With the rise of data engineering-driven automatic annotation strategies, deep learning has demonstrated remarkable performance and strong competitiveness in intelligent fault diagnosis. However, the inherent limitations of automatic annotators inevitably introduce noisy labels, which in turn hinder the generalization and accuracy of diagnostic models. Although numerous Learning with Noisy Labels (LNL) methods attempt to alleviate the impact of label noise through sample selection or label correction, most rely heavily on model predictions to guide training. This self-reinforcing mechanism frequently leads to confirmation bias, especially under high-noise conditions, thereby limiting their e... More >

Considering the large-area distribution, smooth brightness gradients, and blurred boundaries of Mura defects in real industrial scenarios, as well as the challenge of balancing accuracy and efficiency in existing methods, we propose a lightweight deep learning-based detection method for large-area Mura defects, termed SIFNet. The SIFNet adopts a classical encoder-decoder architecture with MobileNet-V2 as the backbone. Furthermore, we design a Graph-based Semantic Interscale-fusion Block (GSIB) that integrates the Semantic Fluid Aggregation Module (SFAM) and the Semantic Graph Inference Module (SGIM) to collaboratively extract high-level semantic features across multiple scales and establish... More >

Existing deep learning-based methods for infrared and visible image fusion typically operate independently of other high-level vision tasks, overlooking the potential benefits these tasks could offer. For instance, semantic features from image segmentation could enrich the fusion results by providing detailed target information. However, segmentation focuses on target-level semantic feature information (e.g., object categories), while fusion focuses more on pixel-level detail feature information (e.g., local textures), creating a feature representation gap. To address this challenge, we propose a self-supervised segmentation feature alignment fusion network (SegFANet), which aligns target-le... More >

Related concepts of entropy play a very important role in dealing with uncertainty in terms of Shannon's information theory. However, for uncertain information involving epistemic uncertainty, which is usually modelled by using Dempster-Shafer theory, the concepts of cross entropy and relative entropy are still not well defined currently. Facing this issue, by reviewing and importing existing related work, this study gives new definitions of cross entropy and relative entropy of mass functions, which are respectively named as cross plausibility entropy and relative plausibility entropy since they are both based on an uncertainty measure called plausibility entropy. The properties of cross an... More >

This paper considers the distributed group target tracking (DGTT) problem under sensors with limited and different field of views (FoVs). Usually, for the tracking of groups, targets within groups are closely spaced and move in a coordinated manner. These groups can split or merge, and the numbers of targets in groups may be large, which lead to more challenging issues related to data association, filtering and computational complexities. Particularly, these challenges may be further complicated in distributed fusion system architectures. To deal with these difficulties, we propose a consensus-based DGTT method within the belief propagation (BP) framework, which introduces undetected targets... More >

The joint integrated probabilistic data association (JIPDA) filter is effective for automatic multi-target tracking in cluttered environments. However, it is well-known that when targets are closely spaced, the JIPDA filter encounters the track coalescence problem, leading to inaccurate state estimations. This paper proposes a novel particle swarm optimization-based JIPDA (PSO-JIPDA) algorithm, which improves the state estimation accuracy by optimizing the posterior probability density, effectively addressing the information fusion challenge in multi-target tracking scenarios with closely spaced targets. The trace of the covariance matrix of the posterior density serves as the objective func... More >

Extended target tracking in occlusion scenarios often suffers from split errors due to sensor limitations and complex target interactions, leading to degraded tracking performance for autonomous vehicles and surveillance systems. To address this issue, in this paper, we propose a Gaussian Wasserstein distance-enhanced spatio-temporal similarity method for split error correction. We first analyze the spatio-temporal characteristics of split extended targets and model their geometric uncertainties via elliptical Gaussian distributions. Then, we integrate the Gaussian Wasserstein distance into the clue-aware trajectory similarity calculation framework to simultaneously capture positional and sh... More >

