Search Results (5,783)

Lane detection is a core perception task for Advanced Driver Assistance Systems (ADAS) and autonomous driving. Current methods struggle to balance accuracy, model complexity and inference efficiency: high-precision models rely on heavy modules with excessive computation, while lightweight ones suffer from weak feature extraction and low precision. To alleviate this inherent trade-off, we propose YOLOv8n-LaneDG based on YOLOv8n-seg. We design a dual-path gated fusion block to strengthen lane features and an efficient upsampling convolution block to reduce computational overhead, and we further design a weighted continuity loss to preserve lane structural integrity. Evaluated on TuSimple, our method lifts mAP@0.5 from 74.3% to 95.2%. It outperforms mainstream lightweight models and matches heavy YOLOv8s-seg with far fewer parameters, delivering a high-precision, deployable lane detection solution for vehicle-end platforms. Full article

Old urban areas face severe spatial supply–demand contradictions as aboveground space nears saturation while public service demand grows. Developing underground public spaces offers a key solution, yet fragmented development limits overall benefits, necessitating coordinated aboveground–underground development to achieve urban renewal and sustainability. Taking Shanghai’s old urban areas as a case, this study constructs an evaluation system with 17 aboveground indicators across 5 dimensions and 9 underground indicators across 3 dimensions. Using the combination of AHP–entropy weight method for weighting, the coupling coordination degree model, and the obstacle degree model, this study identifies the temporal evolution trends in the development levels of the two systems, the characteristics of their coupling coordination stages, and the main constraining factors from 1995 to 2025. The results show: (1) Both systems have shown continuous growth, with underground public space accelerating its development after 2010, and by 2015, it had nearly caught up with the aboveground system in the time-series projection results; (2) The D value of coupling coordination has increased from 0.2431 to 0.9532, experiencing three stages of low coupling coordination, general coupling coordination, and high coupling coordination; (3) The obstacle factors have shown a dynamic evolution path from scale shortage to morphological complexity, and then to the synergy of the aboveground and underground morphologies. In the higher coupling coordination stage, the length of the aboveground bus lines and the landscape shape index of the underground became the dominant obstacles. This study provides a quantitative basis for coordinated planning and decision-making in the renewal of old urban areas. Full article

Fracture evolution of rock–backfill composites (RBCs) under complex loading–unloading and dynamic disturbances is critical for stope stability in deep backfill mining. Using PFC3D, this study constructs numerical models of RBCs to investigate this process, considering burial depths (500, 1000, 1500, 2000 m), interface angles (IA: 60°, 90°), and cement–tailings ratios (CTR—1:4, 1:8), while replicating true triaxial paths and blasting impacts. Systematic analysis of mesoscopic crack quantity, spatiotemporal distribution, and multiscale fracturing reveals that shear cracks dominate damage, with crack counts evolving in stages as strain increases. With greater depth, the number of propagation stages and growth rate inflection points shift systematically. During mining–filling disturbance, crack quantity negatively correlates with depth but turns positive during late static loading beyond 70% peak stress. Spatial crack distribution is synergistically controlled by IA, CTR, and depth. For IA 60°, shear crack angles spread broadly yet concentrate at 50–70°; for IA 90°, they are near-axial, concentrated at 80–90°. The synergistic process progresses through microscopic initiation, mesoscopic accumulation, and macroscopic instability. In terms of failure modes, IA 60° exhibits shear failure along the cemented interface plus tensile fracturing in rock, while IA 90° shows combined diagonal shear and axial tension. Higher CTR yields more extensive fracture networks in backfill, indicating superior synergistic bearing capacity. Full article

We apply the free energy principle to free markets by treating the Market as a random dynamical system with an attracting set, i.e., some characteristic states. This licenses a normal form for stochastic dynamics that inherits from the Helmholtz–Hodge decomposition. Equipped with this functional form—and a suitable parameterization—one can create a generative model of fluctuations in the value of assets and accompanying indicator variables. This affords the opportunity for prospective (ex ante) prediction, scenario modelling and forecasting that could, in principle, be applied to any complex dynamical system exhibiting stochastic chaos. Here, we illustrate the application to portfolio management—in the context of financial services—and use the (posterior) predictive densities over future paths to evaluate the expected free energy that underwrites active inference. In this application, active inference reduces to risk-sensitive control, which can be used to model the optimal decision-making of an agent or investor. In this setting, an investor is characterized by their prior preferences for a high rate of return under drawdown constraints. Using numerical studies and historical financial data, we quantify the improvement in portfolio management, relative to baseline policies. Full article

