Search Results (15,486)

The identification of microRNA (miRNA) biomarkers is crucial in advancing disease research and improving diagnostic precision. Network-based analysis methods are powerful for identifying disease-related biomarkers. However, it is a challenge to generate a robust molecular network that can accurately reflect miRNA interactions and define reliable miRNA biomarkers. To tackle this issue, we propose a disease-related miRNA biomarker identification method based on the knowledge-enhanced bio-network (BIM-Ken) by combining the miRNA expression data and prior knowledge. BIM-Ken constructs the miRNA cooperation network by examining the miRNA interactions based on the miRNA expression data, which contains characteristics about the specific disease, and the information of the network nodes (miRNAs) is enriched by miRNA knowledge (i.e., miRNA-disease associations) from databases. Further, BIM-Ken optimizes the miRNA cooperation network using the well-designed GAE (graph auto-encoder). We improve the loss function by introducing the functional consistency and the difference prompt, so as to facilitate the optimized network to keep the intrinsically important characteristics of the miRNA data about the specific disease and the prior knowledge. The experimental results on the public datasets showed the superiority of BIM-Ken in classification. Subsequently, BIM-Ken was applied to analyze renal cell carcinoma data, and the defined key modules demonstrated involvement in the cancer-related pathways with good discrimination ability. Full article

Hyperspectral image change detection (HSI-CD) provides substantial value in environmental monitoring, urban planning and other fields. In recent years, deep-learning based HSI-CD methods have made remarkable progress due to their powerful nonlinear feature learning capabilities, yet they face several challenges: mixed-pixel phenomenon affecting pixel-level detection accuracy; heterogeneous spatial scales of change targets where coarse-grained features fail to preserve fine-grained details; and dependence on high-quality labels. To address these challenges, this paper introduces WSCDNet, a weakly supervised HSI-CD network employing coarse-to-fine feature learning, with key innovations including: (1) A dual-branch detection framework integrating binary and multiclass change detection at the sub-pixel level that enhances collaborative optimization through a cross-feature coupling module; (2) introduction of multi-granularity aggregation and difference feature enhancement module for detecting easily confused regions, which effectively improves the model’s detection accuracy; and (3) proposal of a weakly supervised learning strategy, reducing model sensitivity to noisy pseudo-labels through decision-level consistency measurement and sample filtering mechanisms. Experimental results demonstrate that WSCDNet effectively enhances the accuracy and robustness of HSI-CD tasks, exhibiting superior performance under complex scenarios and weakly supervised conditions. Full article

Background: Myeloproliferative neoplasms (MPN), a group of chronic hematologic neoplasms, are driven by inflammatory mechanisms that influence disease initiation and progression. Emerging evidence highlights the gut microbiome and plasma metabolome as pivotal immunomodulators, yet their causal roles in MPN pathogenesis remain uncharacterized. Methods: We conducted a two-sample Mendelian randomization (MR) analysis to systematically evaluate causal relationships between 196 gut microbial taxa, 526 plasma metabolites, and MPN risk. Instrumental variables were derived from genome-wide association studies (GWASs) of microbial/metabolite traits. Validation utilized 16S rRNA sequencing data from NCBI Bioproject PRJNA376506. Mediation and multivariable MR analyses elucidated metabolite-mediated pathways linking microbial taxa to MPN. Results: Our MR analysis revealed that 7 intestinal taxa and 17 plasma metabolites are causally linked to MPN. External validation confirmed the three taxa’s differential abundance in MPN cohorts. Mediation analysis revealed two mediated relationships, of which succinylcarnitine mediated 14.5% of the effect, and lysine 27.9%, linking the Eubacterium xylanophilum group to MPN. Multivariate MR analysis showed that both succinylcarnitine (p = 0.004) and lysine (p = 0.040) had a significant causal effect on MPN. Conclusions: This study identifies novel gut microbiota–metabolite axes driving MPN pathogenesis through immunometabolic mechanisms. The validated biomarkers provide potential therapeutic targets for modulating inflammation in myeloproliferative disorders. Full article