The wide-ranging expansion of smart grid networks has resulted in insurmountable difficulties that must be overcome to ensure the security and reliability of crucial energy infrastructures. The information system can be subjected to threats such as cyber-attacks or hardware malfunctioning resulting in a data integrity compromise which implies that the system will consequently not operate correctly. Anomaly detection methods that are relying on centralized data aggregation are problematic to the issues of data privacy and scalability resulting from such approaches. In this paper, we present a completely distinct approach that is based on federated learning that is employed in anomaly detectio... More >

Knowledge reasoning is a critical task in information fusion systems, and its core step is reasoning missing information from existing facts to improve the knowledge graphs. Embedding-based reasoning methods and path-based reasoning methods are two mainstream knowledge reasoning methods. Embedding-based reasoning methods enable fast and direct reasoning but are limited to simple relationships between entities and exhibit poor performance in reasoning complex logical relationships. Path-based reasoning methods perform better in complex reasoning tasks, but suffer from high computational complexity, a large number of model parameters, and low reasoning efficiency. To address the aforementioned... More >

Due to the poor imaging quality of remote sensing images and the small size of targets, remote sensing small target detection has become a current research difficulty and hotspot. Recent years have seen many new algorithms. Remote sensing small target detection methods based on image super-resolution reconstruction have attracted many researchers due to their excellent performance. However, these algorithms still have problems such as weak feature extraction capability and insufficient feature fusion. Then, we propose Enhanced Feature based Small Target Detection Network in Remote Sensing Images (EFSOD), which includes a Edge Enhancement Super-Resolution Reconstruction Module (EESRM) and a C... More >

Detecting personalities in social media content is an important application of personality psychology. Most early studies apply a coherent piece of writing to personality detection, but today, the challenge is to identify dominant personality traits from a series of short, noisy social media posts. To this end, recent studies have attempted to individually encode the deep semantics of posts, often using attention-based methods, and then relate them, or directly assemble them into graph structures. However, due to the inherently disjointed and noisy nature of social media content, constructing meaningful connections remains challenging. While such methods rely on well-defined relationships be... More >

To address the performance degradation of traditional data association algorithms caused by unknown target motion models, environmental interference, and strong maneuvering behaviors in complex dynamic scenarios, this paper proposes an innovative fusion algorithm that integrates reinforcement learning and deep learning. By constructing a policy network that combines Long Short-Term Memory (LSTM) memory units and reinforcement learning dynamic decision-making, a dynamic prediction model for "measurement-target" association probability is established. Additionally, a hybrid predictor incorporating Bayesian networks and multi-order curve fitting is designed to formulate the reward function. To... More >

Sea ice detection is of vital importance for maritime navigation. Satellite imagery is a crucial medium for conveying information about sea ice. Currently, most sea ice detection models mainly rely on texture information to identify sea ice in satellite imagery, while ignoring sea ice size information. This research presents an improved YOLOv8-Based detection algorithm for multi-scale sea ice. First, we propose a fusion module based on the attention mechanism and use it to replace the Concat module in the YOLOv8 network structure. Second, we conduct an applicability analysis of the bounding box regression loss function in YOLOv8 and ultimately select Shape-IoU, which is more suitable for sea... More >

Few-shot learning aims to recognize new-class items under the circumstances with a few labeled support samples. However, many methods may suffer from poor guidance of limited new-class samples that are not suitable for being regarded as class centers. Recent works use word embedding to enrich the new-class distribution message but only use simple mapping between visual and semantic features during training. To solve the aforementioned problems, we propose a fusion method that constructs a class relation graph by semantic meaning as guidance for feature extraction and fusion, to help the learning of the second-order relation information, with a light training request. In addition, we introduc... More >

In the context of neural network-based radar feature extraction and detection methods, single-feature detection approaches exhibit limited capability in distinguishing targets from background in complex environments such as sea clutter. To address this, a Multi-Feature Extraction Network and Graph Fusion Detection Network (MFEn-GFDn) method is proposed, leveraging feature complementarity and enhanced information utilization. MFEn extracts features from various time-frequency maps of radar signals to construct Multi-Feature Graph Data (MFG) for multi-feature graphical representation. Subsequently, GFDn performs fusion detection on MFG containing multi-feature information. By expanding the fea... More >

