Search Results (816)

Addressing the challenge of high-precision time-coordinated path planning for manned and unmanned aerial vehicle (UAV) clusters operating in complex dynamic environments during missions like high-level autonomous coordination, this paper proposes a reinforcement learning-based Adaptive Grey Wolf Optimizer (RL-GWO) method. We formulate a comprehensive multi-objective cost function integrating total flight distance, mission time, time synchronization error, and collision penalties. To solve this model, we design multiple improved GWO strategies and employ a Q-Learning framework for adaptive strategy selection. The RL-GWO algorithm is embedded within a dual-layer “global planning + dynamic replanning” framework. Simulation results demonstrate excellent convergence and robustness, achieving second-level time synchronization accuracy while satisfying complex constraints. In dynamic scenarios, the method rapidly generates safe evasion paths while maintaining cluster coordination, validating its practical value for heterogeneous UAV operations. Full article

This paper presents a kinematics-constrained grid-based path planning algorithm that generates real-time, safe, and executable trajectories, thereby enhancing the performance and reliability of autonomous vehicle parking systems. The grid resolution adapts to the minimum turning radius and steering limits, ensuring feasible motion primitives. The cost function integrates path efficiency, direction-switching penalties, and collision risk to ensure smooth and feasible maneuvers. A cubic spline refinement produces curvature-continuous trajectories suitable for vehicle execution. Simulation and experimental results demonstrate that the proposed method achieves collision-free and curvature-bounded paths with significantly reduced computation time and improved maneuver smoothness compared with conventional A* and Hybrid A*. In both structured and dynamic parking environments, the planner consistently maintained safe clearance and stable tracking performance under variations in vehicle geometry and velocity. These results confirm the robustness and real-time feasibility of the proposed approach, effectively unifying kinematic feasibility, safety, and computational efficiency for practical autonomous parking systems. Full article

Urban drone operations are exposed to unpredictable risks, including engine failure and deliberate signal interference. A recent and ongoing disruption in Jeddah, Saudi Arabia, has seen widespread GPS spoofing that misleads devices by hundreds of kilometers, illustrating how fragile unmanned aerial vehicle (UAV) operations can become when over-reliant on GNSS-based navigation. Such disruptions highlight the urgent need for contingency planning in drone traffic management systems. This study introduces a safety-aware pre-flight path planning framework that proactively integrates emergency landing and GPS fallback options into UAV trajectory pre-flight planning. The planner considers proximity to predesignated emergency landing zones, communication coverage, and airspace restrictions, enabling UAVs to safely complete their operations. The approach is evaluated across realistic mission profiles such as delivery, inspection, and surveillance. Results show that the planner successfully maintains mission feasibility while embedding emergency readiness throughout each flight. This work contributes toward safer, failure-resilient drone integration in urban airspace, ensuring that contingency plans are proactively incorporated into path planning before the failure even occurs. Full article

In complex scenarios, such as industrial parks and underground parking lots, efficient and safe autonomous navigation is essential for driverless operation and automatic parking. However, conventional modular navigation methods, especially the A* algorithm, suffer from excessive node traversal and short paths that bring vehicles dangerously close to obstacles. To address these issues, we propose an autonomous navigation approach based on a layered terrain cost map and a nonlinear predictive control model, which ensures real-time performance, safety, and reduced computational cost. The global planner applies a two-stage A* strategy guided by the hierarchical terrain cost map, improving efficiency and obstacle avoidance, while the local planner combines linear interpolation with nonlinear model predictive control to adaptively adjust the vehicle speed under varying terrain conditions. Experiments conducted in simulated and real underground parking scenarios demonstrate that the proposed method significantly improves the computational efficiency and navigation safety, outperforming the traditional A* algorithm and other baseline approaches in overall performance. Full article

