Distribution Features Research Articles

Asymmetrical Solar Wind Deflection in the Martian Magnetosheath

AbstractAs incident solar wind encounters the martian upper atmosphere, it undergoes deflection particularly in the magnetosheath. However, the plasma flow exhibits asymmetrical distribution features within this transition region, which is investigated by employing a three‐dimensional Hall magnetohydrodynamic (MHD) model from an energy transfer perspective in this study. Simulation results reveal that solar wind protons transfer momentum to ionospheric heavy ions through motional electric field in the hemisphere where the motional electric field points outward from the planet. In the opposite hemisphere, solar wind flow tends to be effectively accelerated by ambipolar and Hall electric fields. The distinct dynamics of solar wind protons in both hemispheres result in the asymmetrical deflection. Furthermore, the extent of asymmetry grows as the cross‐flow component of the upstream interplanetary magnetic field increases, but diminishes as the density of the solar wind proton increases, contingent upon the energy effectively acquired from ambipolar and Hall electric fields.

Machine cross-domain remaining useful life prediction via contrastive adversarial variational recurrent method

The performance degradation process of the machine is non-stationary which varies with the operating environment and is reflected as a temporal shift phenomenon. Models or methods that assume the test and training sets have the same distribution will no longer be suitable for solving problems where domain shifts exist. This brings new challenges for accurately evaluating the machine’s remaining useful life (RUL). This paper studies a contrastive adversarial variational recurrent method for machine RUL prediction under different service conditions. In this new approach, the variational recurrent networks are developed to extract distribution features and latent spaces of raw data, meanwhile, the adversarial strategies are applied to enable the learning of domain-invariant features to make the model achieve cross-domain task processing. To supervise the learning process of the model to learn more mutual information between the extracted features and the raw input data, a contrastive loss is also introduced in the proposed method. Sufficient experiments were conducted to verify the feasibility and superiority of the suggested approach, including 12 sets of cross-scenario tests on the turbofan engine dataset C-MAPSS from NASA. Experimental findings confirm that the proposed method performs satisfactorily and competitively even compared to current state-of-the-art works.

Corrected generalized cross-validation for finite ensembles of penalized estimators

Abstract Generalized cross-validation (GCV) is a widely used method for estimating the squared out-of-sample prediction risk that employs scalar degrees of freedom adjustment (in a multiplicative sense) to the squared training error. In this paper, we examine the consistency of GCV for estimating the prediction risk of arbitrary ensembles of penalized least-squares estimators. We show that GCV is inconsistent for any finite ensemble of size greater than one. Towards repairing this shortcoming, we identify a correction that involves an additional scalar correction (in an additive sense) based on degrees of freedom adjusted training errors from each ensemble component. The proposed estimator (termed CGCV) maintains the computational advantages of GCV and requires neither sample splitting, model refitting, or out-of-bag risk estimation. The estimator stems from a finer inspection of the ensemble risk decomposition and two intermediate risk estimators for the components in this decomposition. We provide a non-asymptotic analysis of the CGCV and the two intermediate risk estimators for ensembles of convex penalized estimators under Gaussian features and a linear response model. Furthermore, in the special case of ridge regression, we extend the analysis to general feature and response distributions using random matrix theory, which establishes model-free uniform consistency of CGCV.

A machine learning framework to generate star cluster realisations

Computational astronomy has reached the stage where running a gravitational $N$-body simulation of a stellar system, such as a Milky Way star cluster, is computationally feasible, but a major limiting factor that remains is the ability to set up physically realistic initial conditions. We aim to obtain realistic initial conditions for $N$-body simulations by taking advantage of machine learning, with emphasis on reproducing small-scale interstellar distance distributions. The computational bottleneck for obtaining such distance distributions is the hydrodynamics of star formation, which ultimately determine the features of the stars, including positions, velocities, and masses. To mitigate this issue, we introduce a new method for sampling physically realistic initial conditions from a limited set of simulations using Gaussian processes. We evaluated the resulting sets of initial conditions based on whether they meet tests for physical realism. We find that direct sampling based on the learned distribution of the star features fails to reproduce binary systems. Consequently, we show that physics-informed sampling algorithms solve this issue, as they are capable of generating realisations closer to reality.

