Long Tail Research Articles

Comparative Analysis of Aerodynamic Drag Between Long Tail and Short Tail Aero Helmets Through Wind Tunnel Testing

Aerodynamic drag is a critical factor influencing the performance of competitive cyclists, particularly in time-trial events, where reducing drag can significantly improve speed and efficiency. Helmets are an essential component of aerodynamic gear, and their design plays a vital role in minimizing air resistance. However, the effect of different helmet shapes and head positions on aerodynamic performance has not been thoroughly examined. This study aims to investigate and compare the aerodynamic performance of long-tail (LT) and short-tail (ST) aero helmets, along with the Kabuto Aero SL, under varying pitch angles and speeds. Wind tunnel testing was conducted using an adult-sized mannequin head, with helmets evaluated at pitch angles ranging from 15° to 45° and wind speeds of 5 to 15 m/s. The results showed that the LT Aero helmet achieved the best performance at lower pitch angles (15°), while the ST Aero helmet performed optimally at a 25° pitch angle. The Kabuto Aero SL helmet demonstrated superior performance at low pitch positions, particularly at 15°. These findings highlight the importance of helmet design and head positioning in optimizing aerodynamic efficiency for cyclists in competitive conditions.

Universal Nonthermal Power-law Distribution Functions from the Self-consistent Evolution of Collisionless Electrostatic Plasmas

Collisionless systems often exhibit nonthermal power-law tails in their distribution functions. Interestingly, collisionless plasmas in various physical scenarios (e.g., the ion population of the solar wind) feature a v −5 tail in their velocity (v) distribution, whose origin has been a long-standing puzzle. We show this power-law tail to be a natural outcome of the collisionless relaxation of driven electrostatic plasmas. Using a quasi-linear analysis of the perturbed Vlasov–Poisson equations, we show that the coarse-grained mean distribution function (DF), f 0, follows a quasi-linear diffusion equation with a diffusion coefficient D(v) that depends on v through the plasma dielectric constant. If the plasma is isotropically forced on scales larger than the Debye length with a white-noise-like electric field, D(v) ∼ v 4 for σ < v < ω P/k, with σ the thermal velocity, ω P the plasma frequency, and k the characteristic wavenumber of the perturbation; the corresponding quasi-steady-state f 0 develops a v −(d + 2) tail in d dimensions (v −5 tail in 3D), while the energy (E) distribution develops an E −2 tail independent of dimensionality. Any redness of the noise only alters the scaling in the high v end. Nonresonant particles moving slower than the phase velocity of the plasma waves (ω P/k) experience a Debye-screened electric field, and significantly less (power-law suppressed) acceleration than the near-resonant particles. Thus, a Maxwellian DF develops a power-law tail, while its core (v < σ) eventually also heats up but over a much longer timescale. We definitively show that self-consistency (ignored in test-particle treatments) is crucial for the emergence of the universal v −5 tail.

RepSGG: Novel Representations of Entities and Relationships for Scene Graph Generation.

Scene Graph Generation (SGG) has achieved significant progress recently. However, most previous works rely heavily on fixed-size entity representations based on bounding box proposals, anchors, or learnable queries. As each representation's cardinality has different trade-offs between performance and computation overhead, extracting highly representative features efficiently and dynamically is both challenging and crucial for SGG. In this work, a novel architecture called RepSGG is proposed to address the aforementioned challenges, formulating a subject as queries, an object as keys, and their relationship as the maximum attention weight between pairwise queries and keys. With more fine-grained and flexible representation power for entities and relationships, RepSGG learns to sample semantically discriminative and representative points for relationship inference. Moreover, the long-tailed distribution also poses a significant challenge for generalization of SGG. A run-time performance-guided logit adjustment (PGLA) strategy is proposed such that the relationship logits are modified via affine transformations based on run-time performance during training. This strategy encourages a more balanced performance between dominant and rare classes. Experimental results show that RepSGG achieves the state-of-the-art or comparable performance on the Visual Genome and Open Images V6 datasets with fast inference speed, demonstrating the efficacy and efficiency of the proposed methods.

Mine Your Own Anatomy: Revisiting Medical Image Segmentation With Extremely Limited Labels.

