Search Results (292)

Precision manufacturing requires handling multi-physics coupling during processing, where digital twin and AI technologies enable rapid robot programming under customized requirements. However, heterogeneous data sources, diverse domain models, and rapidly changing demands pose significant challenges to digital twin system integration. To overcome these limitations, this paper proposes a digital twin modeling strategy based on a metamodel and a virtual–real fusion architecture, which unifies models between the virtual and physical domains. Within this framework, subsystems achieve rapid integration through ontology-driven knowledge configuration, while ROS provides the execution environment for establishing robot manufacturing digital twin scenarios. A case study of a robot shaping system demonstrates that the proposed architecture effectively addresses heterogeneous data association, model interaction, and application customization, thereby enhancing the adaptability and intelligence of precision manufacturing processes. Full article

With the rapid development of social media, short-text data have become increasingly important in fields such as public opinion monitoring, user feedback analysis, and intelligent recommendation systems. However, existing short-text sentiment analysis models often suffer from limited cross-domain adaptability and poor generalization performance. To address these challenges, this study proposes a novel short-text sentiment classification model based on the Bidirectional Encoder Representations from Transformers (BERTs) and a dual-stream Transformer gated attention mechanism. This model first employs Bidirectional Encoder Representations from Transformers (BERTs) and the Chinese Robustly Optimized BERT Pretraining Approach (Chinese-RoBERTa) to achieve data augmentation and multilevel semantic mining, thereby expanding the training corpus and enhancing minority class coverage. Second, a dual-stream Transformer gated attention mechanism was developed to dynamically adjust feature fusion weights, enhancing adaptability to heterogeneous texts. Finally, the model integrates a Bidirectional Gated Recurrent Unit (BiGRU) with Multi-Head Self-Attention (MHSA) to strengthen sequence information modeling and global context capture, enabling the precise identification of key sentiment dependencies. The model’s superior performance in handling data imbalance and complex textual sentiment logic scenarios is demonstrated by the experimental results, achieving significant improvements in accuracy and F1 score. The F1 score reached 92.4%, representing an average increase of 8.7% over the baseline models. This provides an effective solution for enhancing the performance and expanding the application scenarios of short-text sentiment analysis models. Full article

With the growing application of unmanned aerial vehicles (UAVs) in complex, stochastic environments, autonomous navigation and obstacle avoidance represent critical technical challenges requiring urgent solutions. This study proposes an innovative deep reinforcement learning (DRL) framework that leverages multimodal perception through the fusion of LiDAR and depth camera data. A sophisticated multi-sensor data preprocessing mechanism is designed to extract multimodal features, significantly enhancing the UAV’s situational awareness and adaptability in intricate, stochastic environments. In the high-level decision-maker of the framework, to overcome the intrinsic limitation of low sample efficiency in DRL algorithms, this study introduces an advanced decision-making algorithm, Soft Actor-Critic with Prioritization (SAC-P), which markedly accelerates model convergence and enhances training stability through optimized sample selection and utilization strategies. Validated within a high-fidelity Robot Operating System (ROS) and Gazebo simulation environment, the proposed framework achieved a task success rate of 81.23% in comparative evaluations, surpassing all baseline methods. Notably, in generalization tests conducted in previously unseen and highly complex environments, it maintained a success rate of 72.08%, confirming its robust and efficient navigation and obstacle avoidance capabilities in complex, densely cluttered environments with stochastic obstacle distributions. Full article

Chemotherapy-induced senescence (CIS) contributes to tumor persistence and relapse. In this study, we investigated the senolytic activity of piceatannol (PCT) in 5-fluorouracil (5FU)-induced senescent colorectal cancer (CRC) cells. Senescence was established in P53-proficient HCT116 cells and normal colon fibroblasts (CCD18Co) following prolonged 5FU exposure, as shown by increased SA-β-gal activity, upregulation of P16, P21, and P53, mitochondrial depolarization, and enhanced oxidative stress. Subsequent PCT treatment selectively induced apoptosis in senescent populations, while non-senescent or p53-mutant, senescence-resistant HT29 cells were minimally affected. This effect was prevented by N-acetylcysteine, indicating a redox-sensitive mechanism. Mechanistically, PCT triggered mitochondrial depolarization and AIF-associated, caspase-independent apoptosis without increasing ROS. Morphological analysis with MitoTracker and quantitative morphometry using Fiji confirmed a fragmented mitochondrial network, characterized by reduced form factor, length, and number per cell. Western blotting revealed downregulation of fusion proteins (MFN1, MFN2), decreased FIS1, stable DRP1, and marked upregulation of the DRP1 adaptor MFF, consistent with suppressed fusion and enhanced fission competence. Together, these findings demonstrate that PCT selectively targets chemotherapy-induced senescent CRC cells through mitochondrial fragmentation and AIF-dependent apoptosis, highlighting its potential as an adjuvant strategy to limit the long-term burden of therapy-induced senescence. Full article

