首页 > 最新文献

Physica A: Statistical Mechanics and its Applications最新文献

英文 中文
Analysis of the impact of heterogeneous platoon for mixed traffic flow: A fundamental diagram method
IF 2.8 3区 物理与天体物理 Q2 PHYSICS, MULTIDISCIPLINARY Pub Date : 2025-01-22 DOI: 10.1016/j.physa.2025.130398
Le Li, Yunxia Wu, Qiaoqiong Zeng, Yi Wang, Yangsheng Jiang, Zhihong Yao
In the first part of this study, different combination spacing control strategies for platoons are proposed. The combined performance of different strategies in terms of fuel consumption and emission is evaluated by numerical experiments. However, that study mainly focused on assessing the environmental benefits of the strategies and did not deeply explore the traffic flow characteristics under different spacing strategies. Therefore, the second part of this study focuses on analyzing the fundamental diagram of mixed traffic flow to explore further the effects of different control strategies on traffic flow characteristics. Firstly, the fundamental diagram models of mixed traffic flow under ten control strategies are established based on the three-parameter relationship of traffic flow and the definition of density. Subsequently, the theoretical fundamental diagrams are verified by numerical simulation experiments, and the effects of different control strategies on the average speed and capacity of mixed traffic flow are analyzed in detail. Finally, the sensitivity analysis of the free flow speed and the minimum safety spacing is carried out based on the fundamental diagram model. The results show that (1) introducing the CS strategy can significantly improve capacity, and the combination with the VTG strategy has the best effect. When the penetration rate of CAVs is 1, the maximum traffic capacity of the VTG1-CS strategy is close to 10,000 veh/h, which is more than 5 times that of the HV homogeneous traffic flow, while the enhancement of the CTG-CS strategy is about four times. (2) The maximum traffic capacity of the VTG2-CS strategy when the penetration rate of CAVs is 1 is about 110.69 veh/h less than that of the CTG-CS strategy, but it performs better in terms of overall traffic flow in traffic density. However, the BS-CS strategy is weaker in enhancing traffic capacity. (3) The VTG1-CS strategy is the most sensitive to free flow speed, followed by the CTG-CS strategy. In contrast, the VTG2-VTG2 strategy is the least sensitive to free flow speed, and the VTG2-CTG and VTG2-CS strategies based on this strategy are also less sensitive. Finally, the VTG2-VTG2 strategy and VTG2-CS strategy have the highest sensitivity to the minimum safety spacing parameter. To sum up, this study provides a theoretical basis for the mechanism of the effects on traffic flow characteristics with different spacing control strategies in mixed traffic flow.
{"title":"Analysis of the impact of heterogeneous platoon for mixed traffic flow: A fundamental diagram method","authors":"Le Li,&nbsp;Yunxia Wu,&nbsp;Qiaoqiong Zeng,&nbsp;Yi Wang,&nbsp;Yangsheng Jiang,&nbsp;Zhihong Yao","doi":"10.1016/j.physa.2025.130398","DOIUrl":"10.1016/j.physa.2025.130398","url":null,"abstract":"<div><div>In the first part of this study, different combination spacing control strategies for platoons are proposed. The combined performance of different strategies in terms of fuel consumption and emission is evaluated by numerical experiments. However, that study mainly focused on assessing the environmental benefits of the strategies and did not deeply explore the traffic flow characteristics under different spacing strategies. Therefore, the second part of this study focuses on analyzing the fundamental diagram of mixed traffic flow to explore further the effects of different control strategies on traffic flow characteristics. Firstly, the fundamental diagram models of mixed traffic flow under ten control strategies are established based on the three-parameter relationship of traffic flow and the definition of density. Subsequently, the theoretical fundamental diagrams are verified by numerical simulation experiments, and the effects of different control strategies on the average speed and capacity of mixed traffic flow are analyzed in detail. Finally, the sensitivity analysis of the free flow speed and the minimum safety spacing is carried out based on the fundamental diagram model. The results show that (1) introducing the CS strategy can significantly improve capacity, and the combination with the VTG strategy has the best effect. When the penetration rate of CAVs is 1, the maximum traffic capacity of the VTG1-CS strategy is close to 10,000 veh/h, which is more than 5 times that of the HV homogeneous traffic flow, while the enhancement of the CTG-CS strategy is about four times. (2) The maximum traffic