Search Results (114)

As a distributed approach to Artificial Intelligence (AI) model construction over wireless networks, federated learning (FL) based on multi-device collaborative training can protect data privacy, as well as increase the computing load of local model updates. In contrast, split learning (SL) with proper model splitting can adapt to the computation and transmission capabilities among devices. In this paper, while taking advantage of FL and SL, we concentrate on a semi-decentralized hybrid federated split learning (SD-HFSL) framework, in which we surpass the limitations of a single central server and allow the shared split models to be aggregated among multiple edge servers. To verify the importance of latency optimization for training efficiency, we analyze the convergence performance of SD-HFSL while jointly considering the limited computation and communication resources. Then, aiming at maximizing the long-term training efficiency, we propose an online optimization problem that includes local model splitting and device association. Considering that the training latency is unknown to the system a priori, a context-aware online training algorithm with sublinear regret is proposed based on the framework of contextual multi-armed bandit (CMAB), where the edge servers can observe the context information of device sites for latency estimation, followed by the iterative optimization based on the evaluated information in different contexts. Experiments on several neural network models show that the proposed algorithm reduces training latency and improves test accuracy compared with the selected benchmarks. Full article

To address the challenges of combinatorial explosion and expensive evaluations in truck–drone (truck–UAV) collaborative delivery under complex geographical constraints, this paper proposes a Surrogate-assisted Rezone-Enhanced Multi-objective Adaptive Evolutionary Algorithm (SRE-MAEA). As a knowledge-driven decomposition-based surrogate-assisted framework, the proposed algorithm aims to synergistically optimize a four-dimensional conflicting objective space consisting of economic cost, social satisfaction, environmental emissions, and battery resilience. To overcome the curse of dimensionality in high-dimensional and strongly constrained environments, SRE-MAEA constructs an adaptive Rezone Search architecture. By dynamically deconstructing the decision space, it transforms global search pressure into refined knowledge mining within high-potential local regions. The core mechanism incorporates an intelligent sampling strategy based on the Multi-Armed Bandit (MAB). By utilizing real-time evolutionary feedback to dynamically prioritize the Pareto contribution of each rezone, the MAB achieves pruning-level scheduling of expensive evaluation resources. Simulation results on 15 benchmark instances with clustered, random, and mixed spatial distributions demonstrate that SRE-MAEA exhibits superior convergence boundaries and distribution uniformity in terms of IGD and HV metrics, significantly outperforming state-of-the-art regression-based strategies. Furthermore, computational efficiency analysis confirms that by precisely identifying invalid search paths via the MAB mechanism, SRE-MAEA maintains a high-precision Pareto front while reducing the average CPU time by approximately 35.2–48.5%. This effectively resolves the computational bottleneck caused by complex battery resilience integral models. This research provides an efficient algorithmic paradigm for resilient logistics scheduling in extreme environments and holds significant academic value and engineering application prospects. Full article

In edge-intelligent systems, efficient resource management and task scheduling are critical but challenging due to the dynamic and heterogeneous nature of edge nodes (e.g., IoT devices, drones). We model this dynamic resource allocation challenge as an online sleeping Restless Multi-Armed Bandits (RMAB) problem, where each edge node (arm) operates as a Markov decision process. Unlike prior RMAB frameworks assuming perpetual availability, our setting captures the stochastic availability of edge nodes across rounds. The system controller (learner) is unaware of the transition functions, reward distributions, and node availability a priori. The goal is to maximize expected cumulative rewards through adaptive node selection. To explore this target problem, we first derive an asymptotically optimal sleeping-index policy (SIP) as the oracle based on the fluid process transformation. Then we propose OSILA (Online Sleeping Index-aware Learning Algorithm), featuring a Minimum Exploration Guarantee (MEG) mechanism for efficient exploration. This is coupled with a modified Linear Programming-based exploitation mechanism to construct an online sleeping index, effectively handling dynamic node availability. To the best of our knowledge, this work is the first to provide the theoretical analysis (which achieves $\tilde{\mathcal{O}}\left(K{T}^{2/3}\sqrt{logT}\right)$ regret where K is the number of arms and T is the time horizon) to the online sleeping RMAB problem. Empirical results validate both theoretical guarantees and practical effectiveness in dynamic edge computing environments. Full article

