Neural Network Technique Research Articles

Application of Convolutional Neural Network (CNN) and different other techniques for the restoration of degraded folk artworks: a comparative performance analysis

Application of Convolutional Neural Network (CNN) and different other techniques for the restoration of degraded folk artworks: a comparative performance analysis

Classification of Ship Type from Combination of HMM–DNN–CNN Models Based on Ship Trajectory Features

This study proposes an enhanced ship-type classification model that employs a sequential processing methodology integrating hidden Markov model (HMM), deep neural network (DNN), and convolutional neural network (CNN) techniques. Four different ship types—fishing boat, passenger, container, and other ship—were classified using multiple ship trajectory features extracted from the automatic identification system (AIS) and small fishing vessel tracking system. For model optimization, both ship datasets were transformed into various formats corresponding to multiple models, incorporating data enhancement and augmentation approaches. Speed over ground, course over ground, rate of turn, rate of turn in speed, berth distance, latitude/longitude, and heading were used as input parameters. The HMM–DNN–CNN combination was obtained as the optimal model (average F-1 score: 97.54%), achieving individual classification performances of 99.03%, 97.46%, and 95.83% for fishing boats, passenger ships, and container ships, respectively. The proposed approach outperformed previous approaches in prediction accuracy, with further improvements anticipated when implemented on a large-scale real-time data collection system.

MODELING COMMERCIAL BANKS' KEY DRIVERS FOR FUND MOBILIZATION IN NIGERIA USING ARTIFICIAL NEURAL NETWORKS

This study explores the core role driving the willingness of commercial banks to mobilise funds for economic development based on the Multilayer Perceptron (MLP) of the artificial neural network (ANN) technique. This approach allows for a nuanced understanding of interdependencies that traditional linear models may overlook, making it particularly suited for analyzing intricate financial systems in emerging economies like Nigeria. This study is critically supported by the Financial Intermediation Theory, which explains the role of financial institutions as intermediaries that facilitate the flow of funds from savers to borrowers. Data used for the analysis and prediction is purposively obtained from 10 commercial banks in Nigeria. The results show that financial institutions are mostly driven to mobilize funds because of their commitment to ensuring an adequate flow of money to serve the deficit sectors of the economy compared to any other underlying reasons. The prediction performs optimally with an r2 value of 86.5% with a cubic predictability model of ????. ???????????????? +????. ???????????? + ????. ???????????????? − ????. ???????????????? − ????. ???????? = ????.????????????????, and the Sum of Square Error (SSE) of 0.002 is minimal based on practice. This study is significant as it could enable financial institutions to make future role predictions relating to this concept in Nigerian settings or other settings analogous to Nigeria using the derived ANN model. These insights provide a basis for banks in Nigeria and similar economies to make strategic financial decisions, supporting the application of ANN models to predict and enhance financial institutions' roles in economic development.

Investigating the effects of destructive factors on pulse repetition interval modulation type recognition using deep convolutional neural networks based on transfer learning

AbstractAutomation and self‐sufficiency in the complex environment of modern electronic warfare (EW) are critical and necessary issues in electronic intelligence and support systems to detect real‐time and accurate threat radars. The task of these systems is to search, discover, analyse, and identify the parameters of radar signals. However, recognition pulse repetition interval (PRI) modulation is challenging in natural environments due to destructive factors, including missing pulses (MP), spurious pulses (SP), and large outliers (LO) (caused by antenna scanning), which lead to noisy sequences of PRI variation patterns. The current article examines the effects of destructive factors on recognising PRI modulation in radar signals using deep convolutional neural networks (DCNNs). The article uses simulations based on the actual environment to generate data and consider destructive factors with different percentages. The number of images obtained by applying the sum of destructive factors for each range of destructive factors (with different percentages) considered is 30,000. It is common for six types of modulation. Then, the DCNN models, including VGG16, ResNet50V2, InceptionV3, Xception, and MobileNetV2, are trained using the transfer learning method. The simulation results show that the accuracy of training and testing the models decreases significantly with the increase in the percentage of destructive factors. Also, the effects of the model type on the performance of the models have been investigated, and the results have shown that some models are more resistant to destruction and retain more accuracy. Finally, this analysis shows that to improve the performance of deep neural network (DNN) techniques in the face of changes caused by destructive factors, it is necessary to pay attention to these factors and apply appropriate strategies.

