Search Results (535)

Background: Dynamic risk stratification is fundamental to the modern management of pulmonary arterial hypertension (PAH). However, data on the impact of sequential add-on therapy in patients with Group 1.4 PAH—particularly in Latin American populations—remains limited. This study evaluated changes in risk classification using COMPERA 2.0 and REVEAL Lite 2 scores in patients treated with endothelin receptor antagonist (ERA) and phosphodiesterase type 5 inhibitor (PDE5i) combination therapy (macitentan + sildenafil) at a referral center in Mexico. Methods: In this single-center, retrospective cohort study, 25 patients with a confirmed diagnosis of PAH between 1st January 2022 and 31st December 2024 were evaluated at baseline and after 24 weeks of treatment. Clinical, functional, and biochemical parameters were recorded. Within-patient changes were analyzed using the Wilcoxon signed-rank test, and agreement between risk assessment tools was assessed using Spearman’s correlation coefficient. Results: At 24 weeks, patients demonstrated significant improvement in World Health Organization functional class (p = 0.002) and a significant reduction in brain natriuretic peptide levels (p = 0.003). Both COMPERA 2.0 and REVEAL Lite 2 scores showed a consistent shift toward lower-risk categories. A strong concordance between the two tools was observed. Conclusions: Sequential add-on ERA + PDE5i therapy was associated with meaningful improvement in risk stratification among patients with Group 1.4 PAH. These findings support the clinical utility of simplified, noninvasive risk assessment tools in real-world settings, particularly in resource-constrained environments. Full article

Sleep-related respiratory disturbances are difficult to monitor continuously outside specialized laboratories because conventional polysomnography is resource-intensive and intrusive. This study presents a contactless edge-AI engineering prototype for detecting controlled voluntary respiratory-motion suppression and motion artifacts using a 60 GHz frequency-modulated continuous-wave radar. The system integrates a 60 GHz radar front end, lightweight local preprocessing, an INT8 one-dimensional convolutional neural network deployed on the Analog Devices MAX78000 CNN accelerator (Analog Devices Thailand, Chon Buri, Thailand), and an event-driven Raspberry Pi Zero 2W gateway for alert transmission. Evaluation was performed using a controlled healthy-volunteer dataset consisting of normal breathing, voluntary breath-holding-induced respiratory suppression, and deliberate motion artifact. The final valid test set contained 270 technically valid 30 s windows balanced across the three classes. The INT8 model achieved an overall accuracy of 92.6% (95% confidence interval: 88.8–95.2%), with a macro-averaged precision, recall, and F1-score of 92.6%, 92.6%, and 92.5%, respectively. Active CNN inference on the MAX78000 consumed 0.152 ± 0.011 mJ and was completed in 5.20 ± 0.11 ms, corresponding to approximately 280-fold lower active inference energy than Python 3.14.6/TensorFlow Lite 2.21.0-based execution on the Raspberry Pi Zero 2W. These results demonstrate the feasibility of privacy-aware, low-power respiratory-pattern classification at the edge. However, the study should be interpreted strictly as an engineering proof-of-concept based on controlled voluntary breathing and movement tasks in healthy volunteers. It is not a clinically validated apnea or obstructive sleep apnea detection system and did not include polysomnography, oxygen saturation measurement, airflow sensing, sleep staging, or diagnosed patient cohorts. Full article

Background: Radiation dermatitis (ARD), particularly its most severe form, moist desquamation (MD), is a frequent and distressing complication of external beam radiotherapy (RT) in head and neck (H&N) cancer patients. Standard management often provides limited benefit for healing and symptom control. Silicone-based foam dressings, including Mepilex Lite and Mepilex Ag, may offer atraumatic adherence, moisture balance, and pain reduction. This study evaluated their real-world effectiveness for MD after conventional RT. Methods: Ten H&N cancer patients with clinically confirmed MD post-radiotherapy were prospectively followed until healing. Patients received Mepilex Lite or Mepilex Ag based on exudate level and infection risk, with dressings changed every three days. Patient- and healthcare provider-reported measures were collected throughout follow-up. The primary endpoint was time to MD resolution, defined as healing to grade 1 skin status. Secondary endpoints included changes in symptom burden, dressing tolerability and satisfaction, and adverse events. Results: Median age was 69 years (range 44–78). All wounds healed to grade 1, with a mean time of 8.6 days (SD 3.9). No infections or adverse events occurred. Pain, burning, and interference with daily activity decreased, and most patients reported improved comfort. Conclusions: In this small prospective cohort study, use of Mepilex dressings was associated with rapid healing, good tolerability, and improvement in patient-reported symptoms of acute radiation dermatitis. These findings suggest that Mepilex dressings may be a promising management option and warrant evaluation in larger comparative studies. Full article