Part-of-speech (POS) tagging in low-resource, morphologically rich languages (LRLs/MRLs) remains challenging due to extensive affixation, high out-of-vocabulary (OOV) rates, and pervasive polysemy. We propose MRL-POS, a unified Transformer-CRF framework that dynamically selects informative affix features and integrates them with deep contextual embeddings via a novel dual-gating co-attention mechanism. First, a Dynamic Affix Selector adaptively adjusts n-gram ranges and frequency thresholds based on word length to ensure high-precision affix segmentation. Second, the Affix–Context Co-Attention Module employs two gating functions that conditionally amplify contextual dimensions with affix cues and vice versa, enabling robust disambiguation of complex and ambiguous forms. Third, Layer-Wise Attention Pooling aggregates multi-layer XLM-RoBERTa representations, emphasizing those most relevant for morphological and syntactic tagging. Evaluations on Uyghur, Kyrgyz, and Uzbek show that MRL-POS achieves an average F₁ of 84.10%, OOV accuracy of 84.24%, and Poly-F₁ of 72.14%, outperforming strong baselines by up to 8 F₁ points. By explicitly modeling the symmetry between morphological affix cues and sentence-level context through a dual-gating co-attention mechanism, MRL-POS achieves a balanced fusion that both preserves local structure and captures global dependencies. Interpretability analyses confirm that 89.1% of the selected affixes align with linguistic expectations. This symmetric design not only enhances robustness in low-resource and agglutinative settings but also offers a general paradigm for symmetry-aware sequence labeling tasks. Full article

Glycerol-3-phosphate acyltransferases (GPATs) catalyze the initial and rate-limiting step of glycerolipid biosynthesis, yet their contribution to salt tolerance in the soybean (Glycine max (L.) Merr.) plants remains largely uncharacterized. In this study, a total of 27 GmGPAT genes were identified, and their evolutionary relationships, chromosomal distribution, conserved motifs, and cis-regulatory elements were comprehensively analyzed. Through transcriptomic and qPCR analyses, many GmGPATs were found to be predominantly expressed in roots, with GmGPAT1, a plastid-targeted isoform, displaying the most rapid and pronounced transcriptional activation under salt stress. GFP-fusion experiments in transient expression assays confirmed plastid localization of GmGPAT1. Heterologous expression in Escherichia coli together with enzyme kinetics analyses validated its enzymatic function as a GPAT family member. The soybean hairy-root lines overexpressing GmGPAT1 exhibited enhanced root elongation, increased biomass, and improved photosynthetic efficiency under 120 mM NaCl stress, while CRISPR/Cas9 knockout mutants showed pronounced growth inhibition. Physiological assays demonstrated that GmGPAT1 overexpression mitigated oxidative damage by limiting reactive oxygen species (ROS) accumulation and lipid peroxidation, increasing antioxidant enzyme activities (CAT, SOD, POD), and elevating the ratios of AsA/DHA and GSH/GSSG. These changes contributed to redox homeostasis and improved Na⁺ extrusion capacity. A genome-wide association study (GWAS) involving 288 soybean accessions identified a single nucleotide polymorphism in the GmGPAT1 promoter that was significantly correlated with salt tolerance, and the beneficial Hap1 allele emerged as a promising molecular marker for breeding. Together, these analyses emphasize the status of GmGPAT1 as a major regulator of salt stress adaptation through the coordinated modulation of lipid metabolism and redox balance, extend the functional annotation of the soybean GPAT family, and highlight new genetic resources that can be leveraged to enhance tolerance to salt stress in soybean cultivars. Full article