capacity of the VTG2-CS strategy when the penetration rate of CAVs is 1 is about 110.69 veh/h less than that of the CTG-CS strategy, but it performs better in terms of overall traffic flow in traffic density. However, the BS-CS strategy is weaker in enhancing traffic capacity. (3) The VTG1-CS strategy is the most sensitive to free flow speed, followed by the CTG-CS strategy. In contrast, the VTG2-VTG2 strategy is the least sensitive to free flow speed, and the VTG2-CTG and VTG2-CS strategies based on this strategy are also less sensitive. Finally, the VTG2-VTG2 strategy and VTG2-CS strategy have the highest sensitivity to the minimum safety spacing parameter. To sum up, this study provides a theoretical basis for the mechanism of the effects on traffic flow characteristics with different spacing control strategies in mixed traffic flow.</div></div>","PeriodicalId":20152,"journal":{"name":"Physica A: Statistical Mechanics and its Applications","volume":"660 ","pages":"Article 130398"},"PeriodicalIF":2.8,"publicationDate":"2025-01-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143157270","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"物理与天体物理","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
How left-turning vehicles deal with conflicts at intersections: A driving behavior model based on relative motion risk quantification
IF 2.8 3区 物理与天体物理 Q2 PHYSICS, MULTIDISCIPLINARY Pub Date : 2025-01-22 DOI: 10.1016/j.physa.2025.130393
Jun Hua , Bin Li , Lin Wang , Guangquan Lu
Unprotected left turns at intersections in right-hand traffic are a critical factor affecting traffic safety. Traditional risk assessment indicators, which typically rely on vehicle relative positions, fall short in supporting yield/go decisions by left-turning drivers across different types of conflicts, and the corresponding driving behavior models struggle to capture the underlying behavioral mechanisms. To address these limitations, this paper introduces an improved risk assessment indicator based on risk field theory. By quantifying the relative motion risk between interactive vehicles, the proposed indicator offers a unified standard for intuitively determining whether a conflict has been resolved. Building on this, a Perception-decision-action behavioral framework, grounded in the preview-follower theory and risk homeostasis theory, is employed to model decision-making behaviors. This behavioral mechanism-driven model is validated through numerical simulations of vehicle trajectories, achieving a 92.59 % accuracy rate in replicating the decision-making behavior of left-turning vehicles, comparable to the performance of previous data-driven classification models. Furthermore, several cases are analyzed and discussed under different risk preferences and preview times, demonstrating that the model has potential for personalized trajectory planning. Overall, this paper provides a valuable reference model for enhancing intersection safety and advancing trajectory planning in autonomous driving systems.
{"title":"How left-turning vehicles deal with conflicts at intersections: A driving behavior model based on relative motion risk quantification","authors":"Jun Hua ,&nbsp;Bin Li ,&nbsp;Lin Wang ,&nbsp;Guangquan Lu","doi":"10.1016/j.physa.2025.130393","DOIUrl":"10.1016/j.physa.2025.130393","url":null,"abstract":"<div><div>Unprotected left turns at intersections in right-hand traffic are a critical factor affecting traffic safety. Traditional risk assessment indicators, which typically rely on vehicle relative positions, fall short in supporting yield/go decisions by left-turning drivers across different types of conflicts, and the corresponding driving behavior models struggle to capture the underlying behavioral mechanisms. To address these limitations, this paper introduces an improved risk assessment indicator based on risk field theory. By quantifying the relative motion risk between interactive vehicles, the proposed indicator offers a unified standard for intuitively determining whether a conflict has been resolved. Building on this, a Perception-decision-action behavioral framework, grounded in the preview-follower theory and risk homeostasis theory, is employed to model decision-making behaviors. This behavioral mechanism-driven model is validated through numerical simulations of vehicle trajectories, achieving a 92.59 % accuracy rate in replicating the decision-making behavior of left-turning vehicles, comparable to the performance of previous data-driven classification models. Furthermore, several cases are analyzed and discussed under different risk preferences and preview times, demonstrating that the model has potential for personalized trajectory planning. Overall, this paper provides a valuable reference model for enhancing intersection safety and advancing trajectory planning in autonomous driving systems.</div></div>","PeriodicalId":20152,"journal":{"name":"Physica A: Statistical Mechanics and its Applications","volume":"661 ","pages":"Article 130393"},"PeriodicalIF":2.8,"publicationDate":"2025-01-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143128382","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"物理与天体物理","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Complexity of two-level systems
