Distribution Constraints Research Articles

Broad Distributed Game Learning for intelligent classification in rolling bearing fault diagnosis

As a new Single Layer Feedforward Network (SLFN) architecture, Broad Learning System (BLS) has been widely used in the field of fault diagnosis because of its fast-training speed and high generalization capability. However, when features in different classes of signals are similar or weak, BLS generates a large number of redundant features that may be difficult to classify accurately. In view of this, a new Broad Distributed Game Learning (BDGL) method is proposed in this paper, which maps data into the game space by constructing two non-parallel game hyperplanes to achieve game and segmentation of different similar features, thereby making the data linearly differentiable in the game space. Meanwhile, a linear distribution constraint term is designed to reduce noise fitting and weak feature learning in training data learning by limiting the complexity of model parameters, thereby making the solution of the objective function simpler and faster. By comparing the Precision, Recall, F-score, Kappa and Accuracy of BDGL and the comparison methods on the two types of rolling bearing experimental data, the results show that BDGL has a high classification accuracy. In addition, the experimental results on small and noisy samples once again demonstrate the effectiveness of BDGL, which provides an efficient solution for rolling bearing fault diagnosis.

Analysis of the Tourism Revenue Sharing Status at the Aksu-Zhabagly Nature Reserve of Kazakhstan

Sharing tourism-generated revenues with local people has become a popular strategy for implementing sustainability in nature-based tourism destinations globally. Although the local people have received some economic gains from tourism development, there are still some limitations to fair income sharing. These limitations are evident in many underdeveloped countries and lead to a passive situation of local community participation in tourism development. The primary purpose of this article is to determine the level of tourism revenue sharing in the Aksu-Zhabagly tourist destination and, at the same time, to make appropriate recommendations on the remaining issues. To understand the status of tourism revenue sharing, we surveyed the perceptions of 44 nature reserve employees and 66 travel company workers, respectively. The survey results show that although the business operations of tourism organizers do not harm the living environment of the local population, they usually do not spend part of the income from tourism on the common good of the local population. Most residents are unsatisfied with tourism development, and their participation in tourism is also comparatively low. The results also reveal that the comparatively low level of sharing the tourism-associated revenue with local development is the leading indirect cause of residents’ dissatisfaction with the development of the tourism industry. In conclusion, we believe that the results of this study and our recommendations help local authorities understand the importance of removing constraints in the fair distribution of tourism revenues in this tourist destination.

Signal-devices management and data-driven evidential constraints based robust dispatch strategy of virtual power plant

Ensuring the safety and reliability of energy systems is very important in power grid operation. However, inherent intricacies and uncertainties of modern-day power systems, such as the mismatch between signal frequency and equipment response speed and the stochasticity associated with renewable energy and load forecasts, create significant challenges for generation dispatch planning. This study proposes a robust optimization approach with constraints based on signal-devices management and data-driven evidential distribution constraints. The first stage of this approach is to decompose and recombine the net power demand according to the Hilbert-Huang transform and device capability. The signal-device management constraints are then established based on this. The second stage formulates an evidential constraint based on data-driven evidential distribution and chance constraints in a distributionally robust optimization framework that caters to the stochasticity associated with renewable energy and load forecasts. The proposed model is validated on a virtual power plant to assess the approach’s efficacy for different dispatching scenarios. Penalty-based sensitivity analysis provides further insights into the proposed method’s performance for varying levels of CO2 emissions. Simulation results demonstrate that system flexibility becomes increasingly crucial for maintaining system stability and security as the penetration of renewable energy grows. Compared with chance constraint, the proposed data-driven evidential constraint effectively enables the optimization framework to handle stochasticity after sacrificing 0.62% more economic loss and 0.7% more environmental loss. Excessively high penalty parameters for CO2 do not promote economic development, resulting in 21.08% and 52.51% more economic and environmental losses without obvious environmental protection.

