Search Results (756)

This paper considers the control synthesis problem and its solution using symbolic regression. Symbolic regression methods, which were previously called genetic programming methods, allow one to use a computer to find not only the parameters of a given regression function but also its structure. Unlike other works on solving the control synthesis problem using symbolic regression, the novelty of this paper is that for the first time this work employs a training dataset to address the problem of general control synthesis. Initially, the optimal control problem is solved from each point in a given set of initial states, resulting in a collection of control functions expressed as functions of time. A reference model is then integrated into the control object model, which generates optimal motion trajectories using the derived optimal control functions. The control synthesis problem is framed as an approximation task for all optimal trajectories, where the control function is sought as a function of the deviation of the object from the specified terminal state. The optimization criterion for solving the synthesis problem is the accuracy of the object’s movement along the optimal trajectory. The paper includes an example of solving the control synthesis problem for a mobile robot using a supervised machine learning method. A relatively new method of symbolic regression, the method of variational complete binary genetic programming, is studied and proposed for the solution of the control synthesis problem. Full article

The existing research on security risk often focuses on specific types of crime, overlooking an integrated assessment of security risk by leveraging existing police resources. Thus, we draw on crime geography theories, integrating public security business data, socioeconomic data, and spatial analysis techniques, to identify integrated risk points and areas by examining the distribution of police resources and related factors and their influence on security risk. The findings indicate that security risk areas encompass high-incidence areas of public security issues, locations with concentrations of dangerous individuals and key facilities, and regions with a limited police presence, characterized by dense populations, diverse urban functions, high crime probabilities, and inadequate supervision. While both police resources and security risk are concentrated in urban areas, the latter exhibits a more scattered distribution on the urban periphery, suggesting opportunities to optimize resource allocation by extending police coverage to risk hotspots lacking patrol stations. Notably, Level 1 security risk areas often coincide with areas lacking a police presence, underscoring the need for strategic resource allocation. By comprehensively assessing the impact of police resources and public security data on spatial risk distribution, this study provides valuable insights for public security management and police operations. Full article

Interoperability between different virtual platforms requires the ability to search and transfer digital assets across platforms. Digital assets in virtual platforms are represented in different forms or modalities, such as images, meshes, and point clouds. The cross-modal retrieval of three-dimensional (3D) object representations is challenging due to data representation diversity, making common feature space discovery difficult. Recent studies have been focused on obtaining feature consistency within the same classes and modalities using cross-modal center loss. However, center features are sensitive to hyperparameter variations, making cross-modal center loss susceptible to performance degradation. This paper proposes a new 3D cross-modal retrieval method that uses cross-modal supervised contrastive learning (CSupCon) and the fixed projection head (FPH) strategy. Contrastive learning mitigates the influence of hyperparameters by maximizing feature distinctiveness. The FPH strategy prevents gradient updates in the projection network, enabling the focused training of the backbone networks. The proposed method shows a mean average precision (mAP) increase of 1.17 and 0.14 in 3D cross-modal object retrieval experiments using ModelNet10 and ModelNet40 datasets compared to state-of-the-art (SOTA) methods. Full article

In traditional 3D reconstruction using UAV images, only radiance information, which is treated as a geometric constraint, is used in feature matching, allowing for the restoration of the scene’s structure. After introducing radiance supervision, NeRF can adjust the geometry in the fixed-ray direction, resulting in a smaller search space and higher robustness. Considering the lack of NeRF construction methods for aerial scenarios, we propose a new NeRF point sampling method, which is generated using a UAV imaging model, compatible with a global geographic coordinate system, and suitable for a UAV view. We found that NeRF is optimized entirely based on the radiance while ignoring the direct geometry constraint. Therefore, we designed a radiance correction strategy that considers the incidence angle. Our method can complete point sampling in a UAV imaging scene, as well as simultaneously perform digital surface model construction and ground radiance information recovery. When tested on self-acquired datasets, the NeRF variant proposed in this paper achieved better reconstruction accuracy than the original NeRF-based methods. It also reached a level of precision comparable to that of traditional photogrammetry methods, and it is capable of outputting a surface albedo that includes shadow information. Full article