IF 2.8 3区 物理与天体物理 Q2 PHYSICS, MULTIDISCIPLINARY Pub Date : 2025-01-22 DOI: 10.1016/j.physa.2025.130389
Imre Varga
Complexity of two-level systems, e.g. spins, qubits, magnetic moments etc, are analyzed based on the so-called correlational entropy in the case of pure quantum systems and the thermal entropy in case of thermal equilibrium that are suitable quantities essentially free from basis dependence. The complexity is defined as the difference between the Shannon-entropy and the second order Rényi-entropy, where the latter is connected to the traditional participation measure or purity. It is shown that the system attains maximal complexity for special choice of control parameters, i.e. strength of disorder either in the presence of noise of the energy states or the presence of disorder in the off diagonal coupling. It is shown that such a noise or disorder dependence provides a basis free analysis and gives meaningful insights. We also look at similar entropic complexity of spins in thermal equilibrium for a paramagnet at finite temperature, T and magnetic field B, as well as the case of an Ising model in the mean-field approximation. As a result all examples provide important evidence that the investigation of the entropic complexity parameters help to get deeper understanding in the behavior of these systems.
{"title":"Complexity of two-level systems","authors":"Imre Varga","doi":"10.1016/j.physa.2025.130389","DOIUrl":"10.1016/j.physa.2025.130389","url":null,"abstract":"<div><div>Complexity of two-level systems, e.g. spins, qubits, magnetic moments etc, are analyzed based on the so-called correlational entropy in the case of pure quantum systems and the thermal entropy in case of thermal equilibrium that are suitable quantities essentially free from basis dependence. The complexity is defined as the difference between the Shannon-entropy and the second order Rényi-entropy, where the latter is connected to the traditional participation measure or purity. It is shown that the system attains maximal complexity for special choice of control parameters, i.e. strength of disorder either in the presence of noise of the energy states or the presence of disorder in the off diagonal coupling. It is shown that such a noise or disorder dependence provides a basis free analysis and gives meaningful insights. We also look at similar entropic complexity of spins in thermal equilibrium for a paramagnet at finite temperature, <span><math><mi>T</mi></math></span> and magnetic field <span><math><mi>B</mi></math></span>, as well as the case of an Ising model in the mean-field approximation. As a result all examples provide important evidence that the investigation of the entropic complexity parameters help to get deeper understanding in the behavior of these systems.</div></div>","PeriodicalId":20152,"journal":{"name":"Physica A: Statistical Mechanics and its Applications","volume":"661 ","pages":"Article 130389"},"PeriodicalIF":2.8,"publicationDate":"2025-01-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143093343","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"物理与天体物理","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Enhancing the robustness of planar spatial networks
IF 2.8 3区 物理与天体物理 Q2 PHYSICS, MULTIDISCIPLINARY Pub Date : 2025-01-22 DOI: 10.1016/j.physa.2025.130387
Marco Tomassini
Spatial networks cover a large number of important infrastructures such as railways, roads and distribution systems of various kinds. The integrity of these infrastructures is very important for society. Methods for improving the robustness of spatial planar networks are suggested based on adding new links to the networks under the hard constraint that the total added link length is less than a small percentage of the original length. The strategies are first applied to model spatial networks by using numerical simulations for the attacks and failures and the results are satisfactory in terms of the robustness of the modified networks compared to the original ones. The methodology is then applied to two actual spatial networks of the transportation type with equally good results. We conclude that the proposed heuristic strategy is a useful one in this context and can also be applied to actual networks.