ST-GEARS: Advancing 3D downstream research through accurate spatial information recovery

Three-dimensional Spatial Transcriptomics has revolutionized our understanding of tissue regionalization, organogenesis, and development. However, existing approaches overlook either spatial information or experiment-induced distortions, leading to significant discrepancies between reconstruction results and in vivo cell locations, causing unreliable downstream analysis. To address these challenges, we propose ST-GEARS (Spatial Transcriptomics GEospatial profile recovery system through AnchoRS). By employing innovative Distributive Constraints into the Optimization scheme, ST-GEARS retrieves anchors with exceeding precision that connect closest spots across sections in vivo. Guided by the anchors, it first rigidly aligns sections, next solves and denoises Elastic Fields to counteract distortions. Through mathematically proved Bi-sectional Fields Application, it eventually recovers the original spatial profile. Studying ST-GEARS across number of sections, sectional distances and sequencing platforms, we observed its outstanding performance on tissue, cell, and gene levels. ST-GEARS provides precise and well-explainable ‘gears’ between in vivo situations and in vitro analysis, powerfully fueling potential of biological discoveries.

Generative Variational-Contrastive Learning for Self-Supervised Point Cloud Representation.

Self-supervised representation learning for 3D point clouds has attracted increasing attention. However, existing methods in the field of 3D computer vision generally use fixed embeddings to represent the latent features, and impose hard constraints on the embeddings to make the latent feature values of the positive samples converge to consistency, which limits the ability of feature extractors to generalize over different data domains. To address this issue, we propose a Generative Variational-Contrastive Learning (GVC) model, where Gaussian distribution is used to construct a continuous, smoothed representation of the latent features. A distribution constraint and cross-supervision are constructed to improve the transfer ability of the feature extractor over synthetic and real-world data. Specifically, we design a variational contrastive module to constrain the feature distribution instead of feature values corresponding to each sample in the latent space. Moreover, a generative cross-supervision module is introduced to preserve the invariance features and promote the consistency of feature distribution among positive samples. Experimental results demonstrate that GVC achieves SOTA on different downstream tasks. In particular, with only pre-training on the synthetic dataset, GVC achieves a lead of 8.4% and 14.2% when transferring to the real-world dataset in the linear classification and few-shot classification.

A Review of Research on Cold Chain Logistics and Distribution of Fresh Agricultural Products in China

At present, China, as the second largest economy in the world, is in the new development pattern, that is, to build a new development pattern with the domestic macro-cycle as the main body and the domestic and international double-cycle promoting each other, which has high requirements for the smoothness of the circulation system, urgently needs the circulation system to have a high degree of smoothness, and urgently needs to accelerate the upgrading of the logistics distribution industry, so as to realise the synchronous development of the logistics distribution industry and the economy of the country. Moreover, under the background of China's rapid development, people's needs for fresh agricultural products and other cold-chain products, as well as product quality requirements have gradually improved, therefore, under the background of rapid changes in the market, the management of China's cold-chain logistics should also be further improved to meet the market requirements. Based on this, this paper takes cold chain logistics and distribution as an entry point, and through the current development status of cold chain logistics and distribution of fresh agricultural products, the distribution mode status quo, the current research status of the constraints of fresh agricultural products logistics and distribution, as well as distribution optimisation strategy research, etc., it is hoped to draw the research direction and research focus of future cold chain logistics and distribution of fresh agricultural products, with a view to providing reference opinions to promote China's fresh agricultural products in the cold chain logistics development and improvement, so as to meet the market's requirements. In order to provide reference opinions to promote the development and improvement of the cold chain logistics of fresh agricultural products in China, so as to meet the higher requirements of the people for fresh agricultural products.

Disentangled variational auto-encoder for multimodal fusion performance analysis in multimodal sentiment analysis

