Search

Semantic segmentation plays a crucial role in various computer vision tasks, such as autonomous driving in urban scenes. The related researches have made significant progress. However, since most of the researches focus on how to enhance the performance of semantic segmentation models, there is a noticeable lack of attention given to the performance deterioration of these models in severe weather. To address this issue, we study the robustness of the multimodal semantic segmentation model in snowy environment, which represents a subset of severe weather conditions. The proposed method generates realistically simulated snowy environment images by combining unpaired image translation with adversarial snowflake generation, effectively misleading the segmentation model’s predictions. These generated adversarial images are then utilized for model robustness learning, enabling the model to adapt to the harshest snowy environment and enhancing its robustness to artificially adversarial perturbance to some extent. The experimental visualization results show that the proposed method can generate approximately realistic snowy environment images, and yield satisfactory visual effects for both daytime and nighttime scenes. Moreover, the experimental quantitation results generated by MFNet Dataset indicate that compared with the model without enhancement, the proposed method achieves average improvements of 4.82% and 3.95% on mAcc and mIoU, respectively. These improvements enhance the adaptability of the multimodal semantic segmentation model to snowy environments and contribute to road safety. Furthermore, the proposed method demonstrates excellent applicability, as it can be seamlessly integrated into various multimodal semantic segmentation models. [ABSTRACT FROM AUTHOR]

Recent studies have shown that deep-learning-based models for processing Unmanned Aerial Vehicle (UAV) remote sensing images are vulnerable to artificially designed adversarial examples, which can lead to incorrect predictions of deep models when facing adversarial examples. Previous adversarial attack methods have mainly focused on the classification and detection of UAV remote sensing images, and there is still a lack of research on adversarial attacks for object tracking in UAV video. To address this challenge, we propose an attention-enhanced one-shot adversarial attack method for UAV remote sensing object tracking, which perturbs only the template frame and generates adversarial samples offline. First, we employ an attention feature loss to make the original frame's features dissimilar to those of the adversarial frame, and an attention confidence loss to either suppress or enhance different confidence scores. Additionally, by forcing the tracker to concentrate on the background information near the target, a background distraction loss is used to mismatch templates with subsequent frames. Finally, we add total variation loss to generate adversarial examples that appear natural to humans. We validate the effectiveness of our method against popular trackers such as SiamRPN, DaSiamRPN, and SiamRPN++ on the UAV123 remote sensing dataset. Experimental results verify the superior attack performance of our proposed method. [ABSTRACT FROM AUTHOR]

Knowledge graph embedding has received widespread attention in recent years. Most existing models represent time-independent facts as low dimensional embeddings. Nevertheless, knowledge graphs with temporal information provide more accurate and timely data. Hence, we propose P olar T emporal K nowledge Graph E mbedding (PTKE), a novel temporal knowledge graph (TKG) embedding model which belongs to the translation-based model family and embeds time-aware facts into polar coordinate system. PTKE defines time as a constraint of the entity and synchronously embeds the starting and ending timestamps. The fact is divided into the modulus and the angular parts to avoid generating similar time-constrained entities. We use the modulus part to distinguish different time-constrained entities, and the angular part to distinguish time-constrained entities with the same modulus. Experiments on the temporal datasets show that PTKE outperforms prior state-of-the-art static knowledge graph (SKG) embedding models and temporal knowledge graph (TKG) embedding models in the link prediction task and the relation prediction task. Furthermore, the analysis of different time units and semantic expressive ability test on time embeddings prove that PTKE has a great ability on time expression. [ABSTRACT FROM AUTHOR]

Knowledge graphs as external information has become one of the mainstream directions of current recommendation systems. Various knowledge-graph-representation methods have been proposed to promote the development of knowledge graphs in related fields. Knowledge-graph-embedding methods can learn entity information and complex relationships between the entities in knowledge graphs. Furthermore, recently proposed graph neural networks can learn higher-order representations of entities and relationships in knowledge graphs. Therefore, the complete presentation in the knowledge graph enriches the item information and alleviates the cold start of the recommendation process and too-sparse data. However, the knowledge graph's entire entity and relation representation in personalized recommendation tasks will introduce unnecessary noise information for different users. To learn the entity-relationship presentation in the knowledge graph while effectively removing noise information, we innovatively propose a model named k n o w l e d g e — e n h a n c e d   h i e r a r c h i c a l   g r a p h   c a p s u l e   n e t w o r k (KHGCN), which can extract node embeddings in graphs while learning the hierarchical structure of graphs. Our model eliminates noisy entities and relationship representations in the knowledge graph by the entity disentangling for the recommendation and introduces the attentive mechanism to strengthen the knowledge-graph aggregation. Our model learns the presentation of entity relationships by an original graph capsule network. The capsule neural networks represent the structured information between the entities more completely. We validate the proposed model on real-world datasets, and the validation results demonstrate the model's effectiveness. [ABSTRACT FROM AUTHOR]