{"title":"Enhancing the robustness of planar spatial networks","authors":"Marco Tomassini","doi":"10.1016/j.physa.2025.130387","DOIUrl":"10.1016/j.physa.2025.130387","url":null,"abstract":"<div><div>Spatial networks cover a large number of important infrastructures such as railways, roads and distribution systems of various kinds. The integrity of these infrastructures is very important for society. Methods for improving the robustness of spatial planar networks are suggested based on adding new links to the networks under the hard constraint that the total added link length is less than a small percentage of the original length. The strategies are first applied to model spatial networks by using numerical simulations for the attacks and failures and the results are satisfactory in terms of the robustness of the modified networks compared to the original ones. The methodology is then applied to two actual spatial networks of the transportation type with equally good results. We conclude that the proposed heuristic strategy is a useful one in this context and can also be applied to actual networks.</div></div>","PeriodicalId":20152,"journal":{"name":"Physica A: Statistical Mechanics and its Applications","volume":"660 ","pages":"Article 130387"},"PeriodicalIF":2.8,"publicationDate":"2025-01-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143157315","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"物理与天体物理","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Cascading dynamics on coupled networks with load-capacity interplay and concurrent recovery-failure
IF 2.8 3区 物理与天体物理 Q2 PHYSICS, MULTIDISCIPLINARY Pub Date : 2025-01-21 DOI: 10.1016/j.physa.2025.130373
Jianwei Wang, Rouye He, Haozhe Sun, Haofan He
Coupled networks play a crucial role in modern infrastructure, where damage to one network can trigger cascading failures across the entire system. However, most studies on cascading failures in coupled networks have focused solely on failure propagation, overlooking the simultaneous occurrence of recovery and failure. To address this, we develop a general cascading failure model for interdependent networks that considers dynamic load-capacity interactions and concurrent recovery mechanisms. Specifically, the model captures how variations in the load of one network influence the coupled network and how recovery processes mitigate cascading effects. Using this model, we conducted experiments on a coupled power-communication network as a case study, employing various many-to-many coupling strategies. Results indicate disassortative coupling excels at low recovery thresholds, and assortative coupling at high thresholds, both outperforming random coupling and being less affected by recovery sensitivity. Larger node load differences resist random attacks better, while smaller differences resist maximum load attacks more effectively.
{"title":"Cascading dynamics on coupled networks with load-capacity interplay and concurrent recovery-failure","authors":"Jianwei Wang,&nbsp;Rouye He,&nbsp;Haozhe Sun,&nbsp;Haofan He","doi":"10.1016/j.physa.2025.130373","DOIUrl":"10.1016/j.physa.2025.130373","url":null,"abstract":"<div><div>Coupled networks play a crucial role in modern infrastructure, where damage to one network can trigger cascading failures across the entire system. However, most studies on cascading failures in coupled networks have focused solely on failure propagation, overlooking the simultaneous occurrence of recovery and failure. To address this, we develop a general cascading failure model for interdependent networks that considers dynamic load-capacity interactions and concurrent recovery mechanisms. Specifically, the model captures how variations in the load of one network influence the coupled network and how recovery processes mitigate cascading effects. Using this model, we conducted experiments on a coupled power-communication network as a case study, employing various many-to-many coupling strategies. Results indicate disassortative coupling excels at low recovery thresholds, and assortative coupling at high thresholds, both outperforming random coupling and being less affected by recovery sensitivity. Larger node load differences resist random attacks better, while smaller differences resist maximum load attacks more effectively.</div></div>","PeriodicalId":20152,"journal":{"name":"Physica A: Statistical Mechanics and its Applications","volume":"661 ","pages":"Article 130373"},"PeriodicalIF":2.8,"publicationDate":"2025-01-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143093334","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"物理与天体物理","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Opinion dynamics in bounded confidence models with manipulative agents: Moving the Overton window
IF 2.8 3区 物理与天体物理 Q2 PHYSICS, MULTIDISCIPLINARY Pub Date : 2025-01-21 DOI: 10.1016/j.physa.2025.130379
A. Bautista
This paper focuses on the opinion dynamics under the influence of manipulative agents. This type of agents is characterized by the fact that their opinions follow a trajectory that does not respond to the dynamics of the model, although it does influence the rest of the normal agents. Simulation has been implemented to study how one manipulative group modifies the natural dynamics of some opinion models of bounded confidence. It is studied what strategies based on the number of manipulative agents and their common opinion trajectory can be carried out by a manipulative group to influence normal agents and attract them to their opinions. In certain weighted models, some effects are observed in which normal agents move in the opposite direction to the manipulator group. Moreover, the conditions which ensure the influence of a manipulative group on a group of normal agents over time are also established for the Hegselmann–Krause model.
