Search Results (62)

Fatigue in air traffic controllers (ATCOs), particularly within remote tower operations, poses a substantial risk to aviation safety due to its detrimental effects on vigilance, decision-making, and situational awareness. While electroencephalography (EEG) provides a promising avenue for objective fatigue monitoring, existing models often fail to adequately capture both the spatial dependencies across brain regions and the temporal dynamics of cognitive states. To address this challenge, we propose a novel EEG-based fatigue detection framework, Spatio-Temporal Graph with Center Loss Network (STG-CLNet), which jointly models topological brain connectivity and temporal EEG evolution. The model leverages a multi-stage graph convolutional network to encode spatial dependencies and a triple-layer LSTM module to capture temporal progression, while incorporating center loss to enhance feature discriminability in the embedding space. We constructed a domain-specific EEG dataset involving 34 ATCO participants operating in high- and low-traffic remote tower simulations, with fatigue labels derived from three validated subjective metrics. Experimental results demonstrate that STG-CLNet achieves superior classification performance (accuracy = 96.73%, recall = 92.01%, F1-score = 87.15%), outperforming several strong baselines, including LSTM and EEGNet. These findings underscore the potential of STG-CLNet for integration into real-time cognitive monitoring systems in air traffic control, contributing to both theoretical advancement and operational safety enhancement. Full article

Accurate teeth segmentation and orientation are fundamental in modern oral healthcare, enabling precise diagnosis, treatment planning, and dental implant design. In this study, we present a comprehensive approach to teeth segmentation and orientation from panoramic X-ray images, leveraging deep-learning techniques. We built an end-to-end instance segmentation network that uses an encoder–decoder architecture reinforced with grid-aware attention gates along the skip connections. We introduce oriented bounding box (OBB) generation through principal component analysis (PCA) for precise tooth orientation estimation. Evaluating our approach on the publicly available DNS dataset, comprising 543 panoramic X-ray images, we achieve the highest Intersection-over-Union (IoU) score of 82.43% and a Dice Similarity Coefficient (DSC) score of 90.37% among compared models in teeth instance segmentation. In OBB analysis, we obtain the Rotated IoU (RIoU) score of 82.82%. We also conduct detailed analyses of individual tooth labels and categorical performance, shedding light on strengths and weaknesses. The proposed model’s accuracy and versatility offer promising prospects for improving dental diagnoses, treatment planning, and personalized healthcare in the oral domain. Full article

In response to the limitations of traditional image processing algorithms, such as high noise sensitivity and threshold dependency in bridge crack detection, and the extensive labeled data requirements of deep learning methods, this study proposes a novel crack segmentation algorithm based on fuzzy C-means (FCM) clustering and multi-feature fusion. A three-dimensional feature space is constructed using B-channel pixels and fuzzy clustering with $c$ = 3, justified by the distinct distribution patterns of these three regions in the image, enabling effective preliminary segmentation. To enhance accuracy, connected domain labeling combined with a circularity threshold is introduced to differentiate linear cracks from granular noise. Furthermore, a 5 $\times$ 5 neighborhood search strategy, based on crack pixel amplitude, is designed to restore the continuity of fragmented cracks. Experimental results on the Concrete Crack and SDNET2018 datasets demonstrate that the proposed algorithm achieves an accuracy of 0.885 and a recall rate of 0.891, outperforming DeepLabv3+ by 4.2%. Notably, with a processing time of only 0.8 s per image, the algorithm balances high accuracy with real-time efficiency, effectively addressing challenges, such as missed fine cracks and misjudged broken cracks in noisy environments by integrating geometric features and pixel distribution characteristics. This study provides an efficient unsupervised solution for bridge damage detection. Full article

