Chaos Solitons & Fractals最新文献

{"title":"A novel combination of fuzzy PID and deep neural controller in feedback-error-learning framework","authors":"Esfandiar Baghelani ,&nbsp;Mohammad Teshnehlab ,&nbsp;Jafar Roshanian","doi":"10.1016/j.chaos.2025.116250","DOIUrl":"10.1016/j.chaos.2025.116250","url":null,"abstract":"<div><div>This paper proposes a novel hybrid control strategy that integrates fuzzy logic, deep neural networks (DNNs), and classical proportional-integral-derivative (PID) control within the feedback-error-learning (FEL) framework. The proposed method dynamically adapts PID parameters using a fuzzy inference system (FIS) while employing a DNN to learn the system's inverse dynamics, thereby enhancing adaptability and robustness. Notable features include offline pre-training of the DNN using data from PID and FIS-tuned PID controllers, a novel single-sample normalization layer for DNN input preprocessing, and the seamless integration of FIS-adapted PID gains within the FEL framework. Extensive simulations demonstrate significant average improvements over other control methods. Specifically, the proposed method achieves average reductions of 53 % in steady-state error (SSE), 21 % in rise time, 41 % in mean absolute error (MAE), and 21 % lowering of control effort, indicating enhanced disturbance rejection and efficient control effort under uncertainties. These results validate the proposed hybrid framework as a versatile and efficient solution for diverse industrial and engineering applications.</div></div>","PeriodicalId":9764,"journal":{"name":"Chaos Solitons & Fractals","volume":"194 ","pages":"Article 116250"},"PeriodicalIF":5.3,"publicationDate":"2025-03-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143592203","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"数学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Coordinating dynamic signage for evacuation guidance: A multi-agent reinforcement learning approach integrating mesoscopic crowd modeling and fire propagation","authors":"Chuan-Zhi Thomas Xie ,&nbsp;Qihua Chen ,&nbsp;Bin Zhu ,&nbsp;Eric Wai Ming Lee ,&nbsp;Tie-Qiao Tang ,&nbsp;Xianfei Yin ,&nbsp;Zhilu Yuan ,&nbsp;Botao Zhang","doi":"10.1016/j.chaos.2025.116246","DOIUrl":"10.1016/j.chaos.2025.116246","url":null,"abstract":"<div><div>Recurrent fire outbreaks in indoor crowd-gathering facilities, particularly those where pedestrians are unfamiliar with the spatial layout and visibility is limited, present significant challenges to evacuation safety and efficiency. Under such conditions, traditional static signage, which directs pedestrians to the nearest exit without accounting for real-time crowd and fire dynamics, often fails to provide effective guidance. To address these limitations, under the context of dynamic signage, we propose an integrated method capable of offering coordinated, real-time directional guidance of multiple signs, i.e.,: i) the extension of a sub-region-based mesoscopic model (Cellular Transmission Model, CTM) for crowd movement simulation; ii) the adoption of PyroSim to simulate the dynamic propagation of fire and its byproducts; iii) integrating real-time simulation results from i) and ii) into a dynamic environment to optimize signage directions using the Multi-Agent Reinforcement Learning (MARL)-based QMIX algorithm, with multi-objective goals addressing evacuation efficiency, congestion levels, and fire-induced risks simultaneously. Advancements of this paper can be summarized as: i) in terms of environment construction for dynamic crowd evacuation guidance, our approach represents one of the first to integrate sub-regional mesoscopic crowd modeling with dynamic fire propagation simulation. This integration naturally aligns with the granularity of directional guidance, where pedestrians within the same sub-region receive uniform instructions; ii) regarding real-time directional guidance generation for multi-sign, our method extends the discrete MARL algorithm QMIX, which is well-suited for the discrete action space of each sign (i.e., forward, backward, left, right). This extension effectively manages the high-dimensional challenge of coordinating multiple signs simultaneously while optimizing both evacuation efficiency and safety; iii) from the perspective of model application, we demonstrate the effectiveness of our CTM-PyroSim-QMIX framework in a fire evacuation scenario in a real-world karaoke venue, characterized by low visibility and pedestrians' unfamiliarity with the layout. Benchmarking against the traditional static signage approach, we show that the directional guidance generated by our method enhances evacuation efficiency and reduces fire-related and congestion-induced hazards across 10 single and dual fire source cases. Specifically, the maximum improvements observed in evacuation efficiency, fire-related hazards, and congestion-related risks are approximately over 30 %, 50 % and 70 %, respectively.