Search Results (3,211)

In low-light environments, the presence of numerous small, dense, and occluded objects challenges the effectiveness of conventional object detection methods, failing to achieve desirable results. To address this, this paper proposes an efficient object detection network, YOLO_GD, which is designed for precise detection of targets in low-light scenarios. This algorithm, based on the foundational framework of YOLOv5s, implements a cross-layer feature fusion method founded on an information gathering and distribution mechanism. This method mitigates the issue of information loss during inter-layer feature exchange and, building on this, constructs a Bi-level routing spatial attention module to reduce computational redundancy caused by the self-attention mechanism, thereby enhancing the model’s detection accuracy for small objects. Furthermore, through the introduction of a novel deformable convolution, a cross-stage local feature fusion module is established, enabling the model to capture the complex features of input data more accurately and improve detection precision for dense objects. Lastly, the introduction of a probabilistic distance metric in the bounding box regression loss function enhances the network model’s generalization capability, further increasing detection accuracy in occluded scenarios. Experimental results on the ExDark dataset demonstrate that compared to YOLOv5, there is a 5.97% improvement in mean average precision (mAP), effectively enhancing object detection performance in low-light conditions. Full article

The application of contrastive learning in image clustering in the field of unsupervised learning has attracted much attention due to its ability to effectively improve clustering performance. Extracting features for face-oriented clustering using deep learning networks has also become one of the key challenges in this field. Some current research focuses on learning valuable semantic features using contrastive learning strategies to accomplish cluster allocation in the feature space. However, some studies decoupled the two phases of feature extraction and clustering are prone to error transfer, on the other hand, features learned in the feature extraction phase of multi-stage training are not guaranteed to be suitable for the clustering task. To address these challenges, We propose an end-to-end multi-branch feature fusion comparison deep clustering method (SwEAC), which incorporates a multi-branch feature extraction strategy in the representation learning phase, this method completes the clustering center comparison between multiple views and then assigns clusters to the extracted features. In order to extract higher-level semantic features, a multi-branch structure is used to learn multi-dimensional spatial channel dimension information and weighted receptive-field spatial features, achieving cross-dimensional information exchange of multi-branch sub-features. Meanwhile, we jointly optimize unsupervised contrastive representation learning and clustering in an end-to-end architecture to obtain semantic features for clustering that are more suitable for clustering tasks. Experimental results show that our model achieves good clustering performance on three popular image datasets evaluated by three unsupervised evaluation metrics, which proves the effectiveness of end-to-end multi-branch feature fusion comparison deep clustering methods. Full article

Due to the inadequacy in utilizing complementary information from different modalities and the biased estimation of degraded parameters, the unsupervised hyperspectral super-resolution algorithm suffers from low precision and limited applicability. To address this issue, this paper proposes an approach for hyperspectral image super-resolution, namely, the Unsupervised Multimodal Multilevel Feature Fusion network (UMMFF). The proposed approach employs a gated cross-retention module to learn shared patterns among different modalities. This module effectively eliminates the intermodal differences while preserving spatial–spectral correlations, thereby facilitating information interaction. A multilevel spatial–channel attention and parallel fusion decoder are constructed to extract features at three levels (low, medium, and high), enriching the information of the multimodal images. Additionally, an independent prior-based implicit neural representation blind estimation network is designed to accurately estimate the degraded parameters. The utilization of UMMFF on the “Washington DC”, Salinas, and Botswana datasets exhibited a superior performance compared to existing state-of-the-art methods in terms of primary performance metrics such as PSNR and ERGAS, and the PSNR values improved by 18.03%, 8.55%, and 5.70%, respectively, while the ERGAS values decreased by 50.00%, 75.39%, and 53.27%, respectively. The experimental results indicate that UMMFF demonstrates excellent algorithm adaptability, resulting in high-precision reconstruction outcomes. Full article

