This paper investigated an innovative prediction approach using the bidirectional long short-term memory (BiLSTM) model for the forecasting of solar radiation in the smart farm in Naju, South Jeolla Province. Accurate solar radiation prediction holds substantial significance in facilitating efficient solar power generation, significantly impacting agricultural sustainability and resource utilization. This study rigorously assessed the effectiveness of various predictive models for forecasting solar radiation, a crucial factor in optimizing solar energy utilization in greenhouse settings. The variety of statistical and machine learning models aims to improve the accuracy of solar radiation prediction, which is crucial for precise energy management and cultivation practices. An hour-ahead mean absolute error (MAE) of 13.53 demonstrated the proposed BiLSTM model's impressive forecasting capabilities. The comparative analysis among individual models then revealed that the LSTM model achieves an MAE of 15.23, extreme gradient boosting (XGBoost) at 24.64, and autoregressive integrated moving average (ARIMA) at 28.52. This exploration underscored the important role of accurate solar radiation forecasting, specifically highlighting the effectiveness of the BiLSTM model in optimizing solar power generation within greenhouse environments. Its importance extended to the promotion of sustainable agricultural practices and the improvement of resource-efficient energy control strategies.
The article addressed the Lagrange exponential stability of Cohen-Grossberg inertial neural networks (CGINNs) with quaternion-valued state variables and unbounded time-varying delays. The study extended stability analysis to a more complex and realistic model that included the inertial term, representing the system's acceleration-like memory effect, and quaternion-valued variables, representing multidimensional signals such as 3D rotations or color images. Unbounded time-varying delays added complexity while properly replicating real-world neural network (NN) dynamics. Unlike traditional studies that relied on order-reduction transformations, this work introduced a non-reduction order approach. To achieve stability, Lyapunov functional approaches were used with advanced inequality techniques to generate adequate criteria that ensured Lagrange stability under these complex conditions. Finally, Example 1 was presented to validate the efficiency of the proposed method, while Example 2, related to Quaternion-valued NNs (QVNNs), exhibited the efficiency of storing true color image patterns.
This paper examines the well-posedness and adaptive stabilization of a satellite vibration caused by internal disturbances. The structure of the satellite is made up of two flexible, symmetrical wings that are connected to a central body. The wings are modeled as transmission Euler-Bernoulli beams with dynamic boundary conditions. We design high-gain adaptive regulators by measuring velocity feedback at the central body to quickly dampen vibrations. We demonstrate an exponential decay result for the system employing the multiplier method. The theoretical results are supported by a numerical simulation.
In this paper, the output tracking control problem for single-input single-output (SISO) systems with unknown high-frequency gain is investigated. For the situation where the system matrix has unknown parameters and the high-frequency gain cannot be measured, based on the output feedback control strategy, a novel reduced-order model reference adaptive control (MRAC) approach that relies solely on the sign of the gain is proposed. This approach only requires updating a scalar function, which substantially alleviates the computational burden of the designed controller. Furthermore, the control strategy ensures closed-loop stabilization of the system and enables asymptotic tracking of the system's output state. The effectiveness of the proposed method is finally validated through two simulation examples.
This paper proposes a novel robust control strategy for the stabilization of a knee rehabilitation exoskeleton robot. Unlike traditional methods, the designed controller combines a linear state-feedback law with a nonlinear compensation term to effectively address the robot's nonlinear dynamics under parameter uncertainties, external disturbances, and motion constraints. Two complementary approaches are introduced: one assume a constant bound on the nonlinearities and another employs a state-dependent linear constraint. For each approach, tailored Linear Matrix Inequality (LMI) conditions are derived using specific technical lemmas, including Young's inequality, the S-procedure, the Schur complement, and the matrix inversion lemma. The originality of this work lies in the systematic integration of motion constraints and external disturbances into the LMI framework for composite control. Numerical simulations validate the proposed methodology, thereby demonstrating superior robustness and stability performance compared to conventional control strategies.