Analysing the Influence of Augmented Reality on Organization Performance via Supply and Logistics Value Chain Functions: A Hybrid ANN-PLS Model Assessment in the Gulf Cooperation Council Region

Background: Despite the resurgence of interest in augmented reality (AR) due to Industry 4.0 and its ability to resolve several challenges faced by current business models, comprehensive research examining the capabilities of AR in supply chain management (SCM) and logistics remains limited. This article aims to investigate the potential effects of AR technology on organizational performance through the mediation role of SCM and logistics value chain functions to address the existing knowledge gap. Methods: This research employed a cross-sectional design and an explanatory survey as a deductive approach for hypothesis development. The primary data collection method involved the self-administration of a questionnaire to furniture suppliers located in the Gulf Cooperation Council (GCC), including six countries. Of the 656 questionnaires submitted to suppliers, 483 were considered usable, yielding a response rate of 73.6%. The research utilized partial least squares structural equation modelling (PLS-SEM) and artificial neural network (ANN) techniques to evaluate the gathered data. Results: The current paper’s statistical evidence demonstrates that AR implementation has a positive impact on the supply and logistics value chain activities and organizational performance of furniture suppliers in the GCC region. Moreover, it illustrates that the design and planning variable of supply chain value dominates as the primary predictor of organization performance. The results indicated that the ANN strategy provided a more comprehensive explanation of internally generated constructs compared to the PLS-SEM technique. Conclusions: This study demonstrates its usefulness by advising furniture industry decision-makers on what to avoid and what aspects to consider when creating plans and regulations. The report also suggests operations managers apply machine learning (ANN) for prediction and decision-making in supply and operations value chains. This essay looks at how the AR and resource-based supply value chain view may affect company performance across countries, firm sizes, and ages.

ECG signal reconstruction from PPG using a hybrid attention-based deep learning network

Electrocardiography (ECG) and photoplethysmography (PPG) are non-invasive methods used to quantify signals originating from the cardiovascular system. Although there is a strong correlation between the cycles of the two measures, the correlation between the waveforms has received little attention in research. Measuring the PPG is significantly simpler and more convenient compared to the ECG measure. Recent research has demonstrated that PPG signals can be utilized to rebuild the ECG signals, suggesting that healthcare professionals might acquire a comprehensive comprehension of patients' cardiovascular well-being by only measuring PPG. With the advancement of artificial intelligence, the deep learning model has made significant progress in reconstructing ECG signals from PPG signals. However, the quality of the reconstructed ECG signal is still in need of more enhancement. In order to enhance the quality of the reconstructed ECG signal, we propose an innovative hybrid attention-based bidirectional recurrent neural network (Bi-RNN) that incorporates a dilated convolutional neural network technique for the purpose of reconstructing ECG signals from PPG signals. This addresses issues that occur when standard dilated CNN (DCNN) models neglect the link between circumstances and dispersion of gradients. The suggested approach maximizes the utilization of the DCNN and Bi-RNN unit design to provide fusion features. In order to ensure the model's resilience to deformation, it is imperative to initially extract spatial properties utilizing convolutional neural networks (CNNs). Once we have obtained geographic data, we employ BiLSTM to extract temporal features. The proposed model is so-called hybrid attention-based CNN and BiLSTM (HA-CNN-BiLSTM). BiLSTM mitigates the issues of gradient vanishing and exploding while maintaining accuracy. To showcase the advantages of the suggested model, we conduct a comparison between HA-CNN-BiLSTM and each separate state-of-the-art method. The simulation results indicated that the proposed method yielded superior root mean square error (RMSE) when reconstructing the ECG signal across different optimizers. The results also demonstrated that the proposed method results in the lowest RMSE with SGDM optimizer which is 0.031.