With the progressive advancement of remote sensing image technology, its application in the agricultural domain is becoming increasingly prevalent. Both cultivation and transportation processes can greatly benefit from utilizing remote sensing images to ensure adequate food supply. However, such images often exist in harsh environments with many gaps and dense distribution, which poses major challenges to traditional target detection methods. The frequent missed detections and inaccurate bounding boxes severely constrain the further analysis and application of remote sensing images within the agricultural sector. This study presents an enhanced version of the YOLO algorithm, specifically tai... More >

In the evolving framework of the Intelligence of Social Things (IoST), which amalgamates social networks and IoT ecosystems, knowledge graphs are essential for facilitating networked systems to efficiently process and leverage intricate relational data. Knowledge graphs offer essential technical assistance for various artificial intelligence applications, such as e-commerce, intelligent navigation, healthcare, and social media. Nonetheless, current knowledge graphs frequently lack completeness, harboring a considerable quantity of implicit knowledge that remains to be revealed. Consequently, tackling the difficulty of finalising knowledge graphs has emerged as a pressing research priority. M... More >

The methods that identify complex flight maneuvers from multi-sensor flight parameter data fusion and conduct automated quantitative evaluations of anomaly levels could play an important role in enhancing flight safety and pilot training. However, existing methods focus on anomaly detection at individual flight parameter data points, making it challenging to accurately quantify the overall abnormality of a flight maneuver. To address this issue, this paper proposes a novel method for the quantitative evaluation of anomaly levels in complex flight maneuvers using multi-sensor data. The proposed method comprises two stages: complex flight maneuver recognition and anomaly level quantification.... More >

Intelligent system is a research field that attracts much attention at present. Most of the researches on intelligent system focus on intelligent technology and its application. However, an intelligent system is first of all a system, which means it should have the characteristics of a system. Design of conventional system is mainly function- or task-oriented, and adaptation to environment is passive, static and regular. However, intelligent system is faced with a complex, random and dynamic environment, and has dynamic interaction with the environment. Behind this interaction behavior is a fusion of perception, cognition, and decision-making processes, supported by multi-source information... More >

Image fusion aims to integrate complementary information from different sensors into a single fused output for superior visual description and scene understanding. The existing GAN-based fusion methods generally suffer from multiple challenges, such as unexplainable mechanism, unstable training, and mode collapse, which may affect the fusion quality. To overcome these limitations, this paper introduces a diffusion model guided cross-attention learning network, termed as DMFuse, for infrared and visible image fusion. Firstly, to improve the diffusion inference efficiency, we compress the quadruple channels of the denoising UNet network to achieve more efficient and robust model for fusion tas... More >

Cyber security in power systems has become increasingly critical with the rise of network attacks such as Denial-of-Service (DoS) attacks and False Data Injection (FDI) attacks. These threats can severely compromise the integrity and reliability of state estimation, which are fundamental to the operation and control of power systems. In this manuscript, an estimation algorithm based on the fusion of information from multiple estimators is proposed to ensure that state estimation at critical buses can function properly in case of attacks. Our approach leverages a network of estimators that can dynamically adjust to maintain system stability and accuracy. Furthermore, a new detector is adopted... More >

In recent years, the field of electroencephalography (EEG) analysis has witnessed remarkable advancements, driven by the integration of machine learning and artificial intelligence. This survey aims to encapsulate the latest developments, focusing on emerging methods and technologies that are poised to transform our comprehension and interpretation of brain activity. The structure of this paper is organized according to the categorization within the machine learning community, with representation learning as the foundational concept that encompasses both discriminative and generative approaches. We delve into self-supervised learning methods that enable the robust representation of brain sig... More >

In Dempster-Shafer evidence theory (DST), the determination of basic belief assignment (BBA) is an important yet challenging issue before the evidence fusion. The rational mass determination of compound focal elements is crucial for fully taking advantage of DST, i.e., the ability to represent the ambiguity. In this paper, for the compound focal elements, we select and construct the compound-class samples with ambiguous class membership. Then, we use these samples to construct an end-to-end model called Evidential Radial Basis Function Network (E-RBFN), with the input as the sample and the output as the corresponding BBA. The E-RBFN can directly determine the mass values for all focal elemen... More >

