-
2026, Maha Elarbi, Slim Bechikh
A decuple crossover scheme in genetic algorithms: a step toward deep evolution
Evolutionary Intelligence 19 (1), 9, 2026
Abstract
Genetic Algorithms (GAs) are widely used for solving complex optimization problems thanks to their ability to explore vast solution spaces and adapt to diverse constraints. Among the key components of GAs, the crossover operator critically influences the balance between exploration and exploitation, by combining promising genetic material and exploring new regions of the solution space. However, traditional crossover operators typically apply a single recombination per parent pair, which limits their ability to deeply exploit high-quality gene patterns and often leads to premature convergence. To address this limitation, we propose the Decuple Crossover Scheme (DCS), a novel hierarchical crossover scheme that intensifies intra-generational recombination. In DCS, a pair of parents initially produce two offspring, which then undergo multiple recombinations with the original parents, resulting in promising candidate offspring. From this pool, the two best individuals are selected for the next generation, enabling deeper exploitation of genetic material and improved population diversity. The effectiveness of DCS is demonstrated through a proof-of-concept application on the Traveling Salesman Problem (TSP) and the Vehicle Routing Problem (VRP), showcasing its potential for enhancing solution quality and convergence speed. These results highlight the broader applicability of DCS to diverse optimization challenges, making it a promising tool for advancing the field of evolutionary computation.
Zakia Zouaghia, Zahra Kodia, Lamjed Ben SaidTunPredML: A Machine Learning-Based Financial Decision Support System for Crisis-Aware Stock Market Forecasting and Risk Mitigation: Empirical Insights from the Tunisian Stock Market
Computational Economics, 1-62., 2026
Abstract
This paper introduces TunPredML, an intelligent financial decision support system designed to predict stock market prices under volatile and uncertain conditions. The system integrates machine learning models, advanced data analytics, and visualization techniques to enhance financial forecasting and decision-making for investors. First, we analyze the Tunisian stock market’s reaction to recent crises, including financial, political, and health disruptions, to assess their impact on market volatility and losses. Next, we conduct an initial experiment using eight machine learning algorithms: Linear Regression (LR), Support Vector Regression (SVR), eXtreme Gradient Boosting (XGBoost), Simple Recurrent Neural Network (SRNN), Gated Recurrent Unit (GRU), Long Short-Term Memory (LSTM), Artificial Neural Network (ANN), and Random Forest (RF). These models are evaluated on the Tunindex, incorporating event-related data, and assessed using four regression metrics in addition to execution time to ensure both predictive accuracy and computational efficiency. Based on the evaluation results, the most accurate models are selected for a second experiment, where they are combined into an ensemble stacked model to improve predictive performance. To enhance accessibility and usability, TunPredML is deployed as a web-based financial decision support system, offering interactive data visualization and real-time analytics. The platform provides investors and traders with key insights, including model performance metrics, graphical comparisons of predicted versus actual stock prices, error distributions, and 10-day future price forecasts. By leveraging cutting-edge machine learning techniques and a user-friendly digital platform, the proposed system empowers investors to mitigate risks, navigate market uncertainties, and make well-informed investment decisions. The effectiveness of TunPredML is validated using real-world financial data, demonstrating its potential as a robust, data-driven forecasting tool for financial markets, particularly during periods of economic instability.