Recent studies on contrastive learning have achieved remarkable performance solely by leveraging few labels in the context of medical image segmentation. Existing methods mainly focus on instance discrimination and invariant mapping (i.e., pulling positive samples closer and negative samples apart in the feature space). However, they face three common pitfalls: (1) tailness: medical image data usually follows an implicit long-tail class distribution. Blindly leveraging all pixels in training hence can lead to the data imbalance issues, and cause deteriorated performance; (2) consistency: it remains unclear whether a segmentation model has learned meaningful and yet consistent anatomical features due to the intra-class variations between different anatomical features; and (3) diversity: the intra-slice correlations within the entire dataset have received significantly less attention. This motivates us to seek a principled approach for strategically making use of the dataset itself to discover similar yet distinct samples from different anatomical views. In this paper, we introduce a novel semi-supervised 2D medical image segmentation framework termed Mine yOur owNAnatomy (MONA), and make three contributions. First, prior work argues that every pixel equally matters to the model training; we observe empirically that this alone is unlikely to define meaningful anatomical features, mainly due to lacking the supervision signal. We show two simple solutions towards learning invariances-through the use of stronger data augmentations and nearest neighbors. Second, we construct a set of objectives that encourage the model to be capable of decomposing medical images into a collection of anatomical features in an unsupervised manner. Lastly, we both empirically and theoretically, demonstrate the efficacy of our MONA on three benchmark datasets with different labeled settings, achieving new state-of-the-art under different labeled semi-supervised settings. MONA makes minimal assumptions on domain expertise, and hence constitutes a practical and versatile solution in medical image analysis. We provide the PyTorch-like pseudo-code in supplementary.

FLRF: Federated recommendation optimization for long-tail data distribution

FLRF: Federated recommendation optimization for long-tail data distribution

Cloud Droplet Size Distributions Governed by Condensation, Collision–Coalescence, and Sedimentation. Part II: Analytical Expressions for Size Distribution Shape and Asymptotic Behavior for Large-Droplet Tails

Abstract Droplet growth via condensation and collision–coalescence has been investigated in the limit of very weak coalescence growth: a collector-mode approximation emerges for coalescence growth that consists solely of droplets in the tail collecting droplets near the main mode of the cloud droplet size distribution and that does not deplete the mode. In this second part, the approximation is formalized, leading to a simplified form of the collision–coalescence term in the equation governing the evolution of the droplet size distribution. This form allows for analytical solutions for transient growth and for steady-state distributions representing a balance between condensation, collision–coalescence growth, and removal by sedimentation. The solutions lead to an expression for the drizzle growth time, formally, the finite time in which a droplet approaches infinite size. The drizzle growth time is related to a transition radius at which droplet growth switches from condensation-dominated to coalescence-dominated. The solutions also provide a dimensionless group that governs the steady-state distribution shape, which is referred to as the drizzle number. The solutions are checked by comparing to a Monte Carlo model developed in part 1, and it is found that the analytical solution is excellent when the drizzle number is much greater than unity, which is the typical situation for the microphysical conditions achievable in a convection–cloud chamber. The steady-state size distribution has the form of a modified gamma distribution, with a transition to a power-law tail at a sufficiently large radius. The solutions are not only formally valid for a convection–cloud chamber but can also be extended to shallow, mixed-layer clouds such as mixing fogs.

SO-TAD: A surveillance-oriented benchmark for traffic accident detection

Automatic traffic accident detection is a crucial component of Vehicle-to-Infrastructure (V2I) systems and is gaining increasing attention from researchers due to its significant impact on road safety. However, existing datasets often suffer from issues such as data contamination, small scale, and lack of open access, which hinder the advancement of research in this field. To overcome these challenges, we introduce the high-quality, large-scale Surveillance-Oriented Traffic Accident Detection (SO-TAD) dataset, designed with long-tail distribution characteristics. The SO-TAD dataset comprises 2,186 samples, including 282 traffic accident instances, each providing spatio-temporal localization information. Furthermore, within the proposed frame prediction-based traffic accident detection framework, we designed a three-channel scene feature fusion generative adversarial network (TCFF-GAN). This network integrates scene introduction features and scene difference features to generate predictive frame features. Subsequently, traffic accidents are detected based on the stability of the cosine similarity sequence between the predicted frames and the actual frames. We validated the effectiveness of the proposed TCFF-GAN not only through public datasets but also by conducting extensive experiments on the newly introduced SO-TAD dataset. This work also establishes a new benchmark for automatic traffic accident detection research. The code and dataset are available at https://github.com/cccxy-299/so-tad.

