The rise of Industry 4.0 and Industry 5.0, focusing on digital transformation and human-machine collaboration, has boosted the need for advanced fault diagnosis technologies. These must be interpretable to ensure industrial efficiency, reliability, and safety. However, current methods often rely on single-sensor information, require many labeled samples for training, and struggle to justify diagnostic

Lane-level traffic prediction forecasts near-future conditions at specific lane segments, enabling real-time traffic management and particularly aiding autonomous vehicles (AVs) in precise tasks such as car-following and lane changes. Despite substantial advancements in this field, some key challenges remain. First, the traffic state of a lane segment exhibits dynamic, nonlinear spatial correlation

Person search aims to locate target individuals in large image databases captured by multiple non-overlapping cameras. Existing models primarily rely on spatial feature extraction to capture fine-grained local details, which is vulnerable to background clutter and occlusions and leads to unstable feature representations. To address the issues, we propose a Dynamic Frequency Selection and Spatial Interaction

Presently, mental stress is a significant contributor to physical and psychological health issues, making its early detection and monitoring a public health priority. Among various neuroimaging methods, Electroencephalography (EEG) has emerged as a promising tool due to its ability to capture fine-grained temporal dynamics associated with cognitive stress responses. This paper presents a systematic

Multi-view clustering (MVC) has received extensive attention by exploiting the consistent and complementary information among views. To improve the robustness of MVC, most MVC methods assume that the noise implicit in the data follows a predefined distribution. However, due to equipment limitations and transmission environment, the collected multi-view data often contains mixed noise. The predefined

As Chinese society undergoes rapid aging and urbanization, the existing medical service system faces significant challenges, including unequal resource distribution, a shortage of high-quality resources, and inefficient allocation. To address these issues, the hierarchical diagnosis and treatment system (HDTS) has been introduced to optimize medical resource allocation and utilization. However, implementing

The analysis and mining of multi-view data have gained widespread attention, making multi-view anomaly detection a prominent research area. Despite notable advancements in the performance of existing multi-view anomaly detection methods, they still face certain limitations. (1) The existing methods fail to fully leverage the low-rank structure of multi-view data, which results in a lack of necessary

Deep learning has achieved significant success in multi-modality medical image fusion (MMIF). Nevertheless, the distribution of spatial information varies across regions within a medical image. Current methods consider the medical image as a whole, leading to uneven fusion and susceptibility to artifacts in edge regions. To address this problem,we delve into regional information fusion and introduce

Multilabel Class-Incremental Learning (MLCIL) refers to a variant of class-incremental learning and multilabel learning where models are required to learn from images or data associated with multiple labels, and new sets of classes are introduced incrementally. However, most existing MLCIL methods tend to rely heavily on limited single-view features, which makes it challenging for them to effectively

Remote Sensing Visual Grounding (RSVG) is an emerging multimodal RS task that involves grounding textual descriptions to specific objects in remote sensing images. Previous methods often overlook the impact of complex backgrounds and similar geographic entities during feature extraction, which may confuse target features and cause performance bottlenecks. Moreover, remote sensing scenes include extensive

Dynamic Graph Neural Networks have been demonstrated to be effective in modeling dynamic graph structured data, which enables them to solve tasks such as node classification, link prediction, and popular prediction. Existing research has shown a variety of structures within dynamic graphs, ranging from individual representations characterized by microscopic structure to graph representations characterized

Cross-site distribution shift in medical images is a major factor causing model performance degradation, significantly challenging the deployment of pre-trained semantic segmentation models for clinical adoption. In this paper, we propose a novel framework, CertainTTA, to maximally exploit a pretrained model for test time adaptation. Firstly, we leverage variational inference and innovatively construct

The growing adoption of IoT applications underscores the need for advanced data fusion and information acquisition techniques, driving demand for secure, privacy-preserving querying of integrated IoT data. Existing schemes like searchable encryption are practical but leak access patterns, while leakage-free methods using Oblivious RAM or cryptographic techniques incur significant resource overhead

With the rapid development of artificial intelligence, medical image semantic segmentation is being used more widely. However, centralized training can lead to privacy risks. At the same time, MRI provides multiple views that together describe the anatomical structure of a lesion, but a single view may not fully capture all features. Therefore, integrating multi-view information in a federated learning

Federated learning (FL) has emerged as a widely adopted privacy-preserving distributed framework that facilitates information fusion and model training across multiple clients without requiring direct data sharing with a central server. Despite its advantages, recent studies have revealed that FL is vulnerable to gradient inversion attacks, wherein adversaries can reconstruct clients’ private training