We present an experimentally validated, engineering-oriented framework for the design and operation of pin-to-water (PTW) atmospheric discharges to produce hydrogen peroxide (H₂O₂) on demand. Motivated by industrial needs for safe, point-of-use oxidant supply, we combine time-resolved diagnostics (FTIR, OES), liquid-phase analysis (ion chromatography, pH, conductivity), and coupled plasma-chemistry/fluid simulations to link plasma state to aqueous H₂O₂ yield. Under the tested conditions (14.3 kHz, 0.2 kW; electrode to quartz wall distance 12–14 mm; coolant setpoints 0–40 °C), H₂O₂ concentration follows a reproducible non-monotonic trajectory: rapid accumulation during the early treatment (typical peak at ~15–25 min), followed by decline with continued operation. The decline coincides with a robust vibrational-temperature (T_vib) threshold near ~4900 K measured from N₂ emission, and with concurrent NO_X accumulation and bulk acidification. Global chemistry modeling and Fluent flow fields reproduce the observed trend and show that both vibrational excitation (kinetics) and convective transport (mass/heat transfer) determine the productive time window. Based on these results, we formulate practical design rules—electrode gap (power density), discharge current control, thermal/flow management, water quality, and OES-based T_vib monitoring with an automated stop rule—that maximize H₂O₂ yield while avoiding NO_X-dominated suppression. The study provides a clear path for transforming mechanistic plasma insights into deployable, industrial H₂O₂ generator designs. Full article

With the rapid advancement of Autonomous Mobile Robots (AMRs) in industrial automation and intelligent logistics, achieving efficient and safe path planning in dynamic environments has become a critical challenge. These environments require robots to perceive complex scenarios and adapt their motion strategies accordingly, often under real-time constraints. Existing methods frequently struggle to balance efficiency, responsiveness, and safety, especially in the presence of continuously changing dynamic obstacles. While Model Predictive Control (MPC) and Deep Reinforcement Learning (DRL) have each shown promise in this domain, they also face limitations when applied individually—such as high computational demands or insufficient environmental exploration. To address these challenges, we propose a hybrid path planning framework that integrates an optimized DRL algorithm with MPC. We replace the Actor’s output with a learnable noisy linear layer whose mean and scale parameters are optimized jointly with the policy via backpropagation, thereby enhancing exploration while preserving training stability. TD3 produces stepwise control commands that evolve into a short-horizon reference trajectory, while MPC refines this trajectory through constraint-aware optimization to ensure timely obstacle avoidance. This complementary process combines TD3′s learning-based adaptability with MPC’s reliable local feasibility. Extensive experiments conducted in environments with varying obstacle dynamics and densities demonstrate that the proposed method significantly improves obstacle avoidance success rate, trajectory smoothness, and path accuracy compared to traditional MPC, standalone DRL, and other hybrid approaches, offering a robust and efficient solution for autonomous navigation in complex scenarios. Full article

Hospital fraud detection has often relied on periodic audits that miss evolving, internet-mediated patterns in electronic claims. An artificial intelligence and machine learning pipeline is being developed that is leakage-safe, imbalance aware, and aligned with operational capacity for large healthcare datasets. The preprocessing stack integrates four tables, engineers 13 features, applies imputation, categorical encoding, Power transformation, Boruta selection, and denoising autoencoder representations, with class balancing via SMOTE-ENN evaluated inside cross-validation folds. Eight algorithms are compared under a fraud-oriented composite productivity index that weighs recall, precision, MCC, F1, ROC-AUC, and G-Mean, with per-fold threshold calibration and explicit reporting of Type I and Type II errors. Multilayer perceptron attains the highest composite index, while CatBoost offers the strongest control of false positives with high accuracy. SMOTE-ENN provides limited gains once representations regularize class geometry. The calibrated scores support prepayment triage, postpayment audit, and provider-level profiling, linking alert volume to expected recovery and protecting investigator workload. Situated in the Future Internet context, this work targets internet-mediated claim flows and web-accessible provider registries. Governance procedures for drift monitoring, fairness assessment, and change control complete an internet-ready deployment path. The results indicate that disciplined preprocessing and evaluation, more than classifier choice alone, translate AI improvements into measurable economic value and sustainable fraud prevention in digital health ecosystems. Full article

Unmanned surface vehicles (USVs) rely on multi-sensor perception, such as radar, LiDAR, GPS, and vision, to ensure safe and efficient navigation in complex maritime environments. Traditional ant colony optimization (ACO) for path planning, however, suffers from premature convergence, slow adaptation, and poor smoothness in cluttered waters, while the dynamic window approach (DWA) without global guidance can become trapped in local obstacle configurations. This paper presents a sensor-oriented hybrid method that couples an improved ACO for global route planning with an enhanced DWA for local, real-time obstacle avoidance. In the global stage, the ACO state–transition rule integrates path length, obstacle clearance, and trajectory smoothness heuristics, while a cosine-annealed schedule adaptively balances exploration and exploitation. Pheromone updating combines local and global mechanisms under bounded limits, with a stagnation detector to restore diversity. In the local stage, the DWA cost function is redesigned under USV kinematics to integrate velocity adaptability, trajectory smoothness, and goal-deviation, using obstacle data that would typically originate from onboard sensors. Simulation studies, where obstacle maps emulate sensor-detected environments, show that the proposed method achieves shorter paths, faster convergence, smoother trajectories, larger safety margins, and higher success rates against dynamic obstacles compared with standalone ACO or DWA. These results demonstrate the method’s potential for sensor-based, real-time USV navigation and collision avoidance in complex maritime scenarios. Full article

