Search Results (1,060)

With the rapid development of digital intelligence, drones can provide many conveniences for people’s lives, especially in executing rescue missions in special areas. When executing rescue missions in remote areas, communication cannot be fully covered. Therefore, to improve the online adaptability of the task chain link in task planning with a complex system structure as the background, a distributed source-task-capability allocation (DSTCA) problem was constructed. The first task chain coordination mechanism scheme was proposed, and a DSTCA architecture based on the task chain coordination mechanism was constructed to achieve the online adaptability of the swarm. At the same time, the existing algorithms cannot achieve this idea, and the DSTCA-CBBA algorithm based on CNP is proposed. The efficiency change, agent score, and time three indicators are evaluated through specific cases. In response to sudden changes in nodes in the task chain link, the maximum spanning tree algorithm is used to reconstruct the task chain link in a short time, thereby completing the mission task assigned to the drone entity. Meanwhile, the experimental results also prove the effectiveness of the proposed algorithm. Full article

To further enhance the intelligent construction of coal mines and improve the control accuracy of hydraulic support displacement straightness, a digital twin control method for hydraulic support displacement has been proposed. First, a dataset related to hydraulic support is established, and a ridge regression prediction model is developed to achieve digital twin-based displacement decision analysis. Next, by analyzing the mechanical structure and displacement principles of the hydraulic supports, a hydraulic cylinder mathematics model is established, leading to the state-space representation of the controlled object. This study focuses on error control during the multi-agent operation of the hydraulic supports, designing a corresponding controller and using discretization methods to verify the consistency of output displacement between followers and leaders. Finally, simulation experiments based on the digital twin model of hydraulic supports are conducted, validating that the hydraulic supports can be controlled in formation according to actual production requirements. The digital twin control method enables the precise adaptive displacement control of hydraulic supports and provides valuable insights for the intelligent construction of mining faces. Full article

Mobile edge computing is envisioned as a prospective technology for supporting time-sensitive and computation-intensive applications in marine vehicle systems. However, the offloading performance is highly impacted by the poor wireless channel. Recently, an Unmanned Aerial Vehicle (UAV) equipped with an Intelligent Reflecting Surface (IRS), i.e., UIRS, has drawn attention due to its capability to control wireless signals so as to improve the data rate. In this paper, we consider a multi-UIRS-assisted marine vehicle system where UIRSs are deployed to assist in the computation offloading of Unmanned Surface Vehicles (USVs). To improve energy efficiency, the optimization problem of the association relationships, computation resources of USVs, multi-UIRS phase shifts, and multi-UIRS trajectories is formulated. To solve the mixed-integer nonlinear programming problem, we decompose it into two layers and propose an integrated convex optimization and deep reinforcement learning algorithm to attain the near-optimal solution. Specifically, the inner layer solves the discrete variables by using the convex optimization based on Dinkelbach and relaxation methods, and the outer layer optimizes the continuous variables based on the Multi-Agent Twin Delayed Deep Deterministic Policy Gradient (MATD3). The numerical results demonstrate that the proposed algorithm can effectively improve the energy efficiency of the multi-UIRS-assisted marine vehicle system in comparison with the benchmarks. Full article

In this study, we investigate the adaptability of artificial agents within a noisy T-maze that use Markov decision processes (MDPs) and successor feature (SF) and predecessor feature (PF) learning algorithms. Our focus is on quantifying how varying the hyperparameters, specifically the reward learning rate (${\alpha }_r$) and the eligibility trace decay rate ($\lambda$), can enhance their adaptability. Adaptation is evaluated by analyzing the hyperparameters of cumulative reward, step length, adaptation rate, and adaptation step length and the relationships between them using Spearman’s correlation tests and linear regression. Our findings reveal that an ${\alpha }_r$ of 0.9 consistently yields superior adaptation across all metrics at a noise level of 0.05. However, the optimal setting for $\lambda$ varies by metric and context. In discussing these results, we emphasize the critical role of hyperparameter optimization in refining the performance and transfer learning efficacy of learning algorithms. This research advances our understanding of the functionality of PF and SF algorithms, particularly in navigating the inherent uncertainty of transfer learning tasks. By offering insights into the optimal hyperparameter configurations, this study contributes to the development of more adaptive and robust learning algorithms, paving the way for future explorations in artificial intelligence and neuroscience. Full article