Objectives: This study aimed to assess the impact of a 20-week resistance training program on force–velocity (F-V) parameters using an isokinetic two-point method and comparing one-repetition maximum (1-RM) methods in novice lifters. Methods: Previously untrained individuals completed a supervised, three-session weekly resistance training program involving concentric, eccentric, and isometric phases, repeated every 2 to 4 weeks. Isokinetic dynamometry measured the strength of elbow flexors/extensors at 60°/s and 150°/s, and knee flexors/extensors at 60°/s and 240°/s at Baseline, 3 months, and 5 months. F-V parameters, including maximal theoretical force (F0) and the F-V slope, were calculated. Participants also performed 1-RM tests for the upper and lower limbs. Repeated measures ANOVA with effect size (η² > 0.14 as large) was used to analyze changes in F-V parameters and repeated measures correlation was used to test their association with 1-RM outcomes. Results: Eighteen male participants (22.0 ± 3.4 years) were analyzed. F0 significantly increased for all muscle groups (η² = 0.423 to 0.883) except elbow flexors. F-V slope significantly decreased (steeper) for knee extensors and flexors (η² = 0.348 to 0.695). Knee extensors showed greater F0 gains and steeper F-V slopes than flexors (η² = 0.398 to 0.686). F0 gains were associated with 1-RM changes (r = 0.38 to 0.83), while F-V slope changes correlated only with lower limb 1-RM (r = −0.37 to −0.68). Conclusions: The 20-week resistance training program significantly increased F0 and shifted the F-V profile towards a more “force-oriented” state in knee muscles. These changes correlated with improved 1-RM performance. Future studies should include longer follow-ups and control groups. Full article

A cross-sectional survey was distributed to 1322 members of a 1-on-1 personalized strength training studio. A total of 366 respondents (n = 134 male and n = 232 female), all aged over 20 years, reported considerable training experience, with 55% of the males and 42% of the females reporting 5+ years of experience. The data were analyzed and reported descriptively with differences >5% identified based on the use of a 5-point Likert scale, the sample size, and the nature of the observations. Disparities between the males and females were identified; the males reported higher perceptions of managing effort, technique, and programming without supervision compared to the females. Safety was noted as being more important to the females compared to the males. Qualitatively, additional themes were raised including an analogy of the personal relationship between the trainer and trainee being similar to that between medical professionals and patients. This was validated where the participants discussed their adaptations from supervised strength training for maintaining quality of life in aging and recovering from medical conditions and injury. The data are discussed in the context of a previous body of literature suggesting males falsely report higher levels of confidence in tasks compared to females, particularly in relation to effort, role models, and verbal encouragement. We posit that the greater confidence expressed by males at least partially explains the greater engagement in strength training practices by males compared to females, as well as explaining the higher level of participation in supervised strength training by females compared to males. This research proves beneficial for strength training practitioners in enhancing their understanding and expectations of clients, as well as hopefully proving insightful in engaging more people in strength training. Full article

Supervised polarimetric synthetic aperture radar (PolSAR) image classification demands a large amount of precisely labeled data. However, such data are difficult to obtain. Therefore, many unsupervised methods have been proposed for unsupervised PolSAR image classification. The classification maps of unsupervised methods contain many high-confidence samples. These samples, which are often ignored, can be used as supervisory information to improve classification performance on PolSAR images. This study proposes a new unsupervised PolSAR image classification framework. The framework combines high-confidence superpixel pseudo-labeled samples and semi-supervised classification methods. The experiments indicated that this framework could achieve higher-level effectiveness in unsupervised PolSAR image classification. First, superpixel segmentation was performed on PolSAR images, and the geometric centers of the superpixels were generated. Second, the classification maps of rotation-domain deep mutual information (RDDMI), an unsupervised PolSAR image classification method, were used as the pseudo-labels of the central points of the superpixels. Finally, the unlabeled samples and the high-confidence pseudo-labeled samples were used to train an excellent semi-supervised method, similarity matching (SimMatch). Experiments on three real PolSAR datasets illustrated that, compared with the excellent RDDMI, the accuracy of the proposed method was increased by 1.70%, 0.99%, and 0.8%. The proposed framework provides significant performance improvements and is an efficient method for improving unsupervised PolSAR image classification. Full article

The symmetry between production efficiency and safety is a crucial aspect of industrial operations. To enhance the identification of proper safety harness use by workers at height, this study introduces a machine vision approach as a substitute for manual supervision. By focusing on the safety rope that connects the worker to an anchor point, we propose a semantic segmentation mask annotation principle to evaluate proper harness use. We introduce CEMFormer, a novel semantic segmentation model utilizing ConvNeXt as the backbone, which surpasses the traditional ResNet in accuracy. Efficient Multi-Scale Attention (EMA) is incorporated to optimize channel weights and integrate spatial information. Mask2Former serves as the segmentation head, enhanced by Poly Loss for classification and Log-Cosh Dice Loss for mask loss, thereby improving training efficiency. Experimental results indicate that CEMFormer achieves a mean accuracy of 92.31%, surpassing the baseline and five state-of-the-art models. Ablation studies underscore the contribution of each component to the model’s accuracy, demonstrating the effectiveness of the proposed approach in ensuring worker safety. Full article

