Search Results (1,641)

In grid-connected smart integrated energy systems with high shares of renewable generation, source-side variability and inadequate coordination among battery storage, other energy carriers, and the external grid limit local renewable-electricity utilization and impede deep decarbonization. This study proposes a machine-learning-assisted, renewable-driven framework for multi-energy coupling and scenario-based multi-objective optimization of electricity–heat–hydrogen–storage systems. Historical meteorological and load data are processed using K-means clustering and Latin hypercube sampling to construct representative operating scenarios across multiple volatility regimes and characterize source–load uncertainty. The equipment model includes photovoltaic arrays, wind turbines, heat pumps, electrolyzers, fuel cells, grid-interactive battery energy storage, thermal storage, and hydrogen storage; cross-carrier conversion dynamics and emissions from purchased electricity and natural gas are embedded in the energy-balance constraints. A mixed-integer linear programming formulation then co-optimizes battery charging and discharging, grid exchange, and other multi-energy flows with respect to operating cost, carbon emissions, and renewable-energy curtailment. At 95% renewable-energy penetration, the proposed method achieves a renewable-energy absorption rate of 91.6% and a curtailment rate of 8.4%. Across the carbon-price cases, annualized operating cost ranges from 126.5 × 10⁴ to 141.2 × 10⁴ USD yr⁻¹, while carbon-emission intensity ranges from 26.4 to 38.5 gCO₂/kWh_eq. Under the specified high-risk grid disturbances, the coordinated strategy limits load shedding to 1.8%—73% below deterministic scheduling and 79% below the heuristic benchmark—and maintains 92.6% hydrogen self-sufficiency. These results provide a data-driven modeling and decision framework for battery–grid coordination and deep decarbonization in smart integrated energy systems. Full article

This paper presents the development of a simulation game that models traffic interactions with a focus on autonomous parking using machine learning techniques. The simulator is built in the Unity environment and employs the Unity ML-Agents toolkit to train a virtual vehicle capable of performing parking maneuvers autonomously. The training process is based on reinforcement learning, where the agent learns through interaction with the environment using virtual sensors that detect distances and surrounding objects. A custom reward system guides the learning process by encouraging safe, accurate, and efficient parking while penalizing collisions and incorrect maneuvers. The developed simulator demonstrates the potential of interactive environments for research and education in autonomous driving and artificial intelligence. Full article

Image segmentation is a fundamental step in computer vision and a cornerstone of robotic perception, serving as the foundation for interpreting data acquired from vision sensors, enabling robots to analyze complex visual environments, identify and localize objects, and support intelligent decision-making and autonomous control. It plays a critical role in applications such as autonomous navigation, robotic manipulation, medical robotics, agricultural robotics, autonomous vehicles, and human–robot interaction. Image segmentation has evolved from classical methods, which relied on handcrafted rules and mathematical models, to deep learning approaches that learn complex visual patterns directly from data. This evolution reflects advances in algorithms, computational power, and the theoretical foundations of mathematics and data science. Modern deep learning methods rely heavily on large, well-annotated datasets to train sophisticated neural networks. Yet, classical techniques remain valuable in certain scenarios, offering faster, reliable results without extensive computational requirements. Understanding the strengths and limitations of both approaches is key to selecting the right method. This paper surveys image segmentation techniques, comparing them in terms of accuracy, computational cost, and processing speed to guide informed method selection. Full article

Complex diseases, including cancer, rare genetic disorders, neurodevelopmental and psychiatric conditions, and neurodegenerative diseases, arise from interactions among genetic variation, gene regulation, and cellular states that are difficult to capture using a single data type or biological scale. Biological foundation models address this challenge by treating nucleotides and genes as tokens and learning representations that can be transferred to downstream biomedical and clinical tasks. In this review, we examine two major model classes, genomic sequence foundation models and cell foundation models, and compare their tokenization strategies, model architectures, pretraining objectives, and adaptation methods. We summarize their emerging applications in regulatory variant interpretation, disease-associated cell-state analysis, drug-response prediction, and therapeutic target discovery across complex diseases. We distinguish applications supported by experimental or retrospective validation from those that remain primarily computational or conceptual. We further discuss key challenges to clinical translation, including multimodal data integration, model interpretability, benchmarking, patient-specific prediction, and privacy protection. We highlight future opportunities to integrate biological foundation models with emerging frameworks of medical digital twins, agentic AI, and federated learning. By linking model design to translational goals, this review provides a practical framework for evaluating biological foundation models and their readiness for complex disease research and clinical use. Full article