Solving Multi‐Term Time‐Fractional Diffusion Equations Using a High‐Order Fractional Finite Difference Scheme Accompanied by Neural Network Techniques

ABSTRACTThis article is devoted to solving multi‐term time‐fractional diffusion equations with a high‐order finite difference scheme. We approximate the temporal fractional derivatives by the L1‐2‐3 formula, an expansion of the L1 formula with higher accuracy. We employ neural network strategies and automatic differentiation techniques for approximating integer‐order derivatives. In the present work, we propose very important lemmas and theorems to prove the unconditional stability and convergence of the proposed scheme. Extensive numerical experiments for one‐ and two‐dimensional problems, especially for curved boundaries, confirm the theoretical convergence orders. Comparisons with fractional physics‐informed neural networks and finite difference methods in solving the multi‐term time‐fractional diffusion equations demonstrate the superiority of the proposed method. It is also illustrated that the proposed scheme can efficiently and accurately extract the pattern of the solutions even when noise corruption up to ten percent is imposed on the forcing term.

Reproduction and generalization of robot trajectory tracking control method using reinforcement learning and neural network techniques

Abstract. This paper introduces a method for controlling the trajectory of a manipulator robot with uncertainty, using reinforcement learning. The control is designed to work even when there are limitations on the inputs to the system. Reinforcement learning and neural networks are employed alongside standard robust control techniques to enhance the fixed-time convergence of the system state. A novel algorithm is proposed to develop a reinforcement learning-based approach. This approach utilizes radial basis function neural networks and nonsingular fast terminal sliding mode control to ensure error convergence within a predetermined time. This paper presents the task of monitoring the intended path followed by robotic arms in the presence of uncertain and unfamiliar disruptions. The experimental results validate that the suggested approach substantially improves both the stability and accuracy of trajectory tracking, making it more feasible for real-world applications in robotic systems.

Prescribed tracking of stochastic nonlinear systems with indifferentiable non-affine terms and dead zone

This paper considers the constrained tracking problem for a class of stochastic nonlinear systems with non-affine terms and dead zone. The non-affine terms are not required to be differentiable, resulting in that the traditional algorithms cannot address the tracking problem efficiently. To this end, a semi-bounded condition is utilized to convert the non-affine terms into a pseudo-affine form. Moreover, the transformed systems include extra undesired spilled variables and the asymmetric dead zone input. The separation and approximation technique of neural networks are used to address this issue. By introducing a performance function, an adaptive controller is developed such that the signals of the closed-loop system are bounded in probability, and the tracking error satisfies the prescribed performance. Simulation results demonstrate the effectiveness of the proposed method.

Artificial Intelligence-Based Direct Power Control for Power Quality Improvement in a WT-DFIG System via Neural Networks: Prediction and Classification Techniques

This paper discusses the improvement of power quality injected into the AC grid. This approach is achieved by enhancing the quality of injected power signals and mastering the active and reactive power exchanged between the DFIG based wind turbine (WT-DFIG) and the electrical grid, resulting in an improvement of the overall system performance and efficiency. This study includes all WT-DFIG operating modes, successively and continuously, as well as all local reactive power compensation modes. Therefore, novel control strategies are proposed in this paper for wind energy conversion systems based on artificial intelligence techniques. These techniques include Neural Network Prediction (PNN-DPC) and Classification (CNN-DPC). They aim to eliminate the drawbacks and difficulties associated with conventional Direct Power Control (C-DPC), while retaining its advantages. The paper also provides a thorough explanation of the mathematical models for neural network techniques and WT-DFIG system models. The MATLAB/Simulink environment is used to investigate the performance of the proposed techniques under different conditions and operating modes related to different scenarios. The results reveal a significant reduction in the ripple of the generated active power and the compensated local reactive power, better quality of the generated signal currents and a remarkable reduction in the current total harmonic distortion (THD). Furthermore, compared to C-DPC, PNN-DPC achieves a reduction of 72.07% in active power ripples, 77.07% in reactive power ripples, and 76.79% in current Total Harmonic Distortion (THD). CNN-DPC shows similar improvements with 72.04%, 77.13%, and 76.54% of reductions respectively. In addition, CNN-DPC slightly outperforms PNN-DPC. Nevertheless, both proposed control techniques show significant improvements in all characteristics compared to other methods. Consequently, the proposed control strategies indicate that artificial intelligence has the potential to improve the power quality and performance of wind power conversion system.