Underwater sonar target recognition is crucial in fields such as national defense, navigation, and environmental monitoring. However, it faces issues such as the complex characteristics of ship-radiated noise, imbalanced data distribution, non-stationarity, and bottlenecks of existing technologies. This paper proposes the MultiFuseNet-AID network, aiming to address these challenges. The network includes the TriFusion block module, the novel lightweight attention residual network (NLARN), the long- and short-term attention (LSTA) module, and the Mamba module. Through the TriFusion block module, the original, differential, and cumulative signals are processed in parallel, and features such as MFCC, CQT, and Fbank are fused to achieve deep multi-domain feature fusion, thereby enhancing the signal representation ability. The NLARN was optimized based on the ResNet architecture, with the SE attention mechanism embedded. Combined with the long- and short-term attention (LSTA) and the Mamba module, it could capture long-sequence dependencies with an O(N) complexity, completing the optimization of lightweight long sequence modeling. At the same time, with the help of feature fusion, and layer normalization and residual connections of the Mamba module, the adaptability of the model in complex scenarios with imbalanced data and strong noise was enhanced. On the DeepShip and ShipsEar datasets, the recognition rates of this model reached 98.39% and 99.77%, respectively. The number of parameters and the number of floating point operations were significantly lower than those of classical models, and it showed good stability and generalization ability under different sample label ratios. The research shows that the MultiFuseNet-AID network effectively broke through the bottlenecks of existing technologies. However, there is still room for improvement in terms of adaptability to extreme underwater environments, training efficiency, and adaptability to ultra-small devices. It provides a new direction for the development of underwater sonar target recognition technology. Full article

Accurate extraction of dynamically evolving haul roads in open-pit mines from very-high-resolution (VHR) satellite imagery remains a critical challenge due to domain gaps between urban and mining environments, prohibitive annotation costs, and morphological irregularities. This paper introduces OMRoadNet, an unsupervised domain adaptation (UDA) framework for open-pit mine road extraction, which synergizes self-training, attention-based feature disentanglement, and morphology-aware augmentation to address these challenges. The framework employs a cyclic GAN (generative adversarial network) architecture with bidirectional translation pathways, integrating pseudo-label refinement through confidence thresholds and geometric rules (eight-neighborhood connectivity and adaptive kernel resizing) to resolve domain shifts. A novel exponential moving average unit (EMAU) enhances feature robustness by adaptively weighting historical states, while morphology-aware augmentation simulates variable road widths and spectral noise. Evaluations on cross-domain datasets demonstrate state-of-the-art performance with 92.16% precision, 80.77% F1-score, and 67.75% IoU (intersection over union), outperforming baseline models by 4.3% in precision and reducing annotation dependency by 94.6%. By reducing per-kilometer operational costs by 78% relative to LiDAR (Light Detection and Ranging) alternatives, OMRoadNet establishes a practical solution for intelligent mining infrastructure mapping, bridging the critical gap between structured urban datasets and unstructured mining environments. Full article

Due to the inherent limitations in remote sensing image quality, seasonal variations, and radiometric inconsistencies, river extraction based on remote sensing image classification often results in omissions. These challenges are particularly pronounced in the detection of narrow and complex river networks, where fine river features are frequently underrepresented, leading to fragmented and discontinuous water body extraction. To address these issues and enhance both the completeness and accuracy of fine river identification, this study proposes an advanced fine river extraction and optimization method. Firstly, a linear river feature enhancement algorithm for preliminary optimization is introduced, which combines Frangi filtering with an improved GA-OTSU segmentation technique. By thoroughly analyzing the global features of high-resolution remote sensing images, Frangi filtering is employed to enhance the river linear characteristics. Subsequently, the improved GA-OTSU thresholding algorithm is applied for feature segmentation, yielding the initial results. In the next stage, to preserve the original river topology and ensure stripe continuity, a river skeleton refinement algorithm is utilized to retain critical skeletal information about the river networks. Following this, river endpoints are identified using a connectivity domain labeling algorithm, and the bounding rectangles of potential disconnected regions are delineated. To address discontinuities, river endpoints are shifted and reconnected based on structural similarity index (SSIM) metrics, effectively bridging gaps in the river network. Finally, nonlinear water optimization combined K-means clustering segmentation, topology and spectral inspection, and small-area removal are designed to supplement some missed water bodies and remove some non-water bodies. Experimental results demonstrate that the proposed method significantly improves the regularization and completeness of river extraction, particularly in cases of fine, narrow, and discontinuous river features. The approach ensures more reliable and consistent river delineation, making the extracted results more robust and applicable for practical hydrological and environmental analyses. Full article