Objectives: Multimodal large language models (MLLMs) have shown potential for medical image classification. We evaluated four optimization strategies in two MLLMs—GPT-4o (gpt-4o-2024-08-06) and Gemini 2.5 Flash-Lite—for ultrasound-based thyroid nodule malignancy classification using two public datasets and a clinical cohort of nodules with atypia of undetermined significance (AUS) cytology. Methods: Text prompting, few-shot learning, fine-tuning, and a hybrid strategy combining fine-tuning with few-shot learning were evaluated for each model. Performance was assessed using the Digital Database of Thyroid Images (DDTI; n = 80), a 1000-image test subset of TN5000, and an institutional AUS cohort with surgical pathology (n = 84). In the AUS cohort, the best-performing strategy was compared with the consensus classification of three endocrinologists and the American Thyroid Association (ATA) ultrasound risk stratification. Results: For GPT-4o, the hybrid strategy achieved the highest area under the receiver operating characteristic curve (AUC) in DDTI (0.866), TN5000 (0.689), and the AUS cohort (0.836). In the AUS cohort, its specificity was higher than that of endocrinologist consensus and ATA risk stratification when only high-suspicion nodules were classified as malignant (95.1% vs. 70.7% and 70.7%; p = 0.002 and p = 0.001, respectively), while sensitivity did not differ significantly (72.1% vs. 74.4% and 79.1%, respectively; both p > 0.05). However, the hybrid model misclassified 12 of 43 malignant nodules, corresponding to a false-negative rate of 27.9%. When high- and intermediate-suspicion ATA categories were classified as malignant, ATA sensitivity increased to 83.7% and specificity decreased to 56.1%; the hybrid model had a higher AUC than ATA risk stratification (0.836 vs. 0.749; p = 0.017). For Gemini 2.5 Flash-Lite, few-shot learning, fine-tuning, and the hybrid strategy did not improve AUC relative to text prompting in any dataset. Conclusions: The hybrid strategy produced the most consistent performance gains for GPT-4o across the three datasets but did not improve Gemini 2.5 Flash-Lite. The optimized GPT-4o model achieved high specificity in the diagnostically challenging AUS cohort, although its false-negative rate limits its use as a stand-alone diagnostic tool. Further validation in larger, prospective multicenter cohorts is required before clinical use. Full article

Graphene and carbon nanotube (CNT) membranes are promising for filtration, desalination, and water treatment, yet their performance requires the joint interpretation of their architecture, nanoconfined transport, selectivity, fouling, swelling, defects, stability, and operating conditions. Here, GCMembrane-LLM was developed as an evidence-grounded domain-specific large language model. A curated 582-paper corpus generated 12,208 cleaned membrane-specific question–answer pairs for Low-Rank Adaptation (LoRA)-based supervised fine-tuning of Llama-3.1-8B-Instruct, and retrieval-augmented generation provided article-title and page-level traceability. GCMembraneBench included 100 application-oriented questions on graphene oxide (GO) membranes, CNT membranes, GO/CNT hybrids, and cross-material reasoning. Under direct answering without retrieval context, the anonymized and shuffled automatic evaluation showed that GCMembrane-LLM achieved a mean weighted score of 4.237/5.0, exceeding Llama-3.1-8B-Instruct and Doubao-1.5-lite. A stratified 30-question blinded manual assessment showed the same ranking. The application cases further yielded membrane science conclusions: CNT-assisted GO/CNT transport should be evaluated with dispersion, interfacial compatibility, defects, and stability; GO desalination depends on swelling control, interlayer spacing, and defect suppression; and CNT high flux requires joint examination of pore diameter, entrance chemistry, hydration barriers, ion rejection, and operating conditions. GCMembrane-LLM supports source-traceable evidence organization and preliminary hypothesis formulation before experimental validation. Full article

Remote sensing image change detection is widely used in urban expansion analysis, land-use monitoring, and disaster assessment. Nevertheless, it still faces significant challenges due to pseudo-change interference in high-resolution imagery, the large-scale variation in small changed objects, and the need for lightweight models in real-world engineering applications. To address these issues, this paper proposes LDST-ChangeNet, a lightweight dual spatiotemporal attention network for change detection. The network adopts a Siamese EfficientNet-B1 as its dual-branch encoder and employs a differential bi-temporal feature fusion strategy (Diff) to explicitly model temporal discrepancies, enabling efficient feature extraction while significantly reducing model complexity. A Position Attention Module (PAM) is introduced at the encoder bottleneck to suppress pseudo changes caused by non-structural factors. Meanwhile, a lightweight Pyramid Pooling Module (PPM-lite) is incorporated at the entrance of the deepest decoder features to enhance multi-scale contextual representation. Furthermore, a Boundary Attention Module (BAM) is applied in the decoder output stage to improve boundary delineation and small-object change detection. Experimental results on the LEVIR-CD and WHU-CD datasets show that LDST-ChangeNet outperforms other state-of-the-art methods, achieving F1-scores of 90.67% and 91.08%, respectively. The model maintains a lightweight design, requiring only 11.72 M parameters and 10.03 GFLOPs on LEVIR-CD, and 11.77 M parameters and 9.12 GFLOPs on WHU-CD. Full article