This paper presents the Motion and Vision Sensing Integration-based Agile Badminton Robot (MV-BMR), a real-time system that plays badminton with human players. Current badminton robots excel at handling low-speed strikes, such as high clears and net shots, but struggle with high-speed cases, particularly short shots. This challenge arises from two key factors: the shuttlecock’s short flight time, which

Breast ultrasound (BUS) image segmentation is crucial for tumor analysis and cancer diagnosis. However, the challenges of lesion segmentation in BUS images arise from inter-class indistinction caused by low contrast, high speckle noise, artifacts, and blurred boundaries, as well as intra-class inconsistency due to variations in lesion size, shape, and location. To address these challenges, we propose

Fusing a hyperspectral image (HSI) with a multispectral image (MSI) to produce a super-resolution image (SRI) that possesses both fine spatial and spectral resolutions is a widely adopted technique in hyperspectral super-resolution (HSR). Most existing HSR methods accomplish this task within the framework of linear mixing model (LMM). However, a severe challenge lies in the inherent linear constraint

Breast cancer diagnosis using ultrasound imaging presents challenges due to inherent limitations in image quality and the complex nature of lesion interpretation. We propose SgmaFuse, a novel interpretable multimodal framework that integrates histopathological concepts and lesion masks information , treated as domain concepts, with ultrasound imaging for accurate and explainable breast cancer diagnosis

The extraction and utilization of latent information from sensor data is gaining increasing prominence due to its potential for transforming decision-making processes across various sectors. Data mining techniques provide robust tools for analyzing large-scale data generated by advanced network management systems, offering actionable insights that drive operational efficiency and strategic improvements

Deep learning-based medical image fusion has become a prevalent approach to facilitate computer-aided diagnosis and treatment. The mainstream image fusion methods predominantly rely on encoder–decoder architectures and utilize unsupervised loss functions for training, resulting in the blurring or loss of fused image details and limited inference speed. To resolve these problems, this paper presents

Deformable medical image registration is a crucial aspect of medical image analysis. Improving the accuracy and plausibility of registration by information fusion is still a problem that needs to be addressed. To solve this problem, we propose DAFF-Net, a novel framework that systematically unifies three kind of information fusion (low-level fusion, high-level fusion, and loss fusion) to enhance registration

Artificial Intelligence (AI) plays a leading role in Industry 4.0 and future Industry 5.0. Concerns about the opacity of today's neural network AI solutions have led to the Explainable AI (XAI) project, which attempts to open the black box of neural networks. While XAI can help to partially interpret and explain the workings of neural networks, it has not changed their original subsymbolic nature and

The digitization of healthcare has led to the accumulation of vast amounts of patient data through Electronic Health Records (EHRs) systems, creating significant opportunities for advancing intelligent healthcare. Recent breakthroughs in deep learning and information fusion techniques have enabled the seamless integration of diverse data sources, providing richer insights for clinical decision-making

Although large language models (LLMs) have demonstrated impressive reasoning capabilities, the generated responses may contain inaccurate or fictitious information due to noise and redundancy in the data that can interfere with the model's reasoning. Noise is often difficult to avoid in massive data, and manual denoising requires a lot of time, manpower, and material resources. Particularly in the

Surgical workflow recognition is vital for automating tasks, supporting decision-making, and training novice surgeons, ultimately improving patient safety and standardizing procedures. However, data corruption can lead to performance degradation due to issues like occlusion from bleeding or smoke in surgical scenes and problems with data storage and transmission. Therefore, a robust workflow recognition

Unstructured grid data are essential for modelling complex geometries and dynamics in computational physics. Yet, their inherent irregularity presents significant challenges for conventional machine learning (ML) techniques. This paper provides a comprehensive review of advanced ML methodologies designed to handle unstructured grid data in high-dimensional dynamical systems. Key approaches discussed

Human skeleton sequences are a crucial data modality for human motion representation. The primary challenge in skeleton-based action recognition lies in the effective capture of spatio-temporal correlations among skeleton joints. However, when the human body interacts with other objects in the background, these spatio-temporal correlations may become less apparent. To tackle this issue, we analyze

Dempster’s rule of combination is a fundamental element of the Dempster–Shafer evidence Theory, which is designed to integrate uncertain information from various independent sources. Its primary goal is to reduce uncertainty and present information of better quality to a decision-making process. Dempster’s rule of combination addresses the conflicts among the pieces of evidence provided by multiple