The coal mining industry has accumulated a vast amount of knowledge on shearer accident analysis and handling during its development. Accurately identifying and extracting entity information related to shearer maintenance is crucial for advancing downstream tasks in intelligent shearer operations and maintenance. Currently, named entity recognition in the field of shearer maintenance primarily relies on fine-tuning-based methods; however, a gap exists between pretraining and downstream tasks. In this paper, we introduce prompt learning and large language models (LLMs), proposing a named entity recognition method for shearer maintenance based on multi-level clue-guided prompt learning (MCP). This method consists of three key components: (1) the prompt learning layer, which encapsulates the information to be identified and forms multi-level sub-clues into structured prompts based on a predefined format; (2) the LLM layer, which employs a decoder-only architecture-based large language model to deeply process the connection between the structured prompts and the information to be identified through multiple stacked decoder layers; and (3) the answer layer, which maps the output of the LLM layer to a structured label space via a parser to obtain the recognition results of structured named entities in the shearer maintenance domain. By designing multi-level sub-clues, MCP enables the model to extract and learn trigger words related to entity recognition from the prompts, acquiring context-aware prompt tokens. This allows the model to make accurate predictions, bridging the gap between fine-tuning and pretraining while eliminating the reliance on labeled data for fine-tuning. Validation was conducted on a self-constructed knowledge corpus in the shearer maintenance domain. Experimental results demonstrate that the proposed method outperforms mainstream baseline models in the field of shearer maintenance. Full article

Heterogeneous domain adaptation (HDA) utilizes the knowledge of the source domain to model the target domain. Although the two domains are semantically related, the problem of feature and distribution differences in heterogeneous data still needs to be solved. Most of the existing HDA methods only consider the feature or distribution problem but do not consider the geometric semantic information similarity between the domain structures, which leads to a weakened adaptive performance. In order to solve the problem, a centroid connected structure matching network (CCSMN) approach is proposed, which firstly maps the heterogeneous data into a shared public feature subspace to solve the problem of feature differences. Secondly, it promotes the overlap of domain centers and nodes of the same category between domains to reduce the positional distribution differences in the internal structure of data. Then, the supervised information is utilized to generate target domain nodes, and the geometric structural and semantic information are utilized to construct a centroid-connected structure with a reasonable inter-class distance. During the training process, a progressive and integrated pseudo-labeling is utilized to select samples with high-confidence labels and improve the classification accuracy for the target domain. Extensive experiments are conducted in text-to-image and image-to-image HDA tasks, and the results show that the CCSMN outperforms several state-of-the-art baseline methods. Compared with state-of-the-art HDA methods, in the text-to-image transfer task, the efficiency has increased by 8.05%; and in the image-to-image transfer task, the efficiency has increased by about 2%, which suggests that the CCSMN benefits more from domain geometric semantic information similarity. Full article

The integration of satellite data with deep learning has revolutionized various tasks in remote sensing, including classification, object detection, and semantic segmentation. Cloud segmentation in high-resolution satellite imagery is a critical application within this domain, yet progress in developing advanced algorithms for this task has been hindered by the scarcity of specialized datasets and annotation tools. This study addresses this challenge by introducing CloudLabel, a semi-automatic annotation technique leveraging region growing and morphological algorithms including flood fill, connected components, and guided filter. CloudLabel v1.0 streamlines the annotation process for high-resolution satellite images, thereby addressing the limitations of existing annotation platforms which are not specifically adapted to cloud segmentation, and enabling the efficient creation of high-quality cloud segmentation datasets. Notably, we have curated the Annotated Dataset for Training Cloud Segmentation (ADTCS) comprising 32,065 images (512 × 512) for cloud segmentation based on CloudLabel. The ADTCS dataset facilitates algorithmic advancement in cloud segmentation, characterized by uniform cloud coverage distribution and high image entropy (mainly 5–7). These features enable deep learning models to capture comprehensive cloud characteristics, enhancing recognition accuracy and reducing ground object misclassification. This contribution significantly advances remote sensing applications and cloud segmentation algorithms. Full article

