Design Of Artificial Neural Networks Research Articles

Influence of random topology in artificial neural networks: A survey

Abstract Due to the fully-connected complex structure of Artificial Neural Networks (ANNs), systems based on ANN may consume much computational time, energy and space. Therefore, intense research has been recently centered on changing the topology and design of ANNs to obtain high performance. To explore the influence of network structure on ANNs complex systems topologies have been applied in these networks to have more efficient and less complex structures while they are more similar to biological systems at the same time. In this paper, the methodology and results of some recent papers are summarized and discussed in which the authors investigated the efficacy of random complex networks on the performance of Hopfield associative memory and multi-layer ANNs compared with ANNs with small-world, scale-free and regular structures.

An Improved Artificial Neural Network Design for Face Recognition utilizing Harmony Search Algorithm

Face recognition has become an interesting field for researchers where it is used in many applications. One of the most common methods of soft computing is named the artificial neural network (ANN) has been suggested to achieve the face recognition process. Nonetheless, the performance of ANN depends on the number of neurons in the hidden layers and the value of the learning rate. These variables are usually defined based on the trial and error method which is time-consuming. Furthermore, in many cases, it is very difficult to find the optimum value for these variables. Hence, to improve the performance of the ANN for the face recognition process, the optimization algorithm is needed to get promising outcomes. Therefore, this paper introduces an improved ANN design for face recognition using a meta-heuristic optimization algorithm. The ANN represents a distributed processing system consists of neurons which are simply connected elements. One of the most popular techniques for pattern recognition called back propagation algorithm (BP) is used to train the ANN (BP-ANN) to achieve the face recognition process. To enhance the face recognition system performance, the ANN has been hybridized with the well-known meta-heuristic optimization algorithm namely harmony search algorithm (HSA). The HSA based on the principle work of musicians to find the best harmonies. This technique is Implemented based on the results of the fitness function evaluation. In this research, the mean squared error (MSE) has been used as a fitness function. The HSA optimizes the ANN such that the face recognition system provides the lowest MSE and thus enhances the performance of the face recognition system. The accuracy of the optimum hybrid system (HSA-ANN) is investigated using the MATLAB environment conducted for 10 persons. The results revealed that the proposed system (HSA-ANN) achieved lower MSE compare with the ANN. Furthermore, the HSA-ANN gives a better face recognition rate than traditional ANN.

Identification and fault detection in actuator using NN-NARX

In this paper, the use of a Nonlinear Auto Regressive eXogenous Neural Networks model or NN-NARX for identification and fault detection in the actuator of an industrial thermal process is presented. Initially, the techniques of fault detection and diagnosis are exposed; then, emphasis is placed on the models of Artificial Neural Networks for identification and fault detection. Subsequently, the control system of a thermal process used as a case study is described. A monitoring system allows data recording under normal operation conditions for identification using the NN-NARX model. The model is used for residual online generation due to faults that are introduced randomly. Finally, the results of residual generation and evaluation are presented. The designed system is useful for implementation through a hardware device that can be incorporated into the process equipment and support the operator in the presence of failures.

Use of Artificial Neural Network for Initial design of steel structures

Design of steel structures is an iterative process that often turns complicated when requires initial guess. A good initial design guess that comes from past design experience can considerably reduce the number of subsequent analysis and design cycles. It is difficult to form declarative rules to express human intuitions and past experience. Another problem in design process is arriving at optimal solution, where optimization process in most cases is computationally expensive and time consuming. Artificial Neural Network (ANN) is a promising computational model that can perform cognitive tasks, such as learning and optimization. This paper focuses on application of ANN in design so as to make design process more efficient. The aim is to train ANN to arrive at optimal solution by considering design constraints along with practical. This is illustrated with an example of design of compression member which primarily requires initial guess. The economy in design is tried to obtain by providing training set of optimal solutions to a multilayer neural network. The design process followed to generate training set is in accordance with IS: 800-2007. The solutions given by ANN are approximate but have reasonable agreement with the expected solutions.