Zakia Zouaghia, Zahra Kodia, Lamjed Ben SaidSimulated quantum feature maps for interpretable credit risk prediction: a comparative benchmark study
Int J Data Sci Anal 22, 111 (2026), 2026
Abstract
Credit risk prediction presents significant challenges due to data imbalance, complex nonlinear relationships, and stringent regulatory requirements for model interpretability. This research introduces a novel interpretable framework that integrates quantum-inspired feature engineering with classical machine learning to enhance default prediction accuracy while maintaining transparency. By encoding classical financial features into quantum state representations via a ZZFeatureMap circuit and extracting principal components, we create enhanced feature spaces that capture complex interactions beyond conventional methods. We conduct comprehensive benchmarking of eight classifiers (HistGradientBoosting, XGBoost, LightGBM, CatBoost, Random Forest, SVM, MLP, and Logistic Regression) on a substantial dataset of 32,581 credit observations. Our quantum-enhanced models demonstrate significant performance improvements, with HistGradientBoosting achieving the highest performance (ROC AUC: 0.942, specificity: 0.993, precision: 0.968) and LightGBM offering optimal efficiency-accuracy trade-offs (ROC AUC: 0.934 with only 1.1s training time). Gradient boosting models consistently outperformed other approaches, with all quantum-enhanced variants exceeding ROC AUC scores of 0.930 compared to less than 0.900 for non-tree-based models. A key innovation is our reverse interpretation analysis, which maps quantum features back to interpretable classical risk dimensions, addressing a critical gap in quantum-enhanced model explainability for regulatory compliance. Statistical validation through ANOVA and Friedman tests confirms the significance of performance differences between model architectures, with tree-based models showing particular synergy with quantum-augmented feature spaces. This work establishes quantum-inspired feature engineering as a practical enhancement for credit risk assessment, providing financial institutions with immediately applicable methods to improve predictive accuracy while meeting transparency requirements. By demonstrating measurable performance gains without sacrificing interpretability, our framework bridges the gap between advanced machine learning techniques and the practical constraints of regulated financial environments, paving the way for responsible adoption of quantum-enhanced analytics in the financial sector.
-
2025Hamdi Ouechtati, Nadia Ben Azzouna
Multi-objective clustering and dynamic multi-hop routing in an IoT network based on Pareto optimality
Papier conf, 2025
Abstract
Routing is essential in computer networks as it
directly impacts performance metrics such as throughput and
transmission delay. Particularly in an Internet of Things (IoT)
network where the nodes are limited in energy (battery power)
and the radio component is high energy-intensive. We are always
looking to optimise this procedure in order to increase the network
lifetime. In this work, we present a multi-objective, multihop
routing solution that extends network lifetime while balancing
multiple objectives, such as energy consumption, delay, and
reliability. Our solution was compared with other approaches,
such as Energy Optimization Routing (EOR) and Multi-Objective
Optimization Routing (MOWR) based on the Weighted Sum
technique, demonstrating significant improvements.Haithem Mezni, , ,CrossRecSmart: A Cross-Network Anchor-Based Representation Learning for the Recommendation of Smart Services.
Journal of Supercomputing, 2025
Abstract
In modern smart cities, user request handling has evolved beyond conventional software solutions and electronic services. Companies now leverage a diverse range of cutting-edge technologies, such as Artificial Intelligence, the Internet of Things (IoT), Edge/Fog computing, and Cloud computing, to deliver various smart services. These services cover domains such as smart healthcare, smart buildings, smart transportation, smart living, and smart administration. However, a significant challenge hindering the widespread adoption and effective deployment of these services is the limited awareness among citizens of their availability and features, including aspects like pricing models, security policies, and service-level agreements. This issue largely stems from the lack of centralized public repositories where companies can showcase their smart offerings. Consequently, citizens often rely on traditional Web search tools (e.g., search engines, social networks), which limits their ability to fully benefit from the advantages of smart services. In addition, users are often connected to multiple service providers, meaning that their related knowledge (e.g., profiles, service usage, ratings) is distributed across multiple information sources.
