جامعة المعرفة
المصدر المعتمد للمعلومات البحثية والمخرجات هو قاعدة بيانات سكوبس (Elsevier Scopus) مع تدقيق بيانات الباحثين من عمادة البحث العلمي.

Research outputs

المخرجات البحثية

مقالات ومراجعات وأوراق مؤتمرات وفصول كتب، مفهرسة برقم DOI ومربوطة بباحثي الجامعة.

10 مُخرَج نتائج البحث عن «Reinforcement learning»

مقالوصول مفتوح20266استشهاد· Semantic Scholar

Personalized multi-agent reinforcement learning framework for adaptive chronic disease therapy management

Scientific Reports · مجلد 16 (1)

Long-term, flexible therapy strategies are needed for chronic diseases like cardiovascular ailments, diabetes, and chronic kidney disease and they have to deal with patient heterogeneity, changing physiological states and privacy constraints. This research suggests a framework for privacy-preserving and personalized artificial intelligence that combines Federated Learning (FL), a Res-HyperTransformerNet deep prediction model, Personalized Multi-Agent Reinforcement Learning (PMARL) and Explainable Artificial Intelligence (XAI) for adaptive chronic disease management. The framework is structured with two main aims: (i) to create an accurate and privacy-aware predictive model for chronic disease risk using diverse data sources, and (ii) to permit adaptive, individual therapy optimization through multi-agent reinforcement learning. Federated learning is utilized to conduct the training of Res-HyperTransformerNet over distributed Internet of Medical Things (IoMT) nodes without the requirement of transferring raw patient data. The embeddings that are created from patient data are then passed on to a PMARL module, where several agents optimize therapy dimensions like medications, diet, physical activity, and mental health interventions independently. To make the clinical support more understandable, the SHAP-based explainability method is used for both predictive and decision-making parts. The framework is tested using two public datasets—the CDC Chronic Disease dataset and the UCI Chronic Kidney Disease Risk Factor dataset. The performance is measured by employing classification metrics (accuracy, precision, recall, F1-score, MCC) as well as reinforcement learning metrics (reward score, convergence steps, episode return) and federated system metrics (communication overhead, convergence rounds, and training time). The experiments indicate that the proposed framework demonstrated improved performance in terms of predictive accuracy and policy convergence speed compared to the baseline deep learning and reinforcement learning models, and at the same time it is more cost-effective when it comes to communication in a federated setting. This means that the proposed method suggests the potential of being a reproducible and open AI framework for adaptive chronic disease therapy management. The combination of ResNet and Transformer blocks, i.e., Federated Res-HyperTransformerNet, achieved strong performance in both datasets, namely CDC Chronic Disease (Dataset 1) and UCI CKD Risk Factor (Dataset 2). The obtained accuracy for Dataset 1 was 98.61% and for Dataset 2, it was 97.75%, under the conducted experimental settings.

chronic disease managementfederated learningprivacy-preserving healthcarechronic disease risk prediction
مقالوصول مفتوح2026

Reinforcement learning–coupled neural ode modelling reveals ferroptotic resolution failure as a shared dynamical axis linking periodontitis and coronary atherogenesis

Scientific Reports · مجلد 16 (1)

