This page has only limited features, please log in for full access.
This study aims to understand the dynamics of credit and business cycle interactions at the aggregated and disaggregated (sectors and industries) levels in the Indian context. We explore both parametric and non-parametric time-series approach to date the major turning points and calculate the lead-lag measures. We also test for synchronizing credit and business cycles and finding that there is a procyclicality during the crisis period. However, the analysis at sectoral and industry levels exhibit asymmetry as some sectors exhibit countercyclically. The business cycle precedes the credit cycle at the aggregated and disaggregated levels. The repo rate, broad money, real exchange rate, and industrial output significantly explain India's business-credit dynamics.
Seema Saini; Wasim Ahmad; Stelios Bekiros. Understanding the credit cycle and business cycle dynamics in India. International Review of Economics & Finance 2021, 76, 988 -1006.
AMA StyleSeema Saini, Wasim Ahmad, Stelios Bekiros. Understanding the credit cycle and business cycle dynamics in India. International Review of Economics & Finance. 2021; 76 ():988-1006.
Chicago/Turabian StyleSeema Saini; Wasim Ahmad; Stelios Bekiros. 2021. "Understanding the credit cycle and business cycle dynamics in India." International Review of Economics & Finance 76, no. : 988-1006.
In the present study, a new neural network-based terminal sliding mode technique is proposed to stabilize and synchronize fractional-order chaotic ecological systems in finite-time. The Chebyshev neural network is implemented to estimate unknown functions of the system. Moreover, through the proposed Chebyshev neural network observer, the effects of external disturbances are fully taken into account. The weights of the Chebyshev neural network observer are adjusted based on adaptive laws. The finite-time convergence of the closed-loop system, which is a new concept for ecological systems, is proven. Then, the dependency of the system on the value of the fractional time derivatives is investigated. Lastly, the proposed control scheme is applied to the fractional-order ecological system. Through numerical simulations, the performance of the developed technique for synchronization and stabilization are assessed and compared with a conventional method. The numerical simulations strongly corroborate the effective performance of the proposed control technique in terms of accuracy, robustness, and convergence time for the unknown nonlinear system in the presence of external disturbances.
Bo Wang; Hadi Jahanshahi; Hemen Dutta; Ernesto Zambrano-Serrano; Vladimir Grebenyuk; Stelios Bekiros; Ayman A. Aly. Incorporating fast and intelligent control technique into ecology: A Chebyshev neural network-based terminal sliding mode approach for fractional chaotic ecological systems. Ecological Complexity 2021, 47, 100943 .
AMA StyleBo Wang, Hadi Jahanshahi, Hemen Dutta, Ernesto Zambrano-Serrano, Vladimir Grebenyuk, Stelios Bekiros, Ayman A. Aly. Incorporating fast and intelligent control technique into ecology: A Chebyshev neural network-based terminal sliding mode approach for fractional chaotic ecological systems. Ecological Complexity. 2021; 47 ():100943.
Chicago/Turabian StyleBo Wang; Hadi Jahanshahi; Hemen Dutta; Ernesto Zambrano-Serrano; Vladimir Grebenyuk; Stelios Bekiros; Ayman A. Aly. 2021. "Incorporating fast and intelligent control technique into ecology: A Chebyshev neural network-based terminal sliding mode approach for fractional chaotic ecological systems." Ecological Complexity 47, no. : 100943.
Control of supply chains with chaotic dynamics is an important, yet daunting challenge because of the limitations and constraints there are in the amplitude of control efforts. In real-world systems, applying control techniques that need a large amplitude signal is impractical. In the literature, there is no study that considers the control of supply chain systems subject to control input limitations. To this end, in the current study, a new control scheme is proposed to tackle this issue. In the designed control input, limitations in control inputs, as well as robustness against uncertainties, are taken into account. The proposed scheme is equipped with a fixed time disturbance observer to eliminate the destructive effects of uncertainties and disturbances. Additionally, the super-twisting sliding mode technique guarantees the fixed-time convergence of the closed-loop system. After that, a symmetric supply chain system is presented, and its chaotic attractors are demonstrated. Finally, the proposed controller is applied to the symmetric supply chain system. Numerical simulations exhibit the proposed scheme’s excellent performance even though the system is subjected to control input limitations and time-varying uncertainties.
Bo Wang; Hadi Jahanshahi; Christos Volos; Stelios Bekiros; Abdullahi Yusuf; Praveen Agarwal; Ayman Aly. Control of a Symmetric Chaotic Supply Chain System Using a New Fixed-Time Super-Twisting Sliding Mode Technique Subject to Control Input Limitations. Symmetry 2021, 13, 1257 .
