Search

Memristors have several chaotic dynamic models and have been used successfully in various fields, including secure communication systems, information storage, and artificial neural networks. The memristor-based four-dimensional chaotic (FDMC) systems generate unpredictable and intricate time domain signals. Parameter fluctuations in the FDMC system may give birth to chaos, making it difficult to suppress. Stabilizing chaos in the FDMC system improves the circuit's performance. This paper synthesizes a novel time-efficient chatter-free nonlinear robust adaptive control (NLRAC) technique that stabilizes chaos in the FDMC system affected by time-varying unknown bounded exogenous disturbances and model uncertainties. The proposed NLRAC strategy decimates the time-varying unknown bounded exogenous disturbances and model uncertainties effects; it establishes a faster, smoother state-variable trajectories convergence to the zero vicinity. The theoretical analysis and mathematical proofs are based on the Lyapunov stability technique. Computer simulation results show that the proposed NLRAC technique effectively brings the FDMC system's state-variable trajectories to zero with reduced fluctuations for control input signals and state-variable trajectories. This feedback controller's attribute enhances closed-loop stability performance, improves precision, and reduces risk overshoot. The paper includes comparative computer simulation results to endorse the proposed controller performance. [ABSTRACT FROM AUTHOR]

This paper proposes a hybrid forecasting model combining auto-regressive integrated moving average (ARIMA) and artificial neural network (ANN) techniques to improve the software fault forecasting and hence improvising the reliability of software. Software reliability forecasting plays a critical role in software development and maintenance, as it helps to identify potential errors and improve the overall performance of software systems. The proposed model leverages the strengths of both ARIMA and ANN, allowing for more accurate predictions and better handling of complex and dynamic software systems. The effectiveness of the hybrid model is evaluated using real-world software data, demonstrating its superiority over traditional forecasting methods. This research contributes to the development of more robust and reliable software systems, which are essential in today's rapidly evolving technological landscape. [ABSTRACT FROM AUTHOR]

Most data collected during routine monitoring of railway station buildings are categorized as in good health, with only a small percentage of samples corresponding to a damaged state. Standard deep neural networks (DNNs) process target samples regarded as normal samples. When typical DNNs are confronted with imbalanced samples, namely, samples with a low proportion of abnormal samples (e.g., damaged stage), this can lead to a high rate of misdiagnosis. To solve this problem, this paper suggests a novel damage monitoring model for railway station buildings, called cluster-based undersampling and Siamese artificial neural network. In this model, normal samples are undersampled based on clustering, and the clustering center and damage samples are combined in a training dataset to reduce the imbalanced rate of damage samples. SANN maps the original space to a feature space where imbalanced damage states are easier to distinguish. Based on SANN, a data-pair selection strategy based on a feedback mechanism is designed to sufficiently mine sample characteristics. A loss function that combines similarity calculation and multi-classification cross-entropy is proposed to improve the representation and classification performance of the model. Six popular algorithms are compared through experiments based on the actual monitoring datasets obtained at the Shijiazhuang Railway Station in China. For different imbalance ratios, the proposed model displayed the highest performance in all indicators. The recall rate for certain imbalanced classifications increased by over 30% compared to the baseline method, verifying the effectiveness and superiority of the model in identifying imbalanced damage states. [ABSTRACT FROM AUTHOR]

Faced with the cost of local management of IT infrastructure, many transportation operators have decided to use Cloud Computing services via its providers. The latter make resources available to transportation operators in the form of Virtual Machine (VM). Thus, transportation operators only use a limited number of virtual machines capable of satisfying their needs. This contributes to the reduction in the costs of the customer IT infrastructure. However, in DRT Demand-Responsive Transportation system and in order to avoid service overload and largely unused resources, it is important to anticipate the number of future passenger demands. Considering the importance of these challenges, this paper presents a Cloud-based Demand-Responsive Transportation system. Such a system is based on two principles: (I) forecasting passenger demand, in order to prepare the conditions for exploiting resources and achieving their optimal efficiency. For this purpose, actual passenger demand is predicted by applying an artificial neural network based on a Multilayer Feed-Forward Neural Network (MLFF). It constitutes a reference predicting the future passenger demands based on past demands and thus, obtaining an appropriate prediction of future loads. (II) Pre-allocate resources, to avoid overloading or over-provisioning their capacity to better manage peaks in demand, all based on an estimation process that will help predetermine resource requirements. System evaluation is performed by using OpenNebula middleware, and real passenger demand data have shown performance gains ranging up to a 25% margin for utilization rate applied to forecasting future demand. [ABSTRACT FROM AUTHOR]

