefficients) set to 1.5. Subsequently, PSO-ANN was trained using a bank customer dataset to determine the categories of customers with credit problems or not. The results were compared with using ANN without parameter optimization. The obtained results showed an Accuracy rate of 82.6%, Precision of 91.1%, and Recall of 37.1%. This represents an improvement compared to the results of ANN without parameter optimization, which had an Accuracy rate of 80.1%, Precision of 89.5%, and Recall of 32.4%.

Study on tool wear and optimization of machining parameters in laser-assisted fast tool servo machining of glass-ceramic

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.

Advancing Concrete Mix Proportion through Hybrid Intelligence: A Multi-Objective Optimization Approach.

Concrete mixture design has been a key focus in concrete research. This study presents a new method for concrete mixture design by combining artificial neural networks (ANN), genetic algorithms (GA), and Scipy libraries for hybrid intelligent modeling. This method enables the prediction of concrete mechanical properties and the optimization of mix proportions with single or multi-objective goals. The GA is used to optimize the structure and weight parameters of ANN to improve prediction accuracy and generalization ability (R2 > 0.95, RMSE and MAE < 10). Then, the Scipy library combined with GA-ANN is used for the multi-objective optimization of concrete mix proportions to balance the compressive strength and costs of concrete. Moreover, an AI-based concrete mix proportion design system is developed, utilizing a user-friendly GUI to meet specific strength requirements and adapt to practical needs. This system enhances optimization design capabilities and sets the stage for future advancements. Overall, this study focuses on optimizing concrete mixture design using hybrid intelligent modeling and multi-objective optimization, which contributes to providing a novel and practical solution for improving the efficiency and accuracy of concrete mixture design in the construction industry.

Experimental investigation on cutting force and machining parameters optimization in in-situ laser-assisted machining of glass–ceramic

Glass-ceramic is a typical hard and brittle material that is difficult to use for ultra precision machining. In order to improve the machining quality of glass–ceramic, orthogonal experiments on in-situ laser-assisted machining (LAM) of glass–ceramic were carried out with cutting force as the characteristic value. The maximum reduction in the resultant force of cutting force in in-situ LAM was 56.13%. The contribution order of each machining parameter to reducing cutting force is: spindle speed > laser power > feed speed > cutting depth. Response surface methodology (RSM) was used to conduct experiments and establish a regression model for predicting cutting force. The influence law of four machining parameters on cutting force was studied through three-dimensional response surface. The optimal combination of machining parameters to minimize cutting force obtained through RSM optimization is: spindle speed 400.51 rpm, feed speed 0.03 mm/rev, cutting depth 18.91 μm, laser power 74.78 W. The RSM experiments were trained, predicted, and optimized using artificial neural network (ANN) and genetic algorithms (GA). The fitting values of the ANN model are highly consistent with the experimental values of RSM. The optimal machining parameter combination obtained through GA optimization is: spindle speed 400 rpm, feed speed 0.01 mm/rev, cutting depth 20 μm, laser power 75 W. Experiments were conducted using the optimal machining parameters of RSM and ANN respectively, and the results showed that ANN is more ideal for optimizing machining parameters and predicting minimum cutting force. This study provides guidance and reference for glass–ceramic in-situ LAM and parameter optimization method for cutting force.

A deep learning approach to predict and optimise energy in fish processing industries

The fish processing sector is experiencing increased pressure to reduce its energy consumption and carbon footprint as a response to (a) an increasingly stringent energy regulatory landscape, (b) rising fuel prices, and (c) the incentives to improve social and environmental performance. In this paper, a standalone forecasting computational platform is developed to optimise energy usage and reduce energy costs. This short-term forecasting model is achieved using an artificial neural network (ANN) to predict power and temperature at thirty-minute intervals in two cold rooms of a fish processing plant. The proposed ANN function is optimised by genetic algorithms (GA) with simulated annealing algorithms (SA) to model the relationships between future temperature and power and the system variables affecting them. To assess the accuracy of the proposed method, extensive experiments were conducted using real-world data sets. The results of the experiments indicate that the proposed ANN model performs with higher accuracy than (a) the long short-term memory (LSTM) as an artificial recurrent neural network (RNN) architecture, (b) peephole-LSTM, and (c) the gated recurrent unit (GRU). This paper finds that using GA & SA algorithms; ANN parameters can be optimised. The RMSE obtained by the ANN compared with the second-ranked method GRU was consequently 16% and 4% less for the predicted temperature and power. The results in one particular site demonstrate energy cost savings in the range of 15%–18% after applying the forecast-optimiser approach. The proposed prediction model is used in a fish processing plant for energy management and is scalable to other sites.

