Zakaria Bouhanch
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Zakaria Bouhanch has a total of 12 co-authors. Here are the top co-authors by number of shared publications:
- Karim El Moutaouakil
Laboratory of Mathematics and Data Science, Polydisciplinary of Taza, Sidi Mohamed Ben Abdellah University, Taza 30000, Morocco
4 shared publications - Abdellah Ahourag
Laboratory of Mathematics and Data Science, Polydisciplinary Faculty of Taza, Sidi Mohamed Ben Abdellah University, Taza 35000, Morocco
3 shared publications - Abdelfattah Oulaika
Laboratory of Mathematics and Data Science, Polydisciplinary Faculty of Taza, Sidi Mohamed Ben Abdellah University, Taza 35000, Morocco
1 shared publication - Abdellah Touhafi
Department of Engineering Sciences and Technology (INDI), Vrije Universiteit Brussel (VUB), 1050 Brussels, Belgium
1 shared publication - Abdessamad Tridane
Department of Mathematical Sciences, United Arab Emirates University, Al Ain, UAE
1 shared publication - Ahmed Aberqi
ENSA, Sidi Mohamed Ben Abdellah University, Fez, Morocco
1 shared publication
Latest Publications
- Open Access
- 16 November 2026
- Published by MDPI AG in Information
- Vol. 17 (11) , 1157
Hybrid Fuzzy–Reinforcement-Learning Control of Agent-Based Contagion Dynamics on Graphs: Drift Conditions, Topology Dependence and Benchmark Evidence
Agent-based models are widely used to study complex adaptive dynamics in heterogeneous populations, largely because they capture how autonomous agents behave without central coordination. The same decentralization makes stability hard to establish analytically. We take one controlled two-state contagion model on a graph, steered by a single broadcast scalar, and study six controllers on it: a fuzzy inference system, a tabular reinforcement learner, and four ways of combining them. The analysis is a stochastic drift argument on a Perron-weighted Lyapunov function that asks of each controller only a lower bound on its effort above an activation level, not a Lyapunov function of its own. The spectral radius of the interaction operator sets a critical effort, and a controller whose floor exceeds it keeps the population regulated. Each hybrid inherits a floor from the two it combines, which separates the four: safety blending and the hierarchical override keep a floor whatever the learner does, convex fusion and switching do not. Asynchronous updates follow from the same argument; delays and interruptions do not, and are left to simulation. Its application settings are readings of one model rather than independent validations. The trained learner cuts the fuzzy controller’s cost by 61%, yet eight tuned classical and model-based baselines all cost less than any of the six. The hybrids contain the learner’s failure outside its training range, but that failure is produced by the training protocol: a wider range of initial states removes it. A controller call costs the same up to agents, and three further models mark the scope: control is essential in a cascade, marginal under segregation, and counterproductive where it acts non-monotonically.- 16 November 2026
- Published by MDPI AG in Information
- Vol. 17 (11) , 1157
Open AccessHybrid Fuzzy–Reinforcement-Learning Control of Agent-Based Contagion Dynamics on Graphs: Drift Conditions, Topology Dependence and Benchmark Evidence
Agent-based models are widely used to study complex adaptive dynamics in heterogeneous populations, largely because they capture how autonomous agents behave without central coordination. The same decentralization makes stability hard to establish analytically. We take one controlled two-state contagion model on a graph, steered by a single broadcast scalar, and study six controllers on it: a fuzzy inference system, a tabular reinforcement learner, and four ways of combining them. The analysis is a stochastic drift argument on a Perron-weighted Lyapunov function that asks of each controller only a lower bound on its effort above an activation level, not a Lyapunov function of its own. The spectral radius of the interaction operator sets a critical effort, and a controller whose floor exceeds it keeps the population regulated. Each hybrid inherits a floor from the two it combines, which separates the four: safety blending and the hierarchical override keep a floor whatever the learner does, convex fusion and switching do not. Asynchronous updates follow from the same argument; delays and interruptions do not, and are left to simulation. Its application settings are readings of one model rather than independent validations. The trained learner cuts the fuzzy controller’s cost by 61%, yet eight tuned classical and model-based baselines all cost less than any of the six. The hybrids contain the learner’s failure outside its training range, but that failure is produced by the training protocol: a wider range of initial states removes it. A controller call costs the same up to agents, and three further models mark the scope: control is essential in a cascade, marginal under segregation, and counterproductive where it acts non-monotonically. - 6 December 2025
- Published by Springer Nature in Evolutionary Intelligence
- Vol. 19 (1) , 1
From agent-based models to Takagi–Sugeno linear differential equations (TS-LDEs): a fuzzy-logic bridge between discrete and continuous dynamics
- 6 December 2025
- Published by Springer Nature in Evolutionary Intelligence
- Vol. 19 (1) , 1
From agent-based models to Takagi–Sugeno linear differential equations (TS-LDEs): a fuzzy-logic bridge between discrete and continuous dynamics
- Open Access
- 18 September 2025
- Published by Academic Publications in International Journal of Applied Mathematics
- Vol. 38 (2s) , 433-445
ITO-ADAM OPTIMIZER FOR TRAINING LSTM NETWORKS: APPLICATION TO STOCK PRICE FORECASTING
This study introduces ItoAdam, an enhanced optimizer that incorporates Itô’s lemma and Brownian noise into Adam to improve convergence in complex, non-convex settings. By perturbing gradient updates with stochastic noise, ItoAdam enables better exploration of the loss surface and avoids poor local minima. We apply ItoAdam to train Long Short-Term Memory (LSTM) networks for stock price forecasting across 13 major companies sourced from Yahoo Finance. Experiments show that ItoAdam-LSTM consistently outperforms Adam-LSTM across RMSE, MAE, and R², with sensitivity analysis indicating that optimal performance occurs when noise standard deviation lies between 2.1 × 10⁻⁴ and 2.9 × 10⁻⁴. Overall, results demonstrate the effectiveness of combining Itô-driven stochastic optimization, evolutionary hyperparameter tuning, and recurrent architectures for reliable financial time series forecasting in noisy and nonstationary environments.