Computer vision has significantly influenced recent advancements in autonomous driving by providing cutting-edge solutions for various challenges, including object detection, semantic segmentation, and comprehensive scene understanding. One specific challenge is ego-vehicle trajectory segmentation, which involves learning the vehicle’s path and describing it with a segmentation map. This can play an important role in both autonomous driving and advanced driver assistance systems, as it enhances the accuracy of perceiving and forecasting the vehicle’s movements across different driving scenarios. In this work, we propose a deep learning approach for ego-trajectory segmentation that leverages a state-of-the-art segmentation network augmented with guidance cues provided through various merging mechanisms. These mechanisms are designed to direct the vehicle’s path as intended, utilizing training data obtained with a self-supervised approach. Our results demonstrate the feasibility of using self-supervised labels for ego-trajectory segmentation and embedding directional intentions within the network’s decisions through image and guidance input concatenation, feature concatenation, or cross-attention between pixel features and various types of guidance cues. We also analyze the effectiveness of our approach in constraining the segmentation outputs and prove that our proposed improvements bring major boosts in the segmentation metrics, increasing IoU by more than 12% and 5% compared with our two baseline models. This work paves the way for further exploration into ego-trajectory segmentation methods aimed at better predicting the behavior of autonomous vehicles. Full article

The fusion of multimodal medical images, particularly CT and MRI, is driven by the need to enhance the diagnostic process by providing clinicians with a single, comprehensive image that encapsulates all necessary details. Existing fusion methods often exhibit a bias towards features from one of the source images, making it challenging to simultaneously preserve both structural information and textural details. Designing an effective fusion method that can preserve more discriminative information is therefore crucial. In this work, we propose a Coupled Feature-Learning GAN (CFGAN) to fuse the multimodal medical images into a single informative image. The proposed method establishes an adversarial game between the discriminators and a couple of generators. First, the coupled generators are trained to generate two real-like fused images, which are then used to deceive the two coupled discriminators. Subsequently, the two discriminators are devised to minimize the structural distance to ensure the abundant information in the original source images is well-maintained in the fused image. We further empower the generators to be robust under various scales by constructing a discriminative feature extraction (DFE) block with different dilation rates. Moreover, we introduce a cross-dimension interaction attention (CIA) block to refine the feature representations. The qualitative and quantitative experiments on common benchmarks demonstrate the competitive performance of the CFGAN compared to other state-of-the-art methods. Full article

(1) Background: This study aimed to investigate whether yoga practice and physical activity level play an essential role in trait mindfulness and perceived stress reduction. Moreover, the study examined the differences in trait mindfulness and perceived stress between women who practiced yoga and those who engaged in other physical activities or were physically inactive, taking into account the time spent on physical activity in accordance with the World Health Organization recommendations. (2) Methods: A sample of 201 women participated in a cross-sectional online-based study, including 96 yoga practitioners and 105 non-practitioners of yoga (including physically active and inactive individuals). The average age of the participants was 36 years (range, 18–72 years; M = 36.19, SD = 11.64). Respondents completed the Mindful Attention Awareness Scale (MAAS) and the Perceived Stress Scale (PSS-10). (3) Results: Women who practiced yoga and were physically active had a significantly higher level of trait mindfulness and lower perceived stress levels than women who did not practice yoga and were physically inactive. An indirect effect of physical activity on perceived stress through mindfulness was shown only for women practicing yoga for at least 150 min per week. (4) Conclusions: This study revealed the importance of frequent yoga practice in reducing perceived stress and improving mindfulness traits. These findings may serve as a basis for implementing preventive actions in women experiencing high levels of everyday stress. Full article