Learning the random variables in Monte Carlo simulations with stochastic gradient descent: Machine learning for parametric PDEs and financial derivative pricing

AbstractIn financial engineering, prices of financial products are computed approximately many times each trading day with (slightly) different parameters in each calculation. In many financial models such prices can be approximated by means of Monte Carlo (MC) simulations. To obtain a good approximation the MC sample size usually needs to be considerably large resulting in a long computing time to obtain a single approximation. A natural deep learning approach to reduce the computation time when new prices need to be calculated as quickly as possible would be to train an artificial neural network (ANN) to learn the function which maps parameters of the model and of the financial product to the price of the financial product. However, empirically it turns out that this approach leads to approximations with unacceptably high errors, in particular when the error is measured in the ‐norm, and it seems that ANNs are not capable to closely approximate prices of financial products in dependence on the model and product parameters in real life applications. This is not entirely surprising given the high‐dimensional nature of the problem and the fact that it has recently been proved for a large class of algorithms, including the deep learning approach outlined above, that such methods are in general not capable to overcome the curse of dimensionality for such approximation problems in the ‐norm. In this article we introduce a new numerical approximation strategy for parametric approximation problems including the parametric financial pricing problems described above and we illustrate by means of several numerical experiments that the introduced approximation strategy achieves a very high accuracy for a variety of high‐dimensional parametric approximation problems, even in the ‐norm. A central aspect of the approximation strategy proposed in this article is to combine MC algorithms with machine learning techniques to, roughly speaking, learn the random variables (LRV) in MC simulations. In other words, we employ stochastic gradient descent (SGD) optimization methods not to train parameters of standard ANNs but instead to learn random variables appearing in MC approximations. In that sense, the proposed LRV strategy has strong links to Quasi‐Monte Carlo (QMC) methods as well as to the field of algorithm learning. Our numerical simulations strongly indicate that the LRV strategy might indeed be capable to overcome the curse of dimensionality in the ‐norm in several cases where the standard deep learning approach has been proven not to be able to do so. This is not a contradiction to the established lower bounds mentioned above because this new LRV strategy is outside of the class of algorithms for which lower bounds have been established in the scientific literature. The proposed LRV strategy is of general nature and not only restricted to the parametric financial pricing problems described above, but applicable to a large class of approximation problems. In this article we numerically test the LRV strategy in the case of the pricing of European call options in the Black‐Scholes model with one underlying asset, in the case of the pricing of European worst‐of basket put options in the Black‐Scholes model with three underlying assets, in the case of the pricing of European average put options in the Black‐Scholes model with three underlying assets and knock‐in barriers, as well as in the case of stochastic Lorentz equations. For these examples the LRV strategy produces highly convincing numerical results when compared with standard MC simulations, QMC simulations using Sobol sequences, SGD‐trained shallow ANNs, and SGD‐trained deep ANNs.