To bridge the gap between smart service providers and citizens, and to effectively utilize user and service information across multiple networks, we propose CrossRecSmart, a cross-network recommender system built upon a multiplex network of smart services. This system can be conceptualized as a large-scale, distributed, domain-specific marketplace for available smart services. Our approach integrates Graph Neural Networks (GNNs) with cross-network representation learning to construct this multiplex network. The complex and distributed nature of this task is addressed through a cross-network learning model that facilitates collaboration among multiple smart service providers and enables the aggregation of their knowledge. This is achieved by interconnecting multiple networks through bridge nodes, also referred to as anchor entities. Furthermore, we introduce an algorithm for the cross-network recommendation of top-rated smart services. Comparative analyses with existing recommender systems designed for smart cities demonstrate the superiority of our proposed approach, owing to the concept of anchor links., Haithem Mezni, ,Drone-as-a-Service: proximity-aware composition of UAV-based delivery services
Cluster Computing, 2025
Abstract
Recently, drones have emerged as an effective and rapid mean to deliver various packages as services. Exhibiting the same behavior and principles of the service paradigm, drones’ delivery tasks can be abstracted as services, also called DaaS (Drone-as-a-Service). However, drones operate in a dynamic and uncertain environment (flight regulations, weather conditions, charging resources). In addition, the drones’ limited capacity (e.g., flying range, battery capacity, payload) and the delivery constraints (e.g., cost, delivery time) make the delivery missions beyond one drone’s capacity. To cope with the above challenges, and to meet the customers’ and providers’ delivery constraints, composing drone services is a natural solution. We propose a DaaS composition approach that takes advantage of a recent and powerful technology, called knowledge graph. First, we model the drones’ environment (charging stations, skyway segments, drone services) as a heterogeneous information network. Then, we combine knowledge graph embedding with subgraph-aware proximity measure, to arrange drones and charging stations in a low-dimentional vector space. This pre-processing step helped select high-flight capacity drone services, and generate low-congestion delivery paths. Experimental results have proven the approach’s performance and the quality of DaaS compositions, compared to recent state-of-the-art approaches.
Haithem Mezni, , ,Personalized service recommendation in smart mobility networks
Cluster Computing, 2025
Abstract
Vehicle-as-a-Service (VaaS) refers to on-demand rides and the sharing/offering of various kinds of transportation facilities (e.g., smart buses, electric vehicles, business jets, autonomous cars), to move from a source to a destination across one or several regions. Coupled with smart transportation services, which are critical for addressing road network issues (e.g., traffic congestion, parking, safety), VaaS is increasingly adopted in smart cities. For example, a user may express his needs in terms of source/destination regions, time and cost constraints, in addition to preferred transportation modes and services (e.g., only connected buses and electric cars). This user profile is evaluated against each available VaaS, as well as the smart urban network (SUN) conditions. However, current solutions do not consider the customization of VaaS combinations and treat user requests as a traditional vehicle routing problem; while in a SUN context, processing VaaS requests not only consists of finding the optimal transportation path that meets user constraints (e.g., time, cost), but also selecting the top-rated combination of available VaaSs (e.g., sequence of smart buses) that meet the user profile (e.g., connectivity, specific facilities, transit restrictions) and trip constraints. To cope with these challenges, the goal of this paper is to develop an orchestration engine that allows the personalized selection and composition of VaaS services. We applied Fuzzy Relational Concept Analysis as an effective data analysis and clustering technique to solve the following issues: (i) representing VaaS-related knowledge and excluding low-quality VaaSs, (ii) clustering of VaaS services based on their common features and covered regions, (iii) clustering of smart urban regions based on their neighborhood and their frontier stations. At a second stage, a search method based on A* algorithm is proposed to find the optimal local paths in each traversed region of the smart urban network. Finally, a bottom-up lattice parsing method is defined to determine the VaaSs with high quality and high coverage capacity. Comparative experiments with state-of-the-art solutions proved the efficiency of our approach.
, Haithem Mezni, ,Multi-modal VaaS Selection in Smart Mobility Networks via Spectral Hyper-graph Clustering and Quantum-driven Optimization.
Concurrency and Computation: Practice and Experience, 2025
Abstract
In recent years, smart mobility networks have experienced significant growth due to the integration of key technologies such as cloud computing, edge intelligence, and the Internet of Things (IoT) into transportation infrastructure. When combined with the principles of service-oriented computing (SOC), various transportation modes now feature intelligent capabilities, including eco-driving assistance, emergency service integration, V2X communication, environmental sensors, in-vehicle infotainment, Over-the-Air (OTA) updates, driver behavior monitoring, and AI-powered assistance. This has led to the emergence of Connected Vehicle as a Service (CVaaS) as a new paradigm for smart vehicles and transportation services.