Existing 3D object detection frameworks in sensor-based applications heavily rely on large-scale annotated data to achieve optimal performance. However, obtaining such annotations from sensor data—like LiDAR or image sensors—is both time-consuming and costly. Semi-supervised learning offers an efficient solution to this challenge and holds significant potential for sensor-driven artificial intelligence (AI) applications. While it reduces the need for labeled data, semi-supervised learning still depends on a small amount of labeled samples for training. In the initial stages, relying on such limited samples can adversely affect the effective training of student–teacher networks. In this paper, we propose PE-MCAT, a semi-supervised 3D object detection method that generates high-precision pseudo-labels. First, to address the challenges of insufficient local feature capture and poor robustness in point cloud data, we introduce a point enrichment module. This module incorporates information from image sensors and combines multiple feature fusion methods of local and self-features to directly enhance the quality of point clouds and pseudo-labels, compensating for the limitations posed by using only a few labeled samples. Second, we explore the relationship between the teacher network and the pseudo-labels it generates. We propose a multi-class adaptive threshold strategy to initially filter and create a high-quality pseudo-label set. Furthermore, a joint variable threshold strategy is introduced to refine this set further, enhancing the selection of superior pseudo-labels.Extensive experiments demonstrate that PE-MCAT consistently outperforms recent state-of-the-art methods across different datasets. Specifically, on the KITTI dataset and using only 2% of labeled samples, our method improved the mean Average Precision (mAP) by 0.7% for cars, 3.7% for pedestrians, and 3.0% for cyclists. Full article

Deep hashing technology, known for its low-cost storage and rapid retrieval, has become a focal point in cross-modal retrieval research as multimodal data continue to grow. However, existing supervised methods often overlook noisy labels and multiscale features in different modal datasets, leading to higher information entropy in the generated hash codes and features, which reduces retrieval performance. The variation in text annotation information across datasets further increases the information entropy during text feature extraction, resulting in suboptimal outcomes. Consequently, reducing the information entropy in text feature extraction, supplementing text feature information, and enhancing the retrieval efficiency of large-scale media data are critical challenges in cross-modal retrieval research. To tackle these, this paper introduces the Text-Enhanced Graph Attention Hashing for Cross-Modal Retrieval (TEGAH) framework. TEGAH incorporates a deep text feature extraction network and a multiscale label region fusion network to minimize information entropy and optimize feature extraction. Additionally, a Graph-Attention-based modal feature fusion network is designed to efficiently integrate multimodal information, enhance the affinity of the network for different modes, and retain more semantic information. Extensive experiments on three multilabel datasets demonstrate that the TEGAH framework significantly outperforms state-of-the-art cross-modal hashing methods. Full article

This paper introduces WaterGPT, a language model designed for complex multimodal tasks in hydrology. WaterGPT is applied in three main areas: (1) processing and analyzing data such as images and text in water resources, (2) supporting intelligent decision-making for hydrological tasks, and (3) enabling interdisciplinary information integration and knowledge-based Q&A. The model has achieved promising results. One core aspect of WaterGPT involves the meticulous segmentation of training data for the supervised fine-tuning phase, sourced from real-world data and annotated with high quality using both manual methods and GPT-series model annotations. These data are carefully categorized into four types: knowledge-based, task-oriented, negative samples, and multi-turn dialogues. Additionally, another key component is the development of a multi-agent framework called Water_Agent, which enables WaterGPT to intelligently invoke various tools to solve complex tasks in the field of water resources. This framework handles multimodal data, including text and images, allowing for deep understanding and analysis of complex hydrological environments. Based on this framework, WaterGPT has achieved over a 90% success rate in tasks such as object detection and waterbody extraction. For the waterbody extraction task, using Dice and mIoU metrics, WaterGPT’s performance on high-resolution images from 2013 to 2022 has remained stable, with accuracy exceeding 90%. Moreover, we have constructed a high-quality water resources evaluation dataset, EvalWater, which covers 21 categories and approximately 10,000 questions. Using this dataset, WaterGPT achieved the highest accuracy to date in the field of water resources, reaching 83.09%, which is about 17.83 points higher than GPT-4. Full article

SegContrast first paved the way for contrastive learning on outdoor point clouds. Its original formulation targeted individual scans in applications like autonomous driving and object detection. However, mobile mapping purposes such as digital twin cities and urban planning require large-scale dense datasets to capture the full complexity and diversity present in outdoor environments. In this paper, the SegContrast method is revisited and adapted to overcome its limitations associated with mobile mapping datasets, namely the scarcity of contrastive pairs and memory constraints. To overcome the scarcity of contrastive pairs, we propose the merging of heterogeneous datasets. However, this merging is not a straightforward procedure due to the variety of size and number of points in the point clouds of these datasets. Therefore, a data augmentation approach is designed to create a vast number of segments while optimizing the size of the point cloud samples to the allocated memory. This methodology, called CLOUDSPAM, guarantees the performance of the self-supervised model for both small- and large-scale mobile mapping point clouds. Overall, the results demonstrate the benefits of utilizing datasets with a wide range of densities and class diversity. CLOUDSPAM matched the state of the art on the KITTI-360 dataset, with a 63.6% mIoU, and came in second place on the Toronto-3D dataset. Finally, CLOUDSPAM achieved competitive results against its fully supervised counterpart with only 10% of labeled data. Full article