Multimodal Sentiment Analysis (MSA) holds extensive applicability owing to its capacity to analyze and interpret users' emotions, feelings, and perspectives by integrating complementary information from multiple modalities. However, inefficient and unbalanced cross-modal information fusion substantially undermines the accuracy and reliability of MSA models. Consequently, a critical challenge in the field now lies in effectively assessing the information integration capabilities of these models to ensure balanced and equitable processing of multimodal data. In this paper, a Disentanglement-based Variable Auto-Encoder (DVAE) is proposed for systematically assessing fusion performance and investigating the factors that facilitate multimodal fusion. Specifically, a distribution constraint module is presented to decouple the fusion matrices and generate multiple low-dimensional and trustworthy disentangled latent vectors that adhere to the authentic unimodal input distribution. In addition, a combined loss term is modified to effectively balance inductive bias, signal reconstruction, and distribution constraint items to facilitate the optimization of neural network weights and parameters. Utilizing the proposed evaluation method, we can evaluate the fusion performance of multimodal models by contrasting the classification degradation ratio derived from disentangled hidden representations and joint representations. Experiments conducted with eight state-of-the-art multimodal fusion methods on the CMU-MOSEI and CMU-MOSEI benchmark datasets demonstrate that DVAE is capable of effectively evaluating the effects of multimodal fusion. Moreover, the comparative experimental results indicate that the equalizing effect among various advanced mechanisms in multimodal sentiment analysis, as well as the single-peak characteristic of the ground label distribution, both contribute significantly to multimodal data fusion.

Unified bi-encoder bispace-discriminator disentanglement for cross-domain echocardiography segmentation

Disentanglement-based methods effectively facilitate domain-invariant feature learning in Unsupervised Domain Adaptation (UDA) by leveraging complementary domain-specific information relating to statistical distribution differences. However, in scenarios involving cross-domain echocardiography, spectral information is important for determining distribution differences. Existing disentanglement-based methods overlook these spectral differences, resulting in insufficient learning of domain-specific features and unreliable domain-invariant feature disentanglement across different medical centers (domains). In addition, aligning the global marginal distribution in cross-domain disentanglement results in spatially misaligned semantics in domain-invariant features at the pixel level, which hinders robust UDA segmentation. We advance disentanglement learning by designing a novel unified bi-encoder bispace-discriminator disentanglement network (UB2D-Net) to disentangle reliable domain-invariant features and adapt the pixel-level aligned semantics preserved therein, thereby achieving robust cross-domain echocardiography segmentation. A space distribution constraint loss is designed to incorporate bispace (spatial and spectral) knowledge into the unified bi-encoder disentanglement path to promote the learning of sufficient domain-specific features in disentanglement. Furthermore, we leverage the confidence-aware weight, which is a novel form of the spatial attention mechanism, to transfer the pixel-level aligned semantics preserved in UDA for the spatial consistency-guided segmentation. We validated our UB2D-Net for cross-domain left ventricular segmentation on two public echocardiography datasets. Extensive comparison and ablation experiments of UDA segmentation in either CAMUS → EchoNet-Dynamic or EchoNet-Dynamic → CAMUS tasks demonstrated that our method outperformed strong state-of-the-art algorithms.

FeverNet: Enabling accurate and robust remote fever screening

Remote human fever screening via thermal infrared imaging helps reduce the risk of respiratory disease transmission and plays an important role in public health monitoring. However, the accuracy of such systems often falls prey to variations in measurement distance and environment temperature. Most previous methods tend to employ sensors to overcome these variations, which are expensive schemes and have limited performance improvement. To address above problems, this paper presents a novel and robust remote fever screening framework named FeverNet. Specifically, FeverNet introduces depth estimation network and temperature distribution constraints across time periods to reduce the influence of distance variations and environment temperature changes. The fever attention module is thus proposed to enhance feature representation and expand the difference between fever faces and normal ones. In addition, we provide the Extended Thermal Infrared Face dataset (ETIF), which further gives visible images (paired with thermal infrared images) for depth estimation and improve the fever face generated method based on the maximum temperature of the face. Extensive experiments on ETIF demonstrate the advantages of our FeverNet over the state-of-the-art methods.

Massively parallel Bayesian estimation with Sequential Monte Carlo sampling for simultaneous estimation of earthquake fault geometry and slip distribution

In inverse analysis, Bayesian estimation is useful for understanding the reliability of the estimation result or prediction based on it because it can estimate not only optimal parameters but also their uncertainties. The estimation of an earthquake source fault based on observed crustal deformation is a typical inverse problem in the field of earthquake research. In this study, a method for simultaneous Bayesian estimation of earthquake fault plane geometry and spatially variable slip distribution on the plane has been developed. The developed method can be applied to stochastic models with arbitrary probability distribution settings, and it enables to incorporate appropriate constraints for slip distribution in the estimation process, which can lead to enhanced robustness and stability of estimation. Since this method is computationally more expensive than conventional methods, large-scale parallel computing was introduced to cope with the increased computational cost and a supercomputer was used for the analysis. To validate the proposed method, simultaneous Bayesian estimation of fault geometry and slip distribution with slip constraints was performed using the crustal deformation observed in the 2018 Hokkaido Eastern Iburi earthquake. Hierarchical parameterization and massively parallelized Bayesian inference used in this study have broad applicability not only in earthquake research but also in other scientific and engineering fields.