While many multi-armed bandit algorithms assume that rewards for all arms are constant across rounds, this assumption does not hold in many real-world scenarios. This paper considers the setting of recovering bandits, where the reward depends on the number of rounds elapsed since the last time an arm was pulled. We propose a new reinforcement learning (RL) algorithm tailored to this setting, named the State-Separated SARSA (SS-SARSA) algorithm, which treats the elapsed rounds as states. The SS-SARSA algorithm achieves efficient learning by reducing the number of state combinations required for Q-learning/SARSA, which often suffers from combinatorial explosion for large-scale RL problems. Additionally, it makes minimal assumptions about the reward structure and has lower computational complexity. Furthermore, we prove asymptotic convergence to an optimal policy under mild assumptions. Simulation studies demonstrate the superior performance of our algorithm across various settings. Full article

Very High Frequency (VHF) radio communication systems face significant challenges in modern electromagnetic environments, including spectrum congestion, dynamic interference, and varying channel conditions. Existing adaptive approaches rely on static rule-based switching or single-cycle optimization, which cannot accumulate operational experience across decision cycles. This paper proposes a digital twin-enabled online learning framework (DT-MAB) for adaptive waveform selection in tactical VHF communication. The framework employs a contextual multi-armed bandit algorithm (Lin-UCB) that continuously learns the mapping from channel conditions to optimal configurations, with the digital twin serving as a virtual exploration sandbox that screens candidate configurations before physical deployment—preventing link disruptions during exploratory actions. An expanded configuration space of 63 candidates (7 waveforms × 3 MAC protocols × 3 power levels) is constructed, and a hierarchical performance evaluation model combining voice quality, bit error rate, communication delay, and transmission range is developed using the Analytic Hierarchy Process (AHP) as the reward function for online learning. Experimental results across 10 random seeds demonstrate that DT-MAB achieves the lowest mean cumulative regret, reducing regret by 29% relative to MAB without a digital twin and by 16.5% relative to PSO-based optimization on average. Ablation experiments confirm that removing virtual exploration increases performance drop events by 49% (from 250 ± 79 to 373 ± 6), demonstrating that the digital twin is a functionally indispensable component of the online learning architecture. Full article

In this paper, a new hybrid prediction method is proposed for estimating remaining useful life, emissions, and performance parameters using experimental data obtained from a micro-turbojet engine. Experiments were conducted under various rotational speed conditions, yielding a total of 342 measurement points. Turbine speed, exhaust gas temperature, fuel flow rate, and thrust were considered as input variables in the study. Thermal efficiency, total power, CO₂, and NO₂ were considered as output variables. The experimental findings showed that thermal efficiency varied between 0.49% and 7.1%, total power between 0.266 and 13.94 kW, and CO₂ emissions by volume between 0.317% and 2.183%. The proposed RL-MH-LR-CBR approach combines the advantages of multiple methods. In this method, the interpretable formulation of linear regression serves as the foundation. Additionally, in the adaptive meta-heuristic optimization process, a hyper-heuristic selection mechanism based on the UCB1-based multi-arm bandit approach is used to select the optimal algorithm from among the meta-heuristic methods. Finally, the CatBoost-based residual error learning component aims to capture non-linear patterns that cannot be explained by the linear model. The method was compared with 14 different methods on both the NASA C-MAPSS FD001 dataset and real engine data. The results demonstrate that the proposed framework exhibits more balanced, stable, and higher generalization capabilities compared to classical regression models and powerful AI methods, particularly in non-linear, noisy, and heterogeneous outputs. In the real engine dataset, the proposed method produced R² values of 0.968 for CO₂ and 0.936 for NO₂, while the predictive performance was even stronger for thermal efficiency and total power, with corresponding R² values of 0.998 and 0.995, respectively. Additionally, the method demonstrated a clear advantage in hard-to-model outputs by reducing the error level to 0.061 in NO₂ predictions. These findings demonstrate that the proposed approach is not limited to micro-turbojet-engines. The developed method provides a robust decision support framework that is applicable, scalable, and generalizable to predictive maintenance, emissions monitoring, energy systems, aviation analytics, and other highly dynamic engineering problems. Full article