Global agriculture is seriously threatened by plant diseases, which result in large losses in both productivity and quality. Timely and accurate disease detection is essential for effective crop management and food security. This work presents an improved MobileNetV2 architecture with Modified Lite Attention (MLA) Model for detecting plant leaf disease. Our methodology incorporates pre-processing, feature extraction through attention model, convolution layers, and classifying into diseased or healthy categories. Further, multiclassification of diseases is performed on a dataset comprising 4432 samples including whitefly, leaf spot, leaf curl, yellowish and healthy leaves. The proposed attention model is compared with existing attention models like CBAM (Convolutional Block Attention Model), SE (Squeeze and Excitation), ECA (Efficient Channel Attention) and SDMnet (Spatially Dilated Multi-Scale Network) to validate our hybrid MLA feature extraction technique. Customizing the categorization with fully connected layers and utilisation of a pre-trained MobileNetV2 model allow the system to achieve excellent results. Findings show encouraging accuracy, surpassing 97% compared to existing techniques for multiclass dataset classification. The integration of MobileNetV2 with custom dense layers enables robust detection even with limited datasets, making it ideal for use in mobile or low-resource agricultural environments. Further, the proposed method is tested on the PlantVillage dataset consisting of 10,836 samples using K-Fold cross-validation for K = 5 and K = 4 to obtain an average accuracy of 98.4% and 98.69%, respectively. Full article

Human sitting posture recognition is critical for smart seating, ergonomic monitoring, and healthcare systems. However, existing deep learning approaches typically rely on highly complex network architectures that are computationally expensive, hindering their lightweight deployment on edge devices. Furthermore, current methods frequently struggle with indistinct boundaries among multi-class postures and are highly prone to overfitting when constrained by small-sample pressure sensor datasets. To bridge this gap, this paper proposes a novel, lightweight posture recognition framework specifically tailored for pressure distribution maps. First, sitting pressure data is collected using a thin-film pressure array sensor and uniformly mapped into an [M × N] image representation, establishing an effective sample format for Convolutional Neural Network (CNN) inputs. Second, as our primary architectural contribution, we fundamentally optimize the classic LeNet-5 network to enhance complex feature representation without inflating model complexity. Specifically, the depth of the convolutional layers is increased with a progressively increasing channel configuration. Batch Normalization (BN) is introduced to accelerate convergence and ensure training stability, while a Dropout mechanism is embedded within the fully connected layers to strictly penalize overfitting under small-sample constraints. These architectural improvements are synergistically combined with targeted data augmentation strategies—including random translation, rotation, and intensity perturbation—to further strengthen the model’s generalization capability. Experimental results demonstrate that the proposed method achieves a classification accuracy of 95.5% in a five-class sitting posture recognition task, significantly outperforming baseline models such as the traditional LeNet-5, AlexNet-Lite, and VGG-Small. The findings indicate that this approach achieves an optimal balance among recognition accuracy, training stability, and low model complexity, providing a robust algorithmic baseline and proof-of-concept for smart healthcare perception systems, paving the way for future large-scale subject-independent validation. Full article

Proactive robotic assistance in human–robot collaboration (HRC) requires systems that can perceive evolving task contexts, anticipate user needs, and intervene appropriately without disrupting human workflow. We present the Agentic Unified Robotic Assistance (AURA) Framework, which couples Large Language Model (LLM) reasoning grounded by Standard Operating Procedures (SOPs) with a modular layer of specialized Intent, Motion, Perception, Sound, Affordance, and Performance Monitors that supply structured context to a central decision-making module, making the framework reconfigurable and auditable without retraining or re-prompting. We introduce a human-in-the-loop teleoperation data collection methodology and an offline evaluation scheme with an Appropriateness Score (A-Score) tailored to proactive intervention timing, and release a benchmark dataset of annotated multimodal HRC episodes containing workspace and robot wrist camera videos, robot joint states, and labeled intervention events. Across three tasks of varying complexity, we observe progressive gains in intent prediction and decision-making as the modules are supplied with richer grounded context (prior-state memory and tracked object locations), with Combined F1 rising by over 20 points between context-poor and context-rich conditions. The structured grounding allows lightweight multimodal backbones such as Gemini 3.1 Flash Lite to perform on par with heavier reasoning-tier models at roughly one-fifth the inference latency. Together, these contributions establish a scalable framework, benchmark, and evaluation methodology for advancing proactive robotic assistance in collaborative environments. Full article