The molecular axis underlying the epidemiologically established association between periodontitis and coronary heart disease (CHD) remains undefined at mechanistic, systems-level resolution. Classical comparative transcriptomics captures correlational gene lists but cannot reconstruct directional disease-state dynamics or locate the point along a disease-state ordering at which inflammatory resolution fails. ReNODE-Ferro integrates three public bulk transcriptomic datasets (GSE16134, periodontitis, n = 310; GSE28829, CHD staged, n = 29; GSE100927, CHD plaque, n = 104) through a nine-module biologically curated feature space (123 genes), a fully connected latent encoder, a Neural Ordinary Differential Equation (latent dim = 12) learning continuous disease-state dynamics across six biologically defined states (S0–S5), and a model-based reinforcement learning (RL) controller identifying optimal biological intervention policies in latent space. Twenty-four genes were concordantly dysregulated (FDR < 0.05) across all three datasets. Cross-disease fold-change concordance was significant (Spearman r = 0.473, p = 3.29 × 10 − 8, periodontitis vs. CHD staged). Ferroptotic vulnerability and coronary coupling co-varied with r = 0.830 ( p = 3.89 × 10 − 114). Neural ODE tipping-point analysis identified the S2→S3 metabolic strain-to-ferroptosis-primed transition as the transition carrying the highest modelled velocity, although under a held-out validation scheme the velocity profile proved comparatively flat and the location of the maximum unstable across bootstrap refits. S2 was the least responsive state to single-step intervention (3.7%), but it contains only six specimens and was the least stable cluster on resampling. RL policy optimization identified antioxidant restoration, mitochondrial quality enhancement, and pro-resolution amplification as the universal intervention triad (mean reward improvement = 0.583). Robustness analyses added at revision support and delimit these findings. Tissue of origin explained no measurable variance in the nine-module space (PERMANOVA R² < 0.001, p = 1.00) whereas disease status explained 14.0% ( p < 1 × 10⁻⁴), and the ferroptotic vulnerability–coronary coupling association persisted after adjustment for estimated cellular composition (ρ = 0.764) and within every cohort analysed separately (ρ = 0.77–0.89). An independent diffusion-pseudotime ordering reproduced the state sequence (ρ = 0.872) and placed S2 before S3 ( p = 2.4 × 10⁻¹⁰), and leave-one-cohort-out re-derivation recovered the same structure in all three folds. Against 5,000 size-matched random gene panels the curated feature space was strongly informative (empirical p = 2.0 × 10⁻⁴), although an uncurated transcriptome-wide analysis showed the ferroptotic axis to be one of several concordant programmes rather than a uniquely dominant one. Periodontitis and coronary atherogenesis share a conserved ferroptotic-metabolic resolution failure trajectory. ReNODE-Ferro provides a mechanistically grounded, interventionally actionable map of this continuum, establishing ferroptotic vulnerability as a principal and unusually tightly coupled molecular axis of this shared programme. Because all three cohorts are cross-sectional, the reconstructed trajectory is a statistical ordering rather than a demonstrated temporal or causal sequence.

periodontitiscoronary artery diseaseferroptosisneural ordinary differential equations
مقالوصول مفتوح202518استشهاد· Semantic Scholar

Novel deep reinforcement learning based collision avoidance approach for path planning of robots in unknown environment

PLoS ONE · مجلد 20 (1) · e0312559-e0312559

Reinforcement learning is a remarkable aspect of the artificial intelligence field with many applications. Reinforcement learning facilitates learning new tasks based on action and reward principles. Motion planning addresses the navigation problem for robots. Current motion planning approaches lack support for automated, timely responses to the environment. The problem becomes worse in a complex environment cluttered with obstacles. Reinforcement learning can increase the capacity of robotic systems due to the reward system's capability and feedback to the environment. This could help deal with a complex environment. Existing algorithms for path planning are slow, computationally expensive, and less responsive to the environment, which causes late convergence to a solution. Furthermore, they are less efficient for task learning due to post-processing requirements. Reinforcement learning can address these issues using its action feedback and reward policies. This research presents a novel Q-learning-based reinforcement algorithm with deep learning integration. The proposed approach is evaluated in a narrow and cluttered passage environment. Further, improvements in the convergence of reinforcement learning-based motion planning and collision avoidance are addressed. The proposed approach's agent converged in 210th episodes in a cluttered environment and 400th episodes in a narrow passage environment. A state-of-the-art comparison shows that the proposed approach outperformed existing approaches based on the number of turns and convergence of the path by the planner.

collision avoidancerobot path planningdeep reinforcement learningQ-learning
مقالوصول مفتوح202431استشهاد· Semantic Scholar