Hybrid ECBO–ANN Algorithm for Shear Strength of Partially Grouted Masonry Walls

In recent years, artificial neural network (ANN) has become one of the popular and effective machine learning models, having a unique ability to handle very complex problems and the potential to predict accurate results without a defined algorithmic solution. However, the ANN structure and parameters are usually chosen by experience.The behavior of Partially Grouted (PG) masonry shear walls is complex due to the inherent anisotropic properties of the masonry materials and the nonlinear interactions between mortar, blocks, grouted cells, non-grouted cells, and reinforcing steel.In this study, the aim is to develop an artificial neural network model by combining the ECBO meta-heuristic algorithm with the artificial neural network structure to optimize the feed forward propagation network parameters for analyzing the shear strength of PG walls.A total of 255 test data on PG collected from the available literature were used to generate training and test data sets. Various validation criteria such as mean square error, root mean square error and correlation coefficient (R) are used to validate the models.In this study, the optimal number of neurons used in the hidden layer and also the optimal number of CBs required in the ECBO algorithm were obtained. The mathematical formulation of the optimized neural network model with the combination of meta-heuristic algorithm is also presented.

Quantum-inspired tempering for ground state approximation using artificial neural networks

A large body of work has demonstrated that parameterized artificial neural networks (ANNs) can efficiently describe ground states of numerous interesting quantum many-body Hamiltonians. However, the standard variational algorithms used to update or train the ANN parameters can get trapped in local minima, especially for frustrated systems and even if the representation is sufficiently expressive. We propose a parallel tempering method that facilitates escape from such local minima. This methods involves training multiple ANNs independently, with each simulation governed by a Hamiltonian with a different "driver" strength, in analogy to quantum parallel tempering, and it incorporates an update step into the training that allows for the exchange of neighboring ANN configurations. We study instances from two classes of Hamiltonians to demonstrate the utility of our approach using Restricted Boltzmann Machines as our parameterized ANN. The first instance is based on a permutation-invariant Hamiltonian whose landscape stymies the standard training algorithm by drawing it increasingly to a false local minimum. The second instance is four hydrogen atoms arranged in a rectangle, which is an instance of the second quantized electronic structure Hamiltonian discretized using Gaussian basis functions. We study this problem in a minimal basis set, which exhibits false minima that can trap the standard variational algorithm despite the problem’s small size. We show that augmenting the training with quantum parallel tempering becomes useful to finding good approximations to the ground states of these problem instances.

Joint A-SNN: Joint training of artificial and spiking neural networks via self-Distillation and weight factorization

Emerged as a biology-inspired method, Spiking Neural Networks (SNNs) mimic the spiking nature of brain neurons and have received lots of research attention. SNNs deal with binary spikes as their activation and therefore derive extreme energy efficiency on hardware. However, it also leads to an intrinsic obstacle that training SNNs from scratch requires a re-definition of the firing function for computing gradient. Artificial Neural Networks (ANNs), however, are fully differentiable to be trained with gradient descent. In this paper, we propose a joint training framework of ANN and SNN, in which the ANN can guide the SNN’s optimization. This joint framework contains two parts: First, the knowledge inside ANN is distilled to SNN by using multiple branches from the networks. Second, we restrict the parameters of ANN and SNN, where they share partial parameters and learn different singular weights. Extensive experiments over several widely used network structures show that our method consistently outperforms many other state-of-the-art training methods. For example, on the CIFAR100 classification task, the spiking ResNet-18 model trained by our method can reach to 77.39% top-1 accuracy with only 4 time steps.

Fixed-point implementations for feed-forward artificial neural networks

We present scalable and generalized fixed-point hardware designs (source VHDL code is provided) for Artificial Neural Networks (ANNs). Three architectures are presented: multiply-and-add, multiplier-less, fully pipelined. In addition, we include two approaches for ANN binary layers: accumulation-based and fully pipelined. The fully customized hardware architectures allow for design space exploration to establish trade-offs among numerical format, processing time, resource usage, and numerical accuracy. Users can select the ANN architecture, ANN parameters (structure, weights, biases), the numerical format for both the input/output data in every layer and the network parameters (weights and biases). Results are presented in terms of resources, processing time, and numerical accuracy. The proposed architectures were implemented on modern FPGAs. These hardware designs are expected to be used as building blocks on a variety of applications such as CNNs and SNNs, as well as a platform for educational purposes.