Development of methods for monitoring and optimization of underground drainage systems using wireless sensor networks and ultra-wideband antennas

This research focuses on optimizing ultra-wideband (UWB) antennas, which are critical in modern communication systems due to their wide frequency range (3.1–10.6 GHz) and high data transmission capabilities. The study addresses the challenge of optimizing key antenna parameters – such as return loss, peak gain, and radiation efficiency – while also ensuring energy efficiency and network longevity. Traditional optimization methods, such as LEACH-C, often fail to balance these factors, leading to suboptimal performance. To solve this problem, the researchers developed the Generalized Position-based Optimization Neural Network (GPON) for UWB antenna optimization. They also evaluated the Position-based Hybrid Neural Network (PAN) method, comparing its performance with existing algorithms including LEACH-C, Firefly Algorithm (FA), HFAPSO, FA-ANN, and HWOABCA. The GPON model reduced return loss to 25.5 dB at 3.5 GHz and improved peak gain to 4.2 dB i, while maintaining 92 % radiation efficiency. In contrast, PAN demonstrated a 15–25 % improvement in residual energy and extended network lifetime by 20 % compared to LEACH-C. These improvements were due to the integration of advanced neural network techniques in GPON and the effective use of positional data in PAN, enabling more precise and adaptive optimization. The ability to balance multiple performance metrics simultaneously – a challenge previous models struggled with – is a key feature. This balance is crucial for UWB antennas in communication systems where both performance and energy efficiency are vital. The findings are especially relevant for practical applications in wireless sensor networks, mobile communications, and radar systems, requiring long-term network reliability and optimal antenna performance

Free Vibration of Axially Functionally Graded Porous Beams with Varying Cross-Section

This study aims to determine the natural frequencies of axially functionally graded porous material (FGPM) beams with non-uniform cross-sections under a variety of boundary conditions. Two types of pore distribution were used: even and uneven. Initially, an analytical method was used to determine the natural frequencies of FGPM beams with different cross-sections. The Fredholm integral approach was used to obtain the characteristic equations. Furthermore, the collected results are confirmed and compared to the existing literature. The artificial neural network (ANN) technique is then used to predict the fluctuations in the natural frequency of a clamped–simply supported axially FGPM beam with a non-uniform cross-section. The prediction of natural frequencies by ANN is based on a large dataset of over 1[Formula: see text]100 data points acquired from the analytical solution obtained in this study and data available in the literature. This research conducts a parametric analysis to evaluate the influence of numerous aspects, including as beam characteristics, material properties, geometric details, gradient parameters, and porosity distribution, on functionally graded (FG) beam vibration behavior. Finally, both ANN and computational analysis demonstrate that porosity distributions and non-uniform cross-sectional area have a substantial effect on the natural frequencies of axially FG beams.

Various optimized artificial neural network simulations of advection-diffusion processes

The aim of this research is to describe an artificial neural network (ANN) based method to approximate the solutions of the natural advection-diffusion equations. Although the solutions of these equations can be obtained by various effective numerical methods, feed forward neural network (FFNN) techniques combined with different optimization techniques offer a more practicable and flexible alternative than the traditional approaches to solve those equations. However, the ability of FFNN techniques to solve partial differential equations is a questionable issue and has not yet been fully concluded in the existing literature. The reliability and accuracy of computational results can be advanced by the choice of optimization techniques. Therefore, this study aims to take an effective step towards presenting the ability to solve the advection-diffusion equations by leveraging the inherent benefits of ANN methods while avoiding some of the limitations of traditional approaches. In this technique, the solution process requires minimizing the error generated by using a differential equation whose solution is considered as a trial solution. More specifically, this study uses a FFNN and backpropagation technique, one of the variants of the ANN method, to minimize the error and the adjustment of parameters. In the solution process, the loss function (error) needs to be minimized; this is accomplished by fitting the trial function into the differential equation using appropriate optimization techniques and obtaining the network output. Therefore, in this study, the commonly used techniques in the literature, namely gradient descent (GD), particle swarm optimization (PSO) and artificial bee colony (ABC), are selected to compare the effectiveness of gradient and gradient-free optimization techniques in solving the advection-diffusion equation. The calculations with all three optimization techniques for linear and nonlinear advection-diffusion equations have been run several times to obtain the optimum accuracy of the results. The computed results are seen to be very promising and in good agreement with the effective numerical methods and the physics-informed neural network (PINN) method in the literature. It is also concluded that the PSO-based algorithm outperforms other methods in terms of accuracy.