AMA StyleBo Wang, Hadi Jahanshahi, Christos Volos, Stelios Bekiros, Abdullahi Yusuf, Praveen Agarwal, Ayman Aly. Control of a Symmetric Chaotic Supply Chain System Using a New Fixed-Time Super-Twisting Sliding Mode Technique Subject to Control Input Limitations. Symmetry. 2021; 13 (7):1257.
Chicago/Turabian StyleBo Wang; Hadi Jahanshahi; Christos Volos; Stelios Bekiros; Abdullahi Yusuf; Praveen Agarwal; Ayman Aly. 2021. "Control of a Symmetric Chaotic Supply Chain System Using a New Fixed-Time Super-Twisting Sliding Mode Technique Subject to Control Input Limitations." Symmetry 13, no. 7: 1257.
We examine long memory (self-similarity) in digital currencies and international stock exchanges prior and during COVID-19 pandemic. Specifically, ARFIMA and FIGARCH models are respectively employed to evaluate long memory parameter in returns and volatility. The dataset contains 45 cryptocurrency markets and 16 international equity markets. The t-test and F-test are performed to estimated long memory parameters. The empirical findings follow. First, the level of persistence in return series of both markets has increased during the COVID-19 pandemic. Second, during COVID-19 pandemic, variability level in persistence in return series has increased in both digital currencies and stock markets. Third, return series in both markets exhibited comparable level of persistence prior and during the COVID-19 pandemic. Fourth, return series in volatility series of cryptocurrency exhibited high degree of persistence compared to international stock markets during the COVID-19 pandemic. Therefore, it is concluded that COVID-19 pandemic significantly affected long memory in return and volatility of cryptocurrency and international stock markets. In addition, our results suggest that the hybrid long memory model represented by the integration of ARFIMA-FIGARCH is significantly suitable to describe returns and volatility of cryptocurrencies and stocks and to reveal differences before and during COVID-19 pandemic periods.
Salim Lahmiri; Stelios Bekiros. The effect of COVID-19 on long memory in returns and volatility of cryptocurrency and stock markets. Chaos, Solitons & Fractals 2021, 151, 111221 .
AMA StyleSalim Lahmiri, Stelios Bekiros. The effect of COVID-19 on long memory in returns and volatility of cryptocurrency and stock markets. Chaos, Solitons & Fractals. 2021; 151 ():111221.
Chicago/Turabian StyleSalim Lahmiri; Stelios Bekiros. 2021. "The effect of COVID-19 on long memory in returns and volatility of cryptocurrency and stock markets." Chaos, Solitons & Fractals 151, no. : 111221.
Recently, intelligent control techniques have received considerable attention. In most studies, the systems’ model is assumed to be without any delay, and the effects of faults and failure in actuators are ignored. However, in real practice, sensor malfunctioning, mounting limitation, and defects in actuators bring about faults, failure, delay, and disturbances. Consequently, applying controllers that do not consider these problems could significantly deteriorate controllers’ performance. In order to address this issue, in the current paper, we propose a new neural network-based fault-tolerant active control for fractional time-delayed systems. The neural network estimator is integrated with active control to compensate for all uncertainties and disturbances. The suggested method’s stability is achieved based on the concept of active control and the Lyapunov stability theorem. Then, a fractional-order memristor system is investigated, and some characteristics of this chaotic system are studied. Lastly, by applying the proposed control scheme, synchronization results of the fractional time-delayed memristor system in the presence of faults and uncertainties are studied. The simulation results suggest the effectiveness of the proposed control technique for uncertain time-delayed nonlinear systems.
Bo Wang; Hadi Jahanshahi; Christos Volos; Stelios Bekiros; Muhammad Khan; Praveen Agarwal; Ayman Aly. A New RBF Neural Network-Based Fault-Tolerant Active Control for Fractional Time-Delayed Systems. Electronics 2021, 10, 1501 .
AMA StyleBo Wang, Hadi Jahanshahi, Christos Volos, Stelios Bekiros, Muhammad Khan, Praveen Agarwal, Ayman Aly. A New RBF Neural Network-Based Fault-Tolerant Active Control for Fractional Time-Delayed Systems. Electronics. 2021; 10 (12):1501.
Chicago/Turabian StyleBo Wang; Hadi Jahanshahi; Christos Volos; Stelios Bekiros; Muhammad Khan; Praveen Agarwal; Ayman Aly. 2021. "A New RBF Neural Network-Based Fault-Tolerant Active Control for Fractional Time-Delayed Systems." Electronics 10, no. 12: 1501.