Background: Hepatocellular carcinoma (HCC) remains a leading cause of cancer mortality. The c-Met and VEGFR2 pathways synergistically drive HCC progression. Marine natural products offer chemically diverse drug reservoirs; however, conventional activity-guided isolation faces labor intensity, low throughput, and frequent compound rediscovery, limiting marine drug development. Objective: To pioneer an artificial intelligence-driven marine drug discovery workflow integrating deep learning virtual screening for identifying dual c-Met/VEGFR2 promising in silico candidate from marine natural product repositories. Methods: UniSite predicted binding pockets in c-Met (PDB: 4R1V) and VEGFR2 (PDB: 2XIR). Drug-likeness filtering of 695,000 compounds from COCONUT and CMNPD databases yielded 84,730 candidates. DiffDock-based screening identified dual-target binders, validated through 200 ns molecular dynamics simulations, MM-GBSA calculations, and DFT analyses. Results: The marine phthalide CMNPD30506 [(S)-3-ethyl-5,6-dihydroxyphthalide] emerged as the lead candidate, engaging VEGFR2 via four hydrophobic contacts and one π-cation interaction with LYS868, while binding c-Met through four hydrophobic interactions, two hydrogen bonds, and π-π stacking. Molecular dynamics demonstrated stable RMSD profiles and dynamic hydrogen bond enrichment. MM-GBSA revealed binding free energies of −14.79 and −13.28 kcal/mol for VEGFR2 and c-Met, respectively, driven by van der Waals forces. DFT calculations indicated a HOMO-LUMO gap of 2.410 eV. Conclusions: This AI-augmented workflow successfully identified CMNPD30506 as a promising dual c-Met/VEGFR2 HCC therapeutic from marine libraries, overcoming traditional discovery bottlenecks through integrated deep learning and physics-based simulations, exemplifying AI’s potential in marine pharmacological research. Full article

Knowledge-graph-enhanced recommendation leverages external knowledge to characterize item semantics and alleviate the limitations of representation learning under sparse user–item interactions. However, existing methods inadequately model the correspondence between item-level collaborative signals and knowledge semantics, and most graph augmentation strategies rely on random perturbations that fail to distinguish edge-specific retention values. To address these limitations, we propose Knowledge-Stability-Guided Dual-Graph Contrastive Learning for Recommendation (KSDGCL). KSDGCL learns collaborative representations from the user–item interaction graph and knowledge-semantic representations from the knowledge graph, and introduces a cross-graph semantic alignment objective to strengthen the semantic correspondence between the collaborative and knowledge-semantic representations of the same item. To construct informative augmented views, KSDGCL defines edge-level knowledge stability by measuring the consistency of preference matching for the same user–item interaction edge across knowledge-perturbed views. The resulting stability scores are converted into edge retention probabilities to guide augmented interaction graph construction, thereby preserving valuable collaborative relations. Finally, multi-view representations from the original interaction graph, the knowledge graph, and the augmented interaction graphs are fused into comprehensive representations for recommendation. Experiments on Amazon-Book and LastFM show Recall@20 gains of 3.7% and 5.6% over the strongest baseline, respectively, demonstrating the effectiveness of KSDGCL in improving recommendation performance. Full article

Reinforcement learning (RL) has become an effective paradigm for enabling autonomous robots to acquire navigation policies directly from interaction with complex and uncertain environments. Nevertheless, autonomous path planning for Skid-Steer Mobile Manipulators (SSMMs) remains a challenging problem because it requires the coordinated control of the non-holonomic mobile base and the manipulator while simultaneously accounting for obstacle avoidance and wheel–terrain interaction effects. This paper presents and evaluates RL-based path planning strategies for SSMMs, explicitly incorporating coupled dynamics of the mobile platform and manipulator to generate collision-free trajectories under varying terrain conditions. The proposed framework incorporates a slip-aware reward formulation that penalizes discrepancies between commanded and measured robot motion while accounting for longitudinal and lateral slip resulting from wheel–terrain interaction. The main contributions are (i) a unified RL-based framework based on actor–critic techniques for SSMM path planning, integrating the mobile base and manipulator dynamics within a coupled system representation; (ii) a physics-aware multi-objective reward formulation that incorporates wheel–terrain interaction into policy learning; and (iii) the implementation via simulation and field validation of the proposed policies under progressively complex navigation conditions and real underground mining scenarios. The framework is evaluated using four RL algorithms across multiple environments and maps from real mining scenarios, encompassing diverse navigation conditions and start-to-goal configurations. The evaluated methods include Deep Deterministic Policy Gradient (DDPG), Proximal Policy Optimization (PPO), Soft Actor–Critic (SAC), and Twin Delayed DDPG (TD3). Experimental field results show that SAC achieves the lowest planning time, reducing the planning time by 127.3%, 24.1%, and 2.52% compared with PPO, TD3, and DDPG, respectively. SAC also achieves the shortest path, reducing the average path length by 20.32%, 8.58%, and 1.90% compared with PPO, DDPG, and TD3, respectively. Moreover, SAC generates smoother control profiles for both the mobile base and the manipulator arm, while TD3 exhibits competitive performance across several navigation metrics. The proposed framework demonstrates the potential of slip-aware RL for coordinated SSMM navigation, providing a practical foundation for improving the safety, energy efficiency, and operational autonomy of mobile manipulators exposed to complex mining environments. Full article