Modeling the rainfall–runoff process in the Bird Creek River Basin: a comparative analysis of conceptual and artificial neural network techniques

ABSTRACT The modeling of the rainfall–runoff (RR) process is a key component for water resources projects, planning, and management for which conceptual and data-driven modeling techniques are utilized. However, these techniques in the modeling of the RR process have their own benefits, and their performance need to be explored in real basins. In this paper, five conceptual models (namely, AWBM, Sacramento, SimHyd, SMAR, and TANK) and an artificial neural network (ANN) model have been developed and their performances have been assessed using the rainfall, runoff, and other climatic data derived from the Bird Creek Basin, USA. The results obtained from the study suggest that the SimHyd performed the best among all the conceptual models during testing. The ANN model performance in simulating the RR process was found to be the best among all the models developed in this study during testing with the highest values of R = 0.941, E = 0.994 and all threshold statistics and least values of AARE = 38.9 and NRMSE = 0.031. Overall, it can be concluded that although the conceptual models are highly comprehensible, the ANN models are able to simulate the flow more accurately than any of the conceptual models developed in this study.

Implementation of a novel secured authentication protocol for cyber security applications

Robust verification protocols are crucial for maintaining the security and reliability of sensitive information due to the increasing complexity of cyber-attacks. This paper introduces a novel 5G Secure Handover Protocol aimed at addressing security and effectiveness issues encountered in existing systems. The proposed protocol is robust against various attacks, including de-synchronization, replay, man-in-the-middle (MITM), denial of services (DoS), and jamming, ensures perfect forward key secrecy, safeguarding communication confidentiality. The proposed protocol utilizes a combination of spiking neural network and fuzzy logic (SNN-FL) techniques that must choose the goal cell as carefully as possible before initiating the transfer process. By combining fuzzy logic and spiking neural networks to reduce handover latency and thwart several types of cyberattacks, the proposed 5G Secure Handover Protocol improves security. Extensive simulations show its efficacy and emphasize its potential for safe communication in large-scale cybersecurity applications. The paper presents a novel secure authentication protocol that significantly reduces handover delays and improves efficiency. Simulations show its resilience against common security threats, protecting sensitive information and maintaining secure communication channels. The protocol, with low communication expenses, complex spatial, and latency for changeover verification, is ideal for large-scale cybersecurity applications, contributing to the development of secure digital authentication mechanisms.

A survey on feature extraction and learning techniques for link prediction in homogeneous and heterogeneous complex networks

Complex networks are commonly observed in several real-world areas, such as social, biological, and technical systems, where they exhibit complicated patterns of connectedness and organised clusters. These networks have intricate topological characteristics that frequently elude conventional characterization. Link prediction in complex networks, like data flow in telecommunications networks, protein interactions in biological systems, and social media interactions on platforms like Facebook, etc., is an essential element of network analytics and presents fresh research challenges. Consequently, there is a growing emphasis in research on creating new link prediction methods for different network applications. This survey investigates several strategies related to link prediction, ranging from feature extraction based to feature learning based techniques, with a specific focus on their utilisation in dynamic and developing network topologies. Furthermore, this paper emphasises on a wide variety of feature learning techniques that go beyond basic feature extraction and matrix factorization. It includes advanced learning-based algorithms and neural network techniques specifically designed for link prediction. The study also presents evaluation results of different link prediction techniques on homogeneous and heterogeneous network datasets, and provides a thorough examination of existing methods and potential areas for further investigation.