The detection of the impurity rate in machine-picked seed cotton is crucial for precision agriculture. This study proposes a novel Cotton-YOLO-Seg cotton-impurity instance segmentation algorithm based on the you only look once version 8 small segmentation model (Yolov8s-Seg). The algorithm achieves precise pixel-level segmentation of cotton and impurities in seed cotton images and establishes a detection model for the impurity rate, enabling accurate detection of the impurity rate in machine-picked cotton. The proposed algorithm removes the Pyramid 4 (P4) feature layer and incorporates Multi-Scale Convolutional Block Attention (MSCBCA) that integrates the Convolutional Block Attention Module (CBAM) and Multi-Scale Convolutional Attention (MSCA) into the Faster Implementation of Cross Stage Partial Bottleneck with 2 Convolutions (C2f) module of the feature extraction network, forming a novel C2f_MSCBCA module. The SlimNeck structure is introduced in the feature fusion network by replacing the P4 feature layer with the small-target detection layer Pyramid 2 (P2). Additionally, transfer learning is employed using the Common Objects in Context (COCO) instance segmentation dataset. The analysis of 100 groups of cotton image samples shows that the Mean Absolute Error (MAE), Root Mean Square Error (RMSE), and Mean Absolute Percentage Error (MAPE) for impurity rate detection are 0.29%, 0.33%, and 3.70%, respectively, which are reduced by 52.46%, 48.44%, and 53.75% compared to the Yolov8s-seg model. The Precision (P), Recall (R), and mean Average Precision at an intersection over union of 0.5 ([email protected]) are 85.4%, 78.4%, and 80.8%, respectively, which are improved by 4.2%, 6.2%, and 6.4% compared to Yolov8s-seg model, significantly enhancing the segmentation performance of minor impurities. The Cotton-YOLO-Seg model demonstrates practical significance for precisely detecting the impurity rate in machine-picked seed cotton. Full article

Population movement dynamics are a critical part of understanding communicable disease transmission patterns and determining where, when, and with whom to deliver appropriate prevention interventions. This study aimed to identify the origin of the Afghan population and their patterns of movement within Karachi, to assess the polio vaccination status of children under the age of five, and to investigate the travel history and guest arrival patterns of individuals from Afghanistan and other regions known to be affected by wild poliovirus type 1 (WPV1) within the past six months. A cross-sectional survey was conducted in selected 12 union councils of Karachi, Pakistan. The data were collected through interviews with Afghan household members and from the frontline workers (FLWs) responsible for the polio vaccination of the children of the same households. Cohen’s kappa was used to check the agreement between information provided by the household participant and FLWs. A total of 409 Afghan household members were interviewed. Travel of any household member outside the city within the last six months was reported by 105 (25.7%) participants, 140 (34.2%) hosted guests within the last six months, and 92 (22.5%) participants reported that guest children were vaccinated in their households. A total of 230 (56.2%) participants observed polio teams at relatives’ households within Karachi, and 127 (31.1%) observed polio teams at relatives’ households outside Karachi in different districts of Pakistan and Afghanistan. Fair to moderate agreement was observed between information provided by the household members and FLWs on the variable’s duration of living at current residence (Kappa = 0.370), travel history (Kappa = 0.429), guest arrival (Kappa = 0.395), and household children vaccinated for OPV (Kappa = 0.419). Substantial population mobility was observed between Afghanistan and Pakistan as well as significant movement of the Afghan population within Karachi in the last six months. These findings warrant attention and targeted implementation of interventions to enhance and sustain both routine and supplementary immunization activities within this demographic group. Full article

Multimodal brain signal analysis has shown great potential in decoding complex cognitive processes, particularly in the challenging task of inner speech recognition. This paper introduces an innovative I nner Speech Recognition via Cross-Perception (ISRCP) approach that significantly enhances accuracy by fusing electroencephalography (EEG) and functional magnetic resonance imaging (fMRI) data. Our approach comprises three core components: (1) multigranularity encoders that separately process EEG time series, EEG Markov Transition Fields, and fMRI spatial data; (2) a cross-perception expert structure that learns both modality-specific and shared representations; and (3) an attention-based adaptive fusion strategy that dynamically adjusts the contributions of different modalities based on task relevance. Extensive experiments on the Bimodal Dataset on Inner Speech demonstrate that our model outperforms existing methods across accuracy and F1 score. Full article

