Search Results (16)

Fine-grained food image segmentation is essential for accurate dietary assessment and nutritional analysis, yet remains highly challenging due to ambiguous boundaries, inter-class similarity, and dense layouts of meals containing many different ingredients in real-world settings. Existing methods based solely on CNNs, Transformers, or Mamba architectures often fail to simultaneously preserve fine-grained local details and capture contextual dependencies over long distances. To address these limitations, we propose HDF (Hybrid Decoder for Food Image Segmentation), a novel decoding framework built upon the MambaVision backbone. Our approach first employs a convolution-based feature pyramid network (FPN) to extract multi-stage features from the encoder. These features are then thoroughly fused across scales using a Cross-Layer Mamba module that models inter-level dependencies with linear complexity. Subsequently, an Attention Refinement module integrates global semantic context through spatial–channel reweighting. Finally, a Food Co-occurrence Module explicitly enhances food-specific semantics by learning dynamic co-occurrence patterns among categories, improving segmentation of visually similar or frequently co-occurring ingredients. Evaluated on two widely used, high-quality benchmarks, FoodSeg103 and UEC-FoodPIX Complete, which are standard datasets for fine-grained food segmentation, HDF achieves a 52.25% mean Intersection-over-Union (mIoU) on FoodSeg103 and a 76.16% mIoU on UEC-FoodPIX Complete, outperforming current state-of-the-art methods by a clear margin. These results demonstrate that HDF’s hybrid design and explicit co-occurrence awareness effectively address key challenges in food image segmentation, providing a robust foundation for practical applications in dietary logging, nutritional estimation, and food safety inspection. Full article

Background: Cognitive and neuropsychological effects of cancer and its treatments have gained increasing attention over the past decade, with growing evidence of persistent deficits across multiple cancer types. While numerous studies have examined these effects, the literature remains fragmented, and no comprehensive bibliometric synthesis has been conducted to map the field’s intellectual structure and emerging trends. Methods: A bibliometric and science mapping analysis was performed using the Scopus database to identify peer-reviewed articles published between 2015 and 2025 on neuropsychological or cognitive outcomes in adult cancer populations. Data from 179 eligible publications were analyzed with VOSviewer and Microsoft Power BI, applying performance metrics and network mapping techniques, including co-authorship, bibliographic coupling, co-citation, and keyword co-occurrence analyses. Results: Publication output increased steadily over the decade, with leading contributions from the Journal of Neuro-Oncology, Psycho-Oncology, and Brain Imaging and Behavior. Co-citation analysis identified three core intellectual pillars: (i) clinical characterization of cancer-related cognitive impairment, (ii) mechanistic and neuroimaging-based investigations, and (iii) neurosurgical and neuropathological research in brain tumors. Keyword mapping revealed emerging themes in sleep and circadian rhythm research, biological contributors to cognitive decline, and scalable rehabilitation strategies such as web-based cognitive training. Collaborative networks, while showing dense local clusters, remained moderately fragmented across disciplines. Conclusions: This review provides the first quantitative, decade-spanning map of cognitive oncology research, highlighting both consolidated knowledge areas and underexplored domains. Future efforts should prioritize methodological standardization, cross-disciplinary collaboration, and integration of cognitive endpoints into survivorship care, with the ultimate aim of improving functional outcomes and quality of life for cancer survivors. Full article

