Swarm intelligence-based technique to enhance performance of ANN in structural damage detection

The low-cost and small size solid-state sensor arrays are suitable to implement a wide-area electronic nose (e-nose) for real-time air quality monitoring. However, accuracy of these low-cost sensors is not adequate for precise measurements of pollutant concentrations. Artificial neural network (ANN) estimation models are used for the soft calibration of low-cost sensor array measurements and significantly improve the accuracy of low-cost multi-sensor measurements. However, optimality of neural architecture affects the performance of ANN estimation models, and optimization of the ANN architecture for a training data set is essential to improve data-driven modeling performance of ANNs to reach optimal neural complexity and improved generalization. In this study, an optimal architecture ANN estimator design scheme is suggested to improve the estimation performance of ANN models for e-nose applications. To this end, a gray wolf optimization (GWO) algorithm is modified, and an exploitative alpha gray wolf optimization (EA-GWO) algorithm is suggested. This modification enhances local exploitation skill of the best alpha gray wolf search agent, and thus allows the fine-tuning of ANN architectures by minimizing a multi-objective cost function that implements mean error search policy. Experimental study demonstrates the effectiveness of optimal architecture ANN models to estimate CO concentration from the low-cost multi-sensor data.

According to Vision Indonesia, data on people with eye diseases in Indonesia in 2018-2019 were 3 million people or about 1.5% of the total population. So far, public information or knowledge about the recognition of eye disease disorders is still lacking. The problem in this study is how to educate the public about the introduction of eye diseases based on information on symptoms of the disease and how to apply the web-based Artificial Neural Network (ANN) algorithm for the introduction of eye diseases. The ANN algorithm in the eye disease recognition education system can conclude knowledge even though it does not have certainty and takes it into account sequentially so that the process is faster. In terms of educational content about eye disease recognition, this is a novelty to use. This research aims to create an educational system for introducing eye diseases based on information on symptoms of the disease and applying a web-based Artificial Neural Network (ANN) algorithm for the recognition of eye diseases. The method used is the Artificial Neural Network algorithm method. The work of ANN in the education system for the introduction of eye diseases is to make parameters of eye disease symptoms or indicators that will produce the type of eye disease. The research material used is data on types of eye diseases and symptoms of each type of eye disease. The research results are to create an education system that can help the public recognise eye diseases based on the symptoms of these eye diseases that can be run on a web platform. The Artificial Neural Network (ANN) algorithm can manage input analysis data from disease indicators and show the initial results of eye diseases that can be detected. suffered by someone based on Training Results Weights and Bias v11= 1.6769, v01= 0.4356, w11= -1.5233, w01= 0.3242. Based on white box testing, the test results are free from logical errors. The results of this study indicate that the use of the ANN algorithm for eye disease recognition shows accurate results based on eye disease symptom data.

The main idea of this paper is to propose a nondestructive evaluation (NDE) system for two types of damages, core cracking and skin/core debonding, in fiberglass/foam core sandwich structures based on the inverse eigensensitivity-based finite element model updating using the modal test results, and the artificial neural networks. First, the modal testing was conducted on the fabricated fiberglass/foam core sandwich specimens, in the intact and damaged states, and the natural frequencies were extracted. Finite element modeling and inverse eigensensitivity-based model updating of the intact and damaged sandwich structures were conducted and the parameters of the models were identified. Afterward, the updated finite element models were employed to generate a large dataset of the first five harmonic frequencies of the damaged sandwich structures with different damage sizes and locations. This dataset was adopted to train the machine learning models for detection, localization, and size estimation of the core cracking and skin/core debonding damages. A multilayer perceptron neural network classification model was used for detection of types of damages and also a multilayer perceptron neural network regression model was fitted to the dataset for automatically estimation of the locations and dimensions of damages. This intelligent system of damage quantification was also used to make predictions on real damaged specimens not seen by the system. The results indicated that the extracted natural frequencies from the accurate finite element model, in coordination with the experimental data, and using the artificial neural networks can provide an effective system for nondestructive evaluation of foam core sandwich structures.