One important method for classifying images from remote sensing is discriminative feature learning. On the other hand, the majority of the methods that are currently in use do not take into account that the image labels will be tainted and that their performance will suffer as a result of noisy supervised information. However, single-view based feature learning is unable to present the image in its entirety. A multi-view robust discriminative feature learning approach for remote sensing images with noisy labels is proposed in this paper to address these issues. First, the local neighborhood division is carried out with the help of the entropy rate superpixel segmentation. Second, a graph-based multi-view propagation model is used to recover noisy labels in these specific locations. Finally, a multi-view discriminative feature learning model for remote sensing image classification is proposed using recovery labels as supervised information. Extensive testing on three remote sensing image datasets shows that our proposed method outperforms seven other excellent methods and has some advantages in terms of robustness and a number of objective indicators. [ABSTRACT FROM AUTHOR]

Temporal reasoning methods have been successful in temporal knowledge graphs (TKGs) and are widely employed in many downstream application areas. Most existing TKG reasoning models transform time intervals into continuous time snapshots, with each snapshot representing a subgraph of the TKG. Although such processing can produce satisfactory outcomes, it ignores the integrity of a time interval and increases the amount of data. Meanwhile, many previous works focuses on the logic of sequentially occurring facts, disregarding the complex temporal logics of various time intervals. Consequently, we propose a R einforcement Learning-based Model for T emporal Knowledge Graph Reasoning with T ime I ntervals (RTTI), which focuses on time-aware multi-hop reasoning arising from complex time intervals. In RTTI, we construct the time learning part to obtain the time embedding of the current path. It simulates the temporal logic with relation historical encoding and compute the time interval between two facts through the temporal logic feature matrix. Furthermore, we propose a new method for representing time intervals that breaks the original time interval embedding method, and express the time interval using median and embedding changes of two timestamps. We evaluate RTTI on four public TKGs for the link prediction task, and experimental results indicate that our approach can still perform well on more complicated tasks. Meanwhile, our method can search for more interpretable paths in the broader space and improve the reasoning ability in sparse spaces. [ABSTRACT FROM AUTHOR]

The purpose of the paper is to derive a formula to describe the quantitative relationship among the number of the pacing cells required (NPR), the dimension i , and the diffusion coefficient D (electrical coupling or gap junction G). The relationship between NPR and G has been investigated in different dimensions, respectively. That is, for each fixed i , there is a formula to describe the relationship between NPR and G ; and three formulas are required for the three dimensions. However, there is not a universal expression to describe the relationship among NPR, G , and i together. In the manuscript, surveying and investigating the basic law among the existed data, we speculate the preliminary formula of the relationship among the NPR, i , and G ; and then, employing the cftool in MATLAB, the explicit formulas are derived for different cases. In addition, the goodness of fit ( R 2 ) is computed to evaluate the fitting of the formulas. Moreover, the 1D and 2D ventricular tissue models containing biological pacemakers are developed to derive more data to validate the formula. The results suggest that the relationship among the NPR, i , and the G (D) could be described by a universal formula, where the NPR scales with the i (the dimension) power of the product of the square root of G (D) and a constant b which is dependent on the strength of the pacing cells and so on. [ABSTRACT FROM AUTHOR]

In this paper, an approach of community evolution based on gravitational relationship refactoring between the nodes in a dynamic network is proposed, and it can be used to simulate the process of community evolution. A static community detection algorithm and a dynamic community evolution algorithm are included in the approach. At first, communities are initialized by constructing the core nodes chains, the nodes can be iteratively searched and divided into corresponding communities via the static community detection algorithm. For a dynamic network, an evolutionary process is divided into three phases, and behaviors of community evolution can be judged according to the changing situation of the core nodes chain in each community. Experiments show that the proposed approach can achieve accuracy and availability in the synthetic and real world networks. [ABSTRACT FROM AUTHOR]