Sustainable NO[formula omitted] emission reduction at a coal-fired power station through the use of online neural network modeling and particle swarm optimization

Meeting increasingly stringent environmental targets while conforming to new operational demands of load-ramping and low-load operation presents a challenge for coal-fired thermal power stations. Artificial neural networks (ANNs) have been shown to predict efficiency and emissions of power stations, however, existing literature is comprised of offline studies and short-duration tests. In practice, ANN based combustion optimization systems (COS) have experienced mixed success due to the degradation of model performance over time and a lack of customizability. The current work presents a COS directed at reducing NOx at a 490 MW tangentially coal-fired power station over two years of live, closed-loop operation. The system employs a novel software platform called the Griffin AI Toolkit™, which includes a graphical user interface for ANN design and meta-optimization. A unique ANN utilizing swappable synapse weights for improved modeling of operational sub-regimes is validated against support vector regression (SVR), random forests (RF), and kernel partial least squares (KPLS) models, then deployed within the COS. The system leverages particle swarm optimization (PSO) to interrogate the models and perform real-time optimization. This work demonstrates: 1. Substantial NOx emission reductions by the station (22.5%), 2. A hybrid optimization approach applying genetic algorithm (GA) to select neural network structure and PSO to perform combustion optimization, 3. The realization of other performance benefits in an 87% reduction of high-temperature exceedances due to encapsulating operational best-practices within the platform, and 4. The sustainability of the COS in achieving a high degree of acceptance, with a final service factor of 86%.

Using simulation to define the tolerances for the information and physical parameters of memristors-based artificial neural networks

The article covers a solution to a problem of defining the tolerances of information and physical parameters of components of artificial neural networks (ANNs), which are implemented as hardware through the application of nanoscale electronic components with memristive properties (memristors). The developed method foundation is a system approach to the memristors-based ANN (ANNM) design, whereby the ANNMs should be studied as united physical and informational objects. When the ANNM is produced and operated, the errors of its components’ physical parameters provoke information parameter errors. To define the tolerated errors (tolerances), a simulation methodology is used. The potential of the developed method is illustrated through the process of defining tolerances for the synaptic weights and neural biases of a two-layer feed forward ANNM.

Use of Artificial Neural Network in Design of Fly Ash Blended Cement Concrete Mixes

Cement concrete is the most important construction material which is non-homogeneous in nature. Its strength depends on properties of its many constituent materials are diverse in nature. It is important to fix up exact proportions of these materials beforehand so that needed strength in concrete is obtained later on. Sufficient time is needed to check it by making trial mixes of concrete after fixing up the proportions by theoretical calculations and testing these trial mixes after 28 days. In this duration concreting work may be held up in the absence of a final approved mix in terms of quantities of various constituents of concrete. Use of artificial neural networks (ANNs) for the checking of design composition of fly ash blended cement concrete mixes which were designed as per Indian standard guidelines has been made. Prediction of strength of such mixes at a later date by ANN has also been explored in this study. Prediction results of ANNs come close to experimental values and reinforce the utility of ANNs in the area of use of civil engineering materials for improving efficiency in construction.

Reduced-Complexity Artificial Neural Network Equalization for Ultra-High-Spectral-Efficient Optical Fast-OFDM Signals

Digital-based artificial neural network (ANN) machine learning is harnessed to reduce fiber nonlinearities, for the first time in ultra-spectrally-efficient optical fast orthogonal frequency division multiplexed (Fast-OFDM) signals. The proposed ANN design is of low computational load and is compared to the benchmark inverse Volterra-series transfer function (IVSTF)-based nonlinearity compensator. The two aforementioned schemes are compared for long-haul single-mode-fiber-based links at 9.69 Gb/s direct-detected optical Fast-OFDM signals. It is shown that an 80 km extension in transmission-reach is feasible when using ANN compared to IVSTF. This occurs because ANN can tackle stochastic nonlinear impairments, such as parametric noise amplification. Using ANN, the dynamic parameters requirements of the sub-ranging quantizers can also be relaxed compared to linear equalization, such as the reduction of the optimum clipping ratio and quantization bits by 2 dB and 2-bits, respectively, and by 2 dB and 2 bits when compared to the IVTSF equalizer.

Label-free surface-enhanced Raman spectroscopy with artificial neural network technique for recognition photoinduced DNA damage

Taking advantage of surface-enhanced Raman scattering (SERS) methodology with its unique ability to collect abundant intrinsic fingerprint information and noninvasive data acquisition we set up a SERS-based approach for recognition of physically induced DNA damage with further incorporation of artificial neural network (ANN). As a proof-of-concept application, we used the DNA molecules, where the one oligonucleotide (OND) was grafted to the plasmonic surface while complimentary OND was exposed to UV illumination with various exposure doses and further hybridized with the grafted counterpart. All SERS spectra of entrapped DNA were collected by several operators using the portable spectrometer, without any optimization of measurements procedure (e.g., optimization of acquisition time, laser intensity, finding of optimal place on substrate, manual baseline correction, etc.) which usually takes a significant amount of operator's time. The SERS spectra were employed as input data for ANN training, and the performance of the system was verified by predicting the class labels for SERS validation data, using a spectra dataset, which has not been involved in the training process. During that phase, accuracy higher than 98% was achieved with a level of confidence exceeding 95%. It should be noted that utilization of the proposed functional-SERS/ANN approach allows identifying even the minor DNA damage, almost invisible by control measurements, performed with common analytical procedures. Moreover, we introduce the advanced ANN design, which allows not only classifying the samples but also providing the ANN analysis feedback, which associates the spectral changes and chemical transformations of DNA structure.