With the widespread adoption of intelligent technologies in animal husbandry, traditional manual feeding methods can no longer meet the demands for precision and efficiency in modern sheep farming. To address this gap, we present an intelligent robotic feeding system designed to enhance feeding efficiency, reduce labor intensity, and enable precise delivery of feed. This system, developed on the ROS platform, integrates LiDAR-based SLAM with point cloud rendering and an Octomap 3D grid map. It combines an improved bidirectional RRT* algorithm with Dynamic Window Approach (DWA) for efficient path planning and uses 3D LiDAR data along with the RANSAC algorithm for slope detection and navigation information extraction. The YOLOv8s model is utilized for precise sheep pen marker identification, while integration with weighing sensors and a farm management system ensures accurate feed distribution control. The main research contribution lies in the development of a comprehensive, multi-sensor fusion system capable of achieving autonomous feeding in dynamic and complex environments. Experimental results show that the system achieves centimeter-level accuracy in localization and attitude control, with FAST-LIO2 maintaining precision within 1° of attitude angle errors. Compared to baseline performance, the system reduces node count by 17.67%, shortens path length by 0.58 cm, and cuts computation time by 42.97%. At a speed of 0.8 m/s, the robot achieves a maximum longitudinal deviation of 7.5 cm and a maximum heading error of 5.6°, while straight-line deviation remains within ±2.2 cm. In a 30 kg feeding task, the system demonstrates zero feed wastage, highlighting its potential for intelligent feeding in modern sheep farming. Full article

Autonomous docking is a critical capability for enabling fully automated operations in industrial and logistics environments using Autonomous Mobile Robots (AMRs). Traditional rule-based docking approaches often struggle with generalization and robustness in complex, dynamic scenarios. This paper presents a deep reinforcement learning-based autonomous docking framework that integrates Proximal Policy Optimization (PPO) with multi-sensor fusion. It includes YOLO-based vision detection, depth estimation, and LiDAR-based orientation correction. A concise 4D state vector, comprising relative position and angle indicators, is used to guide a continuous control policy. The outputs are linear and angular velocity commands for smooth and accurate docking. The training is conducted in a Gym-compatible Gazebo simulation, acting as a digital twin of the real-world system, and incorporates realistic variations in lighting, obstacle placement, and marker visibility. A designed reward function encourages alignment accuracy, progress, and safety. The final policy is deployed on a real robot via a sim-to-real transfer pipeline, supported by a ROS-based transfer node. Experimental results demonstrate that the proposed method achieves robust and precise docking behavior under diverse real-world conditions, validating the effectiveness of PPO-based learning and sensor fusion for practical autonomous docking applications. Full article

The proliferation of fake profiles on social media presents critical cybersecurity and misinformation challenges, necessitating robust and scalable detection mechanisms. Such profiles weaken consumer trust, reduce user engagement, and ultimately harm brand reputation and platform credibility. As adversarial tactics and synthetic identity generation evolve, traditional rule-based and machine learning approaches struggle to detect evolving and deceptive behavioral patterns embedded in dynamic user-generated content. This study aims to develop an AI-driven, multi-modal deep learning-based detection system for identifying fake profiles that fuses textual, visual, and social network features to enhance detection accuracy. It also seeks to ensure scalability, adversarial robustness, and real-time threat detection capabilities suitable for practical deployment in industrial cybersecurity environments. To achieve these objectives, the current study proposes an integrated AI system that combines the Robustly Optimized BERT Pretraining Approach (RoBERTa) for deep semantic textual analysis, ConvNeXt for high-resolution profile image verification, and Heterogeneous Graph Attention Networks (Hetero-GAT) for modeling complex social interactions. The extracted features from all three modalities are fused through an attention-based late fusion strategy, enhancing interpretability, robustness, and cross-modal learning. Experimental evaluations on large-scale social media datasets demonstrate that the proposed RoBERTa-ConvNeXt-HeteroGAT model significantly outperforms baseline models, including Support Vector Machine (SVM), Random Forest, and Long Short-Term Memory (LSTM). Performance achieves 98.9% accuracy, 98.4% precision, and a 98.6% F1-score, with a per-profile speed of 15.7 milliseconds, enabling real-time applicability. Moreover, the model proves to be resilient against various types of attacks on text, images, and network activity. This study advances the application of AI in cybersecurity by introducing a highly interpretable, multi-modal detection system that strengthens digital trust, supports identity verification, and enhances the security of social media platforms. This alignment of technical robustness with brand trust highlights the system’s value not only in cybersecurity but also in sustaining platform credibility and consumer confidence. This system provides practical value to a wide range of stakeholders, including platform providers, AI researchers, cybersecurity professionals, and public sector regulators, by enabling real-time detection, improving operational efficiency, and safeguarding online ecosystems. Full article