Efficient well design requires accurate estimation of rock petrophysical parameters that represent a reservoir. For compressional waves, particle motion is in the direction of propagation; alternatively, for shear waves, it is perpendicular to the propagation direction. Understanding the velocity of these waves reveals important details about the reservoir. Shear wave velocity (Vs) can be used for estimating mechanical properties of rock that will be used while determining casing setting depth, rate of penetration, and fracture pressure. Unfortunately, Vs data cannot be obtained directly in the field due to field constraints and high cost. On the other hand, compressional sonic data sets are available. There are many time- and money-consuming techniques that target the estimation of Vs from core analysis. Moreover, there are uncertain models such as the Xu–Payne petrophysical model, which are based on pore structures, rock compositions, and fluid properties. Although many studies provide various methods to estimate Vs from empirical correlations, petrophysical models, and artificial intelligence, these studies are limited to small ranges of used data. In this paper, a new artificial neural network (ANN) model is developed to accurately predict Vs as a function of porosity (∅\documentclass[12pt]{minimal}\usepackage{amsmath}\usepackage{wasysym}\usepackage{amsfonts}\usepackage{amssymb}\usepackage{amsbsy}\usepackage{mathrsfs}\usepackage{upgreek}\setlength{\oddsidemargin}{-69pt}\begin{document}$$\boldsymbol{\varnothing }$$\end{document}), gamma-ray (GR), bulk density (ρb)\documentclass[12pt]{minimal}\usepackage{amsmath}\usepackage{wasysym}\usepackage{amsfonts}\usepackage{amssymb}\usepackage{amsbsy}\usepackage{mathrsfs}\usepackage{upgreek}\setlength{\oddsidemargin}{-69pt}\begin{document}$$({{\varvec{\rho}}}_{{\text{b}}})$$\end{document}, and compressional velocity (Vc) with wide data ranges. The new model is built using data set comprising 2350 data points, where 1645 data sets are used to process the model, and the other 705 data sets are used to validate the new model. Results showed high accuracy with a coefficient of determination of about 0.958. The proposed model can be applied directly in Excel sheet without need to any other software. [ABSTRACT FROM AUTHOR]

Feature selection, reducing number of input variables to develop classification model, is an important process to reduce computational and modeling complexity and affects the performance of image process. In this paper, we have proposed new statistical approaches for feature selection based on sample selection. We have applied our new approaches to grapevine leaves data that possess properties of shape, thickness, featheriness, and slickness that are investigated in images. To analyze such kind of data by using image process, thousands of features are created and selection of features plays important role to predict the outcome properly. In our numerical study, convolutional neural networks have been used as feature extractors and then obtained features from the last average pooling layer to detect the type of grapevine leaves from images. These features have been reduced by using our suggested four statistical methods: simple random sampling, ranked set sampling, extreme ranked set sampling, moving extreme ranked set sampling. Then, selected features have been classified with artificial neural network and we obtained the best accuracy of 97.33% with our proposed approaches. Based on our empirical analysis, it has been determined that the proposed approach exhibits efficacy in the classification of grapevine leaf types. Furthermore, it possesses the potential for integration into various computational devices. [ABSTRACT FROM AUTHOR]

The proposed research work analyzes the bio-inspired problem through artificial neural networks with a feed-forward approach utilized to approximate the numerical results for singular nonlinear bio-heat equation (BHE) with boundary conditions based on four different scenarios created on the variation of environmental temperature to illustrate the effects of temperature on the human dermal region. The log-sigmoid function is used to construct the fitness function, while the optimization solvers: pattern search and genetic algorithm, are then hybridized with the active set technique, interior point technique, sequential quadratic programming for accurate and reliable results of the proposed BHE with various scenarios where the convergence of the numerical results is also analyzed. Moreover, a comparison of the proposed technique is expressed through residual error that reveals the nature of the numerical results and their efficiency. Additionally, a comprehensive statistical analysis is presented for the designed technique to better illustrate the accuracy, reliability, and efficiency of the obtained results. [ABSTRACT FROM AUTHOR]