Rural Residential Land is a kind of public pond resource, and the implementation of the collective governance of Rural Residential Land is a response to the dilemma of utilizing the land. This paper takes the attribute of using Rural Residential Land as a public pond resource as an entry point, draws on Autonomous Governance Theory, and utilizes the OLS model and the mediated effect model to explore the influence of Government Embedment on supervisory effectiveness in the collective governance of Rural Residential Land, based on the fieldwork data of 450 farming households in three districts (cities and counties) in Sichuan Province. This study shows that Government Embedment, the Technological Environment and the Cultural Environment can significantly enhance supervisory effectiveness in the collective governance of Rural Residential Land, while the Resource Environment has a negative effect on it. The Resource Environment has a masking effect on the influence of Government Embedment on supervisory effectiveness in the collective governance of Rural Residential Land, while the Technological Environment and the Cultural Environment play a part in the mediating effect. The anonymous whistleblowing mechanism positively moderates the influence of the Technological and Cultural Environments on supervisory effectiveness. Additionally, there is obvious locational heterogeneity in the influence of Government Embedment and the Organizational Environment on supervisory effectiveness. Therefore, a coordinated supervision and sanctioning mechanism should be constructed in towns and villages to promote the integration and complementarity of formal and informal systems; a sound mechanism for anonymous reporting of illegal and irregular use of Rural Residential Land should be established; and the effective implementation of the collective governance of Rural Residential Land should be promoted in accordance with the differences in the location of the villages. Full article

This paper introduces Tensor Visibility Graph-enhanced Attention Networks (TVGeAN), a novel graph autoencoder model specifically designed for MTS learning tasks. The underlying approach of TVGeAN is to combine the power of complex networks in representing time series as graphs with the strengths of Graph Neural Networks (GNNs) in learning from graph data. TVGeAN consists of two new main components: TVG which extend the capabilities of visibility graph algorithms in representing MTSs by converting them into weighted temporal graphs where both the nodes and the edges are tensors. Each node in the TVG represents the MTS observations at a particular time, while the weights of the edges are defined based on the visibility angle algorithm. The second main component of the proposed model is GeAN, a novel graph attention mechanism developed to seamlessly integrate the temporal interactions represented in the nodes and edges of the graphs into the core learning process. GeAN achieves this by using the outer product to quantify the pairwise interactions of nodes and edges at a fine-grained level and a bilinear model to effectively distil the knowledge interwoven in these representations. From an architectural point of view, TVGeAN builds on the autoencoder approach complemented by sparse and variational learning units. The sparse learning unit is used to promote inductive learning in TVGeAN, and the variational learning unit is used to endow TVGeAN with generative capabilities. The performance of the TVGeAN model is extensively evaluated against four widely cited MTS benchmarks for both supervised and unsupervised learning tasks. The results of these evaluations show the high performance of TVGeAN for various MTS learning tasks. In particular, TVGeAN can achieve an average root mean square error of 6.8 for the C-MPASS dataset (i.e., regression learning tasks) and a precision close to one for the SMD, MSL, and SMAP datasets (i.e., anomaly detection learning tasks), which are better results than most published works. Full article

During a crown generation procedure, dental technicians depend on commercial software to generate a margin line to define the design boundary for the crown. The margin line generation remains a non-reproducible, inconsistent, and challenging procedure. In this work, we propose to generate margin line points on prepared teeth meshes using adaptive point learning inspired by the AdaPointTr model. We extracted ground truth margin lines as point clouds from the prepared teeth and crown bottom meshes. The chamfer distance (CD) and infoCD loss functions were used for training a supervised deep learning model that outputs a margin line as a point cloud. To enhance the generation results, the deep learning model was trained based on three different resolutions of the target margin lines, which were used to back-propagate the losses. Five folds were trained and an ensemble model was constructed. The training and test sets contained 913 and 134 samples, respectively, covering all teeth positions. Intraoral scanning was used to collect all samples. Our post-processing involves removing outlier points based on local point density and principal component analysis (PCA) followed by a spline prediction. Comparing our final spline predictions with the ground truth margin line using CD, we achieved a median distance of 0.137 mm. The median Hausdorff distance was 0.242 mm. We also propose a novel confidence metric for uncertainty quantification of generated margin lines during deployment. The metric was defined based on the percentage of removed outliers during the post-processing stage. The proposed end-to-end framework helps dental professionals in generating and evaluating margin lines consistently. The findings underscore the potential of deep learning to revolutionize the detection and extraction of 3D landmarks, offering personalized and robust methods to meet the increasing demands for precision and efficiency in the medical field. Full article