In the task of PolSAR image classification, effectively utilizing convolutional neural networks and vision transformer models with limited labeled data poses a critical challenge. This article proposes a novel method for PolSAR image classification that combines channel-wise convolutional local perception, detachable self-attention, and a residual feedforward network. Specifically, the proposed method comprises several key modules. In the channel-wise convolutional local perception module, channel-wise convolution operations enable accurate extraction of local features from different channels of PolSAR images. The local residual connections further enhance these extracted features, providing more discriminative information for subsequent processing. Additionally, the detachable self-attention mechanism plays a pivotal role: it facilitates effective interaction between local and global information, enabling the model to comprehensively perceive features across different scales, thereby improving classification accuracy and robustness. Subsequently, replacing the conventional feedforward network with a residual feedforward network that incorporates residual structures aids the model in better representing local features, further enhances the capability of cross-layer gradient propagation, and effectively alleviates the problem of vanishing gradients during the training of deep networks. In the final classification stage, two fully connected layers with dropout prevent overfitting, while softmax generates predictions. The proposed method was validated on the AIRSAR Flevoland, RADARSAT-2 San Francisco, and RADARSAT-2 Xi’an datasets. The experimental results demonstrate that the proposed method can attain a high level of classification performance even with a limited amount of labeled data, and the model is relatively stable. Furthermore, the proposed method has lower computational costs than comparative methods. Full article

To address issues commonly observed during the inference phase of large language models—such as inconsistent labels, formatting errors, or semantic deviations—a series of targeted strategies has been proposed. First, a relation label refinement strategy based on semantic similarity and syntactic structure has been designed to calibrate the model’s outputs, thereby improving the accuracy and consistency of label prediction. Second, to meet the contextual modeling needs of different types of instance bags, a multi-level contextual augmentation strategy has been constructed. For multi-sentence instance bags, a graph-based retrieval enhancement mechanism is introduced, which integrates intra-bag entity co-occurrence networks with document-level sentence association graphs to strengthen the model’s understanding of cross-sentence semantic relations. For single-sentence instance bags, a semantic expansion strategy based on term frequency-inverse document frequency is employed to retrieve similar sentences. This enriches the training context under the premise of semantic consistency, alleviating the problem of insufficient contextual information. Notably, the proposed multi-granularity framework captures semantic symmetry between entities and relations across different levels of context, which is crucial for accurate and balanced relation understanding. The proposed methodology offers practical advancements for semantic analysis applications, particularly in knowledge graph development. Full article

Roller bearing manufacturing errors have been proven to be critical factors affecting the vibrations of gear systems. Waviness is one main form of manufacturing error affecting the operational performance and life of bearings. However, most previous studies did not completely incorporate the effects of the uneven bearing waviness on the flexible gear system vibrations. To characterize the contribution of the uneven bearing waviness on the vibrations of the gear system, a gear transmission system dynamics model considering shaft flexibility was established. The evenness sinusoidal waviness model (SWM) and uneven sinusoidal waviness model considering the time-varying contact (SWMS) were compared. The influences of the time-varying gear meshing stiffness excitations and flexibilities of shafts on the vibrations of the gear system were considered. A dynamic model was established, and the vibrations of the flexible gear system with the SWM and SWMS were compared. The vibrations induced by different amplitudes and orders of bearing waviness were analyzed. Note that the waviness of the bearing has a great influence on the system vibrations. The vibrations of the flexible gear system intensified with the increase in the bearing waviness order and amplitude. The vibrations from the gear system with the SWMS were bigger than those of the SWM. This paper introduces an alternative dynamic modeling model enabling the vibration analysis of the flexible gear system with evenness and uneven bearing waviness. Full article