Identification of lactic acid bacteria Enterococcus and Lactococcus by near-infrared spectroscopy and multivariate classification

Lactic acid bacteria are important in numerous biological processes. The fabrication of cheese, for example, uses the lactic acid bacteria found in raw milk such as Lactococcus lactis as starters to improve the organoleptic properties of milk. Conventional methods to determine the genus and species of lactic acid bacteria isolated from raw milk involve genotyping and phenotyping, which require specific preparation and sample destruction. To improve on this situation, we present herein a simple and non-destructive screening method to discriminate between the Lactococcus and Enterococcus species most commonly found in raw milk (L. lactis, E. durans, E. faecalis, and E. faecium). The bacteria are grown on agar plates and assessed by using near-infrared spectroscopy in a spectral range from 800 to 2777 nm. Principle component analysis loading line plots highlight the inter-genus and inter-species differences at various wavelengths, which are mostly assigned to cell-wall compounds such as polysaccharides. The best artificial neural network identification models give 98.8% and 86.3% classification rates at the genus and species level, respectively, for an external validation set made of 80 samples. These results suggest that near-infrared spectroscopy may be used to identify lactic acid bacteria on agar medium.

Application of Computational Intelligence Methods for Predicting Soil Strength

Abstract The aim of this study was to make predictions for soil cone index using artificial neural networks (ANNs), adaptive neuro-fuzzy inference system (ANFIS) and a regression model. Field tests were conducted on three soil textures and obtained results were analyzed by application of a factorial experiment based on a Randomized Complete Block Design with five replications. The four independent variables of percentage of soil moisture content, soil bulk density, electrical conductivity and sampling depth were used to predict soil cone index by ANNs, ANFIS and a regression model. The ANNs design was that of back propagation multilayer networks. Predictions of soil cone index with ANFIS were made using the hybrid learning model. Comparison of results acquired from ANNs, ANFIS and regression models showed that the ANFIS model could predict soil cone index values more accurately than ANNs and regression models. Considering the ANFIS model, a novel result on soil compaction modeling, relative error (ε), and regression coefficient (R 2) were calculated at 2.54% and 0.979, respectively.

Development of Engine Efficiency Characteristic in Dynamic Working States

The objective of this paper is to present a new approach to the problem of combustion engine efficiency characteristic development in dynamic working states. The artificial neural network (ANN) method was used to build a mathematical model of the engine comprising the following parameters: Engine speed, angular acceleration, engine torque, torque change intensity, and fuel mass flow, measured on a test bed on a spark ignition engine in static and dynamic working states. A detailed analysis of ANN design, data preparation, the training method, and the ANN model accuracy are described. The paper presents conducted calculations that clearly show the suitability of the approach in every aspect. Then, a simplified ANN was created, which allows a two dimensional characteristic in dynamic states, including 4 variables, to be determined.

Estimation of Static Young’s Modulus for Sandstone Formation Using Artificial Neural Networks

In this study, we used artificial neural networks (ANN) to estimate static Young’s modulus (Estatic) for sandstone formation from conventional well logs. ANN design parameters were optimized using the self-adaptive differential evolution optimization algorithm. The ANN model was trained to predict Estatic from conventional well logs of the bulk density, compressional time, and shear time. The ANN model was trained on 409 data points from one well. The extracted weights and biases of the optimized ANN model was used to develop an empirical relationship for Estatic estimation based on well logs. This empirical correlation was tested on 183 unseen data points from the same training well and validated using data from three different wells. The optimized ANN model estimated Estatic for the training dataset with a very low average absolute percentage error (AAPE) of 0.98%, a very high correlation coefficient (R) of 0.999 and a coefficient of determination (R2) of 0.9978. The developed ANN-based correlation estimated Estatic for the testing dataset with a very high accuracy as indicated by the low AAPE of 1.46% and a very high R and R2 of 0.998 and 0.9951, respectively. In addition, the visual comparison of the core-tested and predicted Estatic of the validation dataset confirmed the high accuracy of the developed ANN-based empirical correlation. The ANN-based correlation overperformed four of the previously developed Estatic correlations in estimating Estatic for the validation data, Estatic for the validation data was predicted with an AAPE of 3.8% by using the ANN-based correlation compared to AAPE’s of more than 36.0% for the previously developed correlations.