Molecular sequence classification using efficient kernel based embedding

The alarming spread of diseases across the globe has become a major concern for global healthcare agencies. The research community is actively involved in inventing better and more efficient ways of detecting and treating diseases to solve this global challenge. The abundance of molecular sequence data has eased the path for researchers to develop Machine Learning (ML) based solutions. The performance of the ML models used to classify molecular sequences depends heavily on the type of embedding used to obtain an appropriate numerical representation of the molecular sequences. In recent years, many embedding approaches have been introduced for molecular sequence analysis. However, there is still a need for improvement as far as the efficiency of the methods is concerned (i.e., the ability to capture pairwise relationships and patterns effectively, which could affect the classification performance). To provide a solution to this problem, we propose an efficient kernel-based technique for embedding generation from molecular sequences, which involves computing a kernel matrix using the Sinkhorn-Knopp algorithm and the normalized pairwise distances between k-mers in a manner that satisfies the constraints of a probability distribution. Further, kernel principal component analysis (PCA) is applied to get the top PCs, which are then used as the final embedding. As a result of the experiments, we obtained an ROC-AUC score of 0.657 for our method, which is higher than the scores obtained using baselines. This clearly shows that the low-dimensional embedding obtained through the proposed approach provides an efficient and effective solution for molecular sequence analysis.

Energy–Logistics Cooperative Optimization for a Port-Integrated Energy System

In order to achieve carbon peak and neutrality goals, many low-carbon operations are implemented in ports. Integrated energy systems that consist of port electricity and cooling loads, wind and PV energy devices, energy storage, and clean fuels are considered as a future technology. In addition, ports are important hubs for the global economy and trade; logistics optimization is also part of their objective, and most port facilities have complex logistics. This article proposes an energy–logistics collaborative optimization method to fully tap the potential of port-integrated energy systems. A logistics–energy system model is established by deeply examining the operational characteristics of logistics systems and their corresponding energy consumption patterns, considering ships’ operational statuses, quay crane distribution constraints, and power balances. To better represent the ship–energy–logistics optimization problem, a hybrid system modeling technique is employed. The case of Shanghai Port is studied; the results show that costs can be reduced by 3.27% compared to the traditional optimization method, and a sensitivity analysis demonstrates the robustness of the proposed method.

Easy manufacturing constraint based topology optimization of dual-scale and dual-constituent lattice metastructure with thermal dimensional stability

Thermal dimensional stability (TDS) is a crucial issue in the development of high-end industry equipment and precision instruments that work in fluctuating thermal environments. To endow meta-structures with high load-carrying capacity and TDS functionality simultaneously, this paper proposes a topology optimization framework to optimize the topologies of lattice meta-structures at macroscopic structural and microscopic material scales concurrently. An important feature of the current optimization model is the introduction of a material concentration distribution (MCD) constraint to reduce the number of dual-constituent interfaces (DIs), which enables the easy manufacturing of the optimized structures because an additional fabrication process is required for the connection of heterogeneous lattice members. Designs for two dual-scale TDS structures, potentially employed for satellite payload platforms and the supporting structure of space telescopes, are completed. Compared with mono-scale TDS structures, the dual-scale schemes exhibit superior structural performances due to the opening of the dual-scale design space. Numerical experiments are performed to validate the ultra-low structural thermal deformations of the optimized TDS structures with values of 0.0743 μm/℃ and 0.153 μm/℃. Furthermore, the imposition of the MCD constraint significantly reduces the number of DIs from 38 to 10 within a lattice cell, enabling the easy assembly of the demonstrative 3D printing dual-constituent samples.