As “chemical chameleons,” organosulfones have been widely applied in various desulfonylative functionalization reactions. However, the desulfonylative functionalization of (hetero)arylsulfones through the cleavage of inert C(sp²)–SO₂ bonds remains a challenging and underexplored task. Over the past twenty years, the use of (hetero)arylsulfones as arylation reagents has gradually gained attention in diverse cross-coupling reactions under specific catalytic conditions, especially in transition metal-catalysis and photocatalysis chemistry. In this review, we discuss the representative accomplishments and mechanistic insights achieved in desulfonylative reactions of inactive C(sp²)–SO₂ bonds in (hetero)arylsulfones, including: (i) transition-metal-catalyzed desulfonylative cross-coupling reactions and (ii) photo-/electrocatalytic radical desulfonylative coupling reactions. We anticipate that this review will provide an overall perspective in this area to a general audience of researchers and stimulate further innovative strategies for desulfonylative functionalization of inert arylsulfones. Full article

Iodine and fluorine, as halogen elements, are often coexisting in water environments, with nearly 200 million people suffering from fluorosis globally, and, in 11 countries and territories, adolescents have iodine intakes higher than that required for the prevention of iodine deficiency disorders. It has been suggested that excess iodine and/or fluorine can affect thyroid health and intellectual development, especially in children, but their combined effect has been less studied in this population. This study investigated 399 school-age children in Tianjin, China, collected drinking water samples from areas where the school-age children lived, and grouped the respondents according to iodine and fluorine levels. Thyroid health was measured using thyroid hormone levels, thyroid volume, and the presence of thyroid nodules; intelligence quotient (IQ) was assessed using the Raven’s Progressive Matrices (CRT) test; and monoamine neurotransmitter levels were used to explore the potential relationship between thyroid health and intelligence. Multiple linear regression and restricted cubic spline (RCS) analyses showed that iodine and fluorine were positively correlated with thyroid volume and the incidence of thyroid nodules in school-age children, and negatively correlated with IQ; similar results were obtained in the secondary subgroups based on urinary iodine and urinary fluoride levels. Interaction analyses revealed a synergistic effect of iodine and fluorine. A pathway analysis showed that iodine and fluorine were negatively associated with the secretion of free triiodothyronine (FT3) and free tetraiodothyronine (FT4), which in turn were negatively associated with the secretion of thyroid-stimulating hormone (TSH). Iodine and fluorine may affect IQ in school-aged children through the above pathways that affect thyroid hormone secretion; of these, FT3 and TSH were negatively correlated with IQ, whereas FT4 was positively correlated with IQ. The relationship between thyroid hormones and monoamine neurotransmitters may involve the hypothalamic–pituitary–thyroid axis, with FT4 hormone concentrations positively correlating with dopamine (DA), norepinephrine (NE), and 5-hydroxytryptophan (5-HT) concentrations, and FT3 hormone concentrations positively correlating with DA concentrations. Monoamine neurotransmitters may play a mediating role in the effects of iodine and fluoride on intelligence in schoolchildren. However, this study has some limitations, as the data were derived from a cross-sectional study in Tianjin, China, and no attention was paid to the reciprocal effects of iodine and fluorine at different doses on thyroid health and intelligence in schoolchildren in other regions. Full article

Named entity recognition (NER) is a fundamental task in Natural Language Processing (NLP). During the training process, NER models suffer from over-confidence, and especially for the Chinese NER task, it involves word segmentation and introduces erroneous entity boundary segmentation, exacerbating over-confidence and reducing the model’s overall performance. These issues limit further enhancement of NER models. To tackle these problems, we proposes a new model named KCB-FLAT, designed to enhance Chinese NER performance by integrating enriched semantic information with the word-Boundary Smoothing technique. Particularly, we first extract various types of syntactic data and utilize a network named Key-Value Memory Network, based on syntactic information to functionalize this, integrating it through an attention mechanism to generate syntactic feature embeddings for Chinese characters. Subsequently, we employed an encoder named Cross-Transformer to thoroughly combine syntactic and lexical information to address the entity boundary segmentation errors caused by lexical information. Finally, we introduce a Boundary Smoothing module, combined with a regularity-conscious function, to capture the internal regularity of per entity, reducing the model’s overconfidence in entity probabilities through smoothing. Experimental results demonstrate that the proposed model achieves exceptional performance on the MSRA, Resume, Weibo, and self-built ZJ datasets, as verified by the F1 score. Full article