Dermatopathology has rapidly advanced due to the implementation of deep learning models and artificial intelligence (AI). From convolutional neural networks (CNNs) to transformer-based foundation models, these systems are now capable of accurate whole-slide analysis and multimodal integration. This review synthesizes the most recent advents of deep-learning architecture and synthesizes its evolution from first-generation CNNs to hybrid CNN-transformer systems to large-scale foundational models such as Paige’s PanDerm AI and Virchow. Herein, we examine performance benchmarks from real-world deployments of major dermatopathology deep learning models (DermAI, PathAssist Derm), as well as emerging next-generation models still under research and development. We assess barriers to clinical workflow adoption such as dataset bias, AI interpretability, and government regulation. Further, we discuss potential future research directions and emphasize the need for diverse, prospectively curated datasets, explainability frameworks for trust in AI, and rigorous compliance to Good Machine-Learning-Practice (GMLP) to achieve safe and scalable deep learning dermatopathology models that can fully integrate into clinical workflows. Full article

Next-generation cancer immunotherapy increasingly combines tumor-targeting antibodies or antibody–drug conjugates (ADCs) with immune effector cells to enhance therapeutic precision. However, many existing approaches rely on genetic modification or complex manufacturing, limiting their clinical scalability and rapid deployment. To address this issue, we developed an antibody capture protein (ACP)-based surface engineering platform that enables the rapid, reversible, and non-genetic functionalization of NK cells with therapeutic antibodies or ADCs. This approach uses a DMPE-PEG-lipid conjugate to anchor thiolated protein A (ACP) to the NK cell membrane via hydrophobic insertion, thereby stably and selectively binding to the Fc region of IgG molecules. Using this strategy, we developed ACP-modified NK cells (AC-NKs) that can selectively capture therapeutic antibodies (trastuzumab (TZ), trastuzumab-emtansine (T-DM1), and sacituzumab (SZ)) pre-bound to each target antigen on tumor cells and induce antigen-specific cytotoxic responses. The resulting AC-NKs exhibited enhanced tumor recognition and cytotoxicity against HER2-positive and Trop-2-positive cancer cells in vitro. Compared with conventional combination therapies, AC-NKs enhanced immune activation, as demonstrated by effective delivery of cytotoxic agents, enhanced cancer cell engagement, and upregulation of CD107a expression. Notably, the system supports multiple antigen targeting and tunable antibody loading, enabling adaptation to tumor heterogeneity and resistant phenotypes. This platform might also provide a simple, scalable, and safe method for rapidly developing programmable immune cell therapies without genetic modification. Its versatility supports multi-antigen targeting and broad applicability across NK and T cell therapies, offering a promising path toward personalized, off-the-shelf chemoimmunotherapy. Full article

Unmanned aerial vehicles (UAVs) operating in uncertain environments must plan safe and efficient trajectories while avoiding obstacles. This work addresses this challenge by formulating UAV path planning as a stochastic optimal control problem using covariance control. The objective is to generate a closed-loop guidance policy that steers both the mean and covariance of the UAV’s state toward a desired target distribution while ensuring probabilistic collision avoidance with ellipsoidal obstacles. The stochastic problem is convexified and reformulated as a sequence of deterministic optimization problems, enabling efficient computation even from coarse initial guesses. Simulation results demonstrate that the proposed method successfully produces robust trajectories and feedback policies that satisfy chance constraints on obstacle avoidance and reach the target with prescribed statistical characteristics. Full article