Lithium-ion batteries are widely utilized in numerous applications, making it essential to precisely predict their degradation trajectory and remaining useful life (RUL). To improve the stability and applicability of RUL prediction for lithium-ion batteries, this paper uses a new method to predict RUL by combining CNN-LSTM-Attention with transfer learning. The presented model merges the strengths of both convolutional and sequential architectures, and it enhances the model’s capability to grasp comprehensive information by utilizing the attention mechanism, thereby boosting overall performance. The CEEMDAN algorithm is used for NASA batteries with obvious capacity regeneration phenomena to alleviate the difficulties caused by capacity regeneration on model prediction. During the model transfer phase, the CNN and LSTM layers of the pre-trained model from the source domain are kept unchanged during retraining, while the attention and fully connected layers are fine-tuned for NASA batteries and self-tested NCM batteries. The final results indicate that this method achieves superior accuracy relative to other methods while addressing the issue of limited labeled data in the target domain through transfer learning, thereby enhancing the model’s transferability and generalization capabilities. Full article

Gender gaps in spatial skills—a domain relevant to STEM jobs—have been hypothesized to contribute to women’s underrepresentation in STEM fields. To study emerging adults’ beliefs about skill sets and jobs, we asked college students (N = 300) about the relevance of spatial, mathematical, science and verbal skills for each of 82 jobs. Analyses of responses revealed four job clusters—quantitative, basic & applied science, spatial, and verbal. Students’ ratings of individual jobs and job clusters were similar to judgments of professional job analysts (O*NET). Both groups connected STEM jobs to science, math, and spatial skills. To investigate whether students’ interests in STEM and other jobs are related to their own self-concepts, beliefs about jobs, and spatial performance, we asked students in another sample (N = 292) to rate their self-concepts in various academic domains, rate personal interest in each of the 82 jobs, judge cultural gender stereotypes of those jobs, and complete a spatial task. Consistent with prior research, jobs judged to draw on math, science, or spatial skills were rated as more strongly culturally stereotyped for men than women; jobs judged to draw on verbal skills were more strongly culturally stereotyped for women than men. Structural equation modeling showed that for both women and men, spatial task scores directly (and indirectly through spatial self-concept) related to greater interest in the job cluster closest to the one O*NET labeled “STEM”. Findings suggest that pre-college interventions that improve spatial skills might be effective for increasing spatial self-concepts and the pursuit of STEM careers among students from traditionally under-represented groups, including women. Full article

The paper demonstrates a novel methodology for Content-Based Image Retrieval (CBIR), which shifts the focus from conventional domain-specific image queries to more complex text-based query processing. Latent diffusion models are employed to interpret complex textual prompts and address the requirements of effectively interpreting the complex textual query. Latent Diffusion models successfully transform complex textual queries into visually engaging representations, establishing a seamless connection between textual descriptions and visual content. Custom triplet network design is at the heart of our retrieval method. When trained well, a triplet network will represent the generated query image and the different images in the database. The cosine similarity metric is used to assess the similarity between the feature representations in order to find and retrieve the relevant images. Our experiments results show that latent diffusion models can successfully bridge the gap between complex textual prompts for image retrieval without relying on labels or metadata that are attached to database images. This advancement sets the stage for future explorations in image retrieval, leveraging the generative AI capabilities to cater to the ever-evolving demands of big data and complex query interpretations. Full article