Rapid urbanization, increasing demand variability, and digitalisation of urban infrastructure require intelligent decision-support systems that can improve sustainability, resilience, and operational efficiency in smart city operations. Artificial intelligence (AI) and data-driven optimization offer strong potential for adaptive urban services, including dynamic pricing, demand response, resource allocation, and energy-aware management. However, many reinforcement learning applications still focus mainly on short-term performance while giving limited attention to transparency, fairness, stability, and accountability. This study proposes a trustworthy reinforcement learning framework for AI-driven urban decision-making, using sustainable dynamic pricing and resource optimization as mechanisms for adaptive and responsible decision-making. A custom reinforcement learning environment was developed using historical e-commerce transactional data as a methodological proxy to simulate interactions among demand, resource or inventory availability, service categories, price elasticity, and changing market conditions. Three reinforcement learning algorithms, namely Deep Q-Network, Proximal Policy Optimization, and Advantage Actor–Critic, were evaluated under comparable experimental conditions. Performance was assessed using profitability, decision stability, fairness-oriented pricing behavior, decision consistency, and interpretability. To improve transparency, trajectory-based policy audits and SHapley Additive exPlanations were applied to identify the main factors influencing pricing decisions. The results show that the Deep Q-Network agent achieved the most balanced performance, increasing total profit by 12.58% while recording no unethical price increases under low-demand conditions. Explainability analysis showed that stock or resource levels, demand shifts, and price elasticity were the strongest positive drivers of pricing actions, whereas inventory hoarding and unfavorable price increases reduced decision quality. The findings indicate that reinforcement learning can support sustainable and resilient urban decision-making when optimization objectives are combined with trustworthy AI principles. The proposed framework provides a practical basis for accountable AI-based decision-support systems in smart city operations, including demand-responsive services, resource optimization, sustainable dynamic pricing, and energy-aware management. Full article

As urban development in China shifts toward improving existing areas, the focus of evaluation is moving from availability to quality, yet assessments of the neighborhood built environment and living circles still stop at facility provision. This study decomposes the conversion from spatial supply to need fulfillment into three links—availability, reach-and-visibility, and need fulfillment. Encounterability (E) captures how far a spatial element enters everyday experience through physical reach or visual exposure; perceptual affordance (P) captures how well an encountered element supports six perceptual needs: social interaction, recreation and leisure, aesthetic experience, emotional experience, broad learning, and humanistic enrichment. Taking Xi’an’s historic old city as a typical case, public needs were translated through grounded coding into auditable elements, which trained assessors evaluated at the city, district, and neighborhood levels, with a four-quadrant diagnosis locating the gaps. The results show that, within this context of comparatively rich provision, the principal experiential gaps arise at the encounter and support links: encounterability is similar across levels while perceptual affordance diverges, and the share of synergy categories differs significantly across levels (p = 0.007), forming resource–encounter, node–route, and frequency–support mismatches; the principal mismatch patterns are robust to equal weighting and to moderate shifts in the quadrant thresholds. Basic needs fail on quality and advanced needs fail on encounter and interpretation, pointing to three renewal actions: retrofitting, opening, and interpretation. This study extends evaluation objects from facilities to a fuller spectrum of spatial elements, extends encounter to reach and visibility together, and extends output from ranking to gap localization, offering a low-cost diagnostic tool for the human-centered assessment of the built environment, applicable to living-circle evaluation, urban physical examination, and livability improvement in historic neighborhoods. Full article