Geological elements are fundamental components of the Earth’s ecosystem, and accurately identifying their spatial distribution is essential for analyzing environmental processes, guiding land-use planning, and promoting sustainable development. Remote sensing technologies, combined with artificial intelligence algorithms, offer new opportunities for the efficient interpretation of geological features. However, in areas with dense vegetation coverage, the information directly extracted from single-source optical imagery is limited, thereby constraining interpretation accuracy. Supplementary inputs such as synthetic aperture radar (SAR), topographic features, and texture information—collectively referred to as sensitive features and prior knowledge—can improve interpretation, but their effectiveness varies significantly across time and space. This variability often leads to inconsistent performance in general-purpose models, thus limiting their practical applicability. To address these challenges, we construct a geological element interpretation dataset for Northwest China by incorporating multi-source data, including Sentinel-1 SAR imagery, Sentinel-2 multispectral imagery, sensitive features (such as the digital elevation model (DEM), texture features based on the gray-level co-occurrence matrix (GLCM), geological maps (GMs), and the normalized difference vegetation index (NDVI)), as well as prior knowledge (such as base geological maps). Using five mainstream deep learning models, we systematically evaluate the performance improvement brought by various sensitive features and prior knowledge in remote sensing-based geological interpretation. To handle disparities in spatial resolution, temporal acquisition, and noise characteristics across sensors, we further develop a multi-source complement-driven network (MCDNet) that integrates an improved feature rectification module (IFRM) and an attention-enhanced fusion module (AFM) to achieve effective cross-modal alignment and noise suppression. Experimental results demonstrate that the integration of multi-source sensitive features and prior knowledge leads to a 2.32–6.69% improvement in mIoU for geological elements interpretation, with base geological maps and topographic features contributing most significantly to accuracy gains. Full article

Power line detection (PLD) is a crucial task in the electric power industry where accurate PLD forms the foundation for achieving automated inspections. However, recent top-performing power line detection methods tend to generate thick and noisy edge lines, adding to the difficulties of subsequent tasks. In this work, we propose a multi-scale feature-based PLD method named LUM-Net to allow for the detection of power lines in a crisp and precise way. The algorithm utilizes EfficientNetV1 as the backbone network, ensuring effective feature extraction across various scales. We developed a Coordinated Convolutional Block Attention Module (CoCBAM) to focus on critical features by emphasizing both channel-wise and spatial information, thereby refining the power lines and reducing noise. Furthermore, we constructed the Bi-Large Kernel Convolutional Block (BiLKB) as the decoder, leveraging large kernel convolutions and spatial selection mechanisms to capture more contextual information, supplemented by auxiliary small kernels to refine the extracted feature information. By integrating these advanced components into a top-down dense connection mechanism, our method achieves effective, multi-scale information interaction, significantly improving the overall performance. The experimental results show that our method can predict crisp power line maps and achieve state-of-the-art performance on the PLDU dataset (ODS = 0.969) and PLDM dataset (ODS = 0.943). Full article

Accurate weed segmentation in Unmanned Aerial Vehicle (UAV) imagery remains a significant challenge in precision agriculture due to environmental variability, weak contextual representation, and inaccurate boundary detection. To address these limitations, we propose the Multi-Scale and Edge-Aware Network (MSEA-Net), a lightweight and efficient deep learning framework designed to enhance segmentation accuracy while maintaining computational efficiency. Specifically, we introduce the Multi-Scale Spatial-Channel Attention (MSCA) module to recalibrate spatial and channel dependencies, improving local–global feature fusion while reducing redundant computations. Additionally, the Edge-Enhanced Bottleneck Attention (EEBA) module integrates Sobel-based edge detection to refine boundary delineation, ensuring sharper object separation in dense vegetation environments. Extensive evaluations on publicly available datasets demonstrate the effectiveness of MSEA-Net, achieving a mean Intersection over Union (IoU) of 87.42% on the Motion-Blurred UAV Images of Sorghum Fields dataset and 71.35% on the CoFly-WeedDB dataset, outperforming benchmark models. MSEA-Net also maintains a compact architecture with only 6.74 M parameters and a model size of 25.74 MB, making it suitable for UAV-based real-time weed segmentation. These results highlight the potential of MSEA-Net for improving automated weed detection in precision agriculture while ensuring computational efficiency for edge deployment. Full article

Unmanned systems encounter challenging weather conditions during obstacle removal tasks. Researching stable, real-time, and accurate environmental perception methods under such conditions is crucial. Cameras and LiDAR sensors provide different and complementary data. However, the integration of disparate data presents challenges such as feature mismatches and the fusion of sparse and dense information, which can degrade algorithmic performance. Adverse weather conditions, like rain and snow, introduce noise that further reduces perception accuracy. To address these issues, we propose a novel weather-adaptive bird’s-eye view multi-level co-attention fusion 3D object detection algorithm (BEV-MCAF). This algorithm employs an improved feature extraction network to obtain more effective features. A multimodal feature fusion module has been constructed with BEV image feature generation and a co-attention mechanism for better fusion effects. A multi-scale multimodal joint domain adversarial network (M2-DANet) is proposed to enhance adaptability to adverse weather conditions. The efficacy of BEV-MCAF has been validated on both the nuScenes and Ithaca365 datasets, confirming its robustness and good generalization capability in a variety of bad weather conditions. The findings indicate that our proposed algorithm performs better than the benchmark, showing improved adaptability to harsh weather conditions and enhancing the robustness of UVs, ensuring reliable perception under challenging conditions. Full article

