Search Results (190)

Coordinated control of ramp metering, variable speed limits, and intersection signals is critical for mitigating congestion and enhancing efficiency at urban expressway–arterial interfaces. Existing strategies often operate in isolation, leading to fragmented responses and limited adaptability under heterogeneous traffic demands. This study develops a multi-agent reinforcement learning framework based on MADDPG to achieve cooperative decision-making across heterogeneous controllers. An asynchronous control cycle mechanism is designed to accommodate different temporal requirements of ramp meters, speed limits, and signal controllers, ensuring practical feasibility in real-time operations. A conflict-aware reward design further embeds density regulation, speed harmonization, and spillback prevention to stabilize flow dynamics. Simulation experiments on a calibrated urban network demonstrate that the proposed framework delays congestion onset, reduces shockwave propagation, and improves throughput compared with classical benchmarks. In particular, at the mainline merge, average travel time is reduced to 13.56 s (62.4% of VSL-only); at the ramp, occupancy is lowered to 6.4% (40.6% of ALINEA); and at the signalized approach, average delay decreases to 85.71 s (62.7% of actuated control). These results highlight the scalability and deployment potential of the proposed cooperative control approach for system-level traffic management in mixed traffic environments. Full article

This study aimed to systematically identify the active constituents of Kadsura coccinea (Lem.) A. C. Smith (KC) and elucidate their potential mechanisms in treating rheumatoid arthritis (RA) using an integrated analytical and computational approach. Chemical profiling of KC root extract was performed by UPLC-Q-TOF-MS/MS. Active compounds and their targets were predicted using the SwissTargetPrediction database, while RA-related genes were retrieved from OMIM, GeneCards, and DisGeNET. A compound–target network was constructed and analyzed via Cytoscape. Functional enrichment analyses and protein–protein interaction (PPI) clustering were conducted to identify key pathways. Molecular docking was employed to validate interactions between core compounds and key RA targets. A total of 90 compounds were identified, primarily 36 lignans and 29 triterpenoids. Network analysis revealed 145 overlapping targets between KC and RA. These targets were further associated with 65 compounds derived from KC. Key compounds such as kadcoccinone F, kadsuralignan I and schisantherin M were linked to hub targets including MAPK14, MMPs, and JAKs, which are involved in inflammatory signaling, matrix degradation, and immune regulation. Molecular docking confirmed strong binding affinities (ΔG < −5.0 kcal/mol) between representative KC compounds and targets like MMP1, MMP2, JAK2 and JAK3, supported by analyses of hydrogen bonding, hydrophobic, and π-interactions. These results suggest that KC exerts anti-RA effects through multi-component, multi-target mechanisms, primarily modulating inflammatory signaling, immune cell recruitment, and tissue-destructive pathways. This study provides a pharmacological basis for the traditional use of KC in RA management and supports its potential as a complementary therapeutic agent. Full article

With more renewables being integrated into distribution grids, the problem of voltage fluctuation has become prominent. Effective Volt/VAR regulation is a commonly used method to ensure the safe operation of distribution networks. Model-based approaches tend to work well only if detailed network parameters are available, while data-driven approaches can suffer from overfitting and may not generalize well. We created the PHY-GAT-SAC framework to address these issues. Physics-regularized reinforcement learning uses bidirectional graph attention, which combines a physics-informed model with a safety projection method that relies on sensitivity matrices. This makes it so that the voltage regulation is practical, interpretable, and secure. The framework works with two combined branches. One branch takes care of the nonlinear mapping from power injections to voltage states using a forward graph encoder and a reverse consistency constraint. At the same time, another branch extracts features directly from the voltages to improve the perception of system violation risk. The framework has a sensitivity-based safety layer as well. This layer projects every control action into a feasible area formed by linearized voltage restrictions, thus securing operation safety. Experiments on an IEEE 33-node system show that the framework works well. A safety layer guarantees a safe operating range without exact impedance values. And PHY-GAT-SAC greatly lowers voltage violations compared to multi-agent deep reinforcement learning. By successfully combining physics with learning, this study gives a unified framework for merging graph neural networks and reinforcement learning within intricate grid management. Full article