Intelligent traffic control decision-making has long been a crucial issue for improving the efficiency and safety of the intelligent transportation system. The deficiencies of the Type-1 fuzzy traffic control system in dealing with uncertainty have led to a reduced ability to address traffic congestion. Therefore, this paper proposes a Type-2 fuzzy controller for a single intersection. Based on real-time traffic flow information, the green timing of each phase is dynamically determined to achieve the minimum average vehicle delay. Additionally, in traffic light control, various factors (such as vehicle delay and queue length) need to be balanced to define the appropriate reward. Improper reward design may fail to guide the Deep Q-Network algorithm to learn the optimal strategy. To address these issues, this paper proposes a deep reinforcement learning traffic control strategy combined with Type-2 fuzzy control. The output action of the Type-2 fuzzy control system replaces the action of selecting the maximum output Q-value of the target network in the DQN algorithm, reducing the error caused by the use of the max operation of the target network. This approach improves the online learning rate of the agent and increases the reward value of the signal control action. The simulation results using the Simulation of Urban MObility platform show that the traffic signal optimization control proposed in this paper has achieved significant improvement in traffic flow optimization and congestion alleviation, which can effectively improve the traffic efficiency in front of the signal light and improve the overall operation level of traffic flow. Full article

Introduction: The management of anemia in chronic kidney disease (CKD-An) presents significant challenges for nephrologists due to variable responsiveness to erythropoietin-stimulating agents (ESAs), hemoglobin (Hb) cycling, and multiple clinical factors affecting erythropoiesis. The Anemia Control Model (ACM) is a decision support system designed to personalize anemia treatment, which has shown improvements in achieving Hb targets, reducing ESA doses, and maintaining Hb stability. This study aimed to evaluate the association between ACM-guided anemia management with hospitalizations and survival in a large cohort of hemodialysis patients. Methods: This multi-center, retrospective cohort study evaluated adult hemodialysis patients within the European Fresenius Medical Care NephroCare network from 2014 to 2019. Patients treated according to ACM recommendations were compared to those from centers without ACM. Data on demographics, comorbidities, and dialysis treatment were used to compute a propensity score estimating the likelihood of receiving ACM-guided care. The primary endpoint was hospitalizations during follow-up; the secondary endpoint was survival. A 1:1 propensity score-matched design was used to minimize confounding bias. Results: A total of 20,209 eligible patients were considered (reference group: 17,101; ACM adherent group: 3108). Before matching, the mean age was 65.3 ± 14.5 years, with 59.2% men. Propensity score matching resulted in two groups of 1950 patients each. Matched ACM adherent and non-ACM patients showed negligible differences in baseline characteristics. Hospitalization rates were lower in the ACM group both before matching (71.3 vs. 82.6 per 100 person-years, p < 0.001) and after matching (74.3 vs. 86.7 per 100 person-years, p < 0.001). During follow-up, 385 patients died, showing no significant survival benefit for ACM-guided care (hazard ratio = 0.93; p = 0.51). Conclusions: ACM-guided anemia management was associated with a significant reduction in hospitalization risk among hemodialysis patients. These results further support the utility of ACM as a decision-support tool enhancing anemia management in clinical practice. Full article

With the development of unmanned aircraft and artificial intelligence technology, the future of air combat is moving towards unmanned and autonomous direction. In this paper, we introduce a new layered decision framework designed to address the six-degrees-of-freedom (6-DOF) aircraft within-visual-range (WVR) air-combat challenge. The decision-making process is divided into two layers, each of which is addressed separately using reinforcement learning (RL). The upper layer is the combat policy, which determines maneuvering instructions based on the current combat situation (such as altitude, speed, and attitude). The lower layer control policy then uses these commands to calculate the input signals from various parts of the aircraft (aileron, elevator, rudder, and throttle). Among them, the control policy is modeled as a Markov decision framework, and the combat policy is modeled as a partially observable Markov decision framework. We describe the two-layer training method in detail. For the control policy, we designed rewards based on expert knowledge to accurately and stably complete autonomous driving tasks. At the same time, for combat policy, we introduce a self-game-based course learning, allowing the agent to play against historical policies during training to improve performance. The experimental results show that the operational success rate of the proposed method against the game theory baseline reaches 85.7%. Efficiency was also outstanding, with an average 13.6% reduction in training time compared to the RL baseline. Full article