This research work deals with aspects concerned with delamination detection in composite structures as revealed by an approach based on vibration measurements. Variations in vibration characteristics generated in composite laminates indicate the existence of delaminations because degradation due to delamination causes reduction in flexural stiffness and strength of the material and as a result vibration parameters like natural frequency responses are changed. Hence, it is possible to monitor the variation in natural frequencies to identify the presence of delamination, and assess its size and location for online structural health monitoring (SHM). The approach to this paper, therefore, typically depends on undertaking the analysis of structural models implemented by finite element analysis (FEA). The numerical solutions using FE models known as the simulator computes the natural frequencies for the delaminated and undelaminated specimens of composite laminates. However, these FE models are computationally expensive, and surrogate (approximation) models are introduced to curtail the computational expense. The simulator is employed to solve the inverse problem using algorithms based on computational intelligence concepts. An artificial neural network (ANN) model is developed to also solve the inverse problem for delamination detection directly and to provide surrogate models integrated with optimization algorithms (the gradient-based local search and non-dominated sorting genetic algorithm-II) to contain the computationally expensive simulations by FEA. This approach is termed as surrogate assisted optimization and it is seen that the engagement of surrogate models in lieu of the FE models in the optimization loop greatly enhances the accuracy of delamination detection results within an affordable computational cost and provides control over handling different variables. Meanwhile, to aid with the building of effective surrogate models using substantial number of training datasets, K-means clustering algorithm is harnessed and this effectively reduces the large training datasets usually required for ANN training. This paper demonstrated that ANN and optimization algorithms with surrogates show immense potentialities for use in delamination damage detection scenarios. Prediction errors of the algorithms were quantified and they were shown to be satisfactory when applied to previously experimental data. The algorithms in their inverse formulations are capable of predicting accurately delamination parameters. Hence, these algorithms should be employed for application in the domain of SHM where their small computational requirements could be exploited for online damage detection.

Artificial intelligence through deep neural networks is now widely used in a variety of applications that have profoundly altered human livelihoods in a variety of ways. People's daily lives have become much more convenient. Image recognition, smart recommendations, self-driving vehicles, voice translation, and a slew of other neural network innovations have had a lot of success in their respective fields. The authors present the ANN applied in weather forecasting. The prediction technique relies solely upon learning previous input values from intervals in order to forecast future values. And also, Convolutional Neural Networks (CNNs) are a form of deep learning technique that can help classify, recognize, and predict trends in climate change and environmental data. However, due to the inherent difficulties of such results, which are often independently identified, non-stationary, and unstable CNN algorithms should be built and tested with each dataset and system separately. On the other hand, to eradicate error and provides us with data that is virtually identical to the real value we need Artificial Neural Networks (ANN) algorithms or benefit from it. The presented CNN model's forecasting efficiency was compared to some state-of-the-art ANN algorithms. The analysis shows that weather prediction applications become more efficient when using ANN algorithms because it is really easy to put into practice.

The computational cost of training artificial neural network (ANN) algorithms limits the use of large systems capable of processing complex problems. Implementing ANNs on a parallel or distributed platform to improve performance is therefore desirable. This work illustrates a method to predict and evaluate the performance of distributed ANN algorithms by analyzing the performance of the comparatively simple mathematical operations, which are used to construct the ANN. The ANN algorithms are divided into simple components: matrix and vector multiplication, matrix processed through a function, competition in a matrix. These basic operational parts are examined individually and it is demonstrated that the computation processes of distributed neural networks can be derived from the composition of these basic operations. Three popular network architectures are examined: multi-layer perceptrons with back-propagation learning, self-organizing map, and radial basis functions network.

This study analyzed consumer intention to repurchase a smartphone, using an analysis of previous research and suggesting this as a research model. To this end, factors influencing “intention to repurchase” the smartphone were derived as social influence, consumer satisfaction, emotional loyalty, and habit. In addition, statistical analysis was conducted to investigate consumer repurchase intentions and the causal relationships. It is also possible to investigate whether consumer habits are linked to repurchases by analyzing their psychological inclinations; therefore, in this study, 390 people who repurchased a smartphone over the past two years were surveyed, and data were collected. This study analyzed the causal relationships among the factors using SPSS 24.0. Moreover, the causal relationship analysis was enhanced using the artificial neural network (ANN) algorithm. With multiple regression analysis and the ANN algorithm, consumer satisfaction (0.71), emotional loyalty (0.108), and social influence (0.062) were determined to affect the intention to repurchase. This means that the ANN algorithm can be used over multiple regression analysis and improve the results of the analysis. In addition, this study also provided practitioners with a way to improve their understanding of consumer behavior intention to repurchase smartphones.