While graph neural networks (GNNs) have successfully applied generalized convolution operations to the graph domain, providing a direct method to explain the dependency between the output and the presence of certain features and structural patterns in the input graph remains challenging. Inspired by image filters in standard convolutional neural networks (CNN), we propose a neural framework that connects

Intelligent Fault Diagnosis (IFD) plays a crucial role in industrial applications, where developing foundation models analogous to ChatGPT for comprehensive fault diagnosis remains a significant challenge. Current IFD methodologies are constrained by their inability to construct unified models capable of processing heterogeneous signal types, varying sampling rates, and diverse signal lengths across

Hyperspectral image classification (HSIC) is an important research direction in the field of remote sensing image analysis and computer vision, which is of great practical significance. Hyperspectral imaging (HSI) is widely used in a variety of scenarios with its rich spectral and spatial information, but problems such as high-dimensional data characteristics and scarcity of labeled samples challenge

Sleep disorders affect hundreds of millions globally, with accurate assessment of sleep apnea (SA) and sleep staging (SS) essential for clinical diagnosis and early intervention. Manual analysis by sleep experts is time-consuming and subject to inter-rater variability. Deep learning (DL) approaches offer automation potential but face fundamental challenges in multi-modal physiological signal integration

The commonly used maximum mean discrepancy (MMD) criterion has two main drawbacks when reducing cross-domain distribution gaps: firstly, it reduces the distribution discrepancy in a global manner, potentially ignoring local structural information between domains, and secondly, its performance heavily relies on the often-unstable pseudo-label refinement process. To solve these problems, we introduce

Recently, multimodal knowledge distillation-based methods for RGB-T semantic segmentation have been developed to enhance segmentation performance and inference speeds. Technically, the crux of these models lies in the feature imitative distillation-based strategies, where the student models imitate the working principles of the teacher models through loss functions. Unfortunately, due to the significant

The registration of optical and synthetic aperture radar (SAR) images is valuable for exploration due to the inherent complementarity of optical and SAR imagery. However, the substantial radiation and geometric differences between the two modalities present a major obstacle to image registration. Specifically, images from optical and SAR require integration of precise local features and registration-aware

Advancements in Earth observation technology have enabled effective monitoring of complex surface changes. Semantic change detection (SCD) using high-resolution remote sensing images is crucial for urban planning and environmental monitoring. However, existing deep learning-based SCD methods, which combine semantic segmentation (SS) and binary change detection (BCD), face challenges in lightweight

Due to the scarcity problem of electroencephalogram (EEG) data, building high-precision emotion recognition models using deep learning faces great challenges. In recent years, data augmentation has significantly enhanced deep learning performance. Therefore, this paper proposed an innovative self-supervised data augmentation strategy, named SSDAS-EER, to generate high-quality and various artificial

Accurate 3D vessel mapping is essential for surgical planning and interventional treatments. However, the conventional manual slice-by-slice annotation in CT scans is extremely time-consuming, due to the complexity of vessels: sparse distribution, intricate 3D topology, varying sizes, irregular shapes, and low contrast with the background. To address this problem, we propose a few-shot semi-supervised

Inertial sensors are widely used in smartphones, robotics, wearables, aerospace systems, and industrial automation. However, extracting universal features from inertial signals remains challenging. Inertial signal features are encoded in abstract, unreadable waveforms, lacking the visual intuitiveness of images, which makes semantic extraction difficult. The non-stationary nature and complex motion

Reconstructing visual stimuli from functional magnetic resonance imaging (fMRI) is a complex challenge in neuroscience. Most existing approaches rely on mapping neural signals to pretrained models to generate latent variables, which are then used to reconstruct images via a diffusion model. However, this multi-step process can result in the loss of crucial semantic details, limiting reconstruction

Minimally invasive surgeries (MIS) enhance patient outcomes but pose challenges such as limited visibility, complex hand-eye coordination, and manual endoscope control. The rise of the Internet of Medical Things (IoMT) and telesurgery further demands efficient and lightweight solutions. To address these limitations, we propose a novel lightweight hierarchical feature fusion network (LHFF-Net) for surgical

The proliferation of various data sources in urban and territorial environments has significantly facilitated the development of geospatial artificial intelligence (GeoAI) across a wide range of geospatial applications. However, geospatial data, which is inherently linked to geospatial objects, often exhibits data heterogeneity that necessitates specialized fusion and representation strategies while