Background: Smallholder farmers are at the forefront of climate change, necessitating dynamic, continuous adaptation strategies to safeguard their livelihoods and food systems. Although climate-smart technologies and indigenous knowledge are available, traditional top-down agricultural extension models often fall short in promoting inclusive, community-driven ownership, which is vital for long-term resilience. Objective: This paper investigates how effective knowledge brokering can augment the agricultural extension system—facilitating connections among researchers, extension agents, and smallholder farmers—to maintain climate resilience and foster inclusive, locally led adaptation (LLA). Methods: Drawing on the IDRC–Step Change SCALE project, implemented between August 2025 and May 2026, this study assesses the effect of targeted capacity-building interventions within the extension system. By employing active knowledge-brokering mechanisms such as safe-spaced KIIs, FGDs, co-creation workshops, and capacity-building workshops, the project enabled ongoing, bidirectional learning. This strategy ensured that scientific innovations were adapted into context-specific practices, while indigenous knowledge and local priorities directly influenced ongoing agricultural research. Pre- and post-intervention assessment scores were compared using paired-samples t-tests with exact Wilcoxon signed-rank confirmation, taking the knowledge area as the unit of analysis; differences between training rounds were tested by randomized complete block ANOVA with orthogonal country, phase, and country-by-phase contrasts; and qualitative data from KIIs and FGDs were analyzed thematically. Results: The findings indicate that knowledge brokering transforms the extension system into a responsive foundation for agricultural resilience. Key outcomes include a mean knowledge gain of 53.8 percentage points across the four capacity-strengthening rounds, from 26.5% pre-training to 80.3% post-training (95% CI 51.4 to 56.3; paired t(27) = 44.78, p < 0.001), with improvement recorded in all seven knowledge areas in all four rounds; sustained adoption of climate-adaptive technologies across 1042 participant attendances in Nigeria and Senegal; enhanced participation of marginalized groups, with women accounting for 568 attendances (54.5%) overall, though ranging from 38.9% to 60.2% between rounds; and a clear transition toward self-sustaining, locally led adaptation practices. Conclusions: To effectively confront climate uncertainty, agricultural extension must evolve from a mere information dissemination system into an interactive, knowledge-brokering network. Strengthening this system is a vital, scalable pathway to maintaining inclusive resilience in smallholder agriculture. Full article

Serious games have demonstrated significant potential for supporting learning, cognitive stimulation, and skill development. However, most existing solutions rely predominantly on visual and auditory interaction, while the integration of real tactile experiences remains limited despite their potential to support richer multisensory interaction. Frutopia is a hybrid tangible serious game designed to integrate physical interaction with digital gameplay in order to support tangible interaction and tactile exploration. The game was developed following a structured process that combines the iPlus methodology for educational game design with the Scrum agile framework, enabling the systematic definition, implementation, and refinement of gameplay mechanics, tangible interaction, and usability-oriented features. The resulting system incorporates tangible user interaction through conductive physical objects with different textures connected via a Makey Makey interface, enabling players to control in-game actions through real tactile exploration. The game features progressive maze-based challenges inspired by Ecuadorian cultural environments and representative fruits from Ecuadorian regions, integrating multisensory feedback, gamification techniques, and embodied interaction principles to foster engagement and sensory exploration. The system was implemented using the Godot Engine and evaluated through functionality and usability assessments. Functional validation achieved a success rate of 94.74% across the defined test cases, demonstrating the technical stability of the proposed solution. Additionally, a usability evaluation involving 50 participants was conducted using the Serious Games Usability Evaluation Instrument (SGUEI). The assessment produced a final rating of 90.37%, reflecting favorable perceptions of the interaction quality and overall user experience. The results demonstrate the feasibility of integrating tangible interaction and multisensory feedback within serious game environments and suggest that hybrid tangible interfaces can enrich user engagement and interaction quality. This work contributes to the design and development of hybrid tangible serious games by presenting a structured development workflow and providing preliminary evidence of the technical feasibility and usability of tangible interaction in serious game environments. The proposed system establishes a foundation for future studies involving the intended target population and the evaluation of educational and cognitive outcomes. Full article

This paper aims to evaluate the usability and user experience of ad hoc augmented reality systems in the learning experience of mechanical engineering students, focusing on fluid machinery education. Three mobile augmented reality applications were developed to support teachers in explaining the main parts of an impeller blade and its fluid interaction, integrating computer-aided design (CAD) models with velocity and pressure maps derived from computational fluid dynamics (CFD) simulations. By providing multiple means of representation, these tools were developed to support the explanation of complex 2D concepts without requiring specialized hardware. The obtained results revealed that the usability of the developed applications, assessed through the System Usability Scale (SUS), was remarkably effective. Furthermore, the User Experience Questionnaire (UEQ) showed that the average scores for each evaluation criterion were highly positive, especially in the “Stimulation” and “Novelty” areas. Accurate statistical analyses revealed that students’ feedback was not influenced by users’ familiarity with virtual and augmented reality tools. In conclusion, since no objective learning gains were evaluated, this investigation’s outcomes indicate that the developed applications provide an engaging tool with high usability and positive user experience, framing inclusive education as a fundamental design rationale rather than an empirically demonstrated outcome and laying the groundwork for future studies to objectively measure cognitive impact. Full article