Ultrasonic exposure parameters screening in permeability of mycobacterium smegmatis cytoderm induced by cavitation based on artificial neural network identification.

The low intensity ultrasound has been adopted by researchers to enhance the bactericidal effect against bacteria in vitro and in vivo. Although the mechanism is not completely understood, one dominant opinion is that the permeability increases because of acoustic cavitation. However, the relationship between ultrasonic exposure parameters and cavitation effects is not definitely addressed. In this paper, by establishing a modified artificial neural network (ANN) model between ultrasonic parameters and cavitation effects, the cavitation effects can be predicted and inversely the direction for choosing parameters can be given despite of different ultrasonic systems. Compared with the generic model, the computational results obtained by modified model are more close to experimental results with low calculation cost. It means that as an efficient solution, the validity of the new model has been proved. Although the research is of preliminary stage, the new method may have great value and significance because of reducing the experimental expense. The next step of this research is to explore an optimization method to obtain the most suitable parameters based on this identification model. We hope it can give a guideline for future applications in ultrasonic therapy.

On-the-Fly Adaptivity for Nonlinear Twoscale Simulations Using Artificial Neural Networks and Reduced Order Modeling

A multi-fidelity surrogate model for highly nonlinear multiscale problems is proposed. It is based on the introduction of two different surrogate models and an adaptive on-the-fly switching. The two concurrent surrogates are built incrementally starting from a moderate set of evaluations of the full order model. Therefore, a reduced order model (ROM) is generated. Using a hybrid ROM-preconditioned FE solver, additional effective stress-strain data is simulated while the number of samples is kept to a moderate level by using a dedicated and physics-guided sampling technique. Machine learning (ML) is subsequently used to build the second surrogate by means of artificial neural networks (ANN). Different ANN architectures are explored and the features used as inputs of the ANN are fine tuned in order to improve the overall quality of the ML model. Additional ANN surrogates for the stress errors are generated. Therefore, conservative design guidelines for error surrogates are presented by adapting the loss functions of the ANN training in pure regression or pure classification settings. The error surrogates can be used as quality indicators in order to adaptively select the appropriate -- i.e. efficient yet accurate -- surrogate. Two strategies for the on-the-fly switching are investigated and a practicable and robust algorithm is proposed that eliminates relevant technical difficulties attributed to model switching. The provided algorithms and ANN design guidelines can easily be adopted for different problem settings and, thereby, they enable generalization of the used machine learning techniques for a wide range of applications. The resulting hybrid surrogate is employed in challenging multilevel FE simulations for a three-phase composite with pseudo-plastic micro-constituents. Numerical examples highlight the performance of the proposed approach.

Optimizing Levenberg–Marquardt backpropagation technique in predicting factor of safety of slopes after two-dimensional OptumG2 analysis

This study intended to use optimized artificial neural network (ANN) for the design of pure cohesive slopes (by means of considering sufficient safety factors (SF) of stability). A total of 630 finite element limit equilibrium analysis were completed to provide datasets of training and testing for preparation of the ANN-based predictive models. The database consisted of 504 training datasets (80% of the database) and 126 testing datasets (20% of the database). To construct an optimized ANN structure, variables of ANN algorithm such as a number of neurons in hidden layer and the number of hidden layers were changed (e.g. with a series of trial and error process). The input parameters that used in the analysis include setback distance ratio (b/B), the undrained shear strength of the cohesive soil (Cu), applied stresses on the slope (Fy) and slope angle (β) while the final output was the value of SF. The predicted results for datasets from ANN models were assessed based on several well-known statistical indices namely, R2, RMSE and VAF. Also, in order to evaluate the performance of predicted network two ranking systems of (1) colour intensity rating (CIR) and (2) total ranking method (TRM), i.e. based on the result of statistical indices, were utilized. The optimal architecture of 4 × 6 × 1 was found for the ANN structure. After the performance of the optimized ANN model, the results are provided as a simple tansig formula which can be used for further application of engineering purposes. In the optimized ANN network and based on R2, RMSE and VAF, values of (0.999, 0.0350 and 99.9978) and (0.999, 0.0379 and 99.998) were found, respectively, for both of the normalized training and testing datasets. This proves the excellent performance of the proposed ANN model in estimating the SF of the slope. As the final outputs and to show the reliability of the proposed ANN formula, a series of optimized ANN design solution charts are compared to a similar example of measured charts.