Identifying stress in older adults is a crucial field of research in health and well-being. This allows us to take timely preventive measures that can help save lives. That is why a nonobtrusive way of accurate and precise stress detection is necessary. Researchers have proposed many statistical measurements to associate stress with sensor readings from digital biomarkers. With the recent progress of Artificial Intelligence in the healthcare domain, the application of machine learning is showing promising results in stress detection. Still, the viability of machine learning for digital biomarkers of stress is under-explored. In this work, we first investigate the performance of a supervised machine learning algorithm (Random Forest) with manual feature engineering for stress detection with contextual information. The concentration of salivary cortisol was used as the golden standard here. Our framework categorizes stress into No Stress, Low Stress, and High Stress by analyzing digital biomarkers gathered from wearable sensors. We also provide a thorough knowledge of stress in older adults by combining physiological data obtained from wearable sensors with contextual clues from a stress protocol. Our context-aware machine learning model, using sensor fusion, achieved a macroaverage F-1 score of 0.937 and an accuracy of 92.48% in identifying three stress levels. We further extend our work to get rid of the burden of manual feature engineering. We explore Convolutional Neural Network (CNN)-based feature encoder and cortisol biomarkers to detect stress using contextual information. We provide an in-depth look at the CNN-based feature encoder, which effectively separates useful features from physiological inputs. Both of our proposed frameworks, i.e., Random Forest with engineered features and a Fully Connected Network with CNN-based features validate that the integration of digital biomarkers of stress can provide more insight into the stress response even without any self-reporting or caregiver labels. Our method with sensor fusion shows an accuracy and F-1 score of 83.7797% and 0.7552, respectively, without context and 96.7525% accuracy and 0.9745 F-1 score with context, which also constitutes a 4% increase in accuracy and a 0.04 increase in F-1 score from RF. Full article

Medical image diagnosis using deep learning has shown significant promise in clinical medicine. However, it often encounters two major difficulties in real-world applications: (1) domain shift, which invalidates the trained model on new datasets, and (2) class imbalance problems leading to model biases towards majority classes. To address these challenges, this paper proposes a transfer learning solution, named Dynamic Weighting Translation Transfer Learning (DTTL), for imbalanced medical image classification. The approach is grounded in information and entropy theory and comprises three modules: Cross-domain Discriminability Adaptation (CDA), Dynamic Domain Translation (DDT), and Balanced Target Learning (BTL). CDA connects discriminative feature learning between source and target domains using a synthetic discriminability loss and a domain-invariant feature learning loss. The DDT unit develops a dynamic translation process for imbalanced classes between two domains, utilizing a confidence-based selection approach to select the most useful synthesized images to create a pseudo-labeled balanced target domain. Finally, the BTL unit performs supervised learning on the reassembled target set to obtain the final diagnostic model. This paper delves into maximizing the entropy of class distributions, while simultaneously minimizing the cross-entropy between the source and target domains to reduce domain discrepancies. By incorporating entropy concepts into our framework, our method not only significantly enhances medical image classification in practical settings but also innovates the application of entropy and information theory within deep learning and medical image processing realms. Extensive experiments demonstrate that DTTL achieves the best performance compared to existing state-of-the-art methods for imbalanced medical image classification tasks. Full article

Semantic labeling of high-resolution remote sensing images (HRRSIs) holds a significant position in the remote sensing domain. Although numerous deep-learning-based segmentation models have enhanced segmentation precision, their complexity leads to a significant increase in parameters and computational requirements. While ensuring segmentation accuracy, it is also crucial to improve segmentation speed. To address this issue, we propose an efficient asymmetric deep learning network for HRRSIs, referred to as EAD-Net. First, EAD-Net employs ResNet50 as the backbone without pooling, instead of the RepVGG block, to extract rich semantic features while reducing model complexity. Second, a dynamic routing module is proposed in EAD-Net to adjust routing based on the pixel occupancy of small-scale objects. Concurrently, a channel attention mechanism is used to preserve their features even with minimal occupancy. Third, a novel asymmetric decoder is introduced, which uses convolutional operations while discarding skip connections. This not only effectively reduces redundant features but also allows using low-level image features to enhance EAD-Net’s performance. Extensive experimental results on the ISPRS 2D semantic labeling challenge benchmark demonstrate that EAD-Net achieves state-of-the-art (SOTA) accuracy performance while reducing model complexity and inference time, while the mean Intersection over Union (mIoU) score reaching 87.38% and 93.10% in the Vaihingen and Potsdam datasets, respectively. Full article