Backgroud: Salivary gland tumors (SGTs) are rare and diverse neoplasms, presenting significant challenges in diagnosis and management due to their rarity and complexity. Exosomes, lipid bilayer vesicles secreted by almost all cell types and present in all body fluids, have emerged as crucial intercellular communication agents. They play multifaceted roles in tumor biology, including modulating the tumor microenvironment, promoting metastasis, and influencing immune responses. Results: This review focuses on the role of exosomes in SGT, hypothesizing that novel diagnostic and therapeutic approaches can be developed by exploring the mechanisms through which exosomes influence tumor occurrence and progression. By understanding these mechanisms, we can leverage exosomes as diagnostic and prognostic biomarkers, and target them for therapeutic interventions. The exploration of exosome-mediated pathways contributing to tumor progression and metastasis could lead to more effective treatments, transforming the management of SGT and improving patient outcomes. Ongoing research aims to elucidate the specific cargo and signaling pathways involved in exosome-mediated tumorigenesis and to develop standardized techniques for exosome-based liquid biopsies in clinical settings. Conclusions: Exosome-based liquid biopsies have shown promise as non-invasive, real-time systemic profiling tools for tumor diagnostics and prognosis, offering significant potential for enhancing patient care through precision and personalized medicine. Methods like fluorescence, electrochemical, colorimetric, and surface plasmon resonance (SPR) biosensors, combined with artificial intelligence, improve exosome analysis, providing rapid, precise, and clinically valid cancer diagnostics for difficult-to-diagnose cancers. Full article

Quantum many-body systems are of great interest for many research areas, including physics, biology, and chemistry. However, their simulation is extremely challenging, due to the exponential growth of the Hilbert space with system size, making it exceedingly difficult to parameterize the wave functions of large systems by using exact methods. Neural networks and machine learning, in general, are a way to face this challenge. For instance, methods like tensor networks and neural quantum states are being investigated as promising tools to obtain the wave function of a quantum mechanical system. In this tutorial, we focus on a particularly promising class of deep learning algorithms. We explain how to construct a Physics-Informed Neural Network (PINN) able to solve the Schrödinger equation for a given potential, by finding its eigenvalues and eigenfunctions. This technique is unsupervised, and utilizes a novel computational method in a manner that is barely explored. PINNs are a deep learning method that exploit automatic differentiation to solve integro-differential equations in a mesh-free way. We show how to find both the ground and the excited states. The method discovers the states progressively by starting from the ground state. We explain how to introduce inductive biases in the loss to exploit further knowledge of the physical system. Such additional constraints allow for a faster and more accurate convergence. This technique can then be enhanced by a smart choice of collocation points in order to take advantage of the mesh-free nature of the PINN. The methods are made explicit by applying them to the infinite potential well and the particle in a ring, a challenging problem to be learned by an artificial intelligence agent due to the presence of complex-valued eigenfunctions and degenerate states Full article

Artificial intelligence (AI) requires the provision of learnable data to successfully deliver requisite prediction power. In this article, it is demonstrable that standard physico-chemical parameters, while useful, are insufficient for the development of powerful antimicrobial prediction algorithms. Initial models that focussed solely on the values extractable from the knowledge on electrotopological, structural and constitutional descriptors did not meet the acceptance criteria for classifying antimicrobial activity. In contrast, efforts to conceptually define the diametric opposite of an antimicrobial compound helped to advance the predicted category as a learnable trait. Remarkably, the inclusion of ligand–receptor interactions using the ability of the molecules to stimulate transmembrane TAS2Rs receptor helped to increase the ability to distinguish the antimicrobial molecules from the inactive ones, confirming the hypothesis of a predictor–predicted synergy behind bitterness psychophysics and antimicrobial activity. Therefore, in a single bio–endogenic psychophysical vector representation, this manuscript helps demonstrate the contribution to parametrization and the identification of relevant chemical manifolds for molecular design and (re-)engineering. This novel approach to the development of AI models accelerated molecular design and facilitated the selection of newer, more powerful antimicrobial agents. This is especially valuable in an age where antimicrobial resistance could be ruinous to modern health systems. Full article

Advancements in technology that can reshape educational paradigms, with Extended Reality (XR) have a pivotal role. This paper introduces an interactive XR intelligent assistant featuring a virtual teacher that interacts dynamically with PowerPoint presentations using OpenAI’s ChatGPT API. The system incorporates Azure Cognitive Services for multilingual speech-to-text and text-to-speech capabilities, custom lip-syncing solutions, eye gaze, head rotation and gestures. Additionally, panoramic images can be used as a sky box giving the illusion that the AI assistant is located at another location. Findings from three pilots indicate that the proposed technology has a lot of potential to be used as an additional tool for enhancing the learning process. However, special care must be taken into privacy and ethical issues. Full article