In recent years, a growing number of real-time semantic segmentation networks have been developed to improve segmentation accuracy. However, these advancements often come at the cost of increased computational complexity, which limits their inference efficiency, particularly in scenarios such as autonomous driving, where strict real-time performance is essential. Achieving an effective balance between speed and accuracy has thus become a central challenge in this field. To address this issue, we present a lightweight semantic segmentation model tailored for the perception requirements of autonomous vehicles. The architecture follows an encoder–decoder paradigm, which not only preserves the capability for deep feature extraction but also facilitates multi-scale information integration. The encoder leverages a high-efficiency backbone, while the decoder introduces a dynamic fusion mechanism designed to enhance information interaction between different feature branches. Recognizing the limitations of convolutional networks in modeling long-range dependencies and capturing global semantic context, the model incorporates an attention-based feature extraction component. This is further augmented by positional encoding, enabling better awareness of spatial structures and local details. The dynamic fusion mechanism employs an adaptive weighting strategy, adjusting the contribution of each feature channel to reduce redundancy and improve representation quality. To validate the effectiveness of the proposed network, experiments were conducted on a single RTX 3090 GPU. The Dynamic Real-time Integrated Vision Encoder–Segmenter Network (DriveSegNet) achieved a mean Intersection over Union (mIoU) of 76.9% and an inference speed of 70.5 FPS on the Cityscapes test dataset, 74.6% mIoU and 139.8 FPS on the CamVid test dataset, and 35.8% mIoU with 108.4 FPS on the ADE20K dataset. The experimental results demonstrate that the proposed method achieves an excellent balance between inference speed, segmentation accuracy, and model size. Full article

Background: Decoding mental attention states from electroencephalogram (EEG) signals is crucial for numerous applications such as cognitive monitoring, adaptive human–computer interaction, and brain–computer interfaces (BCIs). However, conventional EEG-based approaches often focus on channel-wise processing and are limited to intra-session or subject-specific scenarios, lacking robustness in cross-session or inter-subject conditions. Methods: In this study, we propose a hybrid feature learning framework for robust classification of mental attention states, including focused, unfocused, and drowsy conditions, across both sessions and individuals. Our method integrates preprocessing, feature extraction, feature selection, and classification in a unified pipeline. We extract channel-wise spectral features using short-time Fourier transform (STFT) and further incorporate both functional and structural connectivity features to capture inter-regional interactions in the brain. A two-stage feature selection strategy, combining correlation-based filtering and random forest ranking, is adopted to enhance feature relevance and reduce dimensionality. Support vector machine (SVM) is employed for final classification due to its efficiency and generalization capability. Results: Experimental results on two cross-session and inter-subject EEG datasets demonstrate that our approach achieves classification accuracy of 86.27% and 94.01%, respectively, significantly outperforming traditional methods. Conclusions: These findings suggest that integrating connectivity-aware features with spectral analysis can enhance the generalizability of attention decoding models. The proposed framework provides a promising foundation for the development of practical EEG-based systems for continuous mental state monitoring and adaptive BCIs in real-world environments. Full article

Object detection in aerial images can provide great support in traffic planning, national defense reconnaissance, hydrographic surveys, infrastructure construction, and other fields. Objects in aerial images are characterized by small pixel–area ratios, dense arrangements between objects, and arbitrary inclination angles. In response to these characteristics and problems, we improved the feature extraction network Inception-ResNet using the Fast Architecture Search (FAS) module and proposed a one-stage anchor-free rotation object detector. The structure of the object detector is simple and only consists of convolution layers, which reduces the number of model parameters. At the same time, the label sampling strategy in the training process is optimized to resolve the problem of insufficient sampling. Finally, a decoupled object detection head is used to separate the bounding box regression task from the object classification task. The experimental results show that the proposed method achieves mean average precision (mAP) of 82.6%, 79.5%, and 89.1% on the DOTA1.0, DOTA1.5, and HRSC2016 datasets, respectively, and the detection speed reaches 24.4 FPS, which can meet the needs of real-time detection. Full article