The rapid growth of renewable integration and active consumer participation has made modern power grids increasingly complex and dynamic, where maintaining balanced and efficient energy distribution remains a central challenge. This paper introduces a symmetry-aware optimized fuzzy deep reinforcement learning-gated recurrent unit (OF-DRL-GRU) model that exploits the natural symmetry and asymmetry in demand–generation behavior to achieve stable and adaptive load balancing. The proposed architecture consists of four core modules: a fuzzy logic layer that formulates symmetrically distributed membership functions for interpretable and balanced state transitions; a DRL agent that governs decision actions through a symmetry-preserving reward mechanism balancing exploration and exploitation; a GRU network that models temporal symmetries while performing controlled symmetry-breaking during dynamic fluctuations to enhance generalization; and an improved multi-objective biogeography-based optimization (IMOBBO) algorithm that optimizes fuzzy parameters and model hyper-parameters through adaptive migration alternating between symmetry preservation and deliberate asymmetry, ensuring efficient convergence and global diversity. The synergy among these modules forms a unified symmetry-aware optimization paradigm, reflecting how symmetric structures sustain stability while purposeful asymmetry enhances robustness and adaptivity. The proposed framework is evaluated using three benchmark datasets (UK-DALE, Pecan Street, and REDD) and compared against several advanced and competitive models. Experimental outcomes show that the proposed OF-DRL-GRU model achieves 99.23% accuracy, 99.69% recall, and 99.83% area under the curve (AUC), alongside faster runtime, lower variance, and improved convergence stability. These results demonstrate that incorporating symmetry–asymmetry principles within AI-driven optimization significantly enhances interpretability, resilience, and energy efficiency, paving the way for intelligent, self-adaptive load management in next-generation smart grids. Full article

The agrarian sector, as the key source of livelihood in Sub-Saharan Africa (SSA), has become highly vulnerable to changes in extension service deliveries. Farmers mainly lack access to technical advice, financial credits, farming inputs and mechanization tools while environmental challenges reinforce the adaptation of sustainable management practices. Therefore, an understanding how multi-functional actor relationships determine agricultural knowledge and information (AKI) sharing is required. This study contributes to filling this gap by characterizing horizontal and vertical interactions. By applying a social network analysis, we mapped actor relations along public–private-community co-operations to provide insights into structural dependencies at different administrative levels. Related to three sites distributed over Burkina Faso and Ghana, local perceptions were collected in stakeholder workshops to generate social network narratives. These narratives were analyzed by various metrics to identify patterns of partnerships and key actors. Study results reveal for Burkina Faso a slight shared network topology, while both sites in Ghana reflect a top-down flow of AKI. The statistical findings indicate that agricultural extension services are primarily delivered to farmers through a few key actors such as NGOs and farm-based organizations/cooperatives. Especially at the community level, the results show many reciprocal links between farmers, business actors and NGOs. This highlights a shift toward a pluralistic agricultural extension service system and underpins the demand for policies to support the long-term viability of these actors, in particular for regions where public extension agents are under-represented. Full article