Background/Objective: This study aims to utilize advanced artificial intelligence (AI) image recog-nition technologies to establish a robust system for identifying features in lung computed tomog-raphy (CT) scans, thereby detecting respiratory infections such as SARS-CoV-2 pneumonia. Spe-cifically, the research focuses on developing a new model called Residual-Dense-Attention Gates U-Net (RDAG U-Net) to improve accuracy and efficiency in identification. Methods: This study employed Attention U-Net, Attention Res U-Net, and the newly developed RDAG U-Net model. RDAG U-Net extends the U-Net architecture by incorporating ResBlock and DenseBlock modules in the encoder to retain training parameters and reduce computation time. The training dataset in-cludes 3,520 CT scans from an open database, augmented to 10,560 samples through data en-hancement techniques. The research also focused on optimizing convolutional architectures, image preprocessing, interpolation methods, data management, and extensive fine-tuning of training parameters and neural network modules. Result: The RDAG U-Net model achieved an outstanding accuracy of 93.29% in identifying pulmonary lesions, with a 45% reduction in computation time compared to other models. The study demonstrated that RDAG U-Net performed stably during training and exhibited good generalization capability by evaluating loss values, model-predicted lesion annotations, and validation-epoch curves. Furthermore, using ITK-Snap to convert 2D pre-dictions into 3D lung and lesion segmentation models, the results delineated lesion contours, en-hancing interpretability. Conclusion: The RDAG U-Net model showed significant improvements in accuracy and efficiency in the analysis of CT images for SARS-CoV-2 pneumonia, achieving a 93.29% recognition accuracy and reducing computation time by 45% compared to other models. These results indicate the potential of the RDAG U-Net model in clinical applications, as it can accelerate the detection of pulmonary lesions and effectively enhance diagnostic accuracy. Additionally, the 2D and 3D visualization results allow physicians to understand lesions' morphology and distribution better, strengthening decision support capabilities and providing valuable medical diagnosis and treatment planning tools. Full article

Skin lesion classification is vital for the early detection and diagnosis of skin diseases, facilitating timely intervention and treatment. However, existing classification methods face challenges in managing complex information and long-range dependencies in dermoscopic images. Therefore, this research aims to enhance the feature representation by incorporating local, global, and hierarchical features to improve the performance of skin lesion classification. We introduce a novel dual-track deep learning (DL) model in this research for skin lesion classification. The first track utilizes a modified Densenet-169 architecture that incorporates a Coordinate Attention Module (CoAM). The second track employs a customized convolutional neural network (CNN) comprising a Feature Pyramid Network (FPN) and Global Context Network (GCN) to capture multiscale features and global contextual information. The local features from the first track and the global features from second track are used for precise localization and modeling of the long-range dependencies. By leveraging these architectural advancements within the DenseNet framework, the proposed neural network achieved better performance compared to previous approaches. The network was trained and validated using the HAM10000 dataset, achieving a classification accuracy of 93.2%. Full article

All-solid-state lithium-ion batteries (ASSLBs) have recently received significant attention due to their exceptional energy/power densities, inherent safety, and long-term electrochemical stability. However, to achieve energy- and power-dense ASSLBs, the cathode composite electrodes require optimum ionic and electrical pathways and hence the development of electrode designs that facilitate such requirements is necessary. Among the various available conductive materials, carbon black (CB) is typically considered as a suitable carbon additive for enhancing electrode conductivity due to its affordable price and electrical-network-enhancing properties. In this study, we examined the effect of different weight percentages (wt%) of nano-sized CB as a conductive additive within a cathode composite made up of Ni-rich cathode material (LiNi_0.8Co_0.1Mn_0.1O₂) and solid electrolyte (Li₆PS₅Cl). Composites including 3 wt%, 5 wt%, and 7 wt% CB were produced, achieving capacity retentions of 66.1%, 65.4%, and 44.6% over 50 cycles at 0.5 C. Despite an increase in electrical conductivity of the 7 wt% CB sample, a significantly lower capacity retention was observed. This was attributed to the increased resistance at the solid electrolyte/cathode material interface, resulting from the presence of excessive CB. This study confirms that an excessive amount of nano-sized conductive material can affect the interfacial resistance between the solid electrolyte and the cathode active material, which is ultimately more important to the electrochemical performance than the electrical pathways. Full article