Since December 2019, the new coronavirus has raged in China and subsequently all over the world. From the first days, researchers have tried to discover vaccines to combat the epidemic. Several vaccines are now available as a result of the contributions of those researchers. As a matter of fact, the available vaccines should be used in effective and efficient manners to put the pandemic to an end. Hence, a major problem now is how to efficiently distribute these available vaccines among various components of the population. Using mathematical modeling and reinforcement learning control approaches, the present article aims to address this issue. To this end, a deterministic Susceptible-Exposed-Infectious-Recovered-type model with additional vaccine components is proposed. The proposed mathematical model can be used to simulate the consequences of vaccination policies. Then, the suppression of the outbreak is taken to account. The main objective is to reduce the effects of Covid-19 and its domino effects which stem from its spreading and progression. Therefore, to reach optimal policies, reinforcement learning optimal control is implemented, and four different optimal strategies are extracted. Demonstrating the efficacy of the proposed methods, finally, numerical simulations are presented.
Alireza Beigi; Amin Yousefpour; Amirreza Yasami; J. F. Gómez-Aguilar; Stelios Bekiros; Hadi Jahanshahi. Application of reinforcement learning for effective vaccination strategies of coronavirus disease 2019 (COVID-19). The European Physical Journal Plus 2021, 136, 1 -22.
AMA StyleAlireza Beigi, Amin Yousefpour, Amirreza Yasami, J. F. Gómez-Aguilar, Stelios Bekiros, Hadi Jahanshahi. Application of reinforcement learning for effective vaccination strategies of coronavirus disease 2019 (COVID-19). The European Physical Journal Plus. 2021; 136 (5):1-22.
Chicago/Turabian StyleAlireza Beigi; Amin Yousefpour; Amirreza Yasami; J. F. Gómez-Aguilar; Stelios Bekiros; Hadi Jahanshahi. 2021. "Application of reinforcement learning for effective vaccination strategies of coronavirus disease 2019 (COVID-19)." The European Physical Journal Plus 136, no. 5: 1-22.
In this paper, by considering the Caputo-like delta difference definition, a fractional difference order map with chaotic dynamics and with no equilibria is proposed. The complex dynamical behaviors associated with fractional difference order maps are analyzed employing the phase portraits, bifurcations diagrams, and Lyapunov exponents. The complexity of the sequence generated by the chaotic difference map is studied using the permutation entropy approach. Afterwards, projective synchronization of the systems is investigated. Fuzzy logic engines as intelligent schemes are strong tools for control of various systems. However, studies that apply fuzzy logic engines for control of fractional-order discrete-time systems are rare. Hence, in the current study, by taking advantages of fuzzy systems, a new controller is proposed for the fractional-order discrete-time map. The fuzzy logic engine is implemented in order to enhance the performance and agility of the proposed control technique. The stability of the closed-loop systems and asymptotic convergence of the projective synchronization error based on the proposed control scheme are proven. Finally, numerical simulations which clearly confirm that the offered control technique is able to push the states of the fractional-order discrete-time system to the desired value in a short period of time are presented.
Ernesto Zambrano-Serrano; Stelios Bekiros; Miguel A. Platas-Garza; Cornelio Posadas-Castillo; Praveen Agarwal; Hadi Jahanshahi; Ayman A. Aly. On chaos and projective synchronization of a fractional difference map with no equilibria using a fuzzy-based state feedback control. Physica A: Statistical Mechanics and its Applications 2021, 578, 126100 .
AMA StyleErnesto Zambrano-Serrano, Stelios Bekiros, Miguel A. Platas-Garza, Cornelio Posadas-Castillo, Praveen Agarwal, Hadi Jahanshahi, Ayman A. Aly. On chaos and projective synchronization of a fractional difference map with no equilibria using a fuzzy-based state feedback control. Physica A: Statistical Mechanics and its Applications. 2021; 578 ():126100.
Chicago/Turabian StyleErnesto Zambrano-Serrano; Stelios Bekiros; Miguel A. Platas-Garza; Cornelio Posadas-Castillo; Praveen Agarwal; Hadi Jahanshahi; Ayman A. Aly. 2021. "On chaos and projective synchronization of a fractional difference map with no equilibria using a fuzzy-based state feedback control." Physica A: Statistical Mechanics and its Applications 578, no. : 126100.
Salim Lahmiri; Anastasia Giakoumelou; Stelios Bekiros. Correction to: An adaptive sequential-filtering learning system for credit risk modeling. Soft Computing 2021, 1 -1.
AMA StyleSalim Lahmiri, Anastasia Giakoumelou, Stelios Bekiros. Correction to: An adaptive sequential-filtering learning system for credit risk modeling. Soft Computing. 2021; ():1-1.
Chicago/Turabian StyleSalim Lahmiri; Anastasia Giakoumelou; Stelios Bekiros. 2021. "Correction to: An adaptive sequential-filtering learning system for credit risk modeling." Soft Computing , no. : 1-1.