Public Fire Emergency Literacy (PFEL) is a critical determinant that fundamentally shapes individual survivability and the efficacy of societal safety governance—particularly amid intensifying fire risks characterized by growing complexity and destructive potential. Traditional single-perspective or linear analytical frameworks fail to capture PFEL’s multi-causal and configurational nature. To address this gap, this study integrates the Emergency Management Life Cycle Theory with the WSR system approach to measure PFEL across 36 major Chinese cities using 3872 survey responses and explores its multidimensional attributes and generative mechanisms via multiple methods (Delphi technique, entropy weighting, GIS spatial analysis, multiple regression, fsQCA). Key findings: (1) PFEL exhibits a pronounced cognition precedes capability gap with marked demographic heterogeneity; (2) PFEL displays a distinct “Central > Northeast > East > West” hierarchical gradient and notable spatial disequilibrium—core cities in the Central region (e.g., Wuhan and Zhengzhou) outperform traditional first-tier metropolises in the East; (3) physical infrastructure, organizational management, and individual cognition jointly shape PFEL with significant regional heterogeneity—participation in emergency training emerges as the most potent driver; (4) configurational path analysis indicates that PFEL is determined by a complex conjunctive causal mechanism formed by the combined effects of physical facilities, organizational management and individual initiative. Policy implications cover strengthened public emergency response capacity, differentiated policies, and multi-factor collaborative governance. The findings offer theoretical references and practical guidance for improving public resilience systems and emergency resource allocation. Full article

Traditional target-oriented task allocation and path planning methods often struggle to balance real-time responsiveness to dynamic task alterations with multi-UAV cooperative operations in complex urban environments under meteorological disturbances. To address these challenges, this paper proposes a dynamic path planning method for low-altitude Unmanned Aerial Vehicles (UAVs) tailored for urban inspection missions. Integrating an improved Discrete Particle Swarm Optimization (DPSO) algorithm with a decoupled Soft Actor–Critic (SAC) and B-spline smoothing framework, the proposed approach optimizes upper-level task allocation and lower-level trajectory planning within a 3D joint meteorological-obstacle feasible region. For task scheduling, an improved DPSO algorithm embedded with a spatial topology guidance mechanism dynamically coordinates task flows governed by Poisson processes. effectively addressing the spatial blindness and fragmented route assignments typical of conventional discrete optimization. Concurrently, local trajectory replanning executes receding-horizon spatial exploration via SAC deep reinforcement learning, followed by B-spline refinement to strictly enforce UAV kinematic limits, systematically bridging continuous-space exploration with low-level flight compliance to overcome the kinematic infeasibility common in pure learning-based models. Validated through extensive Monte Carlo comparative simulations ($N=50$) and further verified by a high-fidelity AirSim dynamic physics engine, the results demonstrate that: (1) The improved DPSO constrains the average response latency for high-priority emergency tasks to within 40 s even under 50 concurrent dynamic tasks. (2) The lower-level replanning achieves an average execution time of $3.60\pm 0.18 \mathrm{s}$ and a path success rate of $95.8\pm 1.2\%$, in numerical tests, while maintaining a 96.2% kinematic feasibility rate under realistic rigid-body inertia and aerodynamic drag. While the current 3.60 s latency presents a potential bottleneck for millisecond-level dynamic emergency reactions, the developed framework offers a highly effective and safe closed-loop dynamic scheduling solution that lays a rigorous computational foundation for low-altitude urban inspections. Full article

Background: Preventing mobility-related loss of independence (LoI) is a critical public health priority. While the drivers of LoI are complex, this study examines how personal, social, and environmental factors influence these outcomes to identify actionable preventive targets. We applied the International Classification of Functioning, Disability, and Health (ICF) framework to examine these pathways across racial and ethnic groups. Methods: Using 2023 National Health and Aging Trends Study (NHATS) data (N = 7106), we conducted path analyses among non-Hispanic (NH) White, NH Black, and Hispanic older adults. We assessed associations between health conditions, body function, physical performance, social participation, and environmental factors. Results: The ICF-based model explained 36.6–38.2% of LoI variance. While physical performance was the strongest direct predictor of independence across all groups, indirect pathways varied. Social participation restrictions are associated with higher LoI score among NH White and Black adults. For Hispanic adults, limited English proficiency functioned as a key environmental variable negatively associated with body function and physical performance. Additionally, shared living arrangements among NH Black participants were negatively associated with physical performance. By gender, only NH White females exhibited associations with better physical and social outcomes. Conclusions: Pathways to LoI are associated with group-specific structural factors. To effectively prevent functional decline, healthcare policies should move beyond generic services toward culturally responsive interventions. Prioritizing targeted lifestyle behaviors—specifically social engagement for NH Black populations and linguistic accessibility for Hispanic adults—may help reduce health inequities and proactively preserve independence. Full article