Efficient training of two ANNs using four meta-heuristic algorithms for predicting the FRP strength

In recent years, artificial neural network (ANN) is one of the popular and effective machine learning models that can be used to accurately predict fiber reinforced polymer (FRP) strength. However, the ANN structure and parameters are usually are chosen by experience. In this study, the aim is to use the combination of meta-heuristic algorithm with two different types of artificial neural network structure to optimize the parameters of the feed forward backpropagation and radial basis function networks. In this paper, Particle swarm optimization (PSO), Genetic algorithm (GA), Colliding bodies optimization (CBO), Enhanced colliding bodies optimization (ECBO) algorithms are used to combine with ANNs.A total of 223 test data on Carbon FRP (CFRP) collected from the available literature were used to generate training and test data sets. Various validation criteria such as mean square error, root mean square error and correlation coefficient (R) are used to validate the models. These models consider the effects of concrete compressive strength, concrete sample diameter, concrete sample length, fiber elastic modulus, fiber thickness, fiber strength on the ultimate strength of FRP-concrete.It is shown that ECBO algorithm provide better results and higher accuracy. Also, the comparison of the results of using two neural networks, feed forward backpropagation (FFB) and radial basis function (RBF), indicates that the lower error percentage and more accurate results are related to the FFB neural networks combined with ECBO.

A state‐of‐the‐art survey of predicting students' performance using artificial neural networks

AbstractPredicting students' performance is one of the most important issue in educational data mining. In order to investigate the state‐of‐the‐art research development in predicting students' performance by using artificial neural networks (ANN), we conducted a survey on 39 important studies on this issue from 2016 to 2021. The results show that: (1) objectives of most prediction model is the performance of learners on the program and course; (2) datasets used for training prediction model are collected from logs of the learning management system; (3) the most commonly used ANN is feedforward neural network; (4) researchers use stochastic gradient descent and Adam algorithm to optimizes the parameters in ANN and configure hyper parameters of ANN manually; (5) feature selection is not necessary because ANN can automatically adjust the weights of artificial neurons; and (6) ANN has better performance than the classical classifiers in predicting student performance. The challenges in previous studies were comprehensively analyzed, suggestions for future research were put forward.

An Artificial Network-Based Prediction of Key Reference Zones on Axial Stress–Strain Curves of FRP-Confined Concrete

The accurate prediction of reference points on the axial stress–axial strain relationship of fiber-reinforced polymer (FRP)-confined concrete is vital to pre-design structures made with this system. This study uses an artificial neural network (ANN) for predicting hoop rupture strain (εh,rup) and transition zone, namely transition strain (εc1) and stress (f’c1), on axial stress–strain curves of FRP-confined concrete. These are key parameters for estimating a transition zone of stress–strain curves. In this study, accompanied with these parameters, ultimate condition parameters, including compressive strength and ultimate axial strain, were predicted using a comprehensive database. Various combinations of input data and ANN parameters were used to increase the accuracy of the predictions. A sensitivity analysis and a model validation assessment were performed to evaluate the predictability of the developed models. At the end, a comparison between the proposed models in this study and existing ANN and design-oriented models was presented. It is shown that the accuracy of the developed ANN models in this study is higher or comparable to that of existing ANN models. Additionally, the developed models in this study to predict f’c1 and εc1 exhibit a higher accuracy compared to existing design-oriented models. These results indicate that the proposed ANN models capture the lateral confinement effect on ultimate and transition zones of FRP-confined concrete with a more robust performance compared to existing models.

Optimization of input parameters of ANN–driven plasma source through nature-inspired evolutionary algorithms