{"title":"Opinion dynamics in bounded confidence models with manipulative agents: Moving the Overton window","authors":"A. Bautista","doi":"10.1016/j.physa.2025.130379","DOIUrl":"10.1016/j.physa.2025.130379","url":null,"abstract":"<div><div>This paper focuses on the opinion dynamics under the influence of manipulative agents. This type of agents is characterized by the fact that their opinions follow a trajectory that does not respond to the dynamics of the model, although it does influence the rest of the normal agents. Simulation has been implemented to study how one manipulative group modifies the natural dynamics of some opinion models of bounded confidence. It is studied what strategies based on the number of manipulative agents and their common opinion trajectory can be carried out by a manipulative group to influence normal agents and attract them to their opinions. In certain weighted models, some effects are observed in which normal agents move in the opposite direction to the manipulator group. Moreover, the conditions which ensure the influence of a manipulative group on a group of normal agents over time are also established for the Hegselmann–Krause model.</div></div>","PeriodicalId":20152,"journal":{"name":"Physica A: Statistical Mechanics and its Applications","volume":"660 ","pages":"Article 130379"},"PeriodicalIF":2.8,"publicationDate":"2025-01-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143157316","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"物理与天体物理","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Parameter identification of the Black-Scholes model driven by multiplicative fractional Brownian motion
IF 2.8 3区 物理与天体物理 Q2 PHYSICS, MULTIDISCIPLINARY Pub Date : 2025-01-21 DOI: 10.1016/j.physa.2025.130371
Wentao Hou , Shaojuan Ma
In this paper, we propose a parameter identification method based on deep learning network, which can jointly identify all parameters of the Black–Scholes (BS) model driven by multiplicative fractional Brownian motion (FBM) in a discrete sample trajectory. Firstly, the Convolutional Neural Network (CNN) is combined with the Bi-directional Gated Recurrent Unit (BiGRU) and the attention mechanism (AM) is integrated to construct the new identifier (CBANN). Then, the multiplicative FBM is constructed as the random effect of the BS model, and all the parameters of the model are identified by the new identifier. Finally, extensive numerical simulations are conducted for both known and unknown Hurst exponents, and two empirical studies are performed using real data. The results suggest that, compared to the PENN identifier and the maximum likelihood (ML) identifier, the proposed identifier can simultaneously identify all parameters in the model more quickly and accurately. Additionally, several advantages of the new identifier are discussed, including its strong generalization performance, flexibility in training set proportion settings, and the incorporation of an attention mechanism layer.