In this study, we obtained the fractional formula of the Anuj transformation, which is utilized to acquire an accurate outcome for linear fractional differential equations (LFDEs). It is employed for Riemann-Liouville's and Caputo's fractional derivatives. To do this, we started with developing the Anuj transform of basic functions in mathematics and then examined its primary properties, which may be used in solving different mathematical models, especially fractional differential equations. We then proceeded to present the exact solution for a particular case of a fractional differential equation. We explored four numerical challenges and presented a thorough solution for each to illustrate how the studied transform may be useful. The findings revealed that the newly recommended transformation and the specific solutions that have been supplied are more effective and straightforward in solving mathematical models. The obtained formula has been utilized to solve different cases of fractional differential equations and reach a precise solution. The outcomes have been expressed using two-dimensional graphs.
This paper investigates the predefined-time formation control of quadrotor unmanned aerial vehicles (QUAVs) under input saturation constraints. To mitigate the effects of input saturation, an auxiliary system is meticulously designed. In contrast to other studies which merely attain the asymptotic stability of the auxiliary signals, the auxiliary system proposed ensures the predefined-time stability, thus contributing the stability of entire system. Subsequently, based on the predefined-time stability criterion, a distributed formation controller is developed, thus guaranteeing the predefined-time stability and robustness of formation under input saturation. Finally, simulations validate the effectiveness of the proposed method.
In many disciplines, including biology, image and signal processing, chemistry, sociology, medical imaging, and physics, self-similar networks describe and explain complicated systems with hierarchical or recursive structures. Self-similar network theory is one of the important areas in mathematics, which can be used to model real-world issues. Due to its universal applications, researchers have shown interest in self-similar networks. In this case, topological indices are used as numerical quantities that transform complex self-similar network structures into numerical values. We can discuss the intricate architecture of diamond fractal networks (DFNs) and square fractal networks (SFNs) by using the generalized fractal dimensions (GFD), which is newly defined by using different types of neighborhood degree-based topological indices. In this context, the neighborhood degree-based topological indices, namely the third neighborhood degree-based index developed by De (NDe), the neighborhood version of the hyper-Zegreb index, the neighborhood forgotten topological index, the Sanskruti index, and the neighborhood inverse sum index are derived and computed for the representative networks. Moreover, the multifractal dimension measures are calculated for all indices from the general form of the obtained neighborhood degree-based topological indices. In addition, the comparison graphs of all indices and the generalized fractal dimensions are shown and geometrically discussed for the aggregate structure of the aforementioned networks with respect to all indices for each iteration (k >= 3). Multifractal GFD spectral curves are also compared graphically with all indices at each iteration for the networks considered, and we analyze the complexity level of the networks at each iteration.
In this study, we present a novel fractional-order framework to model the dynamics of breast cancer, incorporating the Liouville-Caputo fractional derivative to capture memory effects inherent in biological systems. The model describes tumor progression and its regulation through chemotherapy within a fractional calculus setting, introducing three control variables-monoclonal antibody drugs, a ketogenic diet, and z-control to influence system behavior. The existence and uniqueness of solutions are rigorously established via Sadovskii's fixed-point theorem, while global stability is examined using Hyers-Ulam stability criteria. Numerical validation is carried out using a predictor-corrector method, and graphical simulations demonstrate the improved accuracy and realism of the fractional-order model compared to its integer-order counterpart. This framework offers a robust theoretical basis for improving breast cancer treatment strategies and has the potential to inform future clinical decision making.
This paper primarily addresses the design of distributed optimal cooperative controllers and the utilization of a reinforcement learning (RL)-based event-triggered mechanism for multi-agent systems (MASs) with unknown dynamics. By setting an extra compensator, the augmented system is constructed to overcome the dependence for system dynamics. Then, to address the issue of computational burden, we utilize an event-triggered mechanism based on reinforcement learning (RL) and neural networks (NNs) to implement the adaptive dynamic programming (ADP) algorithm. Additionally, we take into consideration the trade-off between computational burden and achieving consensus control by introducing a weighting factor in the reward design for MASs. With this reward design, we present an algorithm based on the deep deterministic policy gradient (DDPG) algorithm to learn the event-triggered condition for MASs and achieve a balance between these two factors. The event-triggered mechanism of our algorithm can also identify constraints such as time limitations or computational resource restrictions, aiming to achieve consensus control without violating these constraints. We demonstrate the absence of Zeno behavior and the uniform ultimate boundedness (UUB) of both local consensus error and weight estimation error. Finally, simulation results illustrate the effectiveness of the control algorithm and the weighting factor.