Chronic Obstructive Pulmonary Disease (COPD) is a complex inflammatory lung condition characterized by oxidative stress, changes in airway structure, and gradually worsening airflow blockage. Existing treatments offer only symptomatic management, emphasizing the need for multi-target therapeutic interventions. This study employed a combined approach of network pharmacology and molecular docking to investigate the therapeutic effects of bioactive compounds derived from Cladophora glomerata on COPD. Disease-associated genes were collected from GeneCards, Online Mendelian Inheritance in Man (OMIM), and National Center for Biotechnology Information (NCBI), while compounds from C. glomerata and their predicted molecular targets were obtained from SwissTargetPrediction. A cross-comparison of targets related to compounds and diseases revealed nine common genes, among which three central genes TP53, CASP8, and EGFR were identified using protein–protein interaction (PPI) network analysis. Analysis of gene–disease interactions highlighted Tumor Protein p53 (TP53) and Epidermal Growth Factor Receptor (EGFR) as major regulatory targets. GeneMANIA-based functional and co-expression analysis revealed predominant physical interactions (77.64%) and co-expression relationships (8.01%), highlighting strong functional connectivity among the identified genes. Molecular docking further confirmed that C. glomerata derived compounds, particularly Quinoline, 1,2,3,4-tetrahydro-1-((2-phenylcyclopropyl)sulfonyl)-, trans- (Pubchem ID: 91709903) (−7.5 kcal/mol) and1,2,4-Oxadiazole, 3-(1,3-benzodioxol-5-yl)-5-[(4-iodo-1H-pyrazol-1-yl)methyl]- (Pubchem ID: 5301194) (−7.3 kcal/mol), exhibit favorable predicted binding affinities toward EGFR and TP53 in molecular docking analysis. Overall, these insights suggest that Cladophora glomerata compounds may modulate key COPD-related pathways through multi-target interactions, providing a scientific basis for future experimental studies and the development of marine-derived therapeutic agents for COPD management. Full article

Previous studies, constrained by the overly rigid stability requirements, often fail to adapt to complex systems and struggle to identify stable outcomes that align with the practical context of multi-agent resource allocation. To address the three-sided matching problem in complex socio-technical and business management systems, this paper proposes a fuzzy stable matching method for three-sided agents under a framework of combinatorial preference relations, integrating network and decision theory. First, we construct a membership function to measure the degree of preference satisfaction between elements of different agents, and then define the concept of fuzzy stability. By incorporating preference satisfaction, we introduce the notion of fuzzy blocking strength and derive the generation conditions for blocking triples and fuzzy stability under the fuzzy stable criterion. Furthermore, we abstract the three-sided matching problem with combined preference relations into a shortest path problem. Second, we prove the equivalence between the shortest path solution and the stable matching outcome. We adopt Dijkstra’s algorithm for problem-solving and derive the time complexity of the algorithm under the pruning strategy. Finally, we apply the proposed model and algorithm to a case study of project assignment in software companies, thereby verifying the feasibility and effectiveness of this three-sided matching method. Compared with existing approaches, the fuzzy stable matching method developed in this study demonstrates distinct advantages in handling preference uncertainty and system complexity. It provides a more universal theoretical tool and computational approach for solving flexible resource allocation problems prevalent in real-world scenarios. Full article

This research simulates Aswan City’s urban transportation dynamics utilizing the Multi-Agent Transport Simulation (MATSim) framework. As a fast-expanding urban center, Aswan has many transportation difficulties that require extensive modeling toward sustainable mobility solutions. MATSim, recognized for its agent-based methodology, offers a detailed portrayal and analysis of individual travel behaviors and their interactions within the metropolitan transportation system. This study compiled and combined many databases, including demographic data, road infrastructure, public transit plans, and travel demand trends. These data are altered to produce a realistic digital clone of Aswan’s transportation system. Simulated scenarios analyze the consequences of several actions, such as increased public transit scheduling, traffic flow management, and the adoption of alternative transport modes, on minimizing congestion and boosting accessibility. Pilot findings show that MATSim effectively captures the distinct features of Aswan’s transportation network and offers practical insights for decision-makers. The results identified some opportunities to improve mobility and promote sustainable urban growth in developing cities. This study emphasized the importance of agent-based simulations in designing future transportation systems and urban infrastructure. Full article