As the unique edible nut species in China, Chinese hickory (Carya cathayensis Sarg.) is vulnerable to anthropogenic disturbances that reduce vegetation residue inputs and soil organic matter accumulation. To investigate the effects of net-harvesting-associated understory management on the soil carbon pool management index (CPMI), soil samples were collected from C. cathayensis plantations subjected to net harvesting for 2, 3, 6, and 7 years, with traditional beating as the control. Long-term net harvesting significantly increased particulate and dissolved organic carbon, microbial biomass carbon, and labile organic carbon (p < 0.05). It also altered soil enzyme activities, microbial community composition, and microbial co-occurrence network complexity. Soil physical and chemical properties and carbon pools were key drivers of enzyme activities and microbial complexity. Partial least squares path modeling (PLS-PM) revealed that understory vegetation positively influenced the CPMI (total effect = 0.57), while soil biological processes also contributed to CPMI variation. Overall, net harvesting reduced anthropogenic disturbance, enhanced litter-derived carbon inputs, and promoted soil biological functions, thereby improving the CPMI. These findings provide insights into sustainable soil management and carbon sequestration in C. cathayensis plantations. Full article

Engine noise is a predominant source of noise in the cabin of internal combustion engine vehicles and new energy hybrid vehicles. The conventional multi-channel active noise control (ANC) system, based on the adaptive notch filtered-X least mean square algorithm, is commonly employed to mitigate such multi-tonal noise. However, the computational efficiency and convergence performance of this system may be significantly hindered by the large estimated secondary path length and the frequency-dependent convergence behavior. To overcome these limitations, this paper proposes a computationally efficient and fast-converging multi-channel ANC system by incorporating a local secondary path (LSP) equalization method. The proposed method enhances the convergence speed by equalizing the magnitude responses of estimated secondary paths and reduces the computational complexity through an improved LSP modeling approach. Accordingly, a set of low-order equalized LSP models with normalized amplitude-frequency responses is generated and employed for reference filtering. A computational complexity analysis comparing the conventional system, a recent cost-effective system, and the proposed system is presented. Numerical simulations are conducted to evaluate the convergence speed and noise attenuation performance of these three systems. Additionally, real vehicle experiments are performed using a digital signal processing controller. The results demonstrate that the proposed multi-channel ANC system achieves a superior noise reduction effect. Under accelerated conditions, the average attenuation of the second-order noise component at the four error microphones is measured at 4.4 dB(A), 6.2 dB(A), 13.4 dB(A), and 10.0 dB(A). These findings confirm the practical effectiveness of the proposed multi-channel ANC system. Full article

To address the challenges of small scales, weak features, complex backgrounds, and misalignment in multi-scale fusion for small-object detection in remote sensing images, this study proposes a frequency-guided fusion reconstruction YOLO (FFR-YOLO), an improved YOLOv8 framework. The method performs joint optimization across three levels: the backbone, neck, and front end of the detector head. In the backbone, a frequency-guided anti-alias progressive downsampling module utilizes Haar wavelet decomposition to replace traditional strided convolutions and incorporates a low-frequency-guided high-frequency gating mechanism to mitigate detail loss and background noise interference during downsampling. In the neck, a bridge-guided bidirectional reconstruction fusion module (BRFM) enhances the collaborative reconstruction of multi-scale semantic and detailed information via multi-source weighted fusion and cross-path bridging interactions. At the front end of the detector head, a recalibrated dual-branch local–global fusion (RDLGF) module implements dynamic allocation and complementary fusion of dual-path features. Experiments were conducted on two datasets, DIOR and NWPU VHR-10. The results demonstrate that FFR-YOLO achieves a mAP@0.5 of 85.8% and a mAP@0.5:0.95 of 63.1% on DIOR and 93.6% and 62.1% on NWPU VHR-10. These outcomes present improvements over the baseline YOLOv8, validating the effectiveness and practical value of the proposed method for small-object detection in remote sensing scenarios. Full article

The pursuit of self-evolving AI raises a critical question: when is autonomous self-improvement sustainable rather than degenerative? Drawing an analogy to von Neumann’s complexity threshold for self-reproducing automata, we argue that sustainable recursive self-improvement in large language models (LLMs) requires a functional analogue: introspection—the system’s capacity to simulate its own operations and target modifications. Grounded in Kleene’s Second Recursion Theorem, we construct such introspective self-improvement programs and prove their key properties: completeness of self-modification, necessity of the reflective architecture, undecidability of improvement in general, and equivalence with Schmidhuber’s Gödel machine under a rewrite-equivalence notion, which transfers the global optimality guarantee. An empirical review, organized around these functional criteria, suggests that current LLMs exhibit only quasi-introspection.The available evidence does not establish complete introspection in the formal sense developed here, while pointing to several candidate structural bottlenecks, including incomplete self-access, feedforward processing, and limited computational depth. We outline architectural paths toward the threshold and discuss the safety implications of crossing it. Full article

