Search Results (836)

Broadcasting in Mobile Ad Hoc Networks (MANETs) is significantly challenged by dynamic network topologies. Traditional fuzzy logic-based schemes that often rely on static fuzzy tables and fixed membership functions are limiting their ability to adapt to evolving network conditions. To address these limitations, in this paper, we conduct a comparative study of two innovative broadcasting schemes that enhance adaptability through dynamic fuzzy logic membership functions for the broadcasting problem. The first approach (Model A) dynamically adjusts membership functions based on changing network parameters and fine-tunes the broadcast (BC) versus do-not-broadcast (DNB) ratio. Model B, on the other hand, introduces a multi-profile switching mechanism that selects among distinct fuzzy parameter sets optimized for various macro-level scenarios, such as energy constraints or node density, without altering the broadcasting ratio. Reinforcement learning (RL) is employed in both models: in Model A for BC/DNB ratio optimization, and in Model B for action decisions within selected profiles. Unlike prior fuzzy logic or reinforcement learning approaches that rely on fixed profiles or static parameter sets, our work introduces adaptability at both the membership function and profile selection levels, significantly improving broadcasting efficiency and flexibility across diverse MANET conditions. Comprehensive simulations demonstrate that both proposed schemes significantly reduce redundant broadcasts and collisions, leading to lower network overhead and improved message delivery reliability compared to traditional static methods. Specifically, our models achieve consistent packet delivery ratios (PDRs), reduce end-to-end Delay by approximately 23–27%, and lower Redundancy and Overhead by 40–60% and 40–50%, respectively, in high-density and high-mobility scenarios. Furthermore, this comparative analysis highlights the strengths and trade-offs between reinforcement learning-driven broadcasting ratio optimization (Model A) and parameter-based dynamic membership function adaptation (Model B), providing valuable insights for optimizing broadcasting strategies. Full article

The design of materials with programmable degradation profiles presents a fundamental challenge in pattern recognition across molecular space, requiring the identification of complex structure–property relationships within an exponentially large chemical domain. This paper introduces a novel physics-informed deep learning framework that integrates multi-scale molecular sensing data with reinforcement learning algorithms to enable intelligent characterization and prediction of polymer degradation dynamics. Our method combines three key innovations: (1) a dual-channel sensing architecture that fuses spectroscopic signatures from Graph Isomorphism Networks with temporal degradation patterns captured by transformer-based models, enabling comprehensive molecular state detection across multiple scales; (2) a physics-constrained policy network that ensures sensor measurements adhere to thermodynamic principles while optimizing the exploration of degradation pathways; and (3) a hierarchical signal processing system that balances multiple sensing modalities through adaptive weighting schemes learned from experimental feedback. The framework employs curriculum-based training that progressively increases molecular complexity, enabling robust detection of degradation markers linking polymer architectures to enzymatic breakdown kinetics. Experimental validation through automated synthesis and in situ characterization of 847 novel polymers demonstrates the framework’s sensing capabilities, achieving a 73.2% synthesis success rate and identifying 42 structures with precisely monitored degradation profiles spanning 6 to 24 months. Learned molecular patterns reveal previously undetected correlations between specific spectroscopic signatures and degradation susceptibility, validated through accelerated aging studies with continuous sensor monitoring. Our results establish that physics-informed constraints significantly improve both the validity (94.7%) and diversity (0.82 Tanimoto distance) of generated molecular structures compared with unconstrained baselines. This work advances the convergence of intelligent sensing technologies and materials science, demonstrating how physics-informed machine learning can enhance real-time monitoring capabilities for next-generation sustainable materials. Full article

To address the issue of structural tilting caused by uneven foundation settlement in soft soil areas, this study combined a specific engineering case to conduct numerical simulations of the rectification process for an inclined reinforced concrete building using ABAQUS finite element software. Micropile-raft combined jacking technology was employed, applying staged jacking forces (2400 kN for Axis A, 2200 kN for Axis B, and 1700 kN for Axis C) with precise control through 20 incremental steps. The results demonstrate that this technology effectively halted structural tilting, reducing the maximum inclination rate from 0.51% to 0.05%, significantly below the standard limit. Post-rectification, the peak structural stress decreased by 42%, and displacements were markedly reduced. However, the jacking process led to a notable increase in the column axial forces and directional changes in beam bending moments, reflecting the dynamic redistribution of internal forces. The study confirms that micropile-raft combined jacking technology offers both controllability and safety, while optimized counterforce pile layouts enhance the long-term stability of the rectification system. Based on stress and displacement cloud analysis, a monitoring scheme is proposed, forming an integrated “rectification-monitoring-reinforcement” solution, which provides a technical framework for building rectification in soft soil regions. Full article