DiaDet-R: A lightweight and accurate rotated detector for diatom detection in drowning diagnostics

In the field of forensic science, diatom test is widely utilized to determine the cause and location of death for bodies found in water. Diatom detection plays an important role in the diatom test. However, diatom detection faces challenges due to the imbalanced distribution of diatom features and the complexity of these features. To address these two challenges, we propose DiaDet-R, a diatom rotated detector for drowning diagnosis. Specifically, to tackle the first challenge of feature distribution imbalance, we perform customized data augmentation on our self-established diatom dataset to increase sample diversity. Further, we introduce the Low-level Enhancement Path Aggregation Feature Pyramid Network (LEPAFPN) to better extract tail features of intra-class features that exhibit a long-tail distribution. To address the second challenge of the feature complexity, we propose three strategies: (1) we devise a basic building block, Double Inception Depth-wise Convolution (Double IDC), to enhance the detector’s long-distance modeling capability; (2) we improve the horizontal detector to a rotated object detector to address the issues of overlapping and extensive invalid backgrounds caused by arbitrary angles and shapes of diatom targets; (3) to solve the feature misalignment issue in rotated object detection, we propose the Rotated Alignment Head (RAHead) to align target features. Extensive experimental results on our self-established diatom dataset show that DiaDet-R achieves mAP50 and mAP75 of 95.73% and 89.99%, respectively, with reduced model parameters and GFLOPs to 4.34M and 18.48G, validating that DiaDet-R can detect diatoms quickly and accurately, outperforming mainstream rotated detectors.

Exploration of Imbalanced Regression in state-of-health estimation of Lithium-ion batteries

The state of health (SOH) estimation for lithium-ion batteries based on deep learning (DL) has made great progress. However, due to different electrochemical compositions of lithium-ion batteries, different ways of conducting experiments and other factors, the degradation process of some batteries shows longer early degradation time and shorter later degradation time, resulting in a long-tailed distribution of degradation data. This leads to the problem of data imbalance in SOH estimation tasks, which affects the accuracy of SOH estimation. This article explores the long-tailed distribution phenomenon in the field of batteries and the corresponding imbalanced regression problem it brings to the estimation of battery SOH. In addition, a method for improving model performance is proposed. Specifically, we use a quadratic interpolation and standardization method to analyze the battery data to ensure the consistency of data features. By discretized analysis of continuous problems, the label distribution smoothing (LDS) method is applied to deep neural networks to analyze and solve this imbalanced regression problem. By convolution processing with the kernel function and label distribution, the weights corresponding to different labels are calculated, which improves the estimation accuracy. We conducted battery aging experiments and verified that the degradation data follows a long-tailed distribution. The effectiveness of the final method was validated on our experimental data and a publicly available dataset.

Molecular characterization of the archaic HLA-B*73:01 allele reveals presentation of a unique peptidome and skewed engagement by KIR2DL2.

HLA class I alleles of archaic origin may have been retained in modern humans because they provide immunity against diseases to which archaic humans had evolved resistance. According to this model, archaic introgressed alleles were somehow distinct from those that evolved in African populations. Here we show that HLA-B*73:01, a rare allotype with putative archaic origins, has a relatively rare peptide binding motif with an unusually long-tailed peptide length distribution. We also find that HLA-B*73:01 combines a restricted and unique peptidome with high-cell surface expression, characteristics that make it well-suited to combat one or a number of closely-related pathogens. Furthermore, a crystal structure of HLA-B*73:01 in complex with KIR2DL2 highlights differences from previously solved structures with HLA-C molecules. These molecular characteristics distinguish HLA-B*73:01 from other HLA class I alleles previously investigated and may have provided early modern human migrants that inherited this allele with a selective advantage as they colonized Europe and Asia.