This paper presents an algorithm for reducing speckle noise from optical coherence tomography (OCT) images using an artificial neural network (ANN) algorithm. The noise is modeled using Rayleigh distribution with a noise parameter, sigma, estimated by the ANN. The input to the ANN is a set of intensity and wavelet features computed from the image to be processed, and the output is an estimated sigma value. This is then used along with a numerical method to solve the inverse Rayleigh function to reduce the noise in the image. The algorithm is tested successfully on OCT images of Drosophila larvae. It is demonstrated that the signal-to-noise ratio and the contrast-to-noise ratio of the processed images are increased by the application of the ANN algorithm in comparison with the respective values of the original images.

An artificial neural network (ANN) was applied for the prediction of the heat transfer coefficient in bubble columns, in order to obtain a general model and to facilitate the scale up of these multiphase contactors, covering a wide range of operating conditions, physical properties, and column dimensions, obtained from literature. A large number of data was collected (more than 1000) via a comprehensive literature survey. Selected parameters affecting the heat transfer coefficient were organized in six groups to serve as the input parameters. These were: gas superficial velocity, gas density, liquid density, diameter of the column, liquid viscosity, and gas hold-up. Four Back-Propagation Networks (BPNNS) were built. Two were trained using a different number of input parameters. The first ANN was trained with six inputs, which were the aforementioned parameters. The second was trained with three inputs only. These were gas velocity, liquid viscosity and gas hold-up. Each ANN was examined for two structures i.e., one hidden layer and two hidden layers. Comparison between these networks was made to find the optimal ANN structure with minimum %AARE and the maximum correlation coefficient (%R). It was found that the ANN structure of [6-13-1] with a %AARE of 16.2 and a %R of 94 was the best.

The functionality of piezoelectric devices is of significant importance in the electromechanical impedance (EMI)‐based structural health monitoring (SHM) and damage detection. Despite the previous work, the EMI response characteristics of a degraded piezoelectric‐based smart interface have not been sufficiently investigated due to the difficulty in making realistic functional defects via the experiment. To overcome this issue, we present a predictive simulation strategy to comprehensively investigate the EMI response characteristics of a smart interface subjected typical functional degradations. For that, a bolted steel girder connection is selected as a host structure to experimentally conduct EMI response measurement via the smart interface. Then, a finite element (FE) model corresponding to the experimental model is established and updated to reproduce the measured EMI response. By using the updated FE model, four common degradation types, including shear lag effect, transducer debonding, transducer breakage, and interface detaching are simulated and their effects on the EMI response are comprehensively analyzed. It is found that the interface detaching defect has significant impacts on the primary resonances of the EMI response and generates additional peaks with complex modal shapes. Also, the functional defects can result in distinctive EMI response characteristics, which are promising for assessing the functional condition of the smart interface.

We apply and compare various Artificial Neural Network (ANN) and other algorithms for automatic morphological classification of galaxies. The ANNs are presented here mathematically, as non-linear extensions of conventional statistical methods in Astronomy. The methods are illustrated using different subsets Artificial Neural Network (ANN) and other algorithms for automatic morphological classification of galaxies. The ANNs are presented here mathematically, as non-linear extensions of conventional statistical methods in Astronomy. The methods are illustrated using different subsets from the ESO-LV catalogue, for which both machine parameters and human classification are available. The main methods we explore are: (i) Principal Component Analysis (PCA) which tells how independent and informative the input parameters are. (ii) Encoder Neural Network which allows us to find both linear (PCA-like) and non-linear combinations of the input, illustrating an example of unsupervised ANN. (iii) Supervised ANN (using the Backpropagation or Quasi-Newton algorithms) based on a training set for which the human classification is known. Here the output for previously unclassified galaxies can be interpreted as either a continuous (analog) output (e.g. $T$-type) or a Bayesian {\it a posteriori} probability for each class. Although the ESO-LV parameters are sub-optimal, the success of the ANN in reproducing the human classification is 2 $T$-type units, similar to the degree of agreement between two human experts who classify the same galaxy images on plate material. We also examine the aspects of ANN configurations, reproducibility, scaling of input parameters and redshift information.