Although most of the early research studies on fractional-order systems were based on the Caputo or Riemann–Liouville fractional-order derivatives, it has recently been proven that these methods have some drawbacks. For instance, kernels of these methods have a singularity that occurs at the endpoint of an interval of definition. Thus, to overcome this issue, several new definitions of fractional derivatives have been introduced. The Caputo–Fabrizio fractional order is one of these nonsingular definitions. This paper is concerned with the analyses and design of an optimal control strategy for a Caputo–Fabrizio fractional-order model of the HIV/AIDS epidemic. The Caputo–Fabrizio fractional-order model of HIV/AIDS is considered to prevent the singularity problem, which is a real concern in the modeling of real-world systems and phenomena. Firstly, in order to find out how the population of each compartment can be controlled, sensitivity analyses were conducted. Based on the sensitivity analyses, the most effective agents in disease transmission and prevalence were selected as control inputs. In this way, a modified Caputo–Fabrizio fractional-order model of the HIV/AIDS epidemic is proposed. By changing the contact rate of susceptible and infectious people, the atraumatic restorative treatment rate of the treated compartment individuals, and the sexual habits of susceptible people, optimal control was designed. Lastly, simulation results that demonstrate the appropriate performance of the Caputo–Fabrizio fractional-order model and proposed control scheme are illustrated.
Hua Wang; Hadi Jahanshahi; Miao-Kun Wang; Stelios Bekiros; Jinping Liu; Ayman Aly. A Caputo–Fabrizio Fractional-Order Model of HIV/AIDS with a Treatment Compartment: Sensitivity Analysis and Optimal Control Strategies. Entropy 2021, 23, 610 .
AMA StyleHua Wang, Hadi Jahanshahi, Miao-Kun Wang, Stelios Bekiros, Jinping Liu, Ayman Aly. A Caputo–Fabrizio Fractional-Order Model of HIV/AIDS with a Treatment Compartment: Sensitivity Analysis and Optimal Control Strategies. Entropy. 2021; 23 (5):610.
Chicago/Turabian StyleHua Wang; Hadi Jahanshahi; Miao-Kun Wang; Stelios Bekiros; Jinping Liu; Ayman Aly. 2021. "A Caputo–Fabrizio Fractional-Order Model of HIV/AIDS with a Treatment Compartment: Sensitivity Analysis and Optimal Control Strategies." Entropy 23, no. 5: 610.
Credit risk and business failure classification and prediction are a major topic in financial risk management and corporate finance decision making. In this work, an adaptive sequential-filtering learning system for credit risk modeling. It is basically a three-stage sequential system for credit risk and business failure classification is presented. First, different statistical filters are applied separately to perform a preselection of relevant patterns. Second, genetic algorithms are applied to preselected patterns for refinement purpose. Finally, structural risk minimization approach based on support vector machine uses refined patterns for prediction purpose. We used three credit databases and two data partition schemes: (i) random split with 80% for learning and 20% testing, and (ii) tenfold cross-validation technique. Results from all three data sets and for all partition techniques show the effectiveness of the proposed adaptive sequential-filtering learning system for credit risk modeling against single support vector machines each with specific statistical filter-based patterns. In addition, it outperformed various models validated on the same databases. It is concluded that the presented adaptive sequential system is promising for credit risk monitoring.
Salim Lahmiri; Anastasia Giakoumelou; Stelios Bekiros. An adaptive sequential-filtering learning system for credit risk modeling. Soft Computing 2021, 1 -8.
AMA StyleSalim Lahmiri, Anastasia Giakoumelou, Stelios Bekiros. An adaptive sequential-filtering learning system for credit risk modeling. Soft Computing. 2021; ():1-8.
Chicago/Turabian StyleSalim Lahmiri; Anastasia Giakoumelou; Stelios Bekiros. 2021. "An adaptive sequential-filtering learning system for credit risk modeling." Soft Computing , no. : 1-8.
We consider directional volatility connectedness among energy markets and financial markets over time and frequencies simultaneously during the period 2007–2018. We utilize and expand Barunik and Krehlik (J Financ Econom 16:271-296, 2018) connectedness measurements using HVAR in order to achieve a better perspective of energy markets. Our results indicate that during a crisis, the connectedness among markets increases dramatically. Furthermore, our findings support that markets are mostly driven by short-term factors and are highly speculative. Among energy markets, Natural Gas Futures contribute the least to other markets in all time frames. Besides, London Gas Oil Futures and Heating Oil Futures collaborate. Currencies and Natural Gas Futures are suitable choices for portfolio managers to hedge their risks especially in the long run. The findings of this article can offer new insights to policymakers about the mechanism of connectedness among different markets and international investors.
Ehsan Bagheri; Seyed Babak Ebrahimi; Arman Mohammadi; Mahsa Miri; Stelios Bekiros. The Dynamic Volatility Connectedness Structure of Energy Futures and Global Financial Markets: Evidence From a Novel Time–Frequency Domain Approach. Computational Economics 2021, 1 -25.