Background: In one-dimensional NMR spectra of complex biofluids such as urine and plasma, extensive signal overlap obscures individual metabolite signals. Resolving this overlap by deconvolution is only the first step: turning a set of spectra into a table for subsequent statistical analysis also requires the alignment of signals across samples and their integration into a single feature matrix. Methods: Here, metabodeconplus is presented, an R package that unifies this entire path into a single reproducible end-to-end workflow. From raw one-dimensional spectra, it deconvolutes overlapping signals, aligns resulting signals across samples, and integrates them into a data matrix for built-in sample classification or downstream statistical analysis. Automated parameter optimization removes manual tuning, and a Rust computational backend with parallelization leads to fast runtimes. Results: On the simulated Sim3 spectra, a combined score of correctly identified signals and reconstruction accuracy (maximum 1) rose from 0.712 for the predecessor package to 0.801 for metabodeconplus. For the urinary AKI dataset, metabodeconplus reached a classification accuracy of 73.7 ± 2.20% and an $\mathrm{AUC}=0.827\pm 0.025$, which is comparable to the binning baseline. An advantage is the potential unambiguous metabolite assignment of the deconvoluted signals. Conclusions: The package is freely available as open source on GitHub and on CRAN. Full article

Selecting a sensing architecture for knee osteoarthritis (OA) screening requires balancing biomechanical information, system complexity, and reproducibility. We audited a public Korean multimodal gait dataset and performed a leakage-resistant internal evaluation. The release contained 180 participants (90 normal, 90 knee OA) measured using a smart insole, instrumented gait mat, and inertial measurement units (IMUs); all 1080 JavaScript Object Notation (JSON) files were checked for structural, value, provenance, and duplication errors. The primary benchmark was a fixed class-balanced L2 logistic regression model using nine gait mat variables, evaluated with subject-level repeated stratified five-fold cross-validation and 10,000 outcome-stratified bootstrap resamples. The audit identified 14 source-path metadata errors and one opposing-label duplicate smart insole payload, but no parsing, schema, range, or cross-partition subject errors. The gait mat model achieved an area under the receiver operating characteristic curve (AUROC) of 0.924 (95% confidence interval [CI], 0.879–0.962), balanced accuracy 0.883 (0.833–0.928), sensitivity 0.856, specificity 0.911, and Brier score 0.102. Adding smart insole and/or IMU features did not improve AUROC. Provider-model reproduction was descriptive because the public Validation partition informed model selection. In this release, the compact gait mat feature set provided the most favorable observed balance of discrimination, interpretability, and sensing complexity; external prospective evaluation is required before clinical use. Full article

At every level of resolution, over many orders of magnitude in time, size, and space, every aspect of the universe is constantly evolving under the pressure of the major forces of nature to resolve gradients of disparity in mass and energy. This imperative for change is channeled by two fundamental constraints: the bias of the Second Law of Thermodynamics (SLT) toward increasing entropy, and the mandate by the Principle of Least Action (PLA) that change must occur by the most direct and efficient path possible. While the SLT would seem to predict that the world would unwind rather than complicate itself, the opposite often occurs at the local level. While the evolutionary imperative drives the universe as a whole toward an ever higher level of entropy, it promotes increased local granularity and complexity to effect change in the net direction required by the SLT over the optimal path prescribed by the PLA. This provides a unifying perspective for all the complexity that astronomical and geophysical forces have created in the physical world, and that random variation and natural selection have induced in the living world―a consequence of nature’s imperative to dissipate energy as thoroughly and efficiently as possible. Full article

Multi-agent path planning (MAPP) under partial observability requires agents to coordinate their movements and complete tasks efficiently without access to global information. The planning space and coordination complexity grow rapidly with increasing numbers of agents, targets, and obstacles. We formulate large-scale MAPP as a partially observable networked Markov decision process. Based on this formulation, we propose a decentralized model-based Actor-Critic using the Kronecker-factored trust region (DM-ACKTR) algorithm. The algorithm integrates local model learning with ACKTR-based policy optimization in an independent learning architecture. Each agent learns a local model to predict the next observation and reward. These predictions are used to construct additional transitions for Actor and Critic updates. A neighborhood-based communication mechanism incorporates information from nearby agents into value estimation. Region partitioning reduces each agent’s effective planning space. These improvements enable DM-ACKTR to continue outperforming the baseline algorithms as the scale of the MAPP problem increases. Experiments across three training and five evaluation scenarios show that DM-ACKTR achieves the best overall performance. Among the five evaluated algorithms, it consistently obtains the highest TCR and lowest CR, improving TCR by 2.06–4.35% and reducing CR by 11.26–25.95% relative to the respective best baselines. Full article