{"title":"Parameter identification of the Black-Scholes model driven by multiplicative fractional Brownian motion","authors":"Wentao Hou ,&nbsp;Shaojuan Ma","doi":"10.1016/j.physa.2025.130371","DOIUrl":"10.1016/j.physa.2025.130371","url":null,"abstract":"<div><div>In this paper, we propose a parameter identification method based on deep learning network, which can jointly identify all parameters of the Black–Scholes (BS) model driven by multiplicative fractional Brownian motion (FBM) in a discrete sample trajectory. Firstly, the Convolutional Neural Network (CNN) is combined with the Bi-directional Gated Recurrent Unit (BiGRU) and the attention mechanism (AM) is integrated to construct the new identifier (CBANN). Then, the multiplicative FBM is constructed as the random effect of the BS model, and all the parameters of the model are identified by the new identifier. Finally, extensive numerical simulations are conducted for both known and unknown Hurst exponents, and two empirical studies are performed using real data. The results suggest that, compared to the PENN identifier and the maximum likelihood (ML) identifier, the proposed identifier can simultaneously identify all parameters in the model more quickly and accurately. Additionally, several advantages of the new identifier are discussed, including its strong generalization performance, flexibility in training set proportion settings, and the incorporation of an attention mechanism layer.</div></div>","PeriodicalId":20152,"journal":{"name":"Physica A: Statistical Mechanics and its Applications","volume":"660 ","pages":"Article 130371"},"PeriodicalIF":2.8,"publicationDate":"2025-01-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143157308","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"物理与天体物理","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Harnessing technical indicators with deep learning based price forecasting for cryptocurrency trading
IF 2.8 3区 物理与天体物理 Q2 PHYSICS, MULTIDISCIPLINARY Pub Date : 2025-01-21 DOI: 10.1016/j.physa.2025.130359
Mingu Kang, Joongi Hong, Suntae Kim
The rapid development and significant volatility of the cryptocurrency market make price trend prediction highly challenging. Accurate price predictions are crucial for making informed investment decisions that can lead to higher returns. However, few studies have focused on integrating predictions into actionable trading strategies. This study aims to enhance cryptocurrency trading strategies by integrating deep learning-based price forecasting with technical indicators. Twelve deep learning models were developed and their performance in generating trading signals was compared across various cryptocurrencies and forecast periods. These signals were combined with technical indicators and backtested to identify the optimal strategy, evaluated using the Sharpe ratio. Results show that SegRNN outperformed other models in price forecasting, while a strategy combining TimesNet and Bollinger Bands (BB) achieved the highest trading performance in the ETH market with a returns of 3.19, a maximum drawdown (MDD) of -7.46, and Sharpe ratio of 3.56. Additionally, the integration of technical indicators and AI models demonstrated significant improvements at mid-range intervals, particularly at the 4-hour interval, although no improvement was observed at shorter intervals such as 30 minutes. The study concludes that integrating deep learning with technical indicators can significantly improve the robustness and performance of trading strategies in volatile markets.
{"title":"Harnessing technical indicators with deep learning based price forecasting for cryptocurrency trading","authors":"Mingu Kang,&nbsp;Joongi Hong,&nbsp;Suntae Kim","doi":"10.1016/j.physa.2025.130359","DOIUrl":"10.1016/j.physa.2025.130359","url":null,"abstract":"<div><div>The rapid development and significant volatility of the cryptocurrency market make price trend prediction highly challenging. Accurate price predictions are crucial for making informed investment decisions that can lead to higher returns. However, few studies have focused on integrating predictions into actionable trading strategies. This study aims to enhance cryptocurrency trading strategies by integrating deep learning-based price forecasting with technical indicators. Twelve deep learning models were developed and their performance in generating trading signals was compared across various cryptocurrencies and forecast periods. These signals were combined with technical indicators and backtested to identify the optimal strategy, evaluated using the Sharpe ratio. Results show that SegRNN outperformed other models in price forecasting, while a strategy combining TimesNet and Bollinger Bands (BB) achieved the highest trading performance in the ETH market with a returns of 3.19, a maximum drawdown (MDD) of -7.46, and Sharpe ratio of 3.56. Additionally, the integration of technical indicators and AI models demonstrated significant improvements at mid-range intervals, particularly at the 4-hour interval, although no improvement was observed at shorter intervals such as 30 minutes. The study concludes that integrating deep learning with technical indicators can significantly improve the robustness and performance of trading strategies in volatile markets.</div></div>","PeriodicalId":20152,"journal":{"name":"Physica A: Statistical Mechanics and its Applications","volume":"660 ","pages":"Article 130359"},"PeriodicalIF":2.8,"publicationDate":"2025-01-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143158068","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"物理与天体物理","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Physics-informed neural networks in iterative form of nonlinear equations for numerical algorithms and simulations of delay differential equations
IF 2.8 3区 物理与天体物理 Q2 PHYSICS, MULTIDISCIPLINARY Pub Date : 2025-01-21 DOI: 10.1016/j.physa.2025.130368
Jilong He , Abd’gafar Tunde Tiamiyu
This paper proposes a new high-precision and efficient algorithm for solving delay differential equations using a physics-informed neural network. We utilize initial conditions and two types of neural network methods, namely the Extreme Learning Machine and the Multilayer Perceptron, to construct trial functions that accurately satisfy the initial conditions. These trial functions are then used to discretize the delay differential equations. In contrast to the original physics-informed neural network, we employ an iterative approach by transforming the form of the loss function into an algebraic system generated at configuration points. The algebraic system is iteratively computed to obtain the optimal parameters, which correspond to the optimal solution of the equation. Finally, we validate the effectiveness of our method through six numerical examples, including complex delay differential systems, demonstrating that our approach yields high-precision and efficient numerical results.