DQQS: Deep Reinforcement Learning-Based Technique for Enhancing Security and Performance in SDN-IoT Environments

IEEE Access · مجلد 12 · 60568-60587

The Internet of Things (IoT) is an emerging technology that allow smart devices to communicate through various heterogeneous channels (wired or wireless). However, for conventional networks, it has become a challenging task to efficiently control and manage the data flows of a huge number of devices. Software-defined networking (SDN) is a new way of thinking about networking. Because it is programmable, flexible, agile, and gives you a big picture of the network, it has tried to solve some IoT problems, like scalability, heterogeneity, and complexity. In large-scale SDN-IoT networks, there is a requirement for routing protocols that are both efficient and secure in order to ensure a superior level of quality of service (QoS) and quality of experience (QoE). To address the above stated challenges, a novel deep reinforcement learning (DRL) known as DQQS model is proposed. The aim is to achieve QoS and QoE while also ensuring the security of the SDN-IoT network. The proposed DQQS model dynamically extracts patterns from the past network history by interacting with the underlying network and generating optimized routing policies. This article employs three network metrics—throughput, latency, and the probability of avoiding malicious nodes—to measure the performance of DQQS. Simulations reveal that the proposed framework outperforms four state-of-the-art routing algorithms: OSPF, L-L Routing, Sailfish Routing, and RL-Routing in terms of both throughput and latency. For instance, in an attacked environment, the proposed DQQS model achieved the highest throughput value of 14.5 Mbps, surpassing OSPF at 8 Mbps, L-L at 8.2 Mbps, Sailfish at 9 Mbps, and RL at 9.5 Mbps. Similarly, this model exhibited superior performance in latency, recording the lowest latency value of 52 ms, compared to OSPF 88 ms, L-L 85 ms, Sailfish 72 ms, and RL 75 ms routing algorithms. The experimental results demonstrate that this new DQQS model is a pioneering deep reinforcement learning-based technique that optimally addresses secure routing in the SDN-IoT environment, ensuring enhanced quality of service and experience, and outperforming state-of-the art DL methodologies in both security and network performance metrics.

software-defined networkingInternet of Thingssecure routingdeep reinforcement learning
مقالمفتوح (مستودع)202424استشهاد· Semantic Scholar

Federated-Reinforcement Learning-Assisted IoT Consumers System for Kidney Disease Images

IEEE Transactions on Consumer Electronics · مجلد 70 (4) · 7163-7173

The number of people with kidney disease rises every day for many reasons. Many existing machine-learning-enabled mechanisms for processing kidney disease suffer from long delays and consume much more resources during processing. In this paper, the study shows how federated and reinforcement learning schemes can be used to develop the best delay scheme. The scheme must optimize both the internal and external states of reinforcement learning and the federated learning fog cloud network. This work presents the Adaptive Federated Reinforcement Learning-Enabled System (AFRLS) for Internet of Things (IoT) consumers’ kidney disease image processing. The main relationship between IoT consumers and kidney image is that the data is collected from different IoT consumer sources, such as ultrasound and X-rays in healthcare clinics. In healthcare applications, kidney urinary tasks reduce the time it takes to preprocess federated learning datasets for training and testing and run them on different fog and cloud nodes. AFRLS decides the scheduling on other nodes and improves constraints based on the decision tree. Based on the simulation results, AFRLS is a new strategy that reduces the time tasks need to be delayed compared to other machine learning methods used in fog cloud networks. The AFRLS improved the delay among nodes by 55%, the delay among internal states by 40%, and the training and testing delay by 51%.

federated learningreinforcement learningkidney disease diagnosiskidney ultrasound images
مقالوصول مفتوح202411استشهاد· Semantic Scholar

IR-QLA: Machine Learning-Based Q-Learning Algorithm Optimization for UAVs Faster Trajectory Planning by Instructed- Reinforcement Learning