As an important factor for improving recommendations, time information has been introduced to model users’ dynamic preferences in many papers. However, the sequence of users’ behaviour is rarely studied in recommender systems. Due to the users’ unique behavior evolution patterns and personalized interest transitions among items, users’ similarity in sequential dimension should be introduced to further distinguish users’ preferences and interests. In this paper, we propose a new collaborative filtering recommendation method based on users’ interest sequences (IS) that rank users’ ratings or other online behaviors according to the timestamps when they occurred. This method extracts the semantics hidden in the interest sequences by the length of users’ longest common sub-IS (LCSIS) and the count of users’ total common sub-IS (ACSIS). Then, these semantics are utilized to obtain users’ IS-based similarities and, further, to refine the similarities acquired from traditional collaborative filtering approaches. With these updated similarities, transition characteristics and dynamic evolution patterns of users’ preferences are considered. Our new proposed method was compared with state-of-the-art time-aware collaborative filtering algorithms on datasets MovieLens, Flixster and Ciao. The experimental results validate that the proposed recommendation method is effective and outperforms several existing algorithms in the accuracy of rating prediction. [ABSTRACT FROM AUTHOR]

Highlights: [•] A trust measurement model based on QoS is established. [•] Considering timeliness of history behavior data and aggregation degree of entity, entity’s utility value is calculated based on fuzzy theory. [•] A Wright–Fisher multi-strategy trust evolution model with white noise for Internetware is proposed to predict the evolutionary trend of an Internetware. [•] An incentive mechanism based on evolutionary game theory is proposed to solve the free-riding problem. [ABSTRACT FROM AUTHOR]

As an important technology of social network analysis, link prediction is widely applied in computer science and many other fields. Link prediction can be used to detect missing links or predict whether two unconnected nodes will connect in the future. Various link prediction approaches have been proposed based on similarity metrics or learning in recent years; however, most failed to consider the direct changes during network development, and hence they are not applied to dynamic networks whose structures change continuously over time. In this paper, a novel approach for link prediction in dynamic networks based on the attraction force between nodes (DLPA) is proposed for detecting missing links and for predicting whether potential links will become real links in the future. First, a level is assigned to each node, which is used to represent the influence strength of the node compared to its neighbours in the initial network snapshot. The level must be updated with changes in the nodes. Then, the connection probability of each potential link is calculated based on the levels of the corresponding nodes and the attraction force between them. Thus, missing links can be detected and potential links can be predicted. In addition, the connection probabilities of potential links calculated via the proposed approach can vary with the evolution of the network. Experiments on static and dynamic real-world networks are conducted to evaluate the performance of the proposed approach, and the results demonstrate that the proposed approach outperforms several baseline algorithms in terms of prediction accuracy. [ABSTRACT FROM AUTHOR]

This article proposes a framework P 3 E for evaluating entity extraction problem over cyber-physical system data. As known by us, this article is the first work focusing on this problem, which is an important step for identifying entities in cyber-physical system data. Directed by the initial entities, utilizing the relaxation and verification techniques, P 3 E provides a path expression–based solution for entity extraction problem, which has following characteristics. First, using path expressions, P 3 E provides a condensed presentation for entity locations whose size may get very large when scaling up the data size. Second, requiring only one entity example to indicate the interests, using relaxation technique, P 3 E can discover other similar entities automatically. Third, by adjusting the example given to P 3 E , users can specify their own interesting entities and control the entities discovered by P 3 E. Besides, utilizing the idea of sharing computations, by extending previous automaton techniques, an efficient implementation of P 3 E is provided. Experimental results are reported, which show that P 3 E can provide an effective and efficient solution to the entity extraction problem. [ABSTRACT FROM AUTHOR]