Dynamic rebalancing optimization for bike-sharing systems: A modeling framework and empirical comparison

Station-based Bike-sharing systems have been implemented in multiple major cities, offering a low-cost and environmentally friendly transportation alternative. As a remedy to unbalanced stations, operators typically rebalance bikes by trucks. The resulting dynamic planning has received significant attention from the Operations Research community. Due to its modeling flexibility, mixed-integer programming remains a popular choice. However, the complex planning problem requires significant simplifications to obtain a computationally tractable model. As a result, existing models have used a large variety of modeling assumptions and techniques regarding decision variables and constraints. Unfortunately, the impact of such assumptions on the solutions’ performance in practice remains generally unexplored.In this paper, we first systematically survey the literature on rebalancing problems and their modeling assumptions. We then propose a general mixed-integer programming model for multi-period rebalancing problems that can be easily adapted to different assumptions, including trip modeling, time discretization, trip distribution, and event sequences. We develop an instance generator to synthesize realistic station networks and customer trips, as well as a realistic fine-grained simulator to evaluate the operational performance of rebalancing strategies. Finally, extensive numerical experiments are carried out, both on the synthetic and real-world data, to analyze the effectiveness of various modeling assumptions and techniques. Based on our results, we identify the assumptions that empirically provide the most effective rebalancing strategies in practice. Specifically, a set of specific trip distribution constraints and event sequences ignored in the previous literature seem to provide particularly good results.

Analysis of Parenting Stress, Co-parenting Level, Family Intimacy and Adaptability on Children's Social Skills via self-attention Network

This paper uses the self-attention method to track family intimacy. We propose the Self-Attention Adversarial Deep Subspace Clustering Algorithm (SAADSC). The self-attention adversarial network is used to impose a prior distribution constraint in the feature learning of the autoencoder, which guides the learned feature representation to be more robust, thereby improving the clustering accuracy. The results show that the proposed algorithm outperforms the state-of-the-art methods in terms of accuracy (ACC) and standard mutual information (NMI). Therefore, we can effectively transfer this self-attention method to the analysis of the effects of adaptation on children's social skills.

Patch-based tendency camera multi-constraint learning for unsupervised person re-identification

Unsupervised person re-identification (ReID) is a task that aims to retrieve pedestrians across different cameras from unlabeled data. Existing methods rely on clustering to generate pseudo-labels, but they are inevitably noisy. Although pseudo-label refinement approaches have been presented, the essentiality of patch contours is ignored. The tendency analysis of retrieval between global and patch features has not been well investigated. In this paper, we propose a Patch-based Tendency Camera Multi-Constraint Learning (PTCML) model for unsupervised person ReID. First, to explore the tendentious retrieval of global and patch features, we design a Ranking Tendency Similarity (RTS) score by gauging the distribution discrepancy of distance changes. Second, based on RTS score, we propose a Tendency-based Mutual Complementation (TMC) loss to improve the quality of global and patch pseudo-labels. Third, to resist camera variations, we propose an Adaptive Camera Multi-Constraint (ACM) loss to optimize recognition results with camera distribution constraint and instance constraint simultaneously. Finally, numerous experiments on Market-1501 and MSMT17 demonstrate that our method can significantly surpass the state-of-the-art performance.

A multimodal shared network with a cross-modal distribution constraint for continuous emotion recognition

Continuous emotion recognition has been a compelling topic in affective computing because it can interpret human emotions subtly and continuously. Existing studies have achieved advanced emotion recognition performance using multimodal knowledge. However, these studies generally ignore the circumstances where some particular modalities are missing in the inference phase and thus become sensitive to the absence of modalities. To resolve this issue, we propose a novel multimodal shared network with a cross-modal distribution constraint, i.e. the DS-Net, which aims to improve the robustness of the model to missing modalities. The training process of the proposed network generally includes two components: multimodal shared space modeling and a cross-modal distribution matching constraint. The former utilizes the local and temporal information of multimodal signals for multimodal shared space modeling, while the latter further enhances the multimodal shared space via a loose constraint method. Coupled with the latter, the former can effectively exploit the complementarity between videos and peripheral physiological signals (PPSs), thus enhancing the discriminative capability of the shared space. Based on the shared space, the DS-Net works during the inference phase with only one modality input and can leverage multimodal knowledge to improve emotion recognition accuracy. Comprehensive experiments were conducted on two public datasets. Results demonstrate that the proposed method is competitive or superior to the current state-of-the-art methods. Further experiments indicate that the proposed method can be extended to handle other modalities and to deal with partially missing modalities, demonstrating its potential in real-world applications.