Invariant learning on graphs is essential for uncovering causal relationships in complex phenomena. However, most research has focused on homogeneous information networks with single node and edge types, ignoring the rich heterogeneity of real-world systems. Additionally, many invariant learning methods rely on labeled data and the design of complex graph augmentation or contrastive sampling algorithms

Data streams pose challenges not usually encountered in batch-based Machine Learning (ML). One of them is concept drift, which is characterized by the change in data distribution over time. Among many approaches explored in literature, the fusion of classifiers has been showing good results and is getting growing attention. More specifically, Dynamic Selection (DS) methods, due to the ensemble being

The data-driven preference learning provides a powerful tool to learn preferences of decision makers from data, which is also faced with challenges in a multiattribute context from complex interactions among attributes and interpretability of human behaviors. In order to deal with these challenges, we propose a data-driven method to learn multiattribute utility function based on both attribute-specific

Comparing to single modality, multi-modal biosignals manifest more comprehensive physiological status about cardiac diseases. However, challenges in multi-sensor healthcare data fusion include unified multimodal representation, heterogeneous metadata fusion and adaptability to missing modalities, persist. While previous work has focused on isolated aspects, there is still a need for a unified representation

Exocentric (third-person) to egocentric (first-person) cross-view video generation aims to synthesize the egocentric view of a video from an exocentric view. However, current techniques either use a sub-optimal image-based approach that ignores temporal information, or require target-view cues that limits application flexibility. In this paper, we tackle the challenging cue-free Exocentric-to-Egocentric

Detecting sarcasm in social media is vital for sentiment analysis and cyberbullying prevention. This study introduces a new multimodal method that integrates both text and image data to identify sarcastic content accurately. Using an open-source multimodal Twitter dataset from GitHub, we combine features extracted from text through a BiLSTM (Bidirectional Long Short-Term Memory) model, images through

The Rashomon effect presents a significant challenge in model selection. It occurs when multiple models achieve similar performance on a dataset but produce different predictions, resulting in predictive multiplicity. This is especially problematic in high-stakes environments, where arbitrary model outcomes can have serious consequences. Traditional model selection methods prioritize accuracy and fail

Remaining useful life (RUL) prediction is critical for reducing unplanned maintenance and enhancing the reliability of mechanical systems. However, current RUL prediction methods face two gaps: 1) These methods overlook spatial dependencies among sensor variables for first prediction time (FPT) detection. 2) The prediction performance is limited because they cannot mine local temporal features hidden

Ontology matching (OM) plays a key role in enabling data interoperability and knowledge sharing. Recently, methods based on Large Language Model (LLMs) have shown great promise in OM, particularly through the use of a retrieve-then-prompt pipeline. In this approach, relevant target entities are first retrieved and then used to prompt the LLM to predict the final matches. Despite their potential, these

Large language models have experienced rapid growth, constrained by the computational limits of training foundation models. With the continuous release of new products, high-end devices are increasingly accessible, eventually transitioning into the mid-range and low-end segments. A pivotal focus in current research is the facilitation of joint training across diverse regions and devices. However, this

Link forecasting over Temporal knowledge graphs (TKGs) aims to predict the unknown facts in future timestamps, which has gained increasing attention due to its significant practical value. Logical reasoning plays a pivotal role in this task by achieving explainable reasoning through extracting and applying temporal logical rules. However, existing logical reasoning methods are challenged in sufficiently

As the digital age advances, multimodal emotion recognition (MER) technology is increasingly crucial in fields like smart interaction and mental health assessment. However, emotional recognition in conversational contexts faces numerous challenges, particularly in effectively managing missing multimodal data. To address this issue, we propose RMER-DT (Robust Multimodal Emotion Recognition in Conversational

As health management increasingly gains importance, the demand for personalized systems is on the rise. Although wearable devices and smartphones generate substantial amounts of data, the effective integration and utilization of this information pose significant challenges. Traditional health management systems often depend on single-technology methodologies and encounter difficulties in processing

Graph contrastive learning (GCL) enhances recommendation accuracy by leveraging self-supervised features to refine node representations from large-scale unlabeled data. Traditional GCL-based recommendation models typically construct contrastive views via graph augmentation (e.g., stochastic node/edge dropout) or embedding-space perturbation, aiming to maximize representation consistency. However, these

Land cover change detection with hyperspectral remote sensing images (HyperCD), which focuses on monitoring land cover change on the Earth’s surface, has attracted increasing attention due to its advantages and wide applications in capturing detailed information. Over the past two decades, significant progress has been made in HyperCD, with numerous methods successfully applied to real-world datasets