Fully decoupled radio access networks (FD-RANs) achieve spectral efficiency and coverage flexibility for 6G via independent uplink (UL) and downlink (DL) base station operation, yet dynamic user mobility brings critical challenges to joint user association and resource allocation. Asymmetric interference and heterogeneous base station capacities cause persistent network unfairness, while uncoordinated mobility management triggers ping-pong handovers and heavy handover overheads. To resolve these intertwined problems, we propose a fully decoupled, mobility-resilient and fairness-guaranteed framework, which integrates short-term congestion pricing with the long-term Jain fairness index for equitable resource distribution and introduces a composite handover penalty with a strict physical hysteresis margin to block invalid handovers. We formulate the optimization problem as a novel Sliding-Window Hysteresis-Integrated Fairness Two-Layer Multi-Armed Bandit (SHIFT-MAB) model, embedding an exponentially weighted moving average (EWMA) sliding-window mechanism to track real-time channel fluctuations efficiently. Theoretical analysis confirms the model’s decoupling optimality, sublinear regret bound and fairness convergence. Extensive simulations show that SHIFT-MAB effectively suppresses invalid handovers, ensures high network fairness, optimizes system utility and achieves a superior handover–throughput trade-off. Full article

Quantum computing offers potential computational advantages, yet its integration into autonomous decision-making systems remains largely unexplored. This paper addresses the need for a unified framework that systematically combines quantum computation with agent-based artificial intelligence. We examine how quantum technologies can enhance the capabilities of autonomous agents and, conversely, how agentic AI can support the advancement of quantum systems. We analyze both directions of this synergy and present conceptual and technical foundations for future quantum–agentic platforms. Our work introduces a formal definition of quantum agents and outlines architectures that integrate quantum computing with agent-based systems. As concrete proof-of-concept implementations, we develop and evaluate three quantum agent prototypes: (i) a Grover-based decision agent for quantum search-driven action selection, (ii) a variational quantum reinforcement learning agent for adaptive policy learning in a multi-armed bandit setting, and (iii) an adaptive quantum image encryption agent that autonomously selects encryption strategies based on entropy-driven feedback. These prototypes demonstrate practical realizations of quantum agency in decision-making, learning, and security contexts under NISQ-era constraints. Furthermore, we discuss application domains including quantum-enhanced optimization, hybrid quantum–classical orchestration, autonomous quantum workflow management, and secure quantum information processing. By bridging these fields, we introduce a structured theoretical and architectural framework for quantum–agentic systems, providing formal definitions, system models, and early operational prototypes that illustrate the feasibility of quantum-enhanced agency under NISQ constraints. Full article

Hybrid Split Federated Learning (HSFL for short) in emerging 6G-enabled UAV networks faces persistent challenges in data protection, device trust management, and long-term participation incentives. To address these issues, this study introduces S-HSFL, a security-enhanced framework that embeds verifiable federated learning mechanisms into HSFL and incorporates digital-signature-based authentication throughout the device selection process. This design effectively prevents model tampering and forgery attacks, achieving a defense success rate above 99%. To further strengthen collaborative training, we develop a MAB-GT device selection strategy that integrates multi-armed bandit exploration with multi-stage game-theoretic decision models, spanning non-cooperative, coalition, and repeated games, to encourage high-quality UAV nodes to provide reliable data and sustained computation. Experiments on the Modified National Institute of Standards and Technology (MNIST) dataset under both Independent and Identically Distributed (IID) and non-IID conditions demonstrate that S-HSFL maintains approximately 97% accuracy even in the presence of 30% adversarial UAVs. The MAB-GT strategy significantly improves convergence behavior and final model performance, while incurring only a 10–30% increase in communication overhead. The proposed S-HSFL framework establishes a secure, trustworthy, and efficient foundation for distributed intelligence in next-generation 6G UAV networks. Full article