Current network representation learning models mainly use matrix factorization-based and neural network-based approaches, and most models still focus only on local neighbor features of nodes. Knowledge representation learning aims to learn low-dimensional dense representations of entities and relations from structured knowledge graphs, and most models use the triplets to capture semantic, logical, and topological features between entities and relations. In order to extend the generalization capability of the network representation learning models, this paper proposes a network representation learning algorithm based on multiple remodeling of node attributes named MRNR. The model constructs the knowledge triplets through the textual association relationships between nodes. Meanwhile, a novel co-occurrence word training method has been proposed. Multiple remodeling of node attributes can significantly improve the effectiveness of network representation learning. At the same time, MRNR introduces the attention mechanism to achieve the weight information for key co-occurrence words and triplets, which further models the semantic and topological features between entities and relations, and it makes the network embedding more accurate and has better generalization ability. Full article

To address the challenges of weak model generalization and limited model capacity adaptation in traditional malware detection methods, this article presents a novel malware detection approach based on stacked depthwise separable convolutions and self-attention, termed CoAtNet. This method combines the strengths of the self-attention module’s robust model adaptation and the convolutional networks’ powerful generalization abilities. The initial step involves transforming the malicious code into grayscale images. These images are subsequently processed using a detection model that employs stacked depthwise separable convolutions and an attention mechanism. This model effectively recognizes and classifies the images, automatically extracting essential features from malicious software images. The effectiveness of the method was validated through comparative experiments using both the Malimg dataset and the augmented Blended+ dataset. The approach’s performance was evaluated against popular models, including XceptionNet, EfficientNetB0, ResNet50, VGG16, DenseNet169, and InceptionResNetV2. The experimental results highlight that the model surpasses other malware detection models in terms of accuracy and generalization ability. In conclusion, the proposed method addresses the limitations of traditional malware detection approaches by leveraging stacked depthwise separable convolutions and self-attention. Comprehensive experiments demonstrate its superior performance compared to existing models. This research contributes to advancing the field of malware detection and provides a promising solution for enhanced accuracy and robustness. Full article

The geopolymer concept has gained wide international attention during the last two decades and is now seen as a potential alternative to ordinary Portland cement; however, before full implementation in the national and international standards, the geopolymer concept requires clarity on the commonly used definitions and mix design methodologies. The lack of a common definition and methodology has led to inconsistency and confusion across disciplines. This review aims to clarify the most existing geopolymer definitions and the diverse procedures on geopolymer methodologies to attain a good understanding of both the unary and binary geopolymer systems. This review puts into perspective the most crucial facets to facilitate the sustainable development and adoption of geopolymer design standards. A systematic review protocol was developed based on the Preferred Reporting of Items for Systematic Reviews and Meta-Analyses (PRISMA) checklist and applied to the Scopus database to retrieve articles. Geopolymer is a product of a polycondensation reaction that yields a three-dimensional tecto-aluminosilicate matrix. Compared to unary geopolymer systems, binary geopolymer systems contain complex hydrated gel structures and polymerized networks that influence workability, strength, and durability. The optimum utilization of high calcium industrial by-products such as ground granulated blast furnace slag, Class-C fly ash, and phosphogypsum in unary or binary geopolymer systems give C-S-H or C-A-S-H gels with dense polymerized networks that enhance strength gains and setting times. As there is no geopolymer mix design standard, most geopolymer mix designs apply the trial-and-error approach, and a few apply the Taguchi approach, particle packing fraction method, and response surface methodology. The adopted mix designs require the optimization of certain mixture variables whilst keeping constant other nominal material factors. The production of NaOH gives less CO₂ emission compared to Na₂SiO_3, which requires higher calcination temperatures for Na₂CO₃ and SiO_2. However, their usage is considered unsustainable due to their caustic nature, high energy demand, and cost. Besides the blending of fly ash with other industrial by-products, phosphogypsum also has the potential for use as an ingredient in blended geopolymer systems. The parameters identified in this review can help foster the robust adoption of geopolymer as a potential “go-to” alternative to ordinary Portland cement for construction. Furthermore, the proposed future research areas will help address the various innovation gaps observed in current literature with a view of the environment and society. Full article