</div></div>","PeriodicalId":9764,"journal":{"name":"Chaos Solitons & Fractals","volume":"194 ","pages":"Article 116246"},"PeriodicalIF":5.3,"publicationDate":"2025-03-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143578070","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"数学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Periodic breather waves, stripe-solitons and interaction solutions for the (3+1)-dimensional variable-coefficient Kadomtsev–Petviashvili-like equation","authors":"Muhammad Hamza Rafiq,&nbsp;Ji Lin","doi":"10.1016/j.chaos.2025.116212","DOIUrl":"10.1016/j.chaos.2025.116212","url":null,"abstract":"<div><div>The Kadomtsev–Petviashvili (KP) equation is a key model for weakly nonlinear dispersive waves, helping to understand wave behavior in complex systems like ion-acoustic waves in plasma and fluid dynamics. This work presents the (3+1)-dimensional Kadomtsev–Petviashvili-like (KP-like) equation with variable coefficients, concentrating on its novel localized waves and interaction solutions. The investigation begins by applying the superposition principle to the bilinear form of the equation to construct positive complexiton solutions up to the third order. Additionally, the Hirota bilinear method and ansatz function scheme are used to construct the exact solutions exhibit <span><math><mi>N</mi></math></span>-solitons, lump waves, breather waves and intriguing interactions such as lump-periodic waves, lump-rogue waves. Also, we extract the two cross-stripe solitons, two parallel stripe solitons, <span><math><mi>x</mi></math></span>-periodic breather, <span><math><mi>y</mi></math></span>-periodic breather and <span><math><mrow><mo>(</mo><mi>x</mi><mo>,</mo><mi>y</mi><mo>)</mo></mrow></math></span>-periodic breather waves, each representing different wave characteristics. To demonstrate and highlight the physical significance of the dynamics, we present solutions in 3D and contour plots with careful selected values of the free parameters. The originality of this work stems from the fact that these results, particularly for the equation with variable coefficients, have not been previously examined. This work provides a benchmark analysis of the KP equation, offering new perspectives on soliton dynamics and interactions with variable coefficients.</div></div>","PeriodicalId":9764,"journal":{"name":"Chaos Solitons & Fractals","volume":"194 ","pages":"Article 116212"},"PeriodicalIF":5.3,"publicationDate":"2025-03-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143577991","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"数学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Interpretable credit scoring based on an additive extreme gradient boosting","authors":"Yao Zou ,&nbsp;Meng Xia ,&nbsp;Xingyu Lan","doi":"10.1016/j.chaos.2025.116216","DOIUrl":"10.1016/j.chaos.2025.116216","url":null,"abstract":"<div><div>Credit scoring is a critical component of the financial ecosystem, driving lending decisions, risk assessment, and resource allocation. However, the inherent nonlinear and chaotic nature of creditworthiness poses a significant challenge for traditional credit scoring algorithms. Existing methods often struggle to balance predictive performance with interpretability, leading to a lack of transparency in the decision-making process and hindering their practical application. To address this issue, we propose Add-XGBoost, a novel additive ensemble model leveraging the strengths of Generalized Additive Models (GAM) and Extreme Gradient Boosting (XGBoost). Add-XGBoost enhances interpretability by employing an additive architecture wherein individual decision trees are trained for each feature, facilitating granular feature importance analysis and capturing nonlinear feature effects. Furthermore, Add-XGBoost incorporates second-order feature interactions within the additive framework, enabling a nuanced understanding of complex relationships within credit data. To further enhance robustness, a Lasso regression-based optimization method refines the weights assigned to individual feature functions (shape functions). Empirical evaluation across four diverse credit datasets demonstrates Add-XGBoost’s superior performance compared to existing statistical and machine learning-based credit scoring methods, including ensemble approaches. Crucially, Add-XGBoost excels in providing both global and local interpretability, offering valuable insights into feature interactions and their influence on credit risk. This makes Add-XGBoost a transformative tool, bridging the gap between high-performance credit scoring and transparent, comprehensible decision-making in the financial sector.</div></div>","PeriodicalId":9764,"journal":{"name":"Chaos Solitons & Fractals","volume":"194 ","pages":"Article 116216"},"PeriodicalIF":5.3,"publicationDate":"2025-03-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143577990","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"数学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"The impact of feedback mechanisms on Rayleigh–Bénard penetrative convection in micro-polar fluids","authors":"Reena Nandal ,&nbsp;Vinit Vinod Revankar ,&nbsp;Eliyash Ahmed","doi":"10.1016/j.chaos.2025.116228","DOIUrl":"10.1016/j.chaos.2025.116228","url":null,"abstract":"<div><div>This study examines the effects of feedback control and internal heat sources on the onset criterion of Rayleigh–Bénard convection (RBC) in a horizontal Boussinesq micropolar fluid layer. A linear stability analysis, employing the Chebyshev pseudospectral method, is conducted to compute the eigenvalues and assess the stability of the system under varying conditions. The analysis considers several parameters, including heat conduction, coupling, couple