Frequency instability poses a significant challenge to the overall stability of islanded microgrid systems. Deep reinforcement learning (DRL)-based intelligent control strategies are drawing considerable attention for their ability to operate without the need for previous system dynamics information and the capacity for autonomous learning. This paper proposes an intelligent frequency secondary compensation solution that divides the traditional secondary frequency control into two layers. The first layer is based on a PID controller and the second layer is an intelligent controller based on DRL. To address the typically extensive training durations associated with DRL controllers, this paper integrates transfer learning, which significantly expedites the training process. This scheme improves control accuracy and reduces computational redundancy. Simulation tests are executed on an islanded microgrid with four distributed generators and an IEEE 13-bus system is utilized for further validation. Finally, the proposed method is validated on the OPAL-RT real-time test platform. The results demonstrate the superior performance of the proposed method. Full article

The current study demonstrates the buckling properties of composite laminates reinforced with MWCNT fillers using a novel higher-order shear and normal deformation theory (HSNDT), which considers the effect of thickness in its mathematical formulation. The hybrid HSNDT combines polynomial and hyperbolic functions that ensure the parabolic shear stress profile and zero shear stress boundary condition at the upper and lower surface of the plate, hence removing the need for a shear correction factor. The plate is made up of carbon fiber bounded together with polymer resin matrix reinforced with MWCNT fibers. The mechanical properties are homogenized by a Halpin–Tsai scheme. The MATLAB R2019a code was developed in-house for a finite element model using C⁰ continuity nine-node Lagrangian isoparametric shape functions. The geometric nonlinear and linear stiffness matrices are derived using the principle of virtual work. The solution of the eigenvalue problem enables estimation of the critical buckling loads. A convergence study was carried out and model efficiency was corroborated with the existing literature. The model contains only seven degrees of freedom, which significantly reduces computation time, facilitating the comprehensive parametric studies for the buckling stability of the plate. Full article

Cantonese Automatic Speech Recognition (ASR) is hindered by tonal complexity, acoustic diversity, and a lack of labelled data. This study proposes a phoneme-aware hierarchical augmentation framework that enhances performance without additional annotation. A Phoneme Substitution Matrix (PSM), built from Montreal Forced Aligner alignments and Tacotron-2 synthesis, injects adversarial phoneme variants into both transcripts and their aligned audio segments, enlarging pronunciation diversity. Concurrently, a semantic-aware SpecAugment scheme exploits wav2vec 2.0 attention heat maps and keyword boundaries to adaptively mask informative time–frequency regions; a reinforcement-learning controller tunes the masking schedule online, forcing the model to rely on a wider context. On the Common Voice Cantonese 50 h subset, the combined strategy reduces the character error rate (CER) from 26.17% to 16.88% with wav2vec 2.0 and from 38.83% to 23.55% with Zipformer. At 100 h, the CER further drops to 4.27% and 2.32%, yielding relative gains of 32–44%. Ablation studies confirm that phoneme-level and masking components provide complementary benefits. The framework offers a practical, model-independent path toward accurate ASR for Cantonese and other low-resource tonal languages. This paper presents an intelligent sensing-oriented modeling framework for speech signals, which is suitable for deployment on edge or embedded systems to process input from audio sensors (e.g., microphones) and shows promising potential for voice-interactive terminal applications. Full article

The effectiveness of an innovative retrofit scheme using near-surface-mounted (NSM) X-shaped CFRP ropes for the strengthening of substandard RC beam–column joints was investigated experimentally. Three large-scale beam–column joint subassemblages were constructed with poor reinforcement details. One specimen was subjected to cyclic lateral loading, exhibited shear failure of the joint region and was used as the control specimen. The other specimens were retrofitted and subsequently subjected to the same history of incremental lateral displacement amplitudes with the control subassemblage. The retrofitting was characterized by low labor demands and included wrapping of NSM CFPR-ropes in the two diagonal directions on both lateral sides of the joint as shear reinforcement. Single or double wrapping of the joint was performed, while weights were suspended to prevent the loose placement of the ropes in the grooves. A significant improvement in the seismic performance of the retrofitted specimens was observed with respect to the control specimen, regarding strength and ductility. The proposed innovative scheme effectively prevented shear failure of the joint by shifting the damage in the beam, and the retrofitted specimens showed a more dissipating hysteresis behavior without significant loss of lateral strength and axial load-bearing capacity. The cumulative energy dissipation capacity of the strengthened specimens increased by 105.38% and 122.23% with respect to the control specimen. Full article