Predicting origin-destination flows by considering heterogeneous mobility patterns

The accurate prediction of origin-destination (OD) flows is essential for advancing sustainable urban mobility and supporting resilient urban planning. However, the inherent heterogeneity of mobility patterns results in complex geographic unit relations, diverse spatial organizational structures, and the long-tailed effect on OD flow distribution. This study proposes a novel OD flow prediction method based on graph-based deep learning (named as HMCG-LGBM). Specifically, 1) a modularity-based graph reconstruction strategy is presented for geographic unit relation augmentation by eliminating weak connections; 2) the heterogeneous spatial organization of OD flows is captured by combining the community detection approach and graph attention mechanism with the introduction of socio-economic and spatial features; and 3) a weighted loss function with distribution smoothing paradigm is developed to enhance the prediction for low-probability mobility events, addressing the challenges posed by long-tailed distributions. Extensive experiments conducted on real-world datasets show that the predictive performance of the proposed method is significantly improved, with the RMSE and MAE reduced from the baselines by 11.1%–33.3% and 14.1%–22.2%, respectively. The results also demonstrate the robustness of the proposed method for dealing with imbalanced OD flow distributions, providing valuable insights for spatial interaction predictive modeling in the context of sustainable urban systems.

Homogeneous turbophoresis of heavy inertial particles in turbulent flow

Heavy particles suspended in turbulent flow possess inertia and are ejected from violent vortical structures by centrifugal forces. Once piled up along particle paths, this small-scale mechanism leads to an effective large-scale drift. This phenomenon, known as ‘turbophoresis’, causes particles to leave highly turbulent regions and migrate towards calmer regions, explaining why particles transported by non-homogeneous flows tend to concentrate near the minima of turbulent kinetic energy. It is demonstrated here that turbophoretic effects are just as crucial in statistically homogeneous flows. Although the average turbulent activity is uniform, instantaneous spatial fluctuations are responsible for inertial-range inhomogeneities in the particle distribution. Direct numerical simulations are used to probe particle accelerations, specifically how they correlate to local turbulent activity, yielding an effective coarse-grained dynamics that accounts for particle detachment from the fluid and ejection from excited regions through a space- and time-dependent non-Fickian diffusion. This leads to cast fluctuations in particle distributions in terms of a scale-dependent Péclet number ${\textit {Pe}}_\ell$ , which measures the importance of turbulent advection compared with inertial turbophoresis at a given scale $\ell$ . Multifractal statistics of energy dissipation indicate that $ {\textit {Pe}}_\ell \sim \ell ^\delta /\tau _{p}$ with $\delta \approx 0.84$ . Numerical simulations support this behaviour and emphasise the relevance of the turbophoretic Péclet number in characterising how particle distributions, including their radial distribution function, depends on $\ell$ . This approach also explains the presence of voids with inertial-range sizes, and the fact that their volumes have a non-trivial distribution with a power-law tail $p(\mathcal {V}) \propto \mathcal {V}^{-\alpha }$ , with an exponent $\alpha$ that tends to 2 as ${\textit {Pe}}_\ell \to 0$ .

Measuring DNS-over-HTTPS Downgrades: Prevalence, Techniques, and Bypass Strategies

DNS-over-HTTPS (DoH) is a privacy-enhancing protocol that encrypts plaintext query data in DNS resolution. However, DoH often faces accessibility challenges due to phenomena known as DoH downgrades, where DoH queries are reverted to plaintext DNS queries. Unlike downgrades in other security protocols, which are undoubtedly malicious, the act of downgrading DoH queries can be both desirable and undesirable depending on the context; e.g., enterprise networks are officially advised to avoid or downgrade DoH for security reasons. Recent research has drawn attention to the deeper examination of the phenomena of DoH downgrades, focusing on the prevalence, techniques, and potential bypass strategies. However, existing studies on DoH downgrades have several limitations, notably that they severely overestimate the severity of DoH downgrades across the globe as they lack any distinction between desirable and undesirable downgrades of DoH. In this work, we conduct a large-scale measurement study to provide a more accurate depiction of the DoH downgrade landscape. By minimizing the influence of desirable downgrades of DoH in our measurement probes, we show a skewed long-tail distribution of DoH downgrades across the globe. Our stateful probing techniques also reveal hidden DoH filtering mechanisms that were previously undetected. Furthermore, we design near perfect bypass strategies against existing DoH downgrades. Our study expands our limited understanding of DoH downgrades, offering a more accurate, fine-grained, and comprehensive view of the phenomena.