Background/Objectives: Diabetes mellitus is a chronic metabolic disorder characterized by impaired regulation of blood glucose due to defects in insulin secretion, insulin action, or both. Physiological and lifestyle factors vary among individuals. General medicine is not applicable to all patients. In this scenario, personalized medicine for each individual becomes costly. Effective management of continuous glucose levels with accurate insulin dosage is challenging. To overcome this, a digital twin (DT)-based insulin dosage simulator with an individual’s metabolic system is proposed in this work. Methods: Various machine learning techniques, mathematical models of physiology, and risk assessment using probability are used to predict the dynamics of patient-specific glucose–insulin. Parameters such as carbohydrate intake, sleep patterns, medications, and physical activity were incorporated into this model to capture real-world variations in daily life. For glucose–insulin interactions, the Bergman Minimal Model (BMM) is used; for time-of-day variability, a circadian insulin sensitivity model is used; and for predicting metabolic risks, Bayesian risk estimation (BRE) is used, which includes hyperglycemia risk. To enhance transparency and interpret model predictions, explainable artificial intelligence (XAI) methods are employed. Results: The simulation results showed improved glucose prediction accuracy, enhanced detection of hypoglycemia risk, and optimized insulin dosing strategies compared with traditional approaches. Conclusions: Overall, the proposed digital twin model offers a scalable solution using the latest techniques A “Prescriptive Analytical Framework” is provided using the BMM and BRE for personalized diabetes management and decision support for clinicians. Full article

In early-stage projects, incomplete geological data can affect the selection of retaining structures for deep excavations. This paper proposes an adaptive two-layer Case-Based Reasoning (CBR) framework to address this issue. First, a case database was constructed; feature interaction terms were incorporated into the similarity measure to capture the nonlinear coupling among geological parameters, and a Gradient Boosted Decision Tree (GBDT) was employed to achieve an objective, data-driven allocation of feature weights. The first layer implements a gating mechanism based on logical conjunction and adaptive tolerance thresholds, which automatically switches between the two inference paths when information is missing, preventing invalid hard matches; the second layer applies K-means++ clustering and local inductive reasoning to mitigate the biases caused by data sparsity. Experiments demonstrate that, under conditions of parameter incompleteness and noise interference, the method’s Top-3 recommendation accuracy significantly outperforms traditional models and machine learning baseline models and exhibits strong resistance to interference, providing a solid methodological foundation for retaining structure selection in complex data scenarios. Full article

Multi-UAV Cooperative Target Search (MCTS) is a critical task in low-altitude sensing applications, requiring agents to efficiently explore unknown environments under complex constraints. However, traditional search methods are mostly unscalable and perform poorly in dynamic multi-UAV environments. As a promising alternative, Reinforcement Learning (RL) has emerged to overcome these limitations by enabling agents to learn adaptive policies directly from environmental interactions. A key limitation is that current RL methods lack efficient exploration, which is a critical bottleneck preventing UAVs from finding more targets. To address this limitation, we propose a novel method named AEQMIX, which integrates trajectory entropy maximization into QMIX, an advanced Multi-Agent Reinforcement Learning (MARL) method, to encourage efficient exploration. We formulate the MCTS problem as a Decentralized Partially Observable Markov Decision Process (Dec-POMDP) and design a multi-objective reward function. To mitigate the intractability of density estimation in high-dimensional spaces, we employ a nonparametric particle-based entropy estimator to quantify the spatial diversity of UAV trajectories. This entropy estimate is utilized as an intrinsic reward, incentivizing agents to maximize the distance between their trajectories and those of their neighbors. Extensive simulations demonstrate that AEQMIX significantly outperforms baseline reinforcement learning and traditional optimization methods in terms of search rate, coverage efficiency, and collision avoidance. Compared with DNQMIX, AEQMIX improves the search rate and coverage rate by 9.52% and 11.54%, respectively, while reducing the average collision count by 70.59% in the (40 × 40) environment. Full article