Adenosine signaling plays protective roles in gingival mitochondrial health and inflammation control, with the ectoenzyme CD73 implicated in periodontitis. Here, we investigated the effects of selective adenosine A2a receptor (A2aR) stimulation using the agonist CGS21680 in a mouse model of ligature-induced periodontitis (LIP) and in gingival fibroblast mitochondrial function. Mature C57Bl/6 mice underwent LIP and received daily intraperitoneal injections of CGS21680 (0.1 mg/Kg) or saline. After 8 days, gingival tissues and maxillae were analyzed for alveolar bone loss and Il-1β levels. In parallel, murine gingival fibroblasts (mGFs) were treated with Tnf-α (5 ng/mL) ± CGS21680 (10 µM) to assess mitochondrial function, morphology, and quality control. A2aR activation significantly reduced alveolar bone loss and Il-1β expression in vivo. In vitro, CGS21680 suppressed Tnf-α-induced Cxcl10 and Cxcl12 expressions and enhanced Vegf production. Mitochondrial analysis revealed increased mitochondrial complex levels, membrane potential, and mass, alongside reduced reactive oxygen species (ROS), proton leak, and mitochondrial stress. Ultrastructural studies showed elongated, healthier mitochondria and increased pro-fusion markers, indicating enhanced mitochondrial quality control. Overall, A2aR stimulation attenuates periodontal inflammation and confers mitoprotective effects on gingival fibroblasts, supporting its potential as a therapeutic strategy to both mitigate periodontitis progression and preserve tissue bioenergetics supporting cellular resilience. Full article

Visual–inertial odometry (VIO) is the primary supporting technology for autonomous systems, but it faces three major challenges: initialization sensitivity, dynamic illumination, and multi-sensor fusion. In order to overcome these challenges, this paper proposes stereo direct sparse visual–inertial odometry with efficient second-order minimization. It is entirely implemented using the direct method, which includes a depth initialization module based on visual–inertial alignment, a stereo image tracking module, and a marginalization module. Inertial measurement unit (IMU) data is first aligned with a stereo image to initialize the system effectively. Then, based on the efficient second-order minimization (ESM) algorithm, the photometric error and the inertial error are minimized to jointly optimize camera poses and sparse scene geometry. IMU information is accumulated between several frames using measurement preintegration and is inserted into the optimization as an additional constraint between keyframes. A marginalization module is added to reduce the computation complexity of the optimization and maintain the information about the previous states. The proposed system is evaluated on the KITTI visual odometry benchmark and the EuRoC dataset. The experimental results demonstrate that the proposed system achieves state-of-the-art performance in terms of accuracy and robustness. Full article

Multimodal review helpfulness prediction (MRHP) aims to identify the most helpful reviews by leveraging both textual and visual information. However, prior studies have primarily focused on modeling interactions between these modalities, often overlooking the consistency between review content and ratings, which is a key indicator of review credibility. To address this limitation, we propose CRCNet (Content–Rating Consistency Network), a novel MRHP model that jointly captures the semantic consistency between review content and ratings while modeling the complementary characteristics of text and image modalities. CRCNet employs RoBERTa and VGG-16 to extract semantic and visual features, respectively. A co-attention mechanism is applied to capture the consistency between content and rating, and a Gated Multimodal Unit (GMU) is adopted to integrate consistency-aware representations. Experimental results on two large-scale Amazon review datasets demonstrate that CRCNet outperforms both unimodal and multimodal baselines in terms of MAE, MSE, RMSE, and MAPE. Further analysis confirms the effectiveness of content–rating consistency modeling and the superiority of the proposed fusion strategy. These findings suggest that incorporating semantic consistency into multimodal architectures can substantially improve the accuracy and trustworthiness of review helpfulness prediction. Full article