Accurate and generalizable classification of brain states is essential for understanding their neural underpinnings and improving clinical diagnostics. Traditionally, functional connectivity patterns and graph-theoretic metrics have been utilized. However, cortical gradient features, which reflect global brain organization, offer a complementary approach. We hypothesized that a machine learning model integrating these three feature sets would effectively discriminate between baseline and atypical brain states across a wide spectrum of conditions, even though the underlying neural mechanisms vary. To test this, we extracted features from brain states associated with three meta-conditions including unconsciousness (NREM2 sleep, propofol deep sedation, and propofol general anesthesia), psychedelic states induced by hallucinogens (subanesthetic ketamine, lysergic acid diethylamide, and nitrous oxide), and neuropsychiatric disorders (attention-deficit hyperactivity disorder, bipolar disorder, and schizophrenia). We used support vector machine with nested cross-validation to construct our models. The soft voting ensemble model marked the average balanced accuracy (average of specificity and sensitivity) of 79% (62–98% across all conditions), outperforming individual base models (70–76%). Notably, our models exhibited varying degrees of transferability across different datasets, with performance being dependent on the specific brain states and feature sets used. Feature importance analysis across meta-conditions suggests that the underlying neural mechanisms vary significantly, necessitating tailored approaches for accurate classification of specific brain states. This finding underscores the value of our feature-integrated ensemble models, which leverage the strengths of multiple feature types to achieve robust performance across a broader range of brain states. While our approach offers valuable insights into the neural signatures of different brain states, future work is needed to develop and validate even more generalizable models that can accurately classify brain states across a wider array of conditions. Full article

Anterior cruciate ligament (ACL) plays an important role in stabilising the knee joint, prevents excessive anterior translation of the tibia, and provides rotational stability. ACL injuries commonly occur as a result of rapid deceleration, sudden change in direction, or direct impact to the knee during sports activities. Although several deep learning techniques have recently been applied in the detection of ACL tears, challenges such as effective slice filtering and the nuanced relationship between varying tear grades still remain underexplored. This study used an advanced deep learning model that integrated a T-distribution-based slice attention filtering mechanism with a penalty weight loss function to improve the performance for detection of ACL tears. A T-distribution slice attention module was effectively utilised to develop a robust slice filtering system of the deep learning model. By incorporating class relationships and substituting the conventional cross-entropy loss with a penalty weight loss function, the classification accuracy of our model is markedly increased. The combination of slice filtering and penalty weight loss shows significant improvements in diagnostic performance across six different backbone networks. In particular, the VGG-Slice-Weight model provided an area score of 0.9590 under the receiver operating characteristic curve (AUC). The deep learning framework used in this study offers an effective diagnostic tool that supports better ACL injury detection in clinical diagnosis practice. Full article

To enable the timely adjustment of the control strategy of automobile active safety systems, enhance their capacity to adapt to complex working conditions, and improve driving safety, this paper introduces a new method for predicting road surface state information and recognizing road adhesion coefficients using an enhanced version of the MobileNet V3 model. On one hand, the Squeeze-and-Excitation (SE) is replaced by the Convolutional Block Attention Module (CBAM). It can enhance the extraction of features effectively by considering both spatial and channel dimensions. On the other hand, the cross-entropy loss function is replaced by the Bias Loss function. It can reduce the random prediction problem occurring in the optimization process to improve identification accuracy. Finally, the proposed method is evaluated in an experiment with a four-wheel-drive ROS robot platform. Results indicate that a classification precision of 95.53% is achieved, which is higher than existing road adhesion coefficient identification methods. Full article