AMA StyleEhsan Bagheri, Seyed Babak Ebrahimi, Arman Mohammadi, Mahsa Miri, Stelios Bekiros. The Dynamic Volatility Connectedness Structure of Energy Futures and Global Financial Markets: Evidence From a Novel Time–Frequency Domain Approach. Computational Economics. 2021; ():1-25.
Chicago/Turabian StyleEhsan Bagheri; Seyed Babak Ebrahimi; Arman Mohammadi; Mahsa Miri; Stelios Bekiros. 2021. "The Dynamic Volatility Connectedness Structure of Energy Futures and Global Financial Markets: Evidence From a Novel Time–Frequency Domain Approach." Computational Economics , no. : 1-25.
Due to the importance of consumed control energy in financial systems, employing an optimal controller for these systems could be beneficial. Also, the presence of disturbances is undeniable in most of these systems. Hence, applying optimal mixed H2/H∞ control, which posses the positive features of both H∞ and H2 control, could bring up luminous results for these systems. However, in the literature, no attempt has been made to design thistypeof controller for chaotic financial systems. This issue motivated the current study. In this study, we present a type-2 fuzzy-based optimal mixed H2/H∞ control for a hyperchaotic financial system. In this approach, H∞ attenuates the effect of uncertainties and through H2the consumed control energy is minimized. Also, since the proposed controller is equipped with a type-2 fuzzy observer, it can easily handle uncertainties and unknown functions. Via Lyapunov theorem, it is confirmed that all signals in the system are bounded. In the numerical simulation, firstly, a hyperchaotic financial system with coexisting attractors is investigated. The proposed controller is then applied to the financial system, and the proposed technique's performance is assessed. Numerical simulations clearly confirm the theoretical claims about the effectiveness of the proposed methodology.
Stelios Bekiros; Hadi Jahanshahi; Frank Bezzina; Ayman A. Aly. A novel fuzzy mixed H2/H∞ optimal controller for hyperchaotic financial systems. Chaos, Solitons & Fractals 2021, 146, 110878 .
AMA StyleStelios Bekiros, Hadi Jahanshahi, Frank Bezzina, Ayman A. Aly. A novel fuzzy mixed H2/H∞ optimal controller for hyperchaotic financial systems. Chaos, Solitons & Fractals. 2021; 146 ():110878.
Chicago/Turabian StyleStelios Bekiros; Hadi Jahanshahi; Frank Bezzina; Ayman A. Aly. 2021. "A novel fuzzy mixed H2/H∞ optimal controller for hyperchaotic financial systems." Chaos, Solitons & Fractals 146, no. : 110878.
Disturbances are inevitably found in almost every system and, if not rejected, they could jeopardize the effectiveness of control methods. Thereby, employing state-of-the-art observers could improve the reliability and performance of controllers dramatically. Motivated by this, we develop a new finite-time method for controlling and synchronising fractional-order systems. The deep learning recurrent neural network, which is a strong tool in handling highly complex and time-varying uncertainties, is integrated by terminal sliding mode control. On the basis of Lyapunov stability theorem, the finite-time convergence and stability of the closed-loop system are proven. Then, the proposed technique is applied to a chaotic fractional-order financial model with market confidence. In simulations, it is supposed that the system is operating in the presence of complex disturbances. The results of the proposed technique are compared with terminal sliding mode control. Numerical results illustratively confirm the theoretical claims about the robust performance of the deep learning control technique. Also, it is shown that when the disturbances are high, the conventional methods fail.
Yong-Long Wang; Hadi Jahanshahi; Stelios Bekiros; Frank Bezzina; Yu-Ming Chu; Ayman A. Aly. Deep recurrent neural networks with finite-time terminal sliding mode control for a chaotic fractional-order financial system with market confidence. Chaos, Solitons & Fractals 2021, 146, 110881 .
AMA StyleYong-Long Wang, Hadi Jahanshahi, Stelios Bekiros, Frank Bezzina, Yu-Ming Chu, Ayman A. Aly. Deep recurrent neural networks with finite-time terminal sliding mode control for a chaotic fractional-order financial system with market confidence. Chaos, Solitons & Fractals. 2021; 146 ():110881.
Chicago/Turabian StyleYong-Long Wang; Hadi Jahanshahi; Stelios Bekiros; Frank Bezzina; Yu-Ming Chu; Ayman A. Aly. 2021. "Deep recurrent neural networks with finite-time terminal sliding mode control for a chaotic fractional-order financial system with market confidence." Chaos, Solitons & Fractals 146, no. : 110881.