Overcoming learning bias via Prototypical Feature Compensation for source-free domain adaptation

The focus of Source-free Unsupervised Domain Adaptation (SFUDA) is to effectively transfer a well-trained model from the source domain to an unlabelled target domain. During the target domain adaptation, the source domain data is no longer accessible. Prevalent methodologies attempt to synchronize the data distributions between the source and target domains, utilizing pseudo-labels to impart categorical information, which has made some progress in improving the model’s performance. However, performance impairments persist due to the introduction of learning bias from the source model and the impact of noisy pseudo-labels generated for the target domain. In this research, we reveal that the central cause for feature misalignment during domain transition is the learning bias, which is generated by the discrepancy of information between source and target domain data. The source domain data may contain distinguishable features that do not appear on the target domain, which causes the pre-trained source model to fail to work during domain adaptation. To overcome the information discrepancy, we propose a Prototypical Feature Compensation (PFC) Network. The network extracts representative feature maps of the source domain. Then use them to minimize the discrepancy information in the target domain feature maps. This mechanism facilitates feature alignment across different domains, allowing the model to generate more accurate categorical data through pseudo-labelling. The experimental results and ablation studies demonstrate exceptional performance on three SFUDA datasets and provide evidence of the proposed PFC method’s ability to adjust the feature distribution of both source and target domain data, ensuring their overlap in the latent space.

Assessment of Age-Related Differences in Lower Leg Muscles Quality Using Radiomic Features of Magnetic Resonance Images.

Sarcopenia, characterised by a decline in muscle mass and strength, affects the health of the elderly, leading to increased falls, hospitalisation, and mortality rates. Muscle quality, reflecting microscopic and macroscopic muscle changes, is a critical determinant of physical function. To utilise radiomic features extracted from magnetic resonance (MR) images to assess age-related changes in muscle quality, a dataset of 24 adults, divided into older (male/female: 6/6, 66-79years) and younger (male/female: 6/6, 21-31years) groups, was used to investigate the radiomics features of the dorsiflexor and plantar flexor muscles of the lower leg that are critical for mobility. MR images were processed using MaZda software for feature extraction. Dimensionality reduction was performed using principal component analysis and recursive feature elimination, followed by classification using machine learning models, such as support vector machine, extreme gradient boosting, and naïve Bayes. A leave-one-out validation test was used to train and test the classifiers, and the area under the receiver operating characteristic curve (AUC) was used to evaluate the classification performance. The analysis revealed that significant differences in radiomic feature distributions were found between age groups, with older adults showing higher complexity and variability in muscle texture. The plantar flexors showed similar or higher AUC than the dorsiflexors in all models. When the dorsiflexor muscles were combined with the plantar flexor muscles, they tended to have a higher AUC than when they were used alone. Radiomic features in lower-leg MR images reflect ageing, especially in the plantar flexor muscles. Radiomic analysis can offer a deeper understanding of age-related muscle quality than traditional muscle mass assessments.

MTFDN: An image copy‐move forgery detection method based on multi‐task learning

AbstractImage copy‐move forgery, where an image region is copied and pasted within the same image, is a simple yet widely employed manipulation. In this paper, we rethink copy‐move forgery detection from the perspective of multi‐task learning and summarize two characteristics of this problem: (1) Homology and (2) Manipulated traces. Consequently, we propose a multi‐task forgery detection network (MTFDN) for image copy‐move forgery localization and source/target distinguishment. The network consists of a hard‐parameter sharing feature extractor, global forged homology detection (GFHD) and local manipulated trace detection (LMTD) modules. The difference of feature distribution between the GFHD module and the LMTD module is significantly reduced by sharing parameters. Experimental results on several benchmark copy‐move forgery datasets demonstrate the effectiveness of our proposed MTFDN.