Box-Behnken Design for MAFM Precision Surface Finishing of Al-6063/SiC/B<sub>4</sub>C Composites: A Comparative Study with Nature-Inspired Algorithms

Precision polishing is difficult for advanced materials like silicon carbide and boron carbide. Magnetic abrasive flow machining (MAFM) has become an effective method for cleaning, deburring, and polishing metal and high-tech engineering parts. By finishing hybrid Al/SiC/B4C-metal matrix composites (MMCs), this research uses MAFM for experimental readings. The present work is innovative due to the aluminum workpiece fixture, hybrid composites, and response surface methodology (RSM) modeling. The neural simulation of the MAFM process and nature-inspired error reduction make it unique. Using six input and two output parameters, a generic framework is created. Box-Behnken design (BBD) of response surface methodology plans and executes 54 runs of experimentation. The hybrid artificial neural network (ANN) technique is used to compare the MAFM process systematically. ANN is used to model parameter input-output relations. To anticipate the created surface accurately, regression models must be precise. These hybrid particle swarm optimization (PSO)-genetic algorithm (GA)-simulated annealing (SA) algorithms optimize the MAFM process. Additionally, trained ANN models outperform the BBD model in prediction. For optimal error reduction, the neural network uses Bayesian regularization with 112 iterations. The ANN model regression graph shows a correlation between inputs and outputs. A scanning electron microscope (SEM) with 300-magnification examines the workpiece surface. According to SEM, MAFM provides fine surface textures, thus reducing abnormalities.

A hybrid decision support system in medical emergencies using artificial neural network and hyperbolic secant grey wolf optimization techniques

A hybrid decision support system in medical emergencies using artificial neural network and hyperbolic secant grey wolf optimization techniques

Advanced hybrid neural network techniques for minimizing gas turbine emissions

Purpose Emissions have significant environmental impacts. Hence, minimizing emissions is essential. This study aims to use a hybrid neural network model to predict carbon monoxide (CO) and nitrogen oxide (NOx) emissions from gas turbines (GTs) to enhance emission prediction for GTs in predictive emissions monitoring systems (PEMS). Design/methodology/approach The hybrid model architecture combines convolutional neural networks (CNN) and bidirectional long-short-term memory (Bi-LSTM) networks called CNN-BiLSTM with modified extrinsic attention regression. Over five years, data from a GT power plant was uploaded to Google Colab, split into training and testing sets (80:20), and evaluated using test matrices. The model’s performance was benchmarked against state-of-the-art emissions prediction methodologies. Findings The model showed promising results for GT CO and NOx emissions. CO predictions had a slight underestimation bias of −0.01, with root mean-squared error (RMSE) of 0.064, mean absolute error (MAE) of 0.04 and R2 of 0.82. NOx predictions had an RMSE of 0.051, MAE of 0.036, R2 of 0.887 and a slight overestimation bias of +0.01. Research limitations/implications While the model demonstrates relative accuracy in CO emission predictions, there is potential for further improvement in future research. Practical implications Implementing the model in real-time PEMS and establishing a continuous feedback loop will ensure accuracy in real-world applications, enhance GT functioning and reduce emissions, fuel consumption and running costs. Social implications Accurate GT emissions predictions support stricter emission standards, promote sustainable development goals and ensure a healthier societal environment. Originality/value This paper presents a novel approach that integrates CNN and Bi-LSTM networks. It considers both spatial and temporal data to mitigate previous prediction shortcomings.

Adaptive Fault-Tolerant Tracking Control for Multi-Joint Robot Manipulators via Neural Network-Based Synchronization.

In this paper, adaptive fault-tolerant control for multi-joint robot manipulators is proposed through the combination of synchronous techniques and neural networks. By using a synchronization technique, the position error at each joint simultaneously approaches zero during convergence due to the constraints imposed by the synchronization controller. This aspect is particularly important in fault-tolerant control, as it enables the robot to rapidly and effectively reduce the impact of faults, ensuring the performance of the robot when faults occur. Additionally, the neural network technique is used to compensate for uncertainty, disturbances, and faults in the system via online updating. Firstly, novel robust synchronous control for a robot manipulator based on terminal sliding mode control is presented. Subsequently, a combination of the novel synchronous control and neural network is proposed to enhance the fault tolerance of the robot manipulator. Finally, simulation results for a 3-DOF robot manipulator are presented to demonstrate the effectiveness of the proposed controller in comparison to traditional control techniques.