Higher-order interactions play a critical role in driving the rapid propagation of rumors. We propose a susceptible-exposed-infected-removed (SEIR) model that incorporates group interactions as higher-order terms. Detailed analysis reveals the emergence of bistability in both homogeneous and heterogeneous networks and shows that the bistable region expands as group interactions intensify. By utilizing group interactions as the bifurcation parameter, we derive explicit bifurcation conditions for both network types. For heterogeneous networks, we establish global stability criteria and propose an effective control strategy. Numerical simulations demonstrate the significant influence of group interactions on the bistable region. This study advances the theoretical understanding of rumor propagation dynamics and provides a practical strategy for controlling rumor propagation.
This paper investigates the multiplicity of weak solutions for a double-phase elliptic problem with indefinite interaction, where the nonlinearity involves a potential term k(x) that may change sign and be singular within the domain. The problem is set up as a Dirichlet boundary value problem, where the differential operator has two different phases, involving two exponents p and q that meet a certain condition. Employing critical point theory, we demonstrate that at least one solution exists, and under suitable conditions, there are at least three solutions. These results come from applying abstract variational approaches, particularly the critical point theorems by Bonanno and Marano. The manuscript also presents a detailed variational framework and sets up the necessary preliminaries to support the main results.
In this work, we studied a non-equilibrium point chaotic system with single signum function nonlinearity and multidirectional parameters under the Atangana-Baleanu-Caputo (ABC) fractional derivative. The control parameters were used to generate chaotic signals in multiple directions, such as a 1D line, 2D lattice, and 3D grid. The dynamical properties of the system were analyzed by graphical results, phase plots, and bifurcation plots. The ABC fractional analog circuit was designed using resistors, capacitors, operational amplifiers, and frequency domain approximations in the sense of ABC to ensure the system's feasibility. Random numbers were generated to evaluate the randomness of the system. These numbers were verified by the NIST test suite, and the test results established the strong unpredictability of the system. Text, video, and image files were the components that made up multimedia data, and as the usage of multimedia data sent over the internet continues to grow, so does the need for secure multimedia data. A significant topic in information security is the merging of chaos theory with encryption. For this purpose, we suggested a nonlinear 3D multidirectional chaos-based simple encryption scheme, in which a 3D multidirectional chaotic system was employed for position and value transformation. The proposed image encryption scheme employs a multidirectional chaotic system to enhance randomness and security, beginning with histogram equalization to uniformly distribute pixel intensities. This is followed by sequential row and column rotations and a final exclusive OR (XOR) operation, effectively achieving strong confusion and diffusion in the encrypted image. We computed several metrics to assess the quality of an image, including mean square error (MSE), peak signal-to-noise ratio (PSNR), entropy, the correlation coefficient, and image distance. NPCR (number of pixels change rate) and UACI (unified average change intensity) are standard statistical measures used to evaluate the effectiveness of image encryption, particularly in resisting differential attacks.
The dynamic behavior and regulatory mechanisms of gene regulatory networks (GRNs) have attracted considerable attention in systems biology, as they play a crucial role in elucidating the principles of gene regulation, cellular evolution, and the pathogenesis of complex diseases. GRNs are widely modeled as Boolean networks (BNs) due to their intuitive logic, descriptive simplicity, and computational efficiency. In this paper, a robust set stabilization Lebesgue sampling control method was studied. First, a criterion was proposed to verify the robust set stabilization of BNs, and an algorithm was developed to design the sampled data state feedback controls (SDSFCs) within a given Lebesgue sampling region. Second, an improved sampling region was designed using the truth matrix method to reduce control update frequency while maintaining stability. Finally, the effectiveness of the proposed method was validated through a reduced model of the lac operon in Escherichia coli.
This research studied bipartite leader and leaderless synchronization of fractional-order communication delay in coupled memristor neural networks by utilizing the decoupling approach and the Laplace transform. Further, the synchronization was analyzed under delay-independent criteria. Finally, numerical examples were provided to show the effectiveness of theoretical parts.