stress, scalar controller gain, and internal heat sources. The findings reveal that the introduction of internal heat sources destabilizes the system, while the scalar controller gain significantly delays the onset of convection, thereby enhancing system stability. Additionally, it is demonstrated that an increase in both the coupling and heat conduction parameters contributes positively to system stabilization, whereas an increase in the couple stress parameter hastens the onset of convection. Notably, the investigation indicates that the system demonstrates greater stability when the boundary is heated from above as opposed to from below. These results provide crucial insights for the control of heat transfer in micropolar fluids and suggest that optimizing the scalar controller gain, along with careful tuning of other system parameters, can significantly enhance stability. The implications of this research are substantial for the design of efficient fluid dynamical systems, particularly in scenarios requiring precise control over temperature, pressure, and flow, such as those encountered in chemical processing, power generation, and manufacturing.</div></div>","PeriodicalId":9764,"journal":{"name":"Chaos Solitons & Fractals","volume":"194 ","pages":"Article 116228"},"PeriodicalIF":5.3,"publicationDate":"2025-03-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143577994","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"数学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Nonlinear stability (q-stability) under dilatation or contraction of coordinates","authors":"Tulio M. Oliveira ,&nbsp;Vinicius Wiggers ,&nbsp;Eduardo Scafi ,&nbsp;Silvio Zanin ,&nbsp;Cesar Manchein ,&nbsp;Marcus W. Beims","doi":"10.1016/j.chaos.2025.116215","DOIUrl":"10.1016/j.chaos.2025.116215","url":null,"abstract":"<div><div>This study examines the nonlinear stability of trajectories under coordinate contraction and dilatation in three dynamical systems: the discrete-time dissipative Hénon map, and the conservative, non-integrable, continuous-time Hénon–Heiles and diamagnetic Kepler problems. The nonlinear stability analysis uses the <span><math><mi>q</mi></math></span>-deformed Jacobian and <span><math><mi>q</mi></math></span>-derivative, with trajectory stability assessed for <span><math><mrow><mi>q</mi><mo>&gt;</mo><mn>1</mn></mrow></math></span> (dilatation) and <span><math><mrow><mi>q</mi><mo>&lt;</mo><mn>1</mn></mrow></math></span> (contraction). It is shown that <span><math><mi>q</mi></math></span>-deformed Jacobian adds nonlinear terms to the linear Lyapunov stability analysis, and is named here as <span><math><mi>q</mi></math></span>-<em>stability</em>. Analytical curves in the parameter space mark boundaries of distinct low-periodic motions in the Hénon map. Numerical simulations compute the maximal Lyapunov exponent across the parameter space, in Poincaré surfaces of section, and as a function of total energy in the conservative systems. Simulations show that contraction (dilatation) of coordinates generally decreases (increases) <span><math><mi>q</mi></math></span>-stability exponent when compared to the <span><math><mrow><mi>q</mi><mo>=</mo><mn>1</mn></mrow></math></span> case with positive Lyapunov exponents. Dilatation and contraction tend to increase the <span><math><mi>q</mi></math></span>-stability exponent for Lyapunov stable orbits. Some exceptions to this trend remain unexplained regarding Kolmogorov–Arnold–Moser (KAM) tori stability.</div></div>","PeriodicalId":9764,"journal":{"name":"Chaos Solitons & Fractals","volume":"194 ","pages":"Article 116215"},"PeriodicalIF":5.3,"publicationDate":"2025-03-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143577993","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"数学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Criticality in neural cultures: Insights into memory and connectivity in entorhinal-hippocampal networks","authors":"Ludovico Iannello ,&nbsp;Fabrizio Tonelli ,&nbsp;Federico Cremisi ,&nbsp;Lucio Maria Calcagnile ,&nbsp;Riccardo Mannella ,&nbsp;Giuseppe Amato ,&nbsp;Angelo Di Garbo","doi":"10.1016/j.chaos.2025.116184","DOIUrl":"10.1016/j.chaos.2025.116184","url":null,"abstract":"<div><div>The brain is a complex system of interconnected regions that underlie memory, cognition, and perception. Today, our understanding of the brain’s dynamic processes remains incomplete, particularly regarding differences in electrophysiological activity and inter-regional connectivity among specific areas. To explore this, we investigated the electrical activity, functional connectivity, and interactions of neural cultures differentiated into hippocampal, isocortical, and entorhinal networks using multi-electrode arrays (MEAs) to record extracellular local field potentials. Our results showed that collective synchronization events, or network bursts, were present in all cultures except for the hippocampal networks. Interestingly, introducing entorhinal neuron spheroids onto hippocampal cultures induced synchronized activity. Furthermore, Self-organized criticality analysis confirmed that all networks, except hippocampal cultures, were in a critical regime. Moreover, we found that entorhinal-hippocampal coupling facilitated criticality, promoting recurrent synchronized activity patterns. The consistent scaling exponents across configurations underscore the universality of criticality in biological networks. Finally, power spectrum analysis revealed a theta band peak in connected entorhinal-hippocampal cultures, consistent with <em>in vivo</em> studies, highlighting the role of theta oscillations in memory consolidation. Our findings provide more insights into brain functioning and offer an <em>in vitro</em> model for studying learning and memory.