Spatiotemporal evolution and driving factors analysis of fractional vegetation coverage in the arid region of northwest China

The arid region of northwest China (ARNC) is the most ecologically fragile region in China, and is characterized by harsh natural conditions, severe soil erosion, and poor soil fertility. Understanding long-term vegetation changes in this region is critical for effective environmental monitoring and climate change adaptation. Fractional vegetation coverage (FVC) is a key parameter for characterizing the ecological conditions of the ARNC. However, the reliance on low-resolution FVC and NDVI data due to the lack of medium-resolution data has limited our understanding of the environmental dynamics in this region. Therefore, this study addressed this gap by utilizing Landsat data to generate FVC data, enabling a detailed investigation of the spatial-temporal variations and driving factors of vegetation in the ARNC from 2000 to 2020. The results indicated the following: (1) The FVC was generally low, with an average of 0.191. The FVC was greater in the northwest and lower in the southeast in terms of spatial distribution features. The trend of FVC change in ARNC showed significant spatial variability, with degradation outweighing improvement. (2) The coefficient of variation of FVC was 0.377, indicating significant temporal fluctuations, with more stable conditions in the northwest than in the southeast. (3) The spatial differentiation of the FVC in ARNC was primarily driven by land cover types, evapotranspiration, and precipitation, with explanatory powers exceeding 30 % each. This study is significant because it provides a comprehensive understanding of vegetation dynamics in one of China's most vulnerable regions, offering critical insights for ecological restoration, desertification control, and sustainable development. The findings underscore the importance of targeted ecological governance to address the challenges posed by environmental degradation in the ARNC.

DMMGNet: A Discrimination Mapping and Memory Bank Mean Guidance-based Network for High-performance Few-shot Industrial Anomaly Detection

For deep learning-based industrial anomaly detection, it is still challenging to get adequate images for model training and achieve cold start for cross-product migration, restricting their practical application in real industrial production. Herein, an innovative few-shot anomaly detection network DMMGNet based on discrimination mapping and memory bank mean guidance strategies are demonstrated, which is trained by a new two-branch data augmentation technique. By separating the features stored in memory bank from the features used for training, the two-branch data augmentation method can significantly improve the robustness of few-shot model training and reduce the redundance of memory bank. In the elaborately designed discrimination mapping module, new negative samples are generated by adding dynamic Gaussian noise to normal samples along the channel dimension in feature space to solve the problem of sample imbalance. Meanwhile, the discrimination mapping module also helps to map the feature distribution of positive samples to the target domain more efficiently and reduce the deviation of feature domain, conducive to a more precise separation of positive and negative samples. In addition, a novel mean guidance approach with an optimized loss function is developed to guide the positive sample feature mapping by specifying the local feature space center to form a clear feature domain contour and enhance the detection accuracy. The multiple experimental results validate that our DMMGNet outperforms the most advanced anomaly detection counterparts on image-level AUROC, showing an increase by 0.3-3% on both MVTec AD and MPDD benchmarks under several few-shot scenarios.

3D mineral prospectivity modeling using deep adaptation network transfer learning: A case study of the Xiadian gold deposit, Eastern China

Mineralization distribution is commonly heterogeneous in space due to the various geology and structure conditions or fluid flow and evoluation, causing the possible difference in mineralization distribution regularity between shallow and deep at a deposit. This presents important challenges for three-dimensional mineral prospectivity modeling (3D MPM) for deep zones with the scarcity data conditions. Transfer learning has shown promising generalization performance in tasks involving shifts in data distribution, reducing reliance on labeled samples and enhancing learning capability with limited data. In this study, we propose an approach of 3D MPM, namely DAN-CBAM, based on the deep adaptation network (DAN) augmented with the convolutional block attention module (CBAM). It theoretically can harmonize the distribution of ore-controlling features between shallow and deep zones of deposits while effectively extract critical high-dimensional features and spatial patterns. The Xiadian orogenic gold deposit was selected as a case study to validate the approach. The DAN integrates multi-layer, multi-kernel adaptation at the top layer of the CNN, resulting in improved alignment of marginal distributions across domains. Metrics for distribution similarity such as Wasserstein distance, were reduced by 0.250 and KL divergence decreased by 0.032. Additionally, the inclusion of the CBAM module led to a lower MK-MMD loss and a faster convergence rate. And the DAN-CBAM model achieves superior prediction accuracy (0.85) compared to traditional deep neural network (DNN) models (0.81). These highlight CBAM's effectiveness in enhancing the model's ability to capture spatial similarities in mineralization. Furthermore, the area under the curve (AUC) value of the DAN-CBAM model (0.869) significantly outperforms traditional machine learning methods, including CNN (0.786) and Random Forest (0.703) models, underscoring its superior predictive efficiency in 3D MPM for deep mineralization. Therefore, the proposed DAN-CBAM model is promising to be applied in the 3D MPM, in particular for the deposits with different mineralization distribution regularities in space.