{"title":"Physics-informed neural networks in iterative form of nonlinear equations for numerical algorithms and simulations of delay differential equations","authors":"Jilong He ,&nbsp;Abd’gafar Tunde Tiamiyu","doi":"10.1016/j.physa.2025.130368","DOIUrl":"10.1016/j.physa.2025.130368","url":null,"abstract":"<div><div>This paper proposes a new high-precision and efficient algorithm for solving delay differential equations using a physics-informed neural network. We utilize initial conditions and two types of neural network methods, namely the Extreme Learning Machine and the Multilayer Perceptron, to construct trial functions that accurately satisfy the initial conditions. These trial functions are then used to discretize the delay differential equations. In contrast to the original physics-informed neural network, we employ an iterative approach by transforming the form of the loss function into an algebraic system generated at configuration points. The algebraic system is iteratively computed to obtain the optimal parameters, which correspond to the optimal solution of the equation. Finally, we validate the effectiveness of our method through six numerical examples, including complex delay differential systems, demonstrating that our approach yields high-precision and efficient numerical results.</div></div>","PeriodicalId":20152,"journal":{"name":"Physica A: Statistical Mechanics and its Applications","volume":"660 ","pages":"Article 130368"},"PeriodicalIF":2.8,"publicationDate":"2025-01-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143157309","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"物理与天体物理","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Asymmetric autocorrelation in the crude oil market at multiple scales based on a hybrid approach of variational mode decomposition and quantile autoregression
IF 2.8 3区 物理与天体物理 Q2 PHYSICS, MULTIDISCIPLINARY Pub Date : 2025-01-20 DOI: 10.1016/j.physa.2025.130384
Xinpeng Ding , Jiayi He , Yali Zhang , Yi Yin
Heterogeneous dependence and memory effects are widely recognized in financial markets, including the crude oil future market. However, few studies have examined the correlation between heterogeneous dependence and memory effects. This association reveals differences in the different memory-trait components, yet the literature is lacking. Our study aims to uncover heterogeneous dependence and memory effects on crude oil future returns and their components at multiple scales and to explain the asymmetry of dependence patterns in the crude oil market through the perspective of irrational investor behavior induced by memory effects. The regressions in this study are based on West Texas Intermediate (WTI) crude oil future prices from 1983 to 2023. We propose a hybrid approach that combines variational mode decomposition (VMD) and quantile autoregression (QAR) to process the return and fluctuation series. Similar to the stock market, we find that the QAR coefficients vary across quantiles. The coefficients are positive for the long-term memory component and negative for the anti-persistent component, indicating the momentum and revert effects. The impacts of extreme lagged returns and negative lagged returns on the distribution of coefficients are evident not only in the return series but also in the two components. Lagged fluctuation and extreme lagged fluctuation accelerate the current fluctuation growth at higher quantiles due to rapid accumulation. Finally, the robustness test confirms that the VMD-QAR method is more resistant to noise and sampling disturbances compared to existing methods. Our study contributes to the analysis of the crude oil market in terms of theoretical and analytical methods in finance.