The plasma sources are a device that produces energetic ion streams for applications in diversified fields. However, operating the ion sources with repeatable performance remains challenging and time-consuming due to its nonlinear nature and the complex relation between the input and output parameters. This maiden study examines the efficacy of nature-inspired evolutionary algorithms (NIEAs) for optimizing the input parameters of an ion source model based on an artificial neural network (ANN) that generates high-density negative hydrogen ions. Hence, it requires the development of a predictive ion source model based on ANNs and further optimized using NIEA. This work optimizes the magnetic field and gas pressure as input parameters using the particle swarm optimization (PSO) technique, simulated annealing (SA), and genetic algorithm (GA). The input parameters for different plasma densities and ion saturation currents are adjusted for a constant Radio Frequency (RF) power (900 watts) at 6 mTorr, 7.5 mTorr, 30 mTorr gas pressures and magnetic fields of 40G, 55G, and 86G. The number of iterations, the computation time, and the Root Mean Squared Error (RMSE) defines the performance of the algorithms. SA, GA, and PSO optimized the input parameters by averaging 569, 63, and 32 iterations, while the average computation time remained at 54 seconds, 27 seconds, and 4 seconds, respectively. The RMSEs for SA, GA, and PSO are 1.57, 1.56, and 0.54. The comparison shows that the PSO approach is the most efficient regarding the number of iterations, computation time and RMSE.

Hybridizing Artificial Intelligence Algorithms for Forecasting of Sediment Load with Multi-Objective Optimization

Forecasting of sediment load (SL) is essential for reservoir operations, design of water resource structures, risk management, water resource planning and for preventing natural disasters in the river basin systems. Direct measurement of SL is difficult, labour intensive, and expensive. The development of an accurate and reliable model for forecasting the SL is required. Sediment transport is highly non-linear and is influenced by a variety of factors. Forecasting of the SL using various conventional methods is not highly accurate because of the association of various complex phenomena. In this study, major key factors such as rock type (RT), relief (R), rainfall (RF), water discharge (WD), temperature (T), catchment area (CA), and SL are recognized in developing the one-step-ahead SL forecasting model in the Mahanadi River (MR), which is among India’s largest rivers. Artificial neural networks (ANN) in conjunction with multi-objective genetic algorithm (ANN-MOGA)-based forecasting models were developed for forecasting the SL in the MR. The ANN-MOGA model was employed to optimize the two competing objective functions (bias and error variance) with simultaneous optimization of all associated ANN parameters. The performances of the proposed novel model were finally compared to other existing methods to verify the forecasting capability of the model. The ANN-MOGA model improved the performance by 12.81% and 10.19% compared to traditional AR and MAR regression models, respectively. The results suggested that hybrid ANN-MOGA models outperform traditional autoregressive and multivariate autoregressive forecasting models. Overall, hybrid ANN-MOGA intelligent techniques are recommended for the forecasting of SL in rivers because of their relatively better performance as compared to other existing models and simplicity of application.

Forecasting Quality of Service (QoS) Parameters of IoT based Web Services with an Artificial Electric Field Algorithm trained Artificial Neural Network

Development of an accurate forecasting model for effective prediction of Quality of Service (QoS) parameters of inter-net of things (IoT) based web services is highly desired, such that it improves service management and user experience. Mostly, QoS parameters are volatile in nature which make the IoT based service and recommendation process chal-lenging. Artificial neural network (ANN) based models are found to be worthy in modeling and forecasting nonlinear QoS parameter sequences. However, improper tuning of ANN parameters with conventional training algorithms may lead to a suboptimal model. Nature-inspired optimization methods are found suitable in fine tuning ANN parameters and have shown proficient results on real-world data mining problems. There is lack of such models for QoS parameters prediction that need to be explored. We develop an Artificial Electric Field Algorithm (AEFA) trained ANN (AEFANN) model for effective and accurate prediction of QoS parameters where AEFA is used to search an optimal ANN structure. The optimal ANN structure is achieved by AEFA through an evolutionary process. Two real-world IoT enabled web service datasets are used for evaluating effectiveness of AEFANN in terms of three performance metrics. Experimental procedures and comparative studies are conducted to establish the superiority of the proposed approach over four other similar forecasts. AEFANN obtained relative worth values of 4.13% ~ 69.12 % (5-min granularity) and 43.32% ~ 80.3 % (1-hr granularity) from SERVICE 1 dataset. Similarly, it obtained relative worth values of 7.25% ~ 65.57 % (5-min granularity) and 43.38% ~ 72.43 % (1-hr granularity) from SERVICE 2 dataset when compared to oth-er models. This is a significant improvement over comparative existing similar model.