G[formula omitted]BFNN: Generalized geodesic basis function neural network

Real-world data is typically distributed on low-dimensional manifolds embedded in high-dimensional Euclidean spaces. Accurately extracting spatial distribution features on general manifolds that reflect the intrinsic characteristics of data is crucial for effective feature representation. Therefore, we propose a generalized geodesic basis function neural network (G2BFNN) architecture. The generalized geodesic basis functions (G2BF) are defined based on generalized geodesic distances. The generalized geodesic distance metric (G2DM) is obtained by learning the manifold structure. To implement this architecture, a specific G2BFNN, named discriminative local preserving projection-based G2BFNN (DLPP-G2BFNN) is proposed. DLPP-G2BFNN mainly contains two modules, namely the manifold structure learning module (MSLM) and the network mapping module (NMM). In the MSLM module, a supervised adjacency graph matrix is constructed to constrain the learning of the manifold structure. This enables the learned features in the embedding subspace to maintain the manifold structure while enhancing the discriminability. The features and G2DM learned in the MSLM are fed into the NMM. Through the G2BF in the NMM, the spatial distribution features on manifold are obtained. Finally, the output of the network is obtained through the fully connected layer. Compared with the local response neural network based on Euclidean distance, the proposed network can reveal more essential spatial structure characteristics of the data. Meanwhile, the proposed G2BFNN is a generalized network architecture that can be combined with any manifold learning method, showcasing high scalability. The experimental results demonstrate that the proposed DLPP-G2BFNN outperforms existing methods by utilizing fewer kernels while achieving higher recognition performance.

ACFL: Communication-Efficient adversarial contrastive federated learning for medical image segmentation

Federated learning is a popular machine learning paradigm that achieves decentralized model training on distributed devices, ensuring data decentralization, privacy protection, and enhanced overall learning effectiveness. However, the non-independence and identically distributed (i.e., non-IID) nature of medical data across different institutes has remained a significant challenge in federated learning. Current research has mainly focused on addressing label distribution skew and classification scenarios, overlooking the feature distribution skew settings and more challenging semantic segmentation scenarios. In this paper, we present communication-efficient Adversarial Contrastive Federated Learning (ACFL) for the prevalent feature distribution skew scenarios in medical semantic segmentation. The core idea of the approach is to enhance model generalization by learning each client’s domain-invariant features through adversarial training. Specifically, we introduce a global discriminator that, through contrastive learning in the server, trains to differentiate feature representations from various clients. Meanwhile, the clients learn common domain-invariant features through prototype contrastive learning and global discriminator training. Furthermore, by utilizing Gaussian mixture models for virtual feature sampling on the server, compared to transmitting raw features, the ACFL method possesses the additional advantages of efficient communication and privacy protection. Extensive experiments on two medical semantic segmentation datasets and extension on three classification datasets validated the superiority of the proposed method.