However, with the increasing complexity of AI-driven features and integration with smart city infrastructure, traditional recommender systems can no longer meet user requirements such as personalized connectivity preferences and eco-friendly route optimization. CVaaS recommendations also inherit challenges from traditional transportation systems, including multi-modal integration (e.g., coordinating smart buses and autonomous vehicles), environmental considerations (e.g., smart parking and dedicated lanes for autonomous cars), uncertain demand, user trust, regulatory compliance, and data privacy concerns.
In this paper, we address the challenges of multi-modal transportation and environmental uncertainty, such as traffic congestion and VaaS demand fluctuations. By modeling Smart Urban Network (SUN) traffic and VaaS demand, we predict congestion patterns and VaaS availability using a Long Short-Term Memory (LSTM) model. Additionally, we apply Spectral hyper-graph Theory to cluster the SUN into closely connected regions, identifying traversed areas for trip requests. These preprocessing steps help eliminate high-congestion zones and low-demand VaaS services, improving trip efficiency.
Finally, inspired by the combinatorial nature of VaaS selection, we propose a Quantum-Inspired variant of the Gravitational Search Algorithm (Q-GSA) to explore and evaluate possible VaaS combinations, ultimately selecting an optimal set of smart transportation services. Experimental comparisons with four benchmark methods confirm the superiority of our approach in terms of efficiency and solution quality.Mokhtar LAABIDI, Lilia Rejeb, Lamjed Ben SaidEcological Multimodal Freight Transport Optimization
Selecting the most reliable stochastic routes requires the development of flexible, real-time, single-objective and multi-objective approaches based on technology and data analysis. In the, 2025
Abstract
Abstract—The increasing complexity of global supply chains,
combined with the need for fast, cost-effective, and environmentally
friendly deliveries, has reinforced the importance of
multimodal freight transportation(MFT) as a key solution to
meet modern demands. One of the main challenges in MFT
is to develop an innovative optimization model to plan and
manage the supply chain. In this work, we consider four
modes of transportation (air, road, rail, and sea) and propose
an innovative multi-objective optimization model, designed to
simultaneously minimize transportation costs, transit times,
and CO2 emissions, while integrating the complex operational
constraints inherent in current logistic systems. To address
this problem, we adopt two well-known algorithms : Non-
Dominated Sorting Genetic Algorithm III (NSGA-III) and
Teaching-Learning Optimization (TLBO), through an experimental
study demonstrating the effectiveness of these evolutionary
solution methods in solving these complex optimization
problem.
The results show that TLBO optimization effectively reduces
costs and environmental impact, while the NSGAIII algorithm
improves delivery times.Haithem Mezni, , ,Federated resource prediction in UAV networks for efficient composition of drone delivery services
Computer Networks, 2025
Abstract
As drones continue to see widespread adoption across commercial, private, healthcare, and education sectors, their commercial use is experiencing rapid growth. To enhance drone-based package delivery efficiency and improve customer experience, the vast amount of flight and recharging data collected from drones and stations offers valuable opportunities for predicting both resource availability within the sky network and drones’ capacity to complete delivery missions. However, the variations in regional regulations and privacy restrictions enforced by drone service providers lead to data heterogeneity, making centralized processing of flight and charging history impractical. Running machine learning models locally at the service provider level (drones and stations) addresses privacy concerns, yet processing the large volume and diversity of raw data remains a significant challenge. To deal with these issues, a collaborative learning approach based on historical delivery data presents an elegant solution. Aiming to offer predictive scheduling of drone delivery missions, while taking into consideration the complexity, heterogeneity, and dynamic nature of their flight environment, we propose a predictive and federated approach for the resilient selection and composition of drone delivery services, leveraging the strengths of federated learning (FL) to handle data privacy and heterogeneity. Our method utilizes a federated Recurrent Neural Network (FL-RNN) model that combines predictive capabilities with federated behavior, enabling collaborative forecasting and efficient mission scheduling in low-congestion regions based on the most reliable drone services. Additionally, an enhanced A* search algorithm is defined to identify the optimal delivery path by factoring in station overload probabilities. Besides computational efficiency, experimental results demonstrate the effectiveness of our approach, achieving a 16.66% improvement in prediction accuracy and an 8.89% reduction in delivery costs compared to non-federated and non-predictive solutions.