IEEE Access · مجلد 12 · 91300-91315

Trajectory planning for unmanned aerial vehicles (UAVs) presents a formidable challenge, particularly in environments where details about the terrain and objectives are not known beforehand. This uncertainty has propelled the adoption of UAVs across diverse sectors such as logistics, weather forecasting, security surveillance, and autonomous driving, where their ability to navigate autonomously is crucial. Recent advancements have leveraged deep learning for robust object detection and tracking, significantly enhancing data acquisition from aerial imagery and UAV-based applications. Despite numerous innovations, the critical issue of optimizing UAV trajectories in unknown environments remains largely unaddressed. This paper introduces a novel approach, the Instructed Reinforcement Q-Learning Algorithm (IR-QLA), which utilizes Received Signal Strength (RSS) as a dynamic reward metric to refine trajectory planning continuously. By integrating a unique instructed reinforcement principle, this method significantly accelerates the learning process, improving the UAVs’ navigational efficiencies. Our findings demonstrate that IR-QLA not only surpasses traditional algorithms like Ant Colony and Particle Swarm Optimization in terms of convergence speed but also minimizes the path length and iteration counts needed for trajectory optimization. Future studies will explore alternative reward sources and advanced algorithms to further enhance the precision and speed of UAV trajectory planning, aiming to establish new benchmarks in the field.

UAV trajectory planningQ-learningreceived signal strengthreward function design
مقالوصول مفتوح20247استشهاد· Semantic Scholar

Meta-Learning Guided Weight Optimization for Enhanced Solar Radiation Forecasting and Sustainable Energy Management with VotingRegressor

Sustainability · مجلد 16 (13) · 5505-5505

Solar radiation prediction plays a crucial role in renewable energy management, impacting various decision-making processes aimed at optimizing the utilization of solar resources and promoting sustainability. Ensemble regression methods, notably VotingRegressor, have emerged as promising tools for accurate solar radiation forecasting. By integrating predictions from multiple base estimators, ensemble methods have the potential to capture intricate patterns inherent in solar radiation data. However, achieving optimal predictive performance with ensemble methods heavily relies on the careful weighting assigned to each base estimator, presenting a significant challenge. In this study, a novel approach is presented to enhance solar radiation prediction by utilizing meta-learning techniques to optimize the weighting mechanism in the VotingRegressor ensemble. Meta-learning, a subfield of machine learning focusing on learning algorithms across different tasks, provides a systematic framework for learning to learn. This enables models to adapt and generalize more effectively to new datasets and tasks. Our proposed methodology demonstrated significant improvements, with the VotingRegressor with meta-learning techniques achieving an RMSE of 8.7343, an MAE of 5.42145, and an R² of 0.991913. These results mitigate the need for manual weight tuning and improve the adaptability of the VotingRegressor to varying solar radiation conditions, ultimately contributing to the sustainability of renewable energy systems. The methodology involves a comprehensive exploration of meta-learning techniques, encompassing gradient-based optimization, reinforcement learning, and Bayesian optimization.

solar irradiance forecastingmeta-learningensemble regressionweight optimization
مقالمفتوح (مستودع)20235استشهاد· Semantic Scholar

Energy‐efficient resource allocation over wireless communication systems through deep reinforcement learning

International Journal of Communication Systems · مجلد 38 (1)

Summary As the popularity of the Internet of Things (IoT) increases, so do the energy requirements of IoT terminal equipment. To address the energy shortage problem of equipment and ensure continuous and stable operation in light of renewable energy and an uncertain environment, a rational and efficient energy allocation strategy is required. This paper proposes a deep reinforcement learning energy allocation strategy that uses the DQN algorithm to directly interact with the unknown environment. The best energy allocation method is independent of environmental knowledge, and a pretraining algorithm is proposed to maximise the initialization state of the strategy. Experiments of comparison and simulation are conducted under various channel data circumstances. Results indicate that the proposed energy allocation strategy outperforms the current strategy in multiple channel conditions and has a high capacity for adaptation to changing conditions.

energy-efficient resource allocationdeep reinforcement learningdeep Q-networkInternet of Things