A combined RF–GRNN algorithm for monitoring complex damage of bolted joints with high-level robustness

Bolted joints in aerospace, rail transportation, civil engineering, and other applications are prone to various forms of damage, such as bolt loosening and crack, due to the harsh service environments. The difficulties arising from crosstalk and nonlinear evaluation between composite damage and single damage at bolted joints in practical monitoring environments are particularly pronounced. In response to this challenge, we propose an integrated algorithm, namely the random forest-generalized regression neural network (RF–GRNN) algorithm, characterized by high-level robustness. The proposed algorithm adheres to the core concept of “specificity” and forms a multi-task prediction framework of “classification before regression.” This approach enables efficient damage assessment and mitigates the nonlinear complexity of the prediction model. To evaluate the effectiveness of the RF–GRNN algorithm, its generalization, robustness, and prediction accuracy based on the piezoelectric ultrasonic guided wave principle under 0%–10% noise (the corresponding minimum signal-to-noise ratio was 10.4 dB) interference were investigated. Additionally, we clarify the impact of feature selection and its combination method on the algorithm’s prediction performance, deciphering the intrinsic link between prediction performance and feature distribution. The results demonstrate that the presented algorithm achieves the accurate classification and quantification of multiple bolted structural states, including no damage, crack, loosening, and crack-loosening composite damage. Therefore, the RF–GRNN algorithm is an important attempt to solve the bottleneck present in existing damage monitoring techniques which fail to balance the identification and quantification of multiple damage models.

The Cenozoic Abanico rift system: Implications of increased southward extension in the southern central Andes, in Chile

The late Eocene-Early Miocene intra-arc Abanico extensional basin represents a major feature in central Chile (∼31°-42°S). Such basin system concentrated the magmatic activity along this Andean region and hosted locally more than 3.000 m of volcanic and volcaniclastic deposits (Abanico Formation) over a southward thinning crust (<35 km thick). South of 34°30′S, major changes occur in and out of the basin realm that modify the rather regular distribution of the geological features observed northwards, namely: 1. Southward termination of the exposures of the Farellones Formation, 2. Increased presence of pre-Abanico volcanic and plutonic exposures in the basin realm, 3. Southward width increase of the basin, 4. Abrupt end in the Maule region of the Cretaceous plutonic swaths exposed in the eastern Coastal Cordillera and westward bend of the swaths of Mesozoic units, 5. Increased presence of primitive volcanic rocks in the west-side of the basin, and 6. Presence, south of 36°S, of the Cura-Mallín Formation on the east-side of the basin. These changes are caused by the oblique orientation of the Abanico basin relative to the Mesozoic structural and paleogeographic trends and are enhanced by the increased southward opening of the basin. This opening would have occurred through a westward scissors-like rotation of the block of continental crust located west of the basin, which corresponds to the present-day Coastal Cordillera south of 34°30′S. The eastern border, which is represented by the El Diablo fault, remained essentially fixed. The westward rotation is supported by the north-northeast orientation of the Mesozoic plutonic and stratified swaths south of 34°30′S. Additionally, the swaths of Mesozoic rocks are obliquely interrupted by the similarly oriented western border of the basin. Previous analogue models designed to understand the opening and closure mechanisms of an extensional basin show that greater extension and subsidence in the basin occur next to the mobile border, which in the Abanico basin was located on its west side. This observation aligns with the increased southward presence of primitive volcanic rocks, like the Colbún Formation, in the region where crustal thinning would have been greater. Analogue models show that the increased southward extension allowed the development of wider depocenters. In the Maule region, an eastern depocenter near the El Diablo fault, hosted the Early to Middle Miocene deposits of the Cura-Mallín Formation. During contraction, deeply rooted reverse faults can involve basement rocks of the basin and bring them up to the surface as observed in the Abanico basin realm in the Tinguiririca and Maule regions. This study also highlights the continuity and importance of the El Diablo fault in the configuration of the basin. It is shown that, notwithstanding the existence of major changes south of 34°30′S, this fault represents a major structural element that remained unchanged along the Andean segment comprised between ∼32° and 36°30′S separating the Cenozoic deposits to the west from Mesozoic deposits to the east. This fault can be traced continuously from, at least, the Aconcagua valley (33°S) to the Maule region (36°30′S), and most probably extends further south. Apart from separating the Cenozoic Abanico basin deposits from the Mesozoic units involved in the east-vergent Andean fold-thrust belt, its trace forms an almost straight line that connects the Palomo, Tinguiririca, Planchón-Peteroa, Descabezados, San Pedro and Rezago volcanic centers and complexes, hot-springs, and hydrothermal alterations.