In this novel research, through dynamical analysis, we introduce for the first time a fractional-calculus based artificial macroeconomic model, actually implemented in the Laboratory via a new hardware set up. Firstly, we propose a new model of a discrete-time macroeconomic system where fractional derivatives are incorporated into the system of equations. Using well-known tools and methods, including bifurcation diagrams and Lyapunov exponents, the characteristics of the system are disclosed, and the importance of the fractional-order derivative in the modeling of the system is shown. After that, a laboratory hardware realization is also carried out for the proposed system that provides further insight and a better understanding of the properties of the system. For the hardware realization an Arduino Due™ is chosen in which possess two analog output pins. Experimental results conspicuously illustrate the chaotic behavior of the system. Through the results of the hardware realization, phase portraits and bifurcation diagram of the system are demonstrated, and the effects of the parameters and fractional derivatives are studied. We believe the presented study and its results pave the way for future studies on the incorporation of fractional calculus into macroeconomic models.
Yu-Ming Chu; Stelios Bekiros; Ernesto Zambrano-Serrano; Onofre Orozco-López; Salim Lahmiri; Hadi Jahanshahi; Ayman A. Aly. Artificial macro-economics: A chaotic discrete-time fractional-order laboratory model. Chaos, Solitons & Fractals 2021, 145, 110776 .
AMA StyleYu-Ming Chu, Stelios Bekiros, Ernesto Zambrano-Serrano, Onofre Orozco-López, Salim Lahmiri, Hadi Jahanshahi, Ayman A. Aly. Artificial macro-economics: A chaotic discrete-time fractional-order laboratory model. Chaos, Solitons & Fractals. 2021; 145 ():110776.
Chicago/Turabian StyleYu-Ming Chu; Stelios Bekiros; Ernesto Zambrano-Serrano; Onofre Orozco-López; Salim Lahmiri; Hadi Jahanshahi; Ayman A. Aly. 2021. "Artificial macro-economics: A chaotic discrete-time fractional-order laboratory model." Chaos, Solitons & Fractals 145, no. : 110776.
Like common stocks, Bitcoin price fluctuations are non-stationary and highly noisy. Due to attractiveness of Bitcoin in terms of returns and risk, Bitcoin price prediction is attracting a growing attention from both investors and researchers. Indeed, with the development of machine learning and especially deep learning, forecasting Bitcoin is receiving a particular interest. We implement and apply deep forward neural network (DFFNN) for the analysis and forecasting Bitcoin high-frequency price data. Importantly, we seek to investigate the effect of standard numerical training algorithms on the accuracy obtained by DFFNN; namely, the conjugate gradient with Powell-Beale restarts, the resilient algorithm, and Levenberg-Marquardt algorithm. The DFFNN was applied to a big dataset composed of 65,535 samples. In terms of root mean of squared errors (RMSEs), the simulation results show that the DFFNN trained with the Levenberg-Marquardt algorithm outperforms DFFNN trained with Powell-Beale restarts algorithm and DFFNN trained with resilient algorithm. In addition, the resilient algorithm is fast which suggests that it could be promising in online training and trading. The DFFNN trained with Levenberg-Marquardt algorithm is effective and easy to implement for Bitcoin high-frequency price data forecasting.
Salim Lahmiri; Stelios Bekiros. Deep Learning Forecasting in Cryptocurrency High-Frequency Trading. Cognitive Computation 2021, 13, 485 -487.
AMA StyleSalim Lahmiri, Stelios Bekiros. Deep Learning Forecasting in Cryptocurrency High-Frequency Trading. Cognitive Computation. 2021; 13 (2):485-487.
Chicago/Turabian StyleSalim Lahmiri; Stelios Bekiros. 2021. "Deep Learning Forecasting in Cryptocurrency High-Frequency Trading." Cognitive Computation 13, no. 2: 485-487.
Mathematical modelling plays an indispensable role in our understanding of systems and phenomena. However, most mathematical models formulated for systems either have an integer order derivate or posses constant fractional-order derivative. Hence, their performance significantly deteriorates in some conditions. For the first time in the current paper, we develop a model of an economic system with variable-order fractional derivatives. Our underlying assumption is that the values of fractional derivatives are time-varying functions instead of constant parameters. The effects of variable-order time derivative into the economic system is studied. The dependency of the system's behaviour on the value of the fractional-order derivative is investigated. Afterwards, a nonlinear model predictive controller (NMPC) for hyperchaotic control of the system is suggested. The necessary optimality and sufficient conditions for solving the nonlinear optimal control problem (NOCP) of the NMPC in the form of fractional calculus with variable-order which is formulated as a two-point boundary value problem (TPBVP) are derived. Since the proposed methodology is a robust controller, the efficiency of the proposed controller in the presence of external bounded disturbances is examined. Simulation results show that not only does the presented control approach suppresses the related chaotic behaviour and stabilizes the close-loop system, but it also rejects the external bounded disturbances.