The Boltzmann-Grad Limit of the Lorentz Gas in a Union of Lattices

The Lorentz gas describes an ensemble of noninteracting point particles in an infinite array of spherical scatterers. In the present paper we consider the case when the scatterer configuration P\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$${{\\mathcal {P}}}$$\\end{document} is a fixed union of (translated) lattices in Rd\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$${\\mathbb {R}}^d$$\\end{document}, and prove that in the limit of low scatterer density, the particle dynamics converges to a random flight process. In the special case when the lattices in P\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$${{\\mathcal {P}}}$$\\end{document} are pairwise incommensurable, this settles a conjecture from Marklof and Strömbergsson (J Stat Phys 155:1072–1086, 2014). The proof is carried out by applying a framework developed in recent work by Marklof and Strömbergsson (Mem AMS 294, 2024), and central parts of our proof are the construction of an admissible marking of the point set P\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$${{\\mathcal {P}}}$$\\end{document}, and the verification of the uniform spherical equidistribution condition required in Marklof and Strömbergsson (Mem AMS 294, 2024). Regarding the random flight process obtained in the low density limit of the Lorentz gas, we prove that it can be reconstructed from the corresponding limiting flight processes arising from the individual commensurability classes of lattices in P\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$${{\\mathcal {P}}}$$\\end{document}. We furthermore prove that the free path lengths of the limit flight process have a distribution with a power law tail, whose exponent depends on the number of commensurability classes in P\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$${{\\mathcal {P}}}$$\\end{document}.

A Pareto Tail Plot Without Moment Restrictions

We propose a mean functional that exists for arbitrary probability distributions and characterizes the Pareto distribution within the set of distributions with finite left endpoint. This is in sharp contrast to the mean excess plot, which is meaningless for distributions without an existing mean and has nonstandard behavior when the mean is finite, but the second moment does not exist. The construction of the plot is based on the principle of a single huge jump, which differentiates between distributions with moderately heavy and super heavy tails. We present an estimator of the tail function based on U-statistics and study its large sample properties. Several loss datasets illustrate the use of the new plot.

Effects of vanishing power-law tails of river flows caused by damming on downstream hydrological connectivity

High-intensity dam operations have severely disturbed the power-law behaviors of natural river flows, which have important implications for the entire ecosystem’s integrity, diversity, and sustainability. This study investigated the effects of vanishing power-law tails of river flows caused by damming on downstream hydrological connectivity in the Wanquan river–floodplain (China) and determined the consequent ecological responses. A two-dimensional hydrodynamic model was established to estimate inundation regimes under different hydrological scenarios, and a statistics-based method was used to generate vanishing power-law tails. Connectivity assessments quantified the duration, magnitude, accumulation, and efficiency of connection events in the river–floodplain system for historical hydrological processes, current dam operating schemes, and simulated flow series with compressed power-law tails. The results showed significant reductions in downstream connection duration, magnitude, accumulation, and efficiency with compression of the natural power-law tail, especially for small (P < 20 %) and large (P > 90 %) connection events. Under a fully modified scenario, the cumulative large connection events were reduced by as much as 50 %. Damming also diminished the seasonal fluctuations of lateral exchanges and weakened the synergetic relationships among inflows, inundation extents and connectivity in the river–floodplain system. Furthermore, increasing damming led to an exponential and accelerated loss of downstream connectivity, with noticeable inflection points. Reduced or insulated hydrological exchanges would weaken material cycling, energy flow, and information transmission in the river–floodplain system, ultimately impacting the entire aquatic ecosystem. Our study emphasizes the importance of the power-law tail in the estimation of natural flows, which, although accounting for only a small part of the whole flow series (approximately 6 % in this case), is of great significance for maintaining the downstream connectivity necessary for healthy aquatic ecosystems.

Multimodal Framework for Long-Tailed Recognition

Long-tailed data distribution (i.e., minority classes occupy most of the data, while most classes have very few samples) is a common problem in image classification. In this paper, we propose a novel multimodal framework for long-tailed data recognition. In the first stage, long-tailed data are used for visual-semantic contrastive learning to obtain good features, while in the second stage, class-balanced data are used for classifier training. The proposed framework leverages the advantages of multimodal models and mitigates the problem of class imbalance in long-tailed data recognition. Experimental results demonstrate that the proposed framework achieves competitive performance on the CIFAR-10-LT, CIFAR-100-LT, ImageNet-LT, and iNaturalist2018 datasets for image classification.