An analytical study of TEG loss in a natural gas purification plant based on high-pressure droplet angular scattering

In the process of purifying natural gas, natural gas dehydration plants use triethylene glycol (TEG) as a solvent for absorption. However, the loss of TEGs in the form of droplets can pollute pipelines and create a technological challenge. Using the geometric optical approximation (GOA) method, a model was developed to predict the scattering of droplets at high pressure. Based on this model, a device was designed and constructed to inspect droplets in external pipelines and distillation column tailgate lines online, which are the outlets of the natural gas dehydration unit (TEG absorber tower) of four columns in stable production. This device analyzes the components of the sampled droplets and performs online inspection to ensure smooth and safe operation. The results of the experiment indicate that the TEG content in the droplet samples exceeded 80%, which helped identify the source of the loss. The amount of treatment directly affected the concentration and distribution features of the entrained droplets, whereas the impact of the gas-phase pressure change was negligible. This study investigated three different forms of filtration separation, which provided industrial data for the separation and recovery process of entrained droplets. This study provides a new testing tool and method to examine plate towers under high pressure and provides a theoretical reference for dewatering procedures in natural gas purification plants.

Global feature capture and spatially-aware neural networks for predicting CO2-flooding performance in heterogeneous low-permeable reservoirs

CO2-flooding can enhance crude oil recovery rates by reducing the viscosity of crude oil, improving the mobility ratio between crude oil and water, and leveraging the swelling effects of crude oil components. Furthermore, it facilitates the sequestration of greenhouse gases, leading to the realization of carbon capture, utilization, and storage (CCUS), which holds significant strategic importance for mitigating climate change, safeguarding ecological environments, and achieving sustainable development. Consequently, predicting CO2-flooding performance in heterogeneous low-permeability reservoirs holds crucial significance in sustainable energy production. However, the drawbacks of numerical simulation techniques, such as extensive computational resource consumption and prolonged simulation durations, have prompted extensive research into the utilization of artificial intelligence technologies. Prevalent approaches often treat the problem as a time series issue, which proves inadequate for reservoirs lacking historical production data. Furthermore, this methodology is unable to fully exploit the complex implicit relationships between various factors and the prediction target. Our study proposes a novel method for predicting the performance, which stands apart from previous approaches by not treating the problem as a time series issue, eliminating the need for historical production data for each prediction, and can predict various production variables such as gas production, oil production, water production, etc. in a universal manner. We combine enhanced MultiScale Non-local Neural Networks with ConvNet to handle sparse well network matrices with injection-production parameters. Additionally, we employ MultiScale convolutional networks with spatial attention mechanism to address formation permeability fields with spatial distribution features. Experimental results demonstrate the superiority of our approach in accuracy, achieving a prediction accuracy of over 97%. This research provides an innovative and flexible method, making significant contributions to the intelligentization and sustainable development of the petroleum industry, aligned with global efforts to both reduce carbon emissions and neutralize the existing ones.

Permafrost thaw and thermokarst in the source region of the Yangtze river in the central Tibetan plateau revealed by radar and optical remote sensing

AbstractThe landscape and landforms in permafrost regions are transforming due to climate change and permafrost thaw. This study uses optical and radar remote sensing, alongside spatial analysis, to examine thermokarst features and their driving factors in the source region of the Yangtze River (SRYR) on the central Tibetan Plateau. We analyse the distribution, interaction, and key environmental factors influencing thermokarst ponds and ground surface deformation, which are the two widespread and noticeable thermokarst features. Since the 1960s, the number of small water bodies has doubled from approximately ~2 × 104 to ~4 × 104 by the 2020s, with the median size of these water bodies decreasing from 2.3 × 104 m2 to 1.4 × 104 m2. The permafrost terrain has an average subsidence rate of 6.8 mm/a. About 50.9% of the SRYR exhibits evident thermokarst features. Surficial geological factors, especially geomorphology and slope, are primary factors in shaping the spatial distributions of thermokarst features. Both seasonal deformation and long‐term subsidence rates are more pronounced in areas with thermokarst ponds. However, once pond coverage exceeds around 5%, the amplifying effect on long‐term subsidence rates and seasonal deformation diminishes. The investigation further reveals that the relationship between seasonal deformation and long‐term subsidence is not strictly linear and that the combined increase in seasonal deformation and long‐term subsidence applies only to areas with seasonal deformation below approximately 20 mm. Beyond this threshold, the long‐term subsidence rate is no longer exacerbated by increased seasonal deformation.