Orthogonal frequency division multiplexing (OFDM) has been regarded as an attractive waveform for integrated sensing and communication (ISAC). However, suffering from its high peak-to-average power ratio (PAPR), sensitivity to phase noise (PN), and spectral efficiency saturation, the performance of OFDM in ISAC is limited. Against this background, this paper proposes a constellation-optimized index-modulated OFDM (CO-IM-OFDM) framework that leverages neural networks to design a constellation suitable for subcarrier activation patterns. A correlation model between index modulation and constellation is established, enabling adaptive constellation mapping in IM-OFDM. Then, Adam optimizer is employed to train the constellation tailored for ISAC, enhancing spectral efficiency under PN and PAPR constraints. Furthermore, a weighting factor is defined to characterize the joint communication–sensing performance, thus optimizing the overall system performance. Simulation results demonstrate that the proposed method can achieve improvements in bit error rate (BER) by over 4 dB and in Cramér–Rao bound (CRB) by 2% to 8% compared to traditional IM-OFDM constellation mapping. It overcomes fixed constellation constraints of conventional IM-OFDM systems, offering theoretical innovation waveform design for low-power communication–sensing systems in highly dynamic environments. Full article

The ergodicity and ageing phenomena in a vibrational motor system driven by a periodic external force are investigated. Within the tailored parameter regime, the amplitude and frequency demonstrate contrasting effects on ergodicity. An increase of amplitude induces a transition from non-ergodic to ergodic behavior, whereas a higher driving frequency leads to a transition from ergodic to non-ergodic dynamics. These transitions are attributed to the enhanced ability of larger amplitudes to overcome potential energy barriers and the improved responsiveness of the system to external variations at lower frequencies. Moreover, pronounced ageing effects are observed at low amplitudes or high frequencies. These findings offer new insights into the intrinsic dynamical mechanisms of vibrational motor systems and provide a theoretical foundation for predicting their long-term operational performance. Full article

Space-based gravitational wave detectors, such as the Laser Interferometer Space Antenna (LISA) and Taiji, will observe GWs from $O\left({10}^8\right)$ galactic binary systems, allowing a completely unobscured view of the Milky Way structure. While previous studies have established theoretical expectations based on idealized data-analysis methods that use the true catalog of sources, we present an end-to-end analysis pipeline for inferring galactic structure parameters based on the detector output alone. We employ the GBSIEVER algorithm to extract GB signals from LISA Data Challenge data and develop a maximum likelihood approach to estimate a bulge-disk galactic model using the resolved GBs. We introduce a two-tiered selection methodology, combining frequency derivative thresholding and proximity criteria, to address the systematic overestimation of frequency derivatives that compromises distance measurements. We quantify the performance of our pipeline in recovering key Galactic structure parameters and the potential biases introduced by neglecting the errors in estimating the parameters of individual GBs. Our methodology represents a step forward in developing practical techniques that bridge the gap between theoretical possibilities and observational implementation. Full article

The contamination of drinking water sources with selenium (Se) oxyanions, including selenite (Se(IV)) and selenate (Se(VI)), contains serious health hazards with an oral intake exceeding 400 µg/day and therefore requires urgent attention. Various natural and anthropogenic sources are responsible for high Se concentrations in aquatic environments. In addition, the chemical behavior and speciation of selenium can vary noticeably depending on the origin of the source water. The Se(VI) oxyanion is more soluble and therefore more abundant in surface water. Se levels in contaminated waters often exceed 50 µg/L and may reach several hundred µg/L, well above drinking water limits set by the World Health Organization (40 µg/L) and Germany (10 µg/L), as well as typical industrial discharge limits (5–10 µg/L). Overall, Se is difficult to remove using conventionally available physical, chemical, and biological treatment technologies. The recent literature has therefore highlighted promising advancements in Se removal using emerging technologies. These include advanced physical separation methods such as membrane-based treatment systems and engineered nanomaterials for selective Se decontamination. Additionally, other integrated approaches incorporating photocatalysis coupled adsorption processes, and bio-electrochemical systems have also demonstrated high efficiency in redox transformation and capturing of Se from contaminated water bodies. These innovative strategies may offer enhanced selectivity, removal, and recovery potential for Se-containing species. Here, a current review outlines the sources, distribution, and chemical behavior of Se in natural waters, along with its toxicity and associated health risks. It also provides a broad and multi-perspective assessment of conventional as well as emerging physical, chemical, and biological approaches for Se removal and/or recovery with further prospects for integrated and sustainable strategies. Full article