Modelling of wind and solar power output uncertainty in power systems based on historical data: A characterisation through deterministic parameters

The inherent uncertainty associated with wind and solar energy poses challenges in ensuring the reliability of the power system with a high penetration of renewable energy. Therefore, incorporating uncertainty is vital during the planning of power systems. Traditional analytical methods often necessitate transforming the uncertainty of large-scale power systems into deterministic optimisation planning, while those approaches tend to be overly conservative, yielding unsolvable solutions, or rely on assumptions and data fitting, creating a significant gap with real-world scenarios. To address this, this study employs upper α-quantiles originating from abundant historical data to replace power output expectations to consider uncertainty during the planning. Additionally, random sampling based on historical data generates potential wind and solar output scenarios, and Monte Carlo simulations are used to validate the proposed method's reliability and assess system investment distribution. Using China's power system as a case study, 64 quantile choices are evaluated. Compared to planning through output expectations, using quantiles can reduce the load loss rate from 10−1 to 10−5, and both the cost expectations and the extreme cost risk decrease. The use of fossil fuels has also decreased by 10%. Results underscore the necessity of choosing upper α-quantiles with higher α, such as 85, to account for the long-tailed wind power distribution. However, even overly conservative wind power output α is still challenging to mitigate residual load loss. The combination of photovoltaics and intraday energy storage ensures that the α selection of photovoltaics should not be too low, due to the reason that there is a need to balance the gradual decrease of load loss rates and the steep ascent of expected investment costs in the power system.

Relieving popularity bias in recommendation via debiasing representation enhancement

The interaction data used for training recommender systems often exhibit a long-tail distribution. Such highly imbalanced data distribution results in an unfair learning process among items. Contrastive learning alleviates the above issue by data augmentation. However, it lacks consideration of the significant disparity in popularity between items and may even introduce false negatives during the data augmentation, misleading user preference prediction. To address this issue, we combine contrastive learning with a weighted model for negative validation. By penalizing identified false negatives during training, we limit their potential harm within the training process. Meanwhile, to tackle the scarcity of supervision signals for unpopular items, we design Popularity Associated Modeling to mine the correlation among items. Then we guide unpopular items to learn hidden features favored by specific users from their associated popular items, which provides effective supplementary information for their representation modeling. Extensive experiments on three real-world datasets demonstrate that our proposed model outperforms state-of-the-art baselines in recommendation performance, with Recall@20 improvements of 4.2%, 2.4% and 3.6% across the datasets, but also shows significant effectiveness in relieving popularity bias.

Assessing the Recreational Resource Value of National Park Based on Visitor Perception—A Case of Three-River-Source National Park in China

National parks serve as critical practical sites for advancing the concept of “harmonious coexistence between humans and nature” and hold a strategic role in establishing global ecological security barriers. Scholars and decision-makers have expressed significant interest in rigorous assessments of the recreational resource value in national parks. This paper focuses on the Three-River-Source National Park, examining the characteristics and components of its recreational resource value through the lens of human–environment relationship theory. Analysis spans dimensions of geological and geomorphological value, ecological service value, historical and cultural value, and aesthetic landscape value. By extracting visitor comments rich in vocabulary related to their perceptions, this study compares variations in resource values and the “resource value–visitor perception” synergy within Three-River-Source National Park, employing text analysis, semantic network analysis, and coordination analysis methods. The findings reveal that (1) Visitor perceptions of recreational resource value display a clear hierarchy, with aesthetic landscape value (43.6%) ranking highest, followed by geological and geomorphological value (26.7%), historical and cultural value (19.3%), and ecological service value (10.4%), showing significant variation among categories; the vocabulary across these value types exhibits a pronounced long-tail distribution. (2) The recreational resource value in the park forms a distinct core centered on prominent attractions, accompanied by patterns of vocabulary aggregation and dispersion. (3) Visitors demonstrate strong synergy in their perception of geological and aesthetic value, weaker perception regarding historical and cultural value, and a relatively narrow understanding of ecological service value. This research enhances public comprehension of the recreational resource value of national parks and provides a scientific foundation for the conservation and sustainable use of recreational resources in national parks, advancing the realization of their recreational functions.