- 18 September 2025
- Published by Academic Publications in International Journal of Applied Mathematics
- Vol. 38 (2s) , 433-445
Open AccessITO-ADAM OPTIMIZER FOR TRAINING LSTM NETWORKS: APPLICATION TO STOCK PRICE FORECASTING
This study introduces ItoAdam, an enhanced optimizer that incorporates Itô’s lemma and Brownian noise into Adam to improve convergence in complex, non-convex settings. By perturbing gradient updates with stochastic noise, ItoAdam enables better exploration of the loss surface and avoids poor local minima. We apply ItoAdam to train Long Short-Term Memory (LSTM) networks for stock price forecasting across 13 major companies sourced from Yahoo Finance. Experiments show that ItoAdam-LSTM consistently outperforms Adam-LSTM across RMSE, MAE, and R², with sensitivity analysis indicating that optimal performance occurs when noise standard deviation lies between 2.1 × 10⁻⁴ and 2.9 × 10⁻⁴. Overall, results demonstrate the effectiveness of combining Itô-driven stochastic optimization, evolutionary hyperparameter tuning, and recurrent architectures for reliable financial time series forecasting in noisy and nonstationary environments.
- Open Access
Improved Quantum Particle Swarm Optimization of Optimal Diet for Diabetic Patients
The dietary recommendations for individuals with diabetes focus on maintaining a balanced nutritional intake to manage blood sugar levels. This study suggests a nutritional strategy to improve glycemic control based on an analysis of a dietary optimization problem. The goal is to minimize the overall glycemic loads (GLs) of specific foods. Two variations of the particle swarm optimization (PSO) method, as well as random quantum process optimization (GQPSO), are introduced. The findings demonstrate that the quantum and random methods are more effective than the traditional techniques in reducing the glycemic loads of diets and addressing nutritional deficiencies while also aligning nutrient intake with the recommended levels. The resolution of this diet optimization model, executed multiple times with adjustments to the parameters of both methods, enables dynamic exploration and provides a wide range of diverse and effective food choices.
Open AccessImproved Quantum Particle Swarm Optimization of Optimal Diet for Diabetic Patients
The dietary recommendations for individuals with diabetes focus on maintaining a balanced nutritional intake to manage blood sugar levels. This study suggests a nutritional strategy to improve glycemic control based on an analysis of a dietary optimization problem. The goal is to minimize the overall glycemic loads (GLs) of specific foods. Two variations of the particle swarm optimization (PSO) method, as well as random quantum process optimization (GQPSO), are introduced. The findings demonstrate that the quantum and random methods are more effective than the traditional techniques in reducing the glycemic loads of diets and addressing nutritional deficiencies while also aligning nutrient intake with the recommended levels. The resolution of this diet optimization model, executed multiple times with adjustments to the parameters of both methods, enables dynamic exploration and provides a wide range of diverse and effective food choices.
- Open Access
OPT-FRAC-CHN: Optimal Fractional Continuous Hopfield Network
The continuous Hopfield network (CHN) is a common recurrent neural network. The CHN tool can be used to solve a number of ranking and optimization problems, where the equilibrium states of the ordinary differential equation (ODE) related to the CHN give the solution to any given problem. Because of the non-local characteristic of the “infinite memory” effect, fractional-order (FO) systems have been proved to describe more accurately the behavior of real dynamical systems, compared to the model’s ODE. In this paper, a fractional-order variant of a Hopfield neural network is introduced to solve a Quadratic Knap Sac Problem (QKSP), namely the fractional CHN (FRAC-CHN). Firstly, the system is integrated with the quadratic method for fractional-order equations whose trajectories have shown erratic paths and jumps to other basin attractions. To avoid these drawbacks, a new algorithm for obtaining an equilibrium point for a CHN is introduced in this paper, namely the optimal fractional CHN (OPT-FRAC-CHN). This is a variable time-step method that converges to a good local minima in just a few iterations. Compared with the non-variable time-stepping CHN method, the optimal time-stepping CHN method (OPT-CHN) and the FRAC-CHN method, the OPT-FRAC-CHN method, produce the best local minima for random CHN instances and for the optimal feeding problem.
Open AccessOPT-FRAC-CHN: Optimal Fractional Continuous Hopfield Network
The continuous Hopfield network (CHN) is a common recurrent neural network. The CHN tool can be used to solve a number of ranking and optimization problems, where the equilibrium states of the ordinary differential equation (ODE) related to the CHN give the solution to any given problem. Because of the non-local characteristic of the “infinite memory” effect, fractional-order (FO) systems have been proved to describe more accurately the behavior of real dynamical systems, compared to the model’s ODE. In this paper, a fractional-order variant of a Hopfield neural network is introduced to solve a Quadratic Knap Sac Problem (QKSP), namely the fractional CHN (FRAC-CHN). Firstly, the system is integrated with the quadratic method for fractional-order equations whose trajectories have shown erratic paths and jumps to other basin attractions. To avoid these drawbacks, a new algorithm for obtaining an equilibrium point for a CHN is introduced in this paper, namely the optimal fractional CHN (OPT-FRAC-CHN). This is a variable time-step method that converges to a good local minima in just a few iterations. Compared with the non-variable time-stepping CHN method, the optimal time-stepping CHN method (OPT-CHN) and the FRAC-CHN method, the OPT-FRAC-CHN method, produce the best local minima for random CHN instances and for the optimal feeding problem.