Curcumin, a natural polyphenol derived from turmeric, functions as a potent exogenous antioxidant and exhibits a range of benefits in the prevention and management of metabolic diseases. Despite its extremely low systemic bioavailability, curcumin demonstrates significant bioactivity in vivo, a phenomenon likely attributable to its accumulation in the intestines and subsequent modulation of systemic oxidative stress and inflammation. This article systematically reviews the comprehensive regulatory effects of curcumin on systemic metabolic networks—including glucose metabolism, amino acid metabolism, lipid metabolism, and mitochondrial metabolism—and explores their molecular basis, particularly how curcumin facilitates systemic metabolic improvements by alleviating oxidative stress and interacting with inflammation. Preclinical studies indicate that curcumin accumulates in the intestines, where it remodels the microbiota through prebiotic effects, enhances barrier integrity, and reduces endotoxin influx—all of which are critical drivers of systemic oxidative stress and inflammation. Consequently, curcumin improves insulin resistance, hyperglycemia, and dyslipidemia across multiple organs (liver, muscle, adipose) by activating antioxidant defense systems (e.g., Nrf2), enhancing mitochondrial respiratory function (via PGC-1α/AMPK), and suppressing pro-inflammatory pathways (e.g., NF-κB). Clinical trials have corroborated these effects, demonstrating that curcumin supplementation significantly enhances glycemic control, lipid profiles, adipokine levels, and markers of oxidative stress and inflammation in patients with obesity, type 2 diabetes, and non-alcoholic fatty liver disease. Therefore, curcumin emerges as a promising multi-target therapeutic agent against metabolic diseases through its systemic antioxidant and anti-inflammatory networks. Future research should prioritize addressing its bioavailability limitations and validating its efficacy through large-scale trials to translate this natural antioxidant into a precision medicine strategy for metabolic disorders. Full article

One of the key functions of Air Traffic Management (ATM) is to balance airspace capacity and demand. Despite measures that are taken during the strategic and pre-tactical phases of flight, demand–capacity imbalances still occur in flight, often manifesting as localised regions of high traffic complexity, known as hotspots. These hotspots emerge dynamically, leaving air traffic controllers with limited anticipation time and increased workload. This paper proposes a Machine Learning (ML) framework for the prediction and resolution of hotspots in congested en-route airspace up to an hour in advance. For hotspot prediction, the proposed framework integrates trajectory prediction, spatial clustering, and complexity assessment. The novelty lies in shifting complexity assessment from a sector-level perspective to the level of individual hotspots, whose complexity is quantified using a set of normalised, sector-relative metrics derived from historical data. For hotspot resolution, a Reinforcement Learning (RL) approach, based on Proximal Policy Optimisation (PPO) and a novel neural network architecture, is employed to act on airborne flights. Three single-clearance type agents—a speed agent, a flight-level agent, and a direct routing agent—and a multi-clearance type agent are trained and evaluated on thousands of historical hotspot scenarios. Results demonstrate the suitability of the proposed framework and show that hotspots are strongly seasonal and mainly occur along traffic routes. Furthermore, it is shown that RL agent performance tends to degrade with hotspot complexity in terms of certain performance metrics but remains the same, or even improves, in terms of others. The multi-clearance type agent solves the highest percentage of hotspots; however, the FL agent achieves the best overall performance. Full article

Machine learning (ML) is becoming a key enabler in building energy management systems (BEMS), yet most existing reviews focus on simulations and fail to reflect the realities of real-world deployment. In response to this limitation, the present work aims to present a systematic review dedicated entirely to experimental, field-tested applications of ML in BEMS, covering systems such as Heating, Ventilation & Air-conditioning (HVAC), Renewable Energy Systems (RES), Energy Storage Systems (ESS), Ground Heat Pumps (GHP), Domestic Hot Water (DHW), Electric Vehicle Charging (EVCS), and Lighting Systems (LS). A total of 73 real-world deployments are analyzed, featuring techniques like Model Predictive Control (MPC), Artificial Neural Networks (ANNs), Reinforcement Learning (RL), Fuzzy Logic Control (FLC), metaheuristics, and hybrid approaches. In order to cover both methodological and practical aspects, and properly identify trends and potential challenges in the field, current review uses a unified framework: On the methodological side, it examines key-attributes such as algorithm design, agent architectures, data requirements, baselines, and performance metrics. From a practical standpoint, the study focuses on building typologies, deployment architectures, zones scalability, climate, location, and experimental duration. In this context, the current effort offers a holistic overview of the scientific landscape, outlining key trends and challenges in real-world machine learning applications for BEMS research. By focusing exclusively on real-world implementations, this study offers an evidence-based understanding of the strengths, limitations, and future potential of ML in building energy control—providing actionable insights for researchers, practitioners, and policymakers working toward smarter, grid-responsive buildings. Findings reveal a maturing field with clear trends: MPC remains the most deployment-ready, ANNs provide efficient forecasting capabilities, RL is gaining traction through safer offline–online learning strategies, FLC offers simplicity and interpretability, and hybrid methods show strong performance in multi-energy setups. Full article