An artificial neural network identification method for thermal resistance of exterior walls of buildings based on numerical experiments

Current standards for the detection methods for the thermal resistance of exterior walls of buildings have shortcomings, such as strict conditions, high time consumption, and heavy workloads. To overcome the shortcomings of existing methods, in this study, an artificial neural network identification method was used to detect the thermal resistance of exterior walls. To enhance efficiency and reduce costs, the data required by the neural network modelling were obtained through a numerical experiment based on an unsteady heat transfer model. In this paper, the thermal resistance identification results of three neural networks-Back Propagation (BP), Radial Basis Function (RBF) and Generalized Regression Neural Network (GRNN)-were analysed and compared. The results demonstrated that the GRNN neural network had the best identification effect. Thus, the identification system for the thermal resistance of exterior walls was established using the GRNN neural network. The average test error in the training sample was 0.098%, and the average error in the anti-noise test was 4.82%. The network identification accuracy was verified by five groups of field measured data. In comparison with the conventional heat flux method, the average error was 5.82%, which proved the reliability of the proposed GRNN identification model.

Neural Network-Based Formula for the Buckling Load Prediction of I-Section Cellular Steel Beams

Cellular beams are an attractive option for the steel construction industry due to their versatility in terms of strength, size, and weight. Further benefits are the integration of services thereby reducing ceiling-to-floor depth (thus, building’s height), which has a great economic impact. Moreover, the complex localized and global failures characterizing those members have led several scientists to focus their research on the development of more efficient design guidelines. This paper aims to propose an artificial neural network (ANN)-based formula to precisely compute the critical elastic buckling load of simply supported cellular beams under uniformly distributed vertical loads. The 3645-point dataset used in ANN design was obtained from an extensive parametric finite element analysis performed in ABAQUS. The independent variables adopted as ANN inputs are the following: beam’s length, opening diameter, web-post width, cross-section height, web thickness, flange width, flange thickness, and the distance between the last opening edge and the end support. The proposed model shows a strong potential as an effective design tool. The maximum and average relative errors among the 3645 data points were found to be 3.7% and 0.4%, respectively, whereas the average computing time per data point is smaller than a millisecond for any current personal computer.

Enhancement of Performance for Steam Turbine in Thermal Power Plants Using Artificial Neural Network and Electric Circuit Design

Design and implantation of electric circuit for enhanced performance of steam power plant and artificial neural networks technique are used to control turbine. Artificial neural networks technique is used to control a lot of industrial models practically. Artificial neural network has been applied to control the important variables of turbine in AL–Dura power plant in Baghdad such as pressure, temperature, speed, and humidity. In this study Simulink model was applied in MATLAB program (v 2014 a) by using artificial neural network (ANN). The method of controlling model is by using NARMA to generate data and train network. ANN is offline. ANN requires data to obtain results and for comparison with actual power plant. The values of the input variables have a large effect on the number of nodes and epochs and in hidden layer of the artificial neural network they also affect performance of ANN. The electric circuit of sensors consists of transformer, DC bridge, and voltage regulator. Comparing the results from modeling by ANN and electric circuit with experimental data reveals a good agreement and the maximum deviation between the experimental data and predicted results from ANN and circuit design is less than 1%. The novelty in this paper is applying NARMA controller for the purpose of enhancement of turbine performance.

Probabilistic Damage Detection of a Steel Truss Bridge Model by Optimally Designed Bayesian Neural Network.

Excellent pattern matching capability makes artificial neural networks (ANNs) a very promising approach for vibration-based structural health monitoring (SHM). The proper design of the network architecture with the suitable complexity is vital to the ANN-based structural damage detection. In addition to the number of hidden neurons, the type of transfer function used in the hidden layer cannot be neglected for the ANN design. Neural network learning can be further presented in the framework of Bayesian statistics, but the issues of selection for the hidden layer transfer function with respect to the Bayesian neural network has not yet been reported in the literature. In addition, most of the research works in the literature for addressing the predictive distribution of neural network output is only for a single target variable, while multiple target variables are rarely involved. In the present paper, for the purpose of probabilistic structural damage detection, Bayesian neural networks with multiple target variables are optimally designed, and the selection of the number of neurons, and the transfer function in the hidden layer, are carried out simultaneously to achieve a neural network architecture with suitable complexity. Furthermore, the nonlinear network function can be approximately linear by assuming the posterior distribution of network parameters is a sufficiently narrow Gaussian, and then the input-dependent covariance matrix of the predictive distribution of network output can be obtained with the Gaussian assumption for the situation of multiple target variables. Structural damage detection is conducted for a steel truss bridge model to verify the proposed method through a set of numerical case studies.