</div></div>","PeriodicalId":9764,"journal":{"name":"Chaos Solitons & Fractals","volume":"194 ","pages":"Article 116184"},"PeriodicalIF":5.3,"publicationDate":"2025-03-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143577992","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"数学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Vector annular rogue wave quartets and sextets","authors":"Su-Guang Shi,&nbsp;Li Chen","doi":"10.1016/j.chaos.2025.116218","DOIUrl":"10.1016/j.chaos.2025.116218","url":null,"abstract":"<div><div>Rogue waves, especially high-order forms, have become crucially important carriers of describing the physical mechanism when they are encountered in various application scenarios. This paper aims to construct vector annular high order rogue waves of the (2+1)-dimensional (2D) coupled nonlinear Schrödinger equation. Vector bright–bright annular rogue wave quartets and sextets exhibit layer-like ring–ring–nested structures. The radius and thickness parameters have impact on the annular structures of bright–bright annular rogue wave quartets and sextets, whose radius and thickness of the annular structures are modulated by altering these parameters in approximate solution. The related study for these annular structures of high order rogue wave provides the potential application for the surge of atomic number or optical energy.</div></div>","PeriodicalId":9764,"journal":{"name":"Chaos Solitons & Fractals","volume":"194 ","pages":"Article 116218"},"PeriodicalIF":5.3,"publicationDate":"2025-03-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143577988","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"数学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Neural network-based symbolic calculation approach for solving the Korteweg–de Vries equation","authors":"Xiao-Ran Xie ,&nbsp;Run-Fa Zhang","doi":"10.1016/j.chaos.2025.116232","DOIUrl":"10.1016/j.chaos.2025.116232","url":null,"abstract":"<div><div>In this study, we propose an innovative method that combines neural network models and symbolic computing to quickly solve exact solutions to nonlinear partial differential equations (NLPDEs). By combining the high accuracy of symbolic computing with the strong adaptability of neural networks, this method significantly improves the efficiency and accuracy of decomputation. As an application, this paper uses the neural network symbol calculation method to successfully obtain multiple sets of new analytical solutions of the Korteweg–de Vries equation, and constructs a variety of new neural network models and their heuristic functions. This study provides a new computational paradigm for solving the exact solution of NLPDEs, and has the potential for a wide range of scientific and engineering applications.</div></div>","PeriodicalId":9764,"journal":{"name":"Chaos Solitons & Fractals","volume":"194 ","pages":"Article 116232"},"PeriodicalIF":5.3,"publicationDate":"2025-03-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143577989","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"数学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Discrete memristive hyperchaotic map with heterogeneous and homogeneous multistability and its applications","authors":"Mingjie Zhou ,&nbsp;Guodong Li ,&nbsp;Hepeng Pan ,&nbsp;Xiaoming Song","doi":"10.1016/j.chaos.2025.116227","DOIUrl":"10.1016/j.chaos.2025.116227","url":null,"abstract":"<div><div>Memristors, due to their inherent nonlinear characteristics, are widely applied in discrete dynamical systems. However, existing research on the construction of discrete memristors is limited, and their applications in discrete dynamical systems remain confined. To address this gap, this paper introduces four novel discrete memristor models, selecting one that combines an exponential function with a sine function. By coupling this model with a two-dimensional sine map, we construct a three-dimensional discrete memristor-based hyperchaotic map (SEDMM) that exhibits greater complexity and a broader chaotic region. Analysis reveals that the map displays a variety of dynamical behaviors, including periodic, quasiperiodic, multi-periodic, chaotic, and hyperchaotic states. More importantly, it shows both heterogeneous and homogeneous multistability. Furthermore, a novel color image encryption scheme is developed, and experimental results confirm its improved unpredictability. Finally, the hyperchaotic attractor is captured using a Digital Signal Processor (DSP), and experimental validation confirms the scientific validity and feasibility of the proposed map.</div></div>","PeriodicalId":9764,"journal":{"name":"Chaos Solitons & Fractals","volume":"194 ","pages":"Article 116227"},"PeriodicalIF":5.3,"publicationDate":"2025-03-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143577987","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"数学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}