Background: Rheumatoid arthritis (RA) is a chronic and debilitating autoimmune disease with a complex etiology, creating a significant unmet clinical need for safer and more effective therapeutics. Coix seed oil (CSO), a traditional Chinese medicine with a long history of use against RA, represents a promising candidate; however, its precise mechanisms of action remain largely unexplored. Objectives: This study aimed to elucidate the mechanistic basis for the anti-arthritic effects of CSO, with a specific focus on its role in modulating the gut-joint axis. Methods: A collagen-induced arthritis (CIA) rat model was employed. The therapeutic efficacy of CSO was evaluated through detailed assessments of arthritic symptoms, joint histopathology, and Micro-CT analysis. To unravel the mechanism, an integrative multi-omics approach was applied, combining untargeted fecal metabolomics with targeted serum metabolomics, which pinpointed butyric acid as a key differential metabolite. This was integrated with 16S rRNA sequencing to profile gut microbiota remodeling. The causal role of butyrate was further verified by exogenous sodium butyrate supplementation in CIA mice. Finally, network pharmacology predictions of potential effector proteins were experimentally validated in vivo using immunofluorescence and qPCR. Results: CSO treatment significantly alleviated joint swelling and bone damage in CIA rats after the treatment of 7 days, especially on day 35. CSO primarily restored gut dysbiosis in the CIA model by upregulating butyrate levels, increasing four butyrate-producing probiotics at the genus level, and reducing two pathogenic bacteria. Further exogenous butyrate supplementation validated its ability to improve RA phenotypes. Network pharmacology analysis speculated that there were 142 common targets between CSO and RA, among which NLRP3 was its potential effector protein. In vivo studies verified the suppression of NLRP3 inflammasome activation and reduced expression of subsequent inflammatory mediators by CSO. Conclusions: Coix Seed Oil alleviates RA by orchestrating a dual-mechanism action, it remodels the gut microbiota to enhance the production of the microbiotic metabolite butyrate, while also inhibiting the NLRP3 inflammasome pathway. These findings collectively elucidate that CSO mediates its anti-arthritic effects through a novel “gut-butyrate-joint” axis, underscoring its potential as a promising dietary supplement or therapeutic agent derived from medicine-food homology for the management of RA. Full article

The increasing deployment of hybrid renewable energy systems has introduced significant challenges in optimal energy dispatch and load balancing due to the intrinsic stochasticity and temporal variability of renewable sources, along with the multi-dimensional optimization requirements of simultaneously achieving economic efficiency, grid stability, and environmental sustainability. This paper presents GreenMind, a scalable Deep Reinforcement Learning framework designed to address these challenges through a hierarchical multi-agent architecture coupled with Long Short-Term Memory (LSTM) networks for predictive energy management. The framework employs specialized agents responsible for generation dispatch, storage management, load balancing, and grid interaction, achieving an average decision accuracy of 94.7% through coordinated decision-making enabled by hierarchical communication mechanisms. The integrated LSTM-based forecasting module delivers high predictive accuracy, achieving a 2.7% Mean Absolute Percentage Error for one-hour-ahead forecasting of solar generation, wind power, and load demand, enabling proactive rather than reactive control. A multi-objective reward formulation effectively balances economic, technical, and environmental objectives, resulting in 18.3% operational cost reduction, 23.7% improvement in energy efficiency, and 31.2% enhancement in load balancing accuracy compared to state-of-the-art baseline methods. Extensive validation using synthetic datasets representing diverse hybrid renewable energy configurations over long operational horizons confirms the practical viability of the framework, with 19.6% average cost reduction, 97.7% system availability, and 28.6% carbon emission reduction. The scalability analysis demonstrates near-linear computational growth, with performance degradation remaining below 9% for systems ranging from residential microgrids to utility-scale installations with 2000 controllable units. Overall, the results demonstrate that GreenMind provides a scalable, robust, and practically deployable solution for predictive energy dispatch and load balancing in hybrid renewable energy systems. Full article