Recently, the high proportion of methicillin-resistant Staphylococcus aureus infections worldwide has highlighted the urgent need for novel antibiotics to combat this crisis. The recent progress in computational techniques for use in health and medicine, especially artificial intelligence (AI), has created new and potential approaches to combat antibiotic-resistant bacteria, such as repurposing existing drugs, optimizing current agents, and designing novel compounds. Halicin was previously used as a diabetic medication, acting as a c-Jun N-terminal protein kinase (JNK) inhibitor, and has recently demonstrated unexpected antibacterial activity. Although previous efforts have highlighted halicin’s potential as a promising antibiotic, evidence regarding its effectiveness against clinical strains remains limited, with insufficient proof of its clinical applicability. In this study, we sought to investigate the antibacterial activity of halicin against MRSA clinical strains to validate its clinical applicability, and a C. elegans model infected by MRSA was employed to evaluate the in vivo effect of halicin against MRSA. Our findings revealed the antibacterial activity of halicin against methicillin-resistant S. aureus clinical strains with MICs ranging from 2 to 4 µg/mL. Our study is also the first work to evaluate the in vivo effect of halicin against S. aureus using a C. elegans model, supporting its further development as an antibiotic. Full article

Innovative and sustainable food preservation techniques are vital for enhancing food quality, safety, and reducing environmental impact. In this review, the methods aligned with sustainability goals are explored, focusing on their mechanisms, applications, and environmental benefits. It examines non-thermal technologies such as cold plasma, pulsed light technology, high-pressure processing (HPP), pulsed electric fields (PEFs), and ultraviolet (UV) radiation, which effectively inactivate microbes while preserving nutritional and sensory qualities. Natural preservatives, including plant extracts, microbial agents, and enzymes, are highlighted as eco-friendly alternatives to synthetic chemicals, supporting clean label initiatives. Advanced packaging solutions, such as biodegradable materials, intelligent packaging systems, and modified atmosphere packaging (MAP), are assessed for their role in reducing plastic waste, maintaining product quality, and extending shelf life. The review uses life cycle analyses to evaluate these techniques’ environmental impact, considering factors like energy consumption, greenhouse gas emissions, water use, and waste reduction. It also explores the potential of emerging technologies, such as plasma-activated water (PAW) and nanotechnology, to further enhance sustainability. By identifying research gaps and discussing industry challenges, the review calls for innovation and the broader adoption of these practices to promote food security, improve public health, and foster a more sustainable and resilient food system Full article

Microgrids have emerged as a key element in the transition towards sustainable and resilient energy systems by integrating renewable sources and enabling decentralized energy management. This systematic review, conducted using the PRISMA methodology, analyzed 74 peer-reviewed articles from a total of 4205 studies published between 2014 and 2024. This review examines critical areas such as reinforcement learning, multi-agent systems, predictive modeling, energy storage, and optimization algorithms—essential for improving microgrid efficiency and reliability. Emerging technologies like artificial intelligence (AI), the Internet of Things, and flexible power electronics are highlighted for enhancing energy management and operational performance. However, challenges persist in integrating AI into complex, real-time control systems and managing distributed energy resources. This review also identifies key research opportunities to enhance microgrid scalability, resilience, and efficiency, reaffirming their vital role in sustainable energy solutions. Full article

The challenge of optimizing the distribution path for location logistics in the cold chain warehousing of fresh agricultural products presents a significant research avenue in managing the logistics of agricultural products. The goal of this issue is to identify the optimal location and distribution path for warehouse centers to optimize various objectives. When deciding on the optimal location for a warehousing center, various elements like market needs, supply chain infrastructure, transport expenses, and delivery period are typically taken into account. Regarding the routes for delivery, efficient routes aim to address issues like shortening the overall driving distance, shortened travel time, and preventing traffic jams. Targeting the complex issue of optimizing the distribution path for fresh agricultural products in cold chain warehousing locations, a blend of this optimization challenge was formulated, considering factors like the maximum travel distance for new energy trucks, the load capacity of the vehicle, and the timeframe. The Location-Route Problem with Time Windows (LRPTWs) Mathematical Model thoroughly fine-tunes three key goals. These include minimizing the overall cost of distribution, reducing carbon emissions, and mitigating the depletion of fresh agricultural goods. This study introduces a complex swarm intelligence optimization algorithm (MODRL-SIA), rooted in deep reinforcement learning, as a solution to this issue. Acting as the decision-maker, the agent processes environmental conditions and chooses the optimal course of action in the pool to alter the environment and achieve environmental benefits. The MODRL-SIA algorithm merges a trained agent with a swarm intelligence algorithm, substituting the initial algorithm for decision-making processes, thereby enhancing its optimization efficiency and precision. Create a test scenario that mirrors the real situation and perform tests using the comparative algorithm. The experimental findings indicate that the suggested MODRL-SIA algorithm outperforms other algorithms in every computational instance, further confirming its efficacy in lowering overall distribution expenses, carbon emissions, and the depletion of fresh produce in the supply chain of fresh agricultural products. Full article