Hadi Jahanshahi; Samaneh Sadat Sajjadi; Stelios Bekiros; Ayman A. Aly. On the development of variable-order fractional hyperchaotic economic system with a nonlinear model predictive controller. Chaos, Solitons & Fractals 2021, 144, 110698 .
AMA StyleHadi Jahanshahi, Samaneh Sadat Sajjadi, Stelios Bekiros, Ayman A. Aly. On the development of variable-order fractional hyperchaotic economic system with a nonlinear model predictive controller. Chaos, Solitons & Fractals. 2021; 144 ():110698.
Chicago/Turabian StyleHadi Jahanshahi; Samaneh Sadat Sajjadi; Stelios Bekiros; Ayman A. Aly. 2021. "On the development of variable-order fractional hyperchaotic economic system with a nonlinear model predictive controller." Chaos, Solitons & Fractals 144, no. : 110698.
COVID-19 is a novel coronavirus affecting all the world since December last year. Up to date, the spread of the outbreak continues to complicate our lives, and therefore, several research efforts from many scientific areas are proposed. Among them, mathematical models are an excellent way to understand and predict the epidemic outbreaks evolution to some extent. Due to the COVID-19 may be modeled as a non-Markovian process that follows power-law scaling features, we present a fractional-order SIRD (Susceptible-Infected-Recovered-Dead) model based on the Caputo derivative for incorporating the memory effects (long and short) in the outbreak progress. Additionally, we analyze the experimental time series of 23 countries using fractal formalism. Like previous works, we identify that the COVID-19 evolution shows various power-law exponents (no just a single one) and share some universality among geographical regions. Hence, we incorporate numerous memory indexes in the proposed model, i.e., distinct fractional-orders defined by a time-dependent function that permits us to set specific memory contributions during the evolution. This allows controlling the memory effects of more early states, e.g., before and after a quarantine decree, which could be less relevant than the contribution of more recent ones on the current state of the SIRD system. We also prove our model with Italy’s real data from the Center for Systems Science and Engineering (CSSE) at Johns Hopkins University.
Hadi Jahanshahi; Jesus M. Munoz-Pacheco; Stelios Bekiros; Naif D. Alotaibi. A fractional-order SIRD model with time-dependent memory indexes for encompassing the multi-fractional characteristics of the COVID-19. Chaos, Solitons & Fractals 2021, 143, 110632 -110632.
AMA StyleHadi Jahanshahi, Jesus M. Munoz-Pacheco, Stelios Bekiros, Naif D. Alotaibi. A fractional-order SIRD model with time-dependent memory indexes for encompassing the multi-fractional characteristics of the COVID-19. Chaos, Solitons & Fractals. 2021; 143 ():110632-110632.
Chicago/Turabian StyleHadi Jahanshahi; Jesus M. Munoz-Pacheco; Stelios Bekiros; Naif D. Alotaibi. 2021. "A fractional-order SIRD model with time-dependent memory indexes for encompassing the multi-fractional characteristics of the COVID-19." Chaos, Solitons & Fractals 143, no. : 110632-110632.
The analysis of infant cry signals is becoming an attractive field of research in biomedical physics and engineering for better understanding of the pathologies and appropriate medial diagnosis. The main purpose of the current study is to characterize infant normal and pathological cry signals by studying their respective oscillations by means of approximate entropy and correlation dimension estimated from their respective cepstrums. We analyzed two different sets. The first one is composed of 2638 expiration cry signals and the second set is composed of 1860 inspiration cry signals, both sets equally weighted. After estimating approximate entropy and correlation dimensions from cepstrums, three standard statistical tests are applied to them including the Student t-test, F-test, and two-sample Kolmogorov-Smirnov test. All statistical tests are performed at 5% statistical significance level. The empirical results follow. First, approximate entropy and correlation dimension measures exhibit different statistical characteristics across healthy and unhealthy infant cries from both expiration and inspiration sets. Second, the level of approximate entropy in cepstrums of healthy infant cries is statistically higher than that in cepstrums of unhealthy infant cries. Third, the level of correlation dimension in cepstrums of healthy infant cries is statistically higher than that in cepstrums of unhealthy infant cries. In other words, cepstrums of healthy infant cries show lower randomness and disorder compared to cepstrums of unhealthy infant cries. It is concluded that cepstrum-based approximate entropy and correlation dimension discriminate healthy from pathological infant cry signals and can be employed as effective biomarkers for biomedical diagnosis of cry records in clinical milieu.
Salim Lahmiri; Chakib Tadj; Christian Gargour; Stelios Bekiros. Characterization of infant healthy and pathological cry signals in cepstrum domain based on approximate entropy and correlation dimension. Chaos, Solitons & Fractals 2021, 143, 110639 .