The escalating global demand for energy-efficient and sustainable built environments has catalyzed the advancement of Building Energy Management Systems (BEMSs), particularly through their integration with cutting-edge technologies. This review presents a comprehensive and critical synthesis of the convergence between BEMSs and enabling tools such as the Internet of Things (IoT), wireless sensor networks (WSNs), and artificial intelligence (AI)-based decision-making architectures. Drawing upon 89 peer-reviewed publications spanning from 2019 to 2025, the study systematically categorizes recent developments in HVAC optimization, occupancy-driven lighting control, predictive maintenance, and fault detection systems. It further investigates the role of communication protocols (e.g., ZigBee, LoRaWAN), machine learning-based energy forecasting, and multi-agent control mechanisms within residential, commercial, and institutional building contexts. Findings across multiple case studies indicate that hybrid AI–IoT systems have achieved energy efficiency improvements ranging from 20% to 40%, depending on building typology and control granularity. Nevertheless, the widespread adoption of such intelligent BEMSs is hindered by critical challenges, including data security vulnerabilities, lack of standardized interoperability frameworks, and the complexity of integrating heterogeneous legacy infrastructure. Additionally, there remain pronounced gaps in the literature related to real-time adaptive control strategies, trust-aware federated learning, and seamless interoperability with smart grid platforms. By offering a rigorous and forward-looking review of current technologies and implementation barriers, this paper aims to serve as a strategic roadmap for researchers, system designers, and policymakers seeking to deploy the next generation of intelligent, sustainable, and scalable building energy management solutions. Full article

Background: Pancreatitis, encompassing acute (AP), severe acute (SAP), and chronic (CP) forms, is a life-threatening inflammatory disorder with limited therapeutic options. Current management is largely supportive, highlighting the urgent need for novel interventions targeting underlying molecular pathways. Aim: This review summarizes recent advances in the pathogenesis of pancreatitis, focusing on calcium dysregulation, ferroptosis, and microRNA-mediated mechanisms while exploring the therapeutic potential of phytochemicals as disease-modifying agents. Summary: Aberrant calcium signaling, iron-dependent lipid peroxidation, and microRNA imbalance drive acinar cell injury, inflammatory cascades, and pancreatic fibrosis. Phytochemicals, including flavonoids, terpenoids, alkaloids, and phenolics, have shown protective effects in preclinical models through multi-targeted mechanisms. These include suppression of NF-κB-driven inflammation, activation of the Nrf2/HO-1 antioxidant pathway, modulation of ferroptosis via GPX4 and iron efflux, regulation of calcium signaling, and modulation of microRNA expression. Importantly, several phytochemicals attenuate acinar cell death, reduce cytokine release, and limit fibrosis, thereby improving outcomes in experimental pancreatitis. However, poor solubility, bioavailability, and pharmacokinetic limitations remain significant barriers. Emerging strategies such as nanotechnology-based formulations, prodrug design, and pharmacokinetic profiling, as well as bioavailability studies, may enhance their clinical applicability. Conclusions: Phytochemicals represent a promising reservoir of multitarget therapeutic agents for pancreatitis. Their ability to modulate oxidative stress, inflammatory and calcium signaling, ferroptosis, and microRNA networks highlights their translational potential. Future studies should focus on clinical validation, bioavailability optimization, and advanced delivery platforms to bridge the gap from bench to bedside. Full article