T cells play a vital role in resisting pathogen invasion and maintaining immune homeostasis. However, T cells gradually become exhausted under chronic antigenic stimulation, and this exhaustion is closely related to mitochondrial dysfunction in T cells. Mitochondria play a crucial role in the metabolic reprogramming of T cells to achieve the desired immune response. Here, we compiled the latest research on how mitochondrial metabolism determines T cell function and differentiation, with the mechanisms mainly including mitochondrial biogenesis, fission, fusion, mitophagy, and mitochondrial transfer. In addition, the alterations in mitochondrial metabolism in T-cell exhaustion were also reviewed. Furthermore, we discussed intervention strategies targeting mitochondrial metabolism to reverse T cell exhaustion in detail, including inducing PGC-1α expression, alleviating reactive oxygen species (ROS) production or hypoxia, enhancing ATP production, and utilizing mitochondrial transfer. Targeting mitochondrial metabolism in exhausted T cells may achieve the goal of reversing and preventing T cell exhaustion. Full article

Background/Objectives: Primary malignant lung tumors in children are rare and diagnostically challenging. This study presents a single-center experience in the diagnosis and treatment of these tumors, emphasizing the role of histopathological and genetic profiling in informing individualized therapeutic strategies. Methods: We retrospectively reviewed records of seven pediatric patients (ages 2–18) treated from 2015 to 2025. Diagnostics included laboratory tests, chest CT, bronchoscopy, and histopathological/immunohistochemical analysis. Treatment primarily involved surgical resection, complemented by chemo-, radio-, or targeted therapies when indicated. Results: Inflammatory myofibroblastic tumor (IMT) represented the most commonly diagnosed entity (3/7 cases). The tumors presented with nonspecific symptoms, most frequently dry cough. Tumor type distribution was age-dependent, with aggressive forms such as pleuropulmonary blastoma predominantly affecting younger children, whereas IMT and carcinoid tumors were more common in older patients. Surgical resection remained the mainstay of treatment in the majority of cases. Bronchoscopy served as a valuable adjunct in the initial management of tumors exhibiting intraluminal growth, allowing for direct visualization, tissue sampling, and partial debulking to alleviate airway obstruction. In patients with an initially unresectable IMT harboring specific gene fusion rearrangement (e.g., TFG::ROS1), neoadjuvant targeted therapy with crizotinib enabled adequate tumor shrinkage to allow for subsequent surgical resection. Two patients in the study cohort died as a result of disease progression. Conclusions: A multidisciplinary diagnostic approach—integrating radiologic, bronchoscopic, histopathological, and genetic evaluations—ensures high diagnostic accuracy. While conventional treatments remain curative in many cases, targeted therapies directed at specific molecular alterations may offer essential therapeutic options for selected patients. Full article

Polystyrene microplastics (PS-MPs) released in the environment reportedly affect the reproduction of various organisms, induced oxidative stress and apoptosis, resulting in altered sperm parameters. In this in vitro study, we tested the cytotoxicity and genotoxicity of PS-MPs by exposing human semen samples to PS-MPs levels (105 and 210 μg/mL) for 30–60–90 min. Semen parameters, genome stability, sperm DNA fragmentation (SDF) and reactive oxygen species (ROS) production were analyzed before and after exposure. Moreover, we also evaluated the expression level of spermatozoa-specific expressed genes essential for the fusion with oocyte (DCST1, DCST2, IZUMO1, SPACA6, SOF1, and TMEM95). After PS-MP exposure, semen concentration and morphology did not differ, while sperm vitality and motility decreased in a time-dependent manner. In addition, sperm agglutination was observed in the groups exposed to both PS-MPs concentrations tested. A time- and concentration-dependent reduction in genomic stability, as well as increased SDF and ROS production, was also observed. Moreover, all investigated transcripts were down-regulated after PS-MP exposure. Our results confirm the oxidative stress-mediated genotoxicity and cytotoxicity of PS-MPs on human spermatozoa. The sperm agglutination observed after treatment could be due to the aggregation of PS-MPs already adhered to the sperm membranes, hindering sperm movement and fertilizing capability. Interestingly, the downregulation of genes required for sperm–oocyte fusion, resulting from data on the in vitro experimental system, suggests that PS-MP exposure may have implications for sperm functionality. While these findings highlight potential mechanisms of sperm dysfunction, further investigations using in vivo models are needed to determine their broader biological implications. Possible environmental and working exposure to pollutants should be considered during the counselling for male infertility. Full article