{"title":"Asymmetric autocorrelation in the crude oil market at multiple scales based on a hybrid approach of variational mode decomposition and quantile autoregression","authors":"Xinpeng Ding ,&nbsp;Jiayi He ,&nbsp;Yali Zhang ,&nbsp;Yi Yin","doi":"10.1016/j.physa.2025.130384","DOIUrl":"10.1016/j.physa.2025.130384","url":null,"abstract":"<div><div>Heterogeneous dependence and memory effects are widely recognized in financial markets, including the crude oil future market. However, few studies have examined the correlation between heterogeneous dependence and memory effects. This association reveals differences in the different memory-trait components, yet the literature is lacking. Our study aims to uncover heterogeneous dependence and memory effects on crude oil future returns and their components at multiple scales and to explain the asymmetry of dependence patterns in the crude oil market through the perspective of irrational investor behavior induced by memory effects. The regressions in this study are based on West Texas Intermediate (WTI) crude oil future prices from 1983 to 2023. We propose a hybrid approach that combines variational mode decomposition (VMD) and quantile autoregression (QAR) to process the return and fluctuation series. Similar to the stock market, we find that the QAR coefficients vary across quantiles. The coefficients are positive for the long-term memory component and negative for the anti-persistent component, indicating the momentum and revert effects. The impacts of extreme lagged returns and negative lagged returns on the distribution of coefficients are evident not only in the return series but also in the two components. Lagged fluctuation and extreme lagged fluctuation accelerate the current fluctuation growth at higher quantiles due to rapid accumulation. Finally, the robustness test confirms that the VMD-QAR method is more resistant to noise and sampling disturbances compared to existing methods. Our study contributes to the analysis of the crude oil market in terms of theoretical and analytical methods in finance.</div></div>","PeriodicalId":20152,"journal":{"name":"Physica A: Statistical Mechanics and its Applications","volume":"660 ","pages":"Article 130384"},"PeriodicalIF":2.8,"publicationDate":"2025-01-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143158020","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"物理与天体物理","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
期刊
Physica A: Statistical Mechanics and its Applications
全部 Acc. Chem. Res. ACS Applied Bio Materials ACS Appl. Electron. Mater. ACS Appl. Energy Mater. ACS Appl. Mater. Interfaces ACS Appl. Nano Mater. ACS Appl. Polym. Mater. ACS BIOMATER-SCI ENG ACS Catal. ACS Cent. Sci. ACS Chem. Biol. ACS Chemical Health & Safety ACS Chem. Neurosci. ACS Comb. Sci. ACS Earth Space Chem. ACS Energy Lett. ACS Infect. Dis. ACS Macro Lett. ACS Mater. Lett. ACS Med. Chem. Lett. ACS Nano ACS Omega ACS Photonics ACS Sens. ACS Sustainable Chem. Eng. ACS Synth. Biol. Anal. Chem. BIOCHEMISTRY-US Bioconjugate Chem. BIOMACROMOLECULES Chem. Res. Toxicol. Chem. Rev. Chem. Mater. CRYST GROWTH DES ENERG FUEL Environ. Sci. Technol. Environ. Sci. Technol. Lett. Eur. J. Inorg. Chem. IND ENG CHEM RES Inorg. Chem. J. Agric. Food. Chem. J. Chem. Eng. Data J. Chem. Educ. J. Chem. Inf. Model. J. Chem. Theory Comput. J. Med. Chem. J. Nat. Prod. J PROTEOME RES J. Am. Chem. Soc. LANGMUIR MACROMOLECULES Mol. Pharmaceutics Nano Lett. Org. Lett. ORG PROCESS RES DEV ORGANOMETALLICS J. Org. Chem. J. Phys. Chem. J. Phys. Chem. A J. Phys. Chem. B J. Phys. Chem. C J. Phys. Chem. Lett. Analyst Anal. Methods Biomater. Sci. Catal. Sci. Technol. Chem. Commun. Chem. Soc. Rev. CHEM EDUC RES PRACT CRYSTENGCOMM Dalton Trans. Energy Environ. Sci. ENVIRON SCI-NANO ENVIRON SCI-PROC IMP ENVIRON SCI-WAT RES Faraday Discuss. Food Funct. Green Chem. Inorg. Chem. Front. Integr. Biol. J. Anal. At. Spectrom. J. Mater. Chem. A J. Mater. Chem. B J. Mater. Chem. C Lab Chip Mater. Chem. Front. Mater. Horiz. MEDCHEMCOMM Metallomics Mol. Biosyst. Mol. Syst. Des. Eng. Nanoscale Nanoscale Horiz. Nat. Prod. Rep. New J. Chem. Org. Biomol. Chem. Org. Chem. Front. PHOTOCH PHOTOBIO SCI PCCP Polym. Chem.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1