The rapid increase in the deployment of Internet of Things (IoT) sensor networks has led to an exponential growth in data generation and an unprecedented demand for efficient resource management infrastructure. Ensuring end-to-end communication across multiple heterogeneous network domains is crucial to maintaining Quality of Service (QoS) requirements, such as low latency and high computational capacity, for IoT applications. However, limited computing resources at multi-access edge computing (MEC), coupled with increasing IoT network requests during task offloading, often lead to network congestion, service latency, and inefficient resource utilization, degrading overall system performance. This paper proposes an intelligent task offloading and resource orchestration framework to address these challenges, thereby optimizing energy consumption, computational cost, network congestion, and service latency in dynamic IoT-MEC environments. The framework introduces task offloading and a dynamic resource orchestration strategy, where task offloading to the MEC server ensures an efficient distribution of computation workloads. The dynamic resource orchestration process, Service Function Chaining (SFC) for Virtual Network Functions (VNFs) placement, and routing path determination optimize service execution across the network. To achieve adaptive and intelligent decision-making, the proposed approach leverages Deep Reinforcement Learning (DRL) to dynamically allocate resources and offload task execution, thereby improving overall system efficiency and addressing the optimal policy in edge computing. Deep Q-network (DQN), which is leveraged to learn an optimal network resource adjustment policy and task offloading, ensures flexible adaptation in SFC deployment evaluations. The simulation result demonstrates that the DRL-based scheme significantly outperforms the reference scheme in terms of cumulative reward, reduced service latency, lowered energy consumption, and improved delivery and throughput. Full article

With the rapid advancement of urban underground space development, shield tunnel construction has seen a significant increase. However, at the initial launching stage of shield tunnels in shallow-buried weak strata, engineering risks such as face instability and sudden surface settlement frequently occur. At present, there are relatively few studies on the reinforcement technology of the initial section of shield tunnel in shallow soft ground and the evolution law of ground disturbance. This study takes the launching section of the Guanggang New City depot access tunnel on Guangzhou Metro Line 10 as the engineering background. By applying MIDAS/GTS numerical simulation, settlement monitoring, and theoretical analysis, the reinforcement technology at the tunnel face, the spatiotemporal evolution of ground settlement, and the mechanism of soil disturbance transmission during the launching process in muddy soil layer are revealed. The results show that: (1) the reinforcement scheme combining replacement filling, high-pressure jet grouting piles, and soil overburden counterpressure significantly improves surface settlement control. The primary influence zone is concentrated directly above the shield machine and in the forward excavation area. (2) When the shield machine reaches the junction between the reinforced and unreinforced zones, a large settlement area forms, with the maximum ground settlement reaching −26.94 mm. During excavation in the unreinforced zone, ground deformation mainly occurs beneath the rear reinforced section, with subsidence at the crown and uplift at the invert. (3) The transverse settlement trough exhibits a typical Gaussian distribution and the discrepancy between the measured maximum settlement and the numerical and theoretical values is only 3.33% and 1.76%, respectively. (4) The longitudinal settlement follows a trend of initial increase, subsequent decrease, and gradual stabilization, reaching a maximum when the excavation passes directly beneath the monitoring point. The findings can provide theoretical reference and engineering guidance for similar projects. Full article

With the advance of Artificial Intelligence, Deep Neural Networks are widely employed in various sensor-based systems to analyze operational conditions. However, due to the inherently nondeterministic and probabilistic natures of neural networks, the assurance of overall system performance could become a challenging task. In particular, soft errors could weaken the robustness of such networks and thereby threaten the system’s safety. Conventional fault-tolerant techniques by means of hardware redundancy and software correction mechanisms often involve a tricky trade-off between effectiveness and scalability in addressing the extensive design space of Deep Neural Networks. In this work, we propose a Reinforcement-Learning-based approach to protect neural networks from soft errors by addressing and identifying the vulnerable bits. The approach consists of three key steps: (1) analyzing layer-wise resiliency of Deep Neural Networks by a fault injection simulation; (2) generating layer-wise bit masks by a Reinforcement-Learning-based agent to reveal the vulnerable bits and to protect against them; and (3) synthesizing and deploying bit masks across the network with guaranteed operation efficiency by adopting transfer learning. As a case study, we select several existing neural networks to test and validate the design. The performance of the proposed approach is compared with the performance of other baseline methods, including Hamming code and the Most Significant Bits protection schemes. The results indicate that the proposed method exhibits a significant improvement. Specifically, we observe that the proposed method achieves a significant performance gain of at least 10% to 15% over on the test network. The results indicate that the proposed method dynamically and efficiently protects the vulnerable bits compared with the baseline methods. Full article