Background/Objectives: Heart rate variability (HRV) has been widely investigated as a predictor of disease and mortality across diverse patient populations; however, there remains no consensus on the optimal set or combination of time and frequency domain nor on nonlinear features for reliable prediction across clinical contexts. Given the relevance of the COVID-19 pandemic and the unique clinical profiles of these patients, this retrospective observational study explored the potential of HRV analysis for early prediction of in-hospital mortality using ECG signals recorded during the initial moments of ICU admission in COVID-19 patients. Methods: HRV indices were extracted from four ECG leads (I, II, III, and aVF) using sliding windows of 2, 5, and 7 min across observation intervals of 15, 30, and 60 min. The raw data posed significant challenges in terms of structure, synchronization, and signal quality; thus, from an original set of 381 records from 321 patients, after data pre-processing steps, a final dataset of 82 patients was selected for analysis. To manage data complexity and evaluate predictive performance, two feature selection methods, four feature reduction techniques, and five classification models were applied to identify the optimal approach. Results: Among the feature aggregation methods, compiling feature means across patient windows (Method D) yielded the best results, particularly for longer observation intervals (e.g., using LDA, the best AUC of $0.82\pm 0.13$ was obtained with Method D versus $0.63\pm 0.09$ with Method C using 5 min windows). Linear Discriminant Analysis (LDA) was the most consistent classification algorithm, demonstrating robust performance across various time windows and further improvement with dimensionality reduction. Although Gradient Boosting and Random Forest also achieved high AUCs and F1-scores, their performance outcomes varied across time intervals. Conclusions: These findings support the feasibility and clinical relevance of using short-term HRV as a noninvasive, data-driven tool for early risk stratification in critical care, potentially guiding timely therapeutic decisions in high-risk ICU patients and thereby reducing in-hospital mortality. Full article

In this paper, a security-enhanced three-dimensional (3D) image hiding and encryption method is proposed by combining a layer-based phase-only hologram (POH) under structured light illumination with chaotic encryption and digital image watermarking technology. In the proposed method, the original 3D plaintext image is firstly encoded into a layer-based POH and then further encrypted into an encrypted phase with the help of a chaotic random phase mask (CRPM). Subsequently, the encrypted phase is embedded into a visible ciphertext image by using a digital image watermarking technology based on discrete wavelet transform (DWT) and singular value decomposition (SVD), leading to a 3D image hiding with high security and concealment. The encoding of POH and the utilization of CRPM can substantially enhance the level of security, and the DWT-SVD-based digital image watermarking can effectively hide the information of the 3D plaintext image in a visible ciphertext image, thus improving the imperceptibility of valid information. It is worth noting that the adopted structured light during the POH encoding possesses many optical parameters, which are all served as the supplementary keys, bringing about a great expansion of key space; meanwhile, the sensitivities of the wavelength key and singular matrix keys are also substantially enhanced thanks to the introduction of structured light, contributing to a significant enhancement of security. Numerical simulations are performed to demonstrate the feasibility of the proposed 3D image hiding method, and the simulation results show that the proposed method exhibits high feasibility and apparent security-enhanced effect as well as strong robustness. Full article