Synthetic aperture radar automatic target recognition (SAR-ATR) is a hotspot in the field of remote sensing, which has been widely used in disaster monitoring, environmental monitoring, resource exploration, and crop yield estimates. In recent years, deep convolutional neural networks (DCNNs) have achieved promising performance among a variety of supervised classification methods under the condition of sufficiently labeled samples. However, it is expensive and time-consuming to collect large amounts of labeled samples suitable for DCNNs in SAR domains. To reduce the dependence of SAR-ATR on labeled samples, in this work, a consistency regularization teacher–student semi-supervised (CRTS) method for SAR-ATR is proposed, in which consistency regularization is applied to analyze and divide unlabeled samples and the teacher–student structure is introduced to generate pseudo-labels for the divided unlabeled samples. Firstly, by using consistent pseudo-label prediction, unlabeled samples are divided into consistent unlabeled samples and confident unlabeled samples. Then, in order to improve the quality of pseudo-labeled labels, the student model is used to generate a pseudo-label for consistent unlabeled samples, and the teacher model which is ensembled by the other two student models labels the confident unlabeled samples. Finally, these pseudo-label unlabeled samples are mixed with the labeled samples and trained together to improve recognition performance. Experiments are conducted on the MSTAR dataset, and the results demonstrate the effectiveness of the proposed method. As compared with several state-of-the-art methods, the recognition accuracy shows the superiority of the proposed method, especially when the training dataset is limited. [ABSTRACT FROM AUTHOR]

The track association problem is a challenging task in dense target environments due to the existence of furcation tracks, cross tracks and combination tracks. At present, most of the track association algorithms experience a substantial decline in accuracy in processing the above three types of tracks. In response to the defect, a track association algorithm based on the weighted association graph is presented. Information divergence is introduced to construct the weighted association graph. And association quality is acquired based on the weighted idea to reflect the association relationship among tracks. The algorithm solves the association problem with furcation tracks, cross tracks and combination tracks effectively, and improves the performance of association algorithms in dense target environments. The simulation results show the effectiveness and the superiority of the algorithm. [ABSTRACT FROM AUTHOR]

Highlights: [•] A novel track fusion algorithm is proposed in dense sensor environments. [•] Track filter is used to select the appropriate sensor tracks for fusion. [•] An optimal number of sensor tracks are fused. [•] The superiority of the algorithm is verified in theory and simulation. [ABSTRACT FROM AUTHOR]

The classification of aerial scenes has been extensively studied as the basic work of remote sensing image processing and interpretation. However, the performance of remote sensing image scene classification based on deep neural networks is limited by the number of labeled samples. In order to alleviate the demand for massive labeled samples, various methods have been proposed to apply semi-supervised learning to train the classifier using labeled and unlabeled samples. However, considering the complex contextual relationship and huge spatial differences, the existing semi-supervised learning methods bring different degrees of incorrectly labeled samples when pseudo-labeling unlabeled data. In particular, when the number of labeled samples is small, it affects the generalization performance of the model. In this article, we propose a novel semi-supervised learning method with early labeled and small loss selection. First, the model learns the characteristics of simple samples in the early stage and uses multiple early models to screen out a small number of unlabeled samples for pseudo-labeling based on this characteristic. Then, the model is trained in a semi-supervised manner by combining labeled samples, pseudo-labeled samples, and unlabeled samples. In the training process of the model, small loss selection is used to further eliminate some of the noisy labeled samples to improve the recognition accuracy of the model. Finally, in order to verify the effectiveness of the proposed method, it is compared with several state-of-the-art semi-supervised classification methods. The results show that when there are only a few labeled samples in remote sensing image scene classification, our method is always better than previous methods. [ABSTRACT FROM AUTHOR]

As an important display mode of underwater environments, the sonar image has limitations on the resolution, which often leads to problems with low resolution of underwater objects. Therefore, the image super-resolution algorithm is needed to transform the images from low-resolution to high-resolution. It can improve the visual effect and contribute to subsequent processing such as 3D reconstruction and object recognition. This paper proposes a method for sonar image super-resolution based on generative adversarial networks (GAN). By comparing the super-resolution effects of various interpolation and convolutional neural network algorithms on sonar images, a Residual-in-Residual Dense Block network is employed as the generator of GAN since it has the low distortion and high perceptual quality. Because the sonar image training set does not have enough data, the generator utilizes the transfer learning on the sonar images to produce an optimized network model which is more suitable for super-resolution of sonar image. The VGG19 network is employed as the discriminator. In addition, the perceptual loss is introduced into the loss function of S 2 RGAN to further improve the perceptual quality of super-resolution images. The experimental results indicate that the proposed S 2 RGAN shows excellent performance. The generated super-resolution images of S 2 RGAN have the remarkable advantages of both lower distortion and higher perceptual quality comparing with other methods. Because S 2 RGAN focuses more on the reality and overall visual effect of super-resolution sonar images, it is suitable for various underwater situations. [ABSTRACT FROM AUTHOR]