AMA StyleSalim Lahmiri, Chakib Tadj, Christian Gargour, Stelios Bekiros. Characterization of infant healthy and pathological cry signals in cepstrum domain based on approximate entropy and correlation dimension. Chaos, Solitons & Fractals. 2021; 143 ():110639.
Chicago/Turabian StyleSalim Lahmiri; Chakib Tadj; Christian Gargour; Stelios Bekiros. 2021. "Characterization of infant healthy and pathological cry signals in cepstrum domain based on approximate entropy and correlation dimension." Chaos, Solitons & Fractals 143, no. : 110639.
The human immunodeficiency virus (HIV), as one of the most hazardous viruses, causes destructive effects on the human bodies’ immune system. Hence, an immense body of research has focused on developing antiretroviral therapies for HIV infection. In the current study, we propose a new control technique for a fractional-order HIV infection model. Firstly, a fractional model of the HIV model is investigated, and the importance of the fractional-order derivative in the modeling of the system is shown. Afterward, a type-2 fuzzy logic controller is proposed for antiretroviral therapy of HIV infection. The developed control scheme consists of two individual controllers and an aggregator. The optimal aggregator modifies the output of each individual controller. Simulations for two different strategies are conducted. In the first strategy, only reverse transcriptase inhibitor (RTI) is used, and the superiority of the proposed controller over a conventional fuzzy controller is demonstrated. Lastly, in the second strategy, both RTI and protease inhibitors (PI) are used simultaneously. In this case, an optimal type-2 fuzzy aggregator is also proposed to modify the output of the individual controllers based on optimal rules. Simulations results demonstrate the appropriate performance of the designed control scheme for the uncertain system.
Shu-Bo Chen; Farhad Rajaee; Amin Yousefpour; Raúl Alcaraz; Yu-Ming Chu; J.F. Gómez-Aguilar; Stelios Bekiros; Ayman A. Aly; Hadi Jahanshahi. Antiretroviral therapy of HIV infection using a novel optimal type-2 fuzzy control strategy. Alexandria Engineering Journal 2020, 60, 1545 -1555.
AMA StyleShu-Bo Chen, Farhad Rajaee, Amin Yousefpour, Raúl Alcaraz, Yu-Ming Chu, J.F. Gómez-Aguilar, Stelios Bekiros, Ayman A. Aly, Hadi Jahanshahi. Antiretroviral therapy of HIV infection using a novel optimal type-2 fuzzy control strategy. Alexandria Engineering Journal. 2020; 60 (1):1545-1555.
Chicago/Turabian StyleShu-Bo Chen; Farhad Rajaee; Amin Yousefpour; Raúl Alcaraz; Yu-Ming Chu; J.F. Gómez-Aguilar; Stelios Bekiros; Ayman A. Aly; Hadi Jahanshahi. 2020. "Antiretroviral therapy of HIV infection using a novel optimal type-2 fuzzy control strategy." Alexandria Engineering Journal 60, no. 1: 1545-1555.
A novel approach to solve optimal control problems dealing simultaneously with fractional differential equations and time delay is proposed in this work. More precisely, a set of global radial basis functions are firstly used to approximate the states and control variables in the problem. Then, a collocation method is applied to convert the time-delay fractional optimal control problem to a nonlinear programming one. By solving the resulting challenge, the unknown coefficients of the original one will be finally obtained. In this way, the proposed strategy introduces a very tunable framework for direct trajectory optimization, according to the discretization procedure and the range of arbitrary nodes. The algorithm’s performance has been analyzed for several non-trivial examples, and the obtained results have shown that this scheme is more accurate, robust, and efficient than most previous methods.
Shu-Bo Chen; Samaneh Soradi-Zeid; Yu-Ming Chu; Raúl Alcaraz; José Gómez-Aguilar; Stelios Bekiros; Hadi Jahanshahi. Optimal Control of Time-Delay Fractional Equations via a Joint Application of Radial Basis Functions and Collocation Method. Entropy 2020, 22, 1213 .
AMA StyleShu-Bo Chen, Samaneh Soradi-Zeid, Yu-Ming Chu, Raúl Alcaraz, José Gómez-Aguilar, Stelios Bekiros, Hadi Jahanshahi. Optimal Control of Time-Delay Fractional Equations via a Joint Application of Radial Basis Functions and Collocation Method. Entropy. 2020; 22 (11):1213.
Chicago/Turabian StyleShu-Bo Chen; Samaneh Soradi-Zeid; Yu-Ming Chu; Raúl Alcaraz; José Gómez-Aguilar; Stelios Bekiros; Hadi Jahanshahi. 2020. "Optimal Control of Time-Delay Fractional Equations via a Joint Application of Radial Basis Functions and Collocation Method." Entropy 22, no. 11: 1213.