In the realm of industrial defect detection, unsupervised anomaly detection methods draw considerable attention as a result of their exceptional accomplishments. Among these, knowledge distillation-based methods have emerged as a prominent research focus, favored for their streamlined architecture, precision, and efficiency. However, the challenge of characterizing the variability in anomaly samples hinders the accuracy of detection. To address this issue, our research presents a novel approach for anomaly detection and localization, leveraging feature fusion through inverse knowledge distillation as its cornerstone. We employ the encoder as the guiding teacher model and designate the decode... More >

Data fusion is a prevalent technique for assembling imperfect raw data coming from multiple sources to capture reliable and accurate information. Dempster–Shafer evidence theory is one of useful methodologies in the fusion of uncertain multisource information. The existing literature lacks a thorough and comprehensive review of the recent advances of Dempster– Shafer evidence theory for data fusion. Therefore, the state of the art has to be surveyed to gain insight into how Dempster–Shafer evidence theory is beneficial for data fusion and how it evolved over time. In this paper, we first provide a comprehensive review of data fusion methods based on Dempster–Shafer evidence theory an... More >

Remote sensing image plays an important role in maritime surveillance, and as a result there is increasingly becoming a prominent focus on the detection and recognition of maritime objects. However, most existing studies in remote sensing image classification pay more attention on the performance of model, thus neglecting the transparency and explainability in it. To address the issue, an explainable classification method based on graph network is proposed in the present study, which seeks to make use of the relationship between objects' regions to infer the category information. First, the local visual attention module is designed to focus on different but important regions of the object. T... More >

Facing the challenges of low efficiency and poor quality in UAV 3D path planning within large-scale airspace complex environments, this paper introduces a divide-and-conquer approach, proposing a dual-layer path planning method based on multi-source information fusion. The method decomposes traditional path planning into two steps: heading planning and trajectory planning, ensuring both planning efficiency and path quality. This method segregates the solution process into two distinct stages: heading planning and path planning, thereby ensuring the planning of both efficiency and path quality. Firstly, the path planning phase is formulated as a multi-objective optimization problem, taking in... More >

In the field of extended target tracking and information fusion, constrained by the sparse measurement set from radar, the target contour is commonly estimated as an elliptical shape. This paper uses convolutional neural networks to estimate the size and orientation information of extended targets. First, by establishing a systematic model for elliptical extended targets and modeling its measurement information, data normalization, and length equalization operations were conducted to provide reliable measurement data for subsequent neural network processing. Subsequently, through the construction of a convolutional neural network model, accurate estimation of the contour parameters of ellipt... More >

The rapid advancement of Internet technology, driven by social media and e-commerce platforms, has facilitated the generation and sharing of multimodal data, leading to increased interest in efficient cross-modal retrieval systems. Cross-modal image-text retrieval, encompassing tasks such as image query text (IqT) retrieval and text query image (TqI) retrieval, plays a crucial role in semantic searches across modalities. This paper presents a comprehensive survey of cross-modal image-text retrieval, addressing the limitations of previous studies that focused on single perspectives such as subspace learning or deep learning models. We categorize existing models into single-tower, dual-tower,... More >

Considering the tractability of OGM (Occupancy Grid Map) and its wide use in the dynamic environment representation of mobile robotics, the extraction of motion information from successive OGMs are very important for many tasks, such as SLAM (Simultaneously Localization And Mapping), DATMO (Detection and Tracking of Moving Object) and informaiton fusion for situation awareness. In this paper, we propose a novel motion extraction method based on the signal transform, called as S-KST (Spatial Keystone Transform), for the motion detection and estimation from successive noisy OGMs. It extends the KST in radar imaging or motion compensation to 1D spatial case (1DS-KST) and 2D spatial case (2DS-... More >