For XL-MIMO multi-user frequency division duplex systems, this paper proposes a near-field beam training scheme using a two-phase combinatorial multi-armed bandit (MAB) framework. This scheme leverages the MAB framework, integrating energy-aware user scheduling and hierarchical beam training to balance communication quality and device battery level, thereby effectively enhancing system energy efficiency and extending the device’s lifespan. Specifically, in the first phase, we account for user battery levels by designing an energy-aware upper confidence bound (UCB) algorithm for user scheduling. This algorithm effectively balances exploration and exploitation, prioritizing users with higher achievable rates and sufficient battery level. In the second phase, based on the scheduled users, two UCB algorithms are employed for beam training. In the first layer, discrete Fourier transform codebook-based beam scanning is utilized, and a UCB algorithm is applied to initially acquire angle information for scheduled users. In the second layer, based on the obtained angle information, a candidate set of polar-domain codewords is constructed. Another UCB algorithm is then employed to select the optimal polar-domain codewords. The effectiveness of our scheme is confirmed by simulations, demonstrating notable achievable rate gains for multi-user communications. Full article

Unmanned aerial vehicles (UAVs) equipped with antenna arrays can deliver high-capacity, high-throughput, and low-latency communication services. Considering a UAV-assisted mmWave multi-input and multi-output (MIMO) system, a two-stage beamforming scheme based on a budgeted combinatorial multi-armed bandit (BC-MAB) is proposed to improve the system’s spectral efficiency (SE). The pre-beamformer design problem is initially formulated as a BC-MAB problem. In this framework, the reward is the received energy, while the cost corresponds to the energy consumed by each RF chain and the budget is represented by the residual energy of the UAV. To achieve a favorable trade-off between the number of communication slots and the energy acquired per slot, a pre-beamforming scheme based on the bang-per-buck ratio is introduced to optimize the number of activated RF chains, therefore maximizing the cumulative reward. The second stage utilizes the reduced-dimensional instantaneous channel state information to design and optimize the beamformer to achieve maximum system SE. The proposed scheme achieves more than 7.1% improvement in SE compared to the benchmark schemes. Simulations validate the superiority of the proposed scheme. Full article

The rising demand for long-range, low-power wireless communication in applications such as monitoring, smart metering, and wide-area sensor networks has emphasized the critical need for efficient spectrum utilization in LoRaWAN (Long Range Wide Area Network). In response to this challenge, this paper proposes a novel channel selection framework based on Hierarchical Discrete Pursuit Learning Automata (HDPA), aimed at enhancing the adaptability and reliability of LoRaWAN operations in dynamic and interference-prone environments. HDPA leverages a tree-structure reinforcement learning model to monitor and respond to transmission success in real-time, dynamically updating channel probabilities based on environmental feedback. Simulation results conducted in MATLAB R2023b demonstrate that HDPA significantly outperforms conventional algorithms such as Hierarchical Continuous Pursuit Automata (HCPA) in terms of convergence speed, selection accuracy, and throughput performance. Specifically, HDPA achieved 98.78% accuracy with a mean convergence of 6279 iterations, compared to HCPA’s 93.89% accuracy and 6778 iterations in an eight-channel setup. Unlike the Tug-of-War-based Multi-Armed Bandit strategy, which emphasizes fairness in real-world heterogeneous networks, HDPA offers a computationally lightweight and highly adaptive solution tailored to LoRaWAN’s stochastic channel dynamics. These results position HDPA as a promising framework for improving reliability and spectrum utilization in future IoT deployments. Full article