In the question-and-answer (Q&A) communities of the “China Agricultural Technology Extension Information Platform”, thousands of rice-related Chinese questions are newly added every day. The rapid detection of the same semantic question is the key to the success of a rice-related intelligent Q&A system. To allow the fast and automatic detection of the same semantic rice-related questions, we propose a new method based on the Coattention-DenseGRU (Gated Recurrent Unit). According to the rice-related question characteristics, we applied word2vec with the TF-IDF (Term Frequency–Inverse Document Frequency) method to process and analyze the text data and compare it with the Word2vec, GloVe, and TF-IDF methods. Combined with the agricultural word segmentation dictionary, we applied Word2vec with the TF-IDF method, effectively solving the problem of high dimension and sparse data in the rice-related text. Each network layer employed the connection information of features and all previous recursive layers’ hidden features. To alleviate the problem of feature vector size increasing due to dense splicing, an autoencoder was used after dense concatenation. The experimental results show that rice-related question similarity matching based on Coattention-DenseGRU can improve the utilization of text features, reduce the loss of features, and achieve fast and accurate similarity matching of the rice-related question dataset. The precision and F1 values of the proposed model were 96.3% and 96.9%, respectively. Compared with seven other kinds of question similarity matching models, we present a new state-of-the-art method with our rice-related question dataset. Full article

Visual question answering (VQA) is a multi-modal task involving natural language processing (NLP) and computer vision (CV), which requires models to understand of both visual information and textual information simultaneously to predict the correct answer for the input visual image and textual question, and has been widely used in smart and intelligent transport systems, smart city, and other fields. Today, advanced VQA approaches model dense interactions between image regions and question words by designing co-attention mechanisms to achieve better accuracy. However, modeling interactions between each image region and each question word will force the model to calculate irrelevant information, thus causing the model’s attention to be distracted. In this paper, to solve this problem, we propose a novel model called Multi-modal Explicit Sparse Attention Networks (MESAN), which concentrates the model’s attention by explicitly selecting the parts of the input features that are the most relevant to answering the input question. We consider that this method based on top-k selection can reduce the interference caused by irrelevant information and ultimately help the model to achieve better performance. The experimental results on the benchmark dataset VQA v2 demonstrate the effectiveness of our model. Our best single model delivers 70.71% and 71.08% overall accuracy on the test-dev and test-std sets, respectively. In addition, we also demonstrate that our model can obtain better attended features than other advanced models through attention visualization. Our work proves that the models with sparse attention mechanisms can also achieve competitive results on VQA datasets. We hope that it can promote the development of VQA models and the application of artificial intelligence (AI) technology related to VQA in various aspects. Full article

At present, the state-of-the-art approaches of Visual Question Answering (VQA) mainly use the co-attention model to relate each visual object with text objects, which can achieve the coarse interactions between multimodalities. However, they ignore the dense self-attention within question modality. In order to solve this problem and improve the accuracy of VQA tasks, in the present paper, an effective Dense Co-Attention Networks (DCAN) is proposed. First, to better capture the relationship between words that are relatively far apart and make the extracted semantics more robust, the Bidirectional Long Short-Term Memory (Bi-LSTM) neural network is introduced to encode questions and answers; second, to realize the fine-grained interactions between the question words and image regions, a dense multimodal co-attention model is proposed. The model’s basic components include the self-attention unit and the guided-attention unit, which are cascaded in depth to form a hierarchical structure. The experimental results on the VQA-v2 dataset show that DCAN has obvious performance advantages, which makes VQA applicable to a wider range of AI scenarios. Full article