Structural Equation Modeling (SEM) systematically validated hierarchical pathways among multiple factors by constructing a dual framework integrating latent variable measurement and path analysis, utilizing covariance matrices derived from online questionnaires of Wuliangye consumers in Sichuan Province. Statistical analysis quantified path coefficient significance through maximum likelihood estimation, revealing via factor loadings and goodness-of-fit tests that consumer ethnocentrism directly promotes purchase intention, while simultaneously refuting the null hypothesis regarding perceived behavioral control-thus deconstructing the "trigger-transmission" causal chain among variables. Crucially, SEM findings revealed environmental stimuli as the predominant factor, indirectly influencing purchasing behavior through perceived value, contrary to existing literature asserting equal impacts from consumer ethnocentrism, environmental stimuli, and perceived behavioral control. Statistical evidence further demonstrated higher online purchase frequency for premium Wuliangye liquor, aligning with Generation Z's e-commerce preferences. By implementing stricter website-based participant screening than prior studies, this research optimized the analytical model, yielding data-driven strategic recommendations: strengthening e-commerce platforms, enhancing promotional expertise, leveraging cultural localization, and prioritizing premium product development. These actionable insights significantly advance sales optimization strategies for Wuliangye products in Sichuan's dynamic market.
A model of fractional-order discontinuous impulsive delayed gene regulatory networks (GRNs) was investigated in this paper. The impulsive perturbations were at fixed moments of time and measured the impulsive control effects which can be controlled appropriately. A fractional-order modeling approach was applied and distributed delays were taken into account for greater model flexibility. In this paper, rather than studying the classical Lyapunov-type stability of an equilibrium point, we addressed the extended Lipschitz stability behavior of the considered GRNs. By applying the impulsive fractional Lyapunov functions technique, new criteria were derived to ensure the global uniform Lipschitz stability for the fractional impulsive delayed GRNs. Furthermore, the effects of considering uncertain parameters were also analyzed. Finally, an illustrating example was given to support the obtained theoretical results.
The realization of intelligent transportation is inseparable from the perception and processing of traffic information. In the field of intelligent transportation, video surveillance, infrared, magnetic induction sensors, other methods have been applied, to a certain extent to meet the needs. However, the above method has some limitations, such as complex installation, high cost, blind spot detection, weather influence. Therefore, this paper proposes a traffic information classification algorithm based on distributed optical fiber sensing, which uses the distributed perception ability of optical fiber to obtain traffic vibration data, combined with video data, and realizes high-precision classification of vibration signals through neural network. This method uses multi-modal fusion technology to extract key features of fiber distributed sensing data and video data respectively through ResNet and video understanding network, and then extracts multi-scale features corresponding to the two modes from different levels of the feature extraction network. Finally, multi-modal cross-attention feature enhancement fusion module is used to achieve multi-modal feature fusion. The information complementation between different modes is realized effectively, and the classification of traffic information is completed. In this study, we conducted tests on the traffic data set we collected, and the framework showed excellent performance in various types of identification, which can provide a reference for the construction of intelligent transportation.
This study presented a novel approach to investigating the existence, uniqueness, and stability of solutions for an initial value problem involving fractional differential equations of variable order. In contrast to conventional methods in the literature, which often utilized generalized intervals and piecewise constant functions, we introduced a new fractional operator that is more appropriate for this problem. The existence and uniqueness of the solutions ware demonstrated through Leray-Schauder fixed point theorem and Banach's theorem, with an analysis of the uniform stability of the problem. The strength of our approach lies in its straightforwardness and reliance on fewer restrictive assumptions. The study concluded with an application that features a practical example, accompanied by visual illustrations.
In this paper, semi-tensor product (STP) and related properties of dimension keeping semi-tensor product (DK-STP) are analyzed. The commutativity and anticommutativity of DK-STP are studied by means of matrix mapping, and sufficient conditions for both are obtained. The structure matrix of the Lie bracket of non-square matrices (NSM) is discussed, and some properties are derived. The correspondences between the special Lie subalgebras of square matrix and Lie subalgebras of NSM are discussed through a homomorphism.