Signs of Legal and Pseudolegal Authority: A Corpus-Based Comparison of Contemporary Courtroom Filings

AbstractLegal language exists in a peculiar state of tension. It is theoretically expected to meet the specific technical needs of a range of professions while simultaneously remaining entirely accessible to the public at large. Its success at that latter aim is at best limited, with laypeople generally more able to recognize that a given text is legal in character than they are to grasp its technical content. For such readers, the primary semiotic function of legal language is an indexical one, indicating that a text possesses a particular authoritative status even if its intended legal function remains opaque. This paper explores that authoritative indexicality of legal language through the multisemiotic analysis of two corpora: a corpus of legitimate legal documents filed in an American courthouse written by licensed attorneys and a corpus of pseudolegal documents filed in that same courthouse written by members of the Sovereign Citizen conspiracy movement. Sovereign Citizens appropriate features characteristic of legitimate legal language in their pseudolegal writings in an effort to imbue them with real legal authority. The comparison of these two corpora therefore provides a unique perspective on which features of legal writing most clearly communicate authority to non-lawyers. In addition to discussing the ways in which legal authority is manifested in these two corpora, this paper also outlines a novel method for the visualization of the spatial distribution of target features in a corpus of static multimodal texts by employing probability density estimation to generate a series of feature-based heatmaps.

Dual-Path Neural Network based on Deep Features and Transfer Learning for Bearing Fault Diagnosis

The safe operation of mechanical equipment is a basic requirement in the industrial manufacturing process. As an important component of mechanical equipment, rolling bearings are prone to unforeseen failures due to long-term operation under complex conditions. The occurrence of failures, no matter how big or small, will cause economic losses. Therefore, reliable diagnosis of rolling bearings is crucial. Aiming at the problem of insufficient feature recognition of convolutional neural networks under strong noise background, a deep feature extraction network integrating multiscale convolutional neural network (MSCNN) and bidirectional gated recurrent unit (BiGRU) is proposed. MSCNN and BiGRU are used to extract multiscale features and temporal features from noisy vibration signals respectively, and different weights are assigned to the fused features through the attention mechanism module to achieve important feature selection. Furthermore, in order to solve the problem of different feature distributions between the source domain and the target domain under variable working conditions, transfer learning is introduced in the proposed deep feature extraction network. The difference in feature distribution between the source domain and the target domain is measured by a multi-level distance formula, and the measurement result is added to the loss function. The back propagation of the loss is used to achieve the alignment of feature distribution between the source domain and the target domain. Finally, the model uses the SoftMax function as a classifier for rolling bearing fault diagnosis. Experimental comparison and analysis show that the proposed model has good migration ability and achieves a higher fault identification accuracy.

Approach angle estimation method for ships based on deep learning

Accurately estimating the ship's approach angle is crucial during berthing, or passing through navigational structures. It forms the foundation for ship navigation decisions. This study introduces the LiDAR point cloud-based ship pose perception network (PP-Net), a novel deep learning-based method for acquiring ship approach angles. Addressing the challenge of manually annotating approach angles, the ship pose perception method based on point cloud feature distribution (FD) was proposed to obtain initial angle estimates. The max-pooling function was utilized to address the disorder of point clouds, and a multi-resolution feature extractor was employed to enhance the network's robustness in extracting features from inconsistently dense point clouds. By using iterative farthest point sampling (IFPS), datasets with varying numbers of point clouds were standardized to a fixed number of points, thereby normalizing input dimensions and improving computational efficiency. Additionally, a novel loss function was proposed to improve the model's predictive accuracy. Experimental validation conducted in the scenario of ships entering ship lifts demonstrates the effectiveness of the proposed method. The outcomes can support safe navigation for ships in restricted waterways.