In recent years, machine learning techniques such as convolutional neural networks have been used for mineral prospectivity mapping. Since a diverse range of geoscientific data is often available for training, it is computationally challenging to select a subset of features that optimizes model performance. Our study aims to demonstrate the effect of optimal input feature selection on convolutional neural network model performance in mineral prospectivity mapping applications. We demonstrate results from both exhaustive and algorithmic feature selection methods in the context of copper porphyry prospectivity modeling and analyze the performance and stability of optimally trained models. Using the QUEST dataset from central interior British Columbia, such a feature selection technique improves model performance by 6.8% over models that use all available features, yet consumes around 2.2% of the computational resources needed to exhaustively search for the optimal feature subset. Full article

This paper introduces an innovative methodology for optimizing recommendation strategies across different populations within the food industry. While previous approaches to recommending courses have overlooked cultural and age-based preferences, our work demonstrates how understanding these differences can significantly enhance the attractiveness for consumers and create new opportunities for marketing. By simulating diverse populations using a fuzzy logic approach, based on individual characteristics such as age, gender, geographical area, and city size, the study evaluates how recommendation algorithms perform within a generated menu database. Results show that algorithms like State–Action–Reward–State–Action (SARSA), multi-armed bandit (MAB), and Deep-Q Network (DQN) exhibit varying levels of efficiency depending on the population. Notably, the DQN improves accumulated reward over a random recommender by 71.60% for “Foodies”, 65.02% for “Veggies”, 63.46% for “Spanish”, and 8.89% for “Seniors”, while MAB achieves similar performance with fewer resources. Statistically significant differences (p < 0.005) are found in the performance of the DQN between populations, with large effect sizes according to Cliff’s delta. These findings highlight recommender systems as an opportunity to navigate market demand, optimize supply chains, and reduce food waste. A better understanding of public preferences enables more effective alignment of supply and demand across the entire food supply chain. As a conclusion, while the DQN effectively captures target group preferences, the optimum recommendation strategy should be chosen by balancing algorithmic performance, computational efficiency, and the specific requirements of the food sector. Full article

Chronic kidney disease (CKD) impacts over 850 million people globally, representing a critical public health issue, yet existing risk assessment methodologies inadequately address the complexity of disease progression trajectories. Traditional machine learning approaches encounter critical limitations including inefficient hyperparameter selection and lack of clinical transparency, hindering their deployment in healthcare settings. This study introduces an innovative computational framework that integrates adaptive Multi-Armed Bandit (MAB) strategies with BorderlineSMOTE sampling techniques to improve CKD risk assessment. The proposed methodology leverages XGBoost within an ensemble learning paradigm enhanced by Upper Confidence Bound exploration strategy, coupled with a comprehensive interpretability system incorporating SHAP and LIME analytical tools to ensure model transparency. To address the challenge of algorithmic interpretability while maintaining clinical utility, a four-level risk categorization framework was developed, employing cross-validated stratification methods and balanced performance evaluation metrics, thereby ensuring fair predictive accuracy across diverse patient populations and minimizing bias toward dominant risk categories. Through rigorous empirical evaluation on clinical datasets, we performed extensive comparative analysis against sixteen established algorithms using paired statistical testing with Bonferroni correction. The MAB-optimized framework achieved superior predictive performance with accuracy of 91.8%, F1-score of 91.0%, and ROC-AUC of 97.8%, demonstrating superior performance within the evaluated cohort of reference algorithms (p-value < 0.001). Remarkably, our optimized framework delivered nearly ten-fold computational efficiency gains relative to conventional grid search methods while preserving robust classification performance. Feature importance analysis identified albumin-to-creatinine ratio, eGFR measurements, and CKD staging as dominant prognostic factors, demonstrating concordance with established clinical nephrology practice. This research addresses three core limitations in healthcare artificial intelligence: optimization computational cost, model interpretability, and consistent performance across heterogeneous clinical populations, offering a practical solution for improved CKD risk stratification in clinical practice. Full article