The design of automobile chassis structures is fundamentally linked to the optimization of mass and structural robustness. While conventional chassis structures predominantly utilize metals, achieving further mass reduction and enhanced rigidity necessitates the adoption of composite sandwich materials, typically comprising carbon fiber-reinforced polymer (C.F.R.P.) laminate skins bonded to an aluminum honeycomb core. This study focuses on presenting a framework methodology for minimizing the mass of a race car chassis by calculating an optimal baseline lamination sequence through the modification of the composite material parameters on either side of the aluminum core, using an optimization algorithm (O.A.), finite element (F.E.) analysis, composite mechanics theory, and failure criteria. Optimal solutions were derived by varying the laminae orientation and sequence parameters under two scenarios: unconstrained and constrained laminae angles. The optimization results indicate that the proposed lamination scheme reduces mass by 12.36 kg (41.66%) compared to the original lamination, with constraints imposed on laminae angles having no significant impact on the ultimate optimal outcome. Full article

With the development of robotics, robots are playing an increasingly critical role in complex tasks such as flexible manufacturing, physical human–robot interaction, and intelligent assembly. These tasks place higher demands on the force control performance of robots, particularly in scenarios where the environment is unknown, making constant force control challenging. This study first analyzes the robot and its interaction model with the environment, highlighting the limitations of traditional force control methods in addressing unknown environmental stiffness. Based on this analysis, a variable admittance control strategy is proposed using the deep deterministic policy gradient algorithm, enabling the online tuning of admittance parameters through reinforcement learning. Furthermore, this strategy is integrated with a quaternion-based nonlinear model predictive control scheme, ensuring coordination between pose tracking and constant-force control and enhancing overall control performances. The experimental results demonstrate that the proposed method improves constant force control accuracy and task execution stability, validating the feasibility of the proposed approach. Full article

In the Karaganda coal basin, deteriorating geomechanical conditions have been observed, including seam disturbances, diminished strength of argillite–aleurolite strata, water ingress, and pronounced floor heave, all of which markedly increase the labor intensity of maintaining developmental headings. The maintenance and operation of these entries for a reference coal yield of 1000 t necessitate 72–75 man-shifts, of which 90–95% are expended on mitigating ground pressure effects and restoring support integrity. Conventional heave control measures—such as relief drifts, slotting, drainage, secondary blasting, and the application of concrete or rock–bolt systems—deliver either transient efficacy or incur prohibitive labor and material expenditures while lacking unified methodologies for predictive forecasting and support parameter design. This study therefore advocates for an integrated framework that synergizes geomechanical characterization, deformation prognosis, and the tailored selection of reinforcement schemes (incorporating both sidewall and floor-anchoring systems with directed preloading), calibrated to seam depth, geometry, and lithological properties. Employing deformation state assessments to optimize reinforcement layouts for floor stabilization in coal mine workings is projected to curtail repair volumes by 30–40% whilst significantly enhancing operational safety, efficiency, and the punctuality of face preparation. Full article

Maritime vision sensing can be applied to maritime unmanned systems to perform search and rescue (SAR) missions under complex marine environments, as multiple unmanned aerial vehicles (UAVs) and unmanned surface vehicles (USVs) are able to conduct vision sensing through the air, the water-surface, and underwater. However, in these vision-based maritime SAR systems, collaboration between UAVs and USVs is a critical issue for successful SAR operations. To address this challenge, in this paper, we propose a long-endurance collaborative SAR scheme which exploits the complementary strengths of the maritime unmanned systems. In this scheme, a swarm of UAVs leverages a multi-agent reinforcement-learning (MARL) method and probability maps to perform cooperative first-phase search exploiting UAV’s high altitude and wide field of view of vision sensing. Then, multiple USVs conduct precise real-time second-phase operations by refining the probabilistic map. To deal with the energy constraints of UAVs and perform long-endurance collaborative SAR missions, a multi-USV charging scheduling method is proposed based on MARL to prolong the UAVs’ flight time. Through extensive simulations, the experimental results verified the effectiveness of the proposed scheme and long-endurance search capabilities. Full article

In a multi-cell network, interference management between adjacent cells is a key factor that determines the performance of the entire cellular network. In particular, in order to control inter-cell interference while providing a high data rate to users, it is very important for the base station (BS) of each cell to appropriately control the transmit power in the downlink. However, as the number of cells increases, controlling the downlink transmit power at the BS becomes increasingly difficult. In this paper, we propose a multi-agent deep reinforcement learning (MADRL)-based transmit power control scheme to maximize the sum rate in multi-cell networks. In particular, the proposed scheme incorporates a long short-term memory (LSTM) architecture into the MADRL scheme to retain state information across time slots and to use that information for subsequent action decisions, thereby improving the sum rate performance. In the proposed scheme, the agent of each BS uses only its local channel state information; consequently, it does not need to receive signal messages from adjacent agents. The simulation results show that the proposed scheme outperforms the existing MADRL scheme by reducing the amount of signal messages exchanged between links and improving the sum rate. Full article