Epidemic models are normally used to describe the spread of infectious diseases. In this paper, we will discuss an epidemic model with time delay. Firstly, the existence of the positive fixed point is proven; and then, the stability and Hopf bifurcation are investigated by analyzing the distribution of the roots of the associated characteristic equations. Thirdly, the theory of normal form and manifold is used to drive an explicit algorithm for determining the direction of Hopf bifurcation and the stability of the bifurcation periodic solutions. Finally, some simulation results are carried out to validate our theoretic analysis. [ABSTRACT FROM AUTHOR]

This paper investigates the Minimizing-Interference-for-Multiple-Paths (MIMP) problem for routing with minimum interference in wireless sensor networks, which is defined as: Given k routing requests { s 1 , t 1 } , ... , { s k , t k } , find k paths connecting these routing requests with minimum (wireless) interference. A key point to solve this problem is how to quantify interference level among multiple routing paths. However, all the existing metrics cannot measure interference precisely under some certain circumstances, e.g., some of the routing paths have common nodes or links. This paper proposes a metric that can measure interference precisely among any set of paths, even though these paths have some nodes or links in common. For this proposed metric, the MIMP problem is NP-hard even for k = 2. A heuristic Distributed On-line Algorithm for Minimizing Interference (DOAMI) is given to solve the MIMP problem. DOAMI has good communication and time complexity in theory, whose efficiency is also verified by simulation results. [ABSTRACT FROM AUTHOR]

The common track fusion algorithms in multi-sensor systems have some defects, such as serious imbalances between accuracy and computational cost, the same treatment of all the sensor information regardless of their quality, high fusion errors at inflection points. To address these defects, a track fusion algorithm based on the reliability (TFR) is presented in multi-sensor and multi-target environments. To improve the information quality, outliers in the local tracks are eliminated at first. Then the reliability of local tracks is calculated, and the local tracks with high reliability are chosen for the state estimation fusion. In contrast to the existing methods, TFR reduces high fusion errors at the inflection points of system tracks, and obtains a high accuracy with less computational cost. Simulation results verify the effectiveness and the superiority of the algorithm in dense sensor environments. [ABSTRACT FROM AUTHOR]

Abstract: Since hyperspectral images contain fine spectral information of the target objects, there is continuous demand for the detailed analysis about such images. A somewhat neglected but critically important challenge regarding hyperspectral image is the presence of “spatial stray light” – a phenomenon caused by scattering of photons from target objects. In this study, neighborhood unhomogeneity method is used to detect the edge of spatial stray light region in hyperspectral images. Analyses were conducted on reflectance datasets of standard card, potato leaf, and corn kernels from three inbred lines. By using neighborhood unhomogeneity method, the edge of spatial stray light region could be detected obviously and experimental results show the effectiveness of the proposed method. [Copyright &y& Elsevier]

Abstract: In this paper, a fuzzy clustering method based on evolutionary programming (EPFCM) is proposed. The algorithm benefits from the global search strategy of evolutionary programming, to improve fuzzy c-means algorithm (FCM). The cluster validity can be measured by some cluster validity indices. To increase the convergence speed of the algorithm, we exploit the modified algorithm to change the number of cluster centers dynamically. Experiments demonstrate EPFCM can find the proper number of clusters, and the result of clustering does not depend critically on the choice of the initial cluster centers. The probability of trapping into the local optima will be very lower than FCM. [Copyright &y& Elsevier]

In recent years, synthetic aperture radar (SAR) automatic target recognition has played a crucial role in multiple fields and has received widespread attention. Compared with optical image recognition with massive annotation data, lacking sufficient labeled images limits the performance of the SAR automatic target recognition (ATR) method based on deep learning. It is expensive and time-consuming to annotate the targets for SAR images, while it is difficult for unsupervised SAR target recognition to meet the actual needs. In this situation, we propose a semi-supervised sample mixing method for SAR target recognition, named multi-block mixed (MBM), which can effectively utilize the unlabeled samples. During the data preprocessing stage, a multi-block mixed method is used to interpolate a small part of the training image to generate new samples. Then, the new samples are used to improve the recognition accuracy of the model. To verify the effectiveness of the proposed method, experiments are carried out on the moving and stationary target acquisition and recognition (MSTAR) data set. The experimental results fully demonstrate that the proposed MBM semi-supervised learning method can effectively address the problem of annotation insufficiency in SAR data sets and can learn valuable information from unlabeled samples, thereby improving the recognition performance. [ABSTRACT FROM AUTHOR]