Ship stiffened panels, typically flat plates reinforced with various types of stiffeners, form a substantial part of a ship’s structure and are susceptible to resonance, especially in areas such as the after peak structure, engine room, and accommodation compartments. These vibrations are primarily excited by main engine and propeller forces. Conventional methods such as finite element analysis (FEA) and plate theory are widely used to estimate vibration frequencies, but they are time-consuming and computationally intensive when applied to numerous stiffened panels. This study proposes a machine learning approach using an artificial neural network (ANN) algorithm to efficiently predict the vibration frequencies of ship stiffened panels. A crude oil tanker is chosen as the case study, and FEA is conducted to generate the vibration frequency and mass data for panels across critical regions. The input layer features for the ANN include panel area, thickness, number and area of stiffeners, fluid density, number of fluid contact sides, and overall structural stiffness. The ANN model predicts two outputs: the fundamental vibration frequency and the mass of the panel structure. To evaluate the model performance, hyperparameters such as the number of hidden neurons are optimized. The results indicate that the ANN achieves accurate predictions while significantly reducing the time and resources required compared with conventional methods. This approach offers a promising tool for accelerating the local vibration analysis process in ship structural design.

In this work, a computational framework is proposed for fatigue damage estimation in structural systems by integrating operational experimental measurements in a high-fidelity, large-scale finite element model. The proposed method is applied in a linear steel substructure of a lignite grinder assembly at a Public Power Corporation power plant. A finite element model of the steel base is developed and updated to match the dynamic characteristics measured in real operating conditions. This is achieved through coupled use of numerical and experimental methods for identifying, updating, and optimizing a high-fidelity finite element model. The full stress time histories of the complex mechanical assembly are estimated, at critical locations, by imposing operational vibration measurements from a limited number of sensors in the updated finite element model. Fatigue damage and remaining lifetime is subsequently estimated via commonly adopted engineering approaches, such as Palmgren–Miner damage rule, S–N curves, and rainflow cycle counting. Incorporation of a numerical model of the structure in the response estimation procedure permits stress estimation at unmeasured locations, thereby enabling the drawing of a complete and substantially dense fatigue map consistent with the vibration measurements. Fatigue predictions via the proposed framework are highly correlated to experimental fatigue results, proving the efficiency and applicability of the framework.

Unmanned Aerial Vehicles (UAVs) have become an integral part of several real-world applications. Their combination with other evolving paradigms such as image recognition using machine learning or deep learning algorithms has contributed to the suitability for use in smart agriculture and weed detection applications. In this paper, the performances of the Artificial Neural Network (ANN) and AlexNet algorithms for weed detection using UAV-based images have been studied. An image dataset containing 15336 segments with the following breakdown: 3249 of soil, 7376 of soybean, 3520 grass and 1191 of broadleaf weeds has been used. The partitioning for train and test sets has been done in the ratio of 70:30. Simulation results show that the conventional ANN algorithm provide an accuracy of 48.09% while the AlexNet algorithms gives an accuracy 99.8% on the test dataset.

Grey wolf optimization (GWO) is a recent and popular swarm-based metaheuristic approach. It has been used in numerous fields such as numerical optimization, engineering problems, and machine learning. The different variants of GWO have been developed in the last 5 years for solving optimization problems in diverse fields. Like other metaheuristic algorithms, GWO also suffers from local optima and slow convergence problems, resulted in degraded performance. An adequate equilibrium among exploration and exploitation is a key factor to the success of meta-heuristic algorithms especially for optimization task. In this paper, a new variant of GWO, called inertia motivated GWO (IMGWO) is proposed. The aim of IMGWO is to establish better balance between exploration and exploitation. Traditionally, artificial neural network (ANN) with backpropagation (BP) depends on initial values and in turn, attains poor convergence. The metaheuristic approaches are better alternative instead of BP. The proposed IMGWO is used to train the ANN to prove its competency in terms of prediction. The proposed IMGWO-ANN is used for medical diagnosis task. Some benchmark medical datasets including heart disease, breast cancer, hepatitis, and parkinson's diseases are used for assessing the performance of IMGWO-ANN. The performance measures are described in terms of mean squared errors (MSEs), classification accuracies, sensitivities, specificities, the area under the curve (AUC), and receiver operating characteristic (ROC) curve. It is found that IMGWO outperforms than three popular metaheuristic approaches including GWO, genetic algorithm (GA), and particle swarm optimization (PSO). Results confirmed the potency of IMGWO as a viable learning technique for an ANN.