Optimization design of a new variable type hierarchical fuzzy system with interpretability improvement

This paper proposes a variable-type hierarchical fuzzy system (VTHFS) with high accuracy and strong interpretability. An improved rear-part direct-connected structure is used in the VTHFS, which eliminates the intermediate variables of the hierarchical fuzzy system (HFS). A new feature sorting method is proposed to find suitable input variables for each layer of subsystems of VTHFS. Under the proposed topology structure, layer by layer training of VTHFS can be achieved by changing the expected output of each layer, thereby reducing residual errors layer by layer and improving the prediction accuracy of VTHFS. Three fuzzy set distribution constraints are used in parameter optimization of VTHFS to improve the interpretability, including integrity, distinguishability, and footprint of uncertainty. The type of fuzzy set is automatically adjusted according to the uncertainty characteristics of input data measured by fuzziness, which further enhances the semantic interpretability of the VTHFS and solves the problem of requiring prior knowledge to define the fuzzy set type in existing research. Finally, the proposed VTHFS is tested on the regression data sets in the real world. Experimental results demonstrate the effectiveness of the feature sorting method and the fuzzy set type adjustment method. Through a large number of quantitative indicators, it can be confirmed that VTHFS has stronger interpretability and higher prediction accuracy compared to other fuzzy systems.

Muddy irrigation ditch understanding for agriculture environmental monitoring

Understanding an irrigation ditch plays an important role in intelligent agriculture environmental monitoring, especially in field environments where large chunks of ditches are particularly covered by various types of natural unstructured soil, vegetation and weeds. However, due to the diverse and unstructured muddy ditches, understanding them remains a challenge. Traditional approaches of understanding a scene from three-dimensional (3D) point clouds or multi-sensor fusion are energy intensive and computationally complex, making them quite laborious in application on a resource-constrained system. In this study, we propose a methodology to understand irrigation ditches and reconstruct them in a 3D scene, using only a resource-constrained monocular camera, without prior training. Spatial similar textures projections are extracted and clustered. Through geometric constraints of distribution and orientation, similar texture projections are refined and their corresponding surfaces are shaped. By contours and evidence lines, the ditch bottom surfaces are represented. Thus an irrigation ditch can be understood and reconstructed in a 3D environment, which can be used in agricultural automatic control system, agricultural robots, and precise agriculture. Unlike machine learning-based algorithms, the proposed method requires no prior training nor knowledge of the camera’s internal parameters such as focal length, field angle, and aperture. Additionally, pure geometric features make the presented method robust to varying illumination and colour. The percentage of incorrectly classified pixels was compared to the ground truth. Experimental results demonstrated that the approach can successfully elucidate irrigation ditches, meeting requirements in safety monitoring in an agriculture environment.

Exploring the potential of federated learning for diffusion model: Training and fine-tuning

Diffusion models, a state-of-the-art generative model, have drawn attention for their capacity to produce high-quality, divers, and flexible content. However, the training of these models typically necessitates large datasets, a task that can be hindered by challenges related to privacy concerns and data distribution constraints. Due to the amount of data and hardware required for large model training, all centralized training will be done by large companies or labs with computing power. Federated Learning provides a decentralized method that allows for model training across several data sources while maintaining the data's localization, reducing privacy threats. This research proposes and evaluate a novel approach for utilizing Federated Learning in the context of diffusion models. This paper investigates the feasibility of training and fine-tuning diffusion models in a federated setting, considering various data distributions and privacy constraints. This study used the Federated Averaging (FedAvg) technique to train the unconditional diffusion model as well as to fine-tune the pre-trained diffusion mode. The experimental results demonstrate that federated training of diffusion models can achieve comparable performance to centralized training methods while preserving data locality. Additionally, Federated Learning can be effectively applied to fine-tune pre-trained diffusion model, enabling adaptation to specific tasks without exposing sensitive data. Overall, this work demonstrates Federated Learning's potential as a useful tool for training and fine-tuning diffusion models in a privacy-preserving manner.