Doxorubicin (Dox) is considered one of the most effective treatments for triple-negative breast cancer (TNBC); however, it can cause limited efficacy, recurrence/chemoresistance, and cardiotoxicity. Using a murine preclinical MDA-MB-231 TNBC model, we determined that targeting the substance P/neurokinin-1 receptor signaling axis can increase efficacy of the standard-of-care treatment currently used for TNBC, i.e., doxorubicin (Dox), while also attenuating Dox-induced, cardiotoxicity in TNBC. The in vivo studies outlined in this manuscript validate aprepitant (AP), a neurokinin-1 receptor antagonist, as a safe, dual-purpose chemosensitizer and cardioprotectant. These studies provide preclinical evidence supporting further evaluation of a continuous daily AP regimen in TNBC models in combination with Dox, laying the groundwork for future investigations into its safety, dosing, and potential clinical application. Because AP is already FDA-approved for single-dose anti-emetic use, repurposing it for chronic administration offers a rapid path to clinical translation, with the potential to redefine chemotherapy paradigms and tangibly improve survival and quality of life in TNBC. Full article

To address low threat avoidance efficiency and poor global path adaptability in UAV path planning under threatening environments, this paper proposes a hybrid A*-Artificial Potential Field (APF) path planning method based on spatio-temporal grid optimization. First, a new global fine-grained spatio-temporal grid system is developed by integrating advantages of GeoSOT binary encoding and BeiDou grid location code subdivision rules, enabling unified modeling of complex spatio-temporal environments. Ground threat and maze scenarios are constructed for verification. Second, traditional A* and APF algorithms are improved: the A* algorithm is enhanced with threat costs, dynamic neighborhood search, and local backtrack mechanisms to address low efficiency and incompatibility with threat avoidance; the APF algorithm is optimized with a dual gravitational field collaboration mechanism and distance-parameter-based repulsive field model to overcome local minima and unreachable goals. Finally, a sliding window-driven path association model achieves seamless collaboration between global and local planning. Experimental results show the proposed method outperforms traditional algorithms in comprehensive performance, with the improved A* algorithm excelling in path length, computation time, threat value, and search nodes, and the improved APF algorithm achieving complete safe obstacle avoidance in dynamic environments. The collaborative mechanism effectively handles complex scenarios. Full article

After an aero-engine shuts down, the high temperature within the core flow path prevents conventional borescope probes from performing immediate internal inspections due to their limited thermal resistance, thereby constraining rapid turnaround capabilities for aircraft. To address this challenge, this study proposes an active cooling strategy using coolant flow to keep the probe within a safe temperature range. Three cooling structures incorporating pressure-drop modules—annular, annular-slit, and round-hole configurations—were designed and numerically investigated to assess the effects of geometric parameters and coolant properties (temperature, pressure, nitrogen mixing ratio) on cooling performance. The results demonstrate that the round-hole structure with a 1.0 mm diameter achieves optimal cooling, maintaining an average probe mirror temperature of 286.2 K under coolant conditions of 285 K and 0.5 MPa. Cooling efficiency exhibits a strong linear negative correlation with coolant temperature, while its relationship with pressure is highly structure-dependent. Nitrogen doping significantly improves the heat transfer capacity of the coolant. The implemented three-stage pressure-drop module performs consistently, with the pressure loss per stage determined solely by the inlet pressure. This study provides valuable insights and a theoretical foundation for the design of high-temperature-resistant borescope equipment capable of operating in the harsh environments of aero-engines. Full article

Smart routing has emerged as a critical enabler of sustainable shipping, addressing the growing demand for energy-efficient, safe, and adaptive vessel navigation in both maritime and inland waterborne transport. This review examines the current landscape of trajectory optimization approaches by analyzing selected peer-reviewed studies and categorizing them into six thematic areas: AI/ML-based prediction, optimization and path planning algorithms, data-driven methods using AIS and GIS, weather routing and environmental modeling, digital platforms and decision support systems, and hybrid or rule-based frameworks for autonomous navigation. The analysis highlights recent advances in deep learning for trajectory forecasting, multi-objective and heuristic optimization techniques, and the use of real-time environmental data in routing decisions. Supplemental review using Scopus-based topic mapping confirms the centrality of integrated digital strategies, high-performance computing, and physics-informed modeling in emerging research. Despite notable progress, the field remains fragmented, with limited real-time integration, underexplored regulatory alignment, and a lack of explainable AI applications. The review concludes by outlining future directions, including the development of hybrid and interpretable optimization frameworks, and expanding research tailored to inland navigation with its distinct operational challenges. These insights aim to support the design of next-generation navigation systems that are robust, intelligent, and environmentally compliant. Full article