Accurate detection and reliable grasping of small bolts are essential for intelligent manufacturing and automated assembly. However, this remains a challenge due to the small size, slender geometry, and metallic reflective surfaces of bolts. In this paper, we propose a vision-guided robotic bolt handling framework that integrates lightweight object detection, optimization-oriented grasp execution, and collision-aware trajectory planning. The lightweight YOLOv8n-BoltLite detector, improved with E-C2f, LCA, SA-PAN, and WD-IoU loss, enhances localization accuracy and feature representation for small and slender bolts. A robotic grasping framework is designed to transform detection results into executable robotic actions through 3D pose estimation, mid-shank grasp point generation, and optimization-oriented execution formulation. Additionally, a five-segment trajectory planning strategy ensures safe and efficient robot motion. Experimental results show that YOLOv8n-BoltLite achieves a five-run average mAP of 99.64 ± 0.05% with 198 FPS, and 3.02 M parameters. On an additional challenging external test set involving illumination variation, clutter, partial occlusion, reflection, and clustered bolts, the proposed detector achieves 94.62 ± 0.18%, outperforming recent lightweight detectors under the same training protocol. Robotic experiments involving 1000 controlled grasping trials and 300 multi-target grasping attempts demonstrate a controlled-condition success rate of 97.0% and improved target-selection reliability in multi-bolt scenes. These results suggest that the proposed framework offers a practical and efficient solution for automated bolt handling in intelligent manufacturing environments. Full article

Aiming at the core pain point that in existing object detection models, it is difficult to balance detection accuracy and real-time inference efficiency on edge computing devices in UAV-based intelligent inspection of power transmission lines, this paper proposes a lightweight YOLO-PowerLiteV2 model for anomaly target detection in power transmission lines to address the shortcomings of YOLO-PowerLite. Based on YOLO11n as the baseline, the model achieves compression of model volume while guaranteeing detection performance through four core improvements: the C3k2-UIB lightweight backbone module, the MCA (Multi-scale Cross-Axis) attention mechanism, the MBConv lightweight detection head, and the MFM (Modulation Feature Fusion) module. Experiments were conducted on a dataset constructed from 5563 aerial images of transmission lines containing three types of targets: bird nests, defective insulators, and balloons. The results show that YOLO-PowerLiteV2 achieves a mAP@50 of 95.2%, with only 0.97 M parameters and 2.8 G floating point operations (FLOPs). Compared with the baseline model, the number of parameters is reduced by 62.5%, and FLOPs are decreased by 56.25%. On the NVIDIA Jetson Xavier NX edge platform, the model achieves 59.5 FPS with only 16.8 ms latency, outperforming the baseline by 31% in frame rate. Its comprehensive performance outperforms mainstream lightweight detection models. The model demonstrates excellent adaptability to UAV edge-terminal deployment requirements, thereby providing technical support for real-time intelligent inspection of power transmission lines. Full article

Compact face verifiers at access-control and surveillance terminals must operate under specular reflection, off-frontal pose, and mask occlusion, disturbances that frequently co-occur in practice. Existing objectives optimize identity discrimination and score-threshold reliability separately. As a result, disturbance cues leak into the identity embedding and inflate the impostor-score tail near the operating false-acceptance rate (FAR)—a structural weakness that backbone scaling alone does not resolve within a fixed parameter budget. We propose RCF-Face, a 1.12 M-parameter verifier for the sub-2 M-parameter, sub-0.2 GFLOP budget of Ampere-class edge GPUs, trained under a unified objective that combines representation-level leakage suppression (HSIC-based identity–disturbance factorization with augmentation-based counterfactual consistency) and decision-level score shaping via a softplus tail-risk penalty anchored to the target FAR. Across four disturbance-focused protocols (CFP-FP, IJB-C, RMFRD, and a reflection-augmented subset), RCF-Face reaches a Composite-Disturbance Score (CDS, the mean verification accuracy over the four protocols) of 89.05 at 0.166 GFLOPs, improving on the capacity-matched AdaFace-Lite baseline by 4.67 percentage points, with both per-protocol gains over this baseline significant under Bonferroni correction. Zero-shot evaluation on two open-source reflection-related datasets (SoF and MeGlass) shows that the robustness gains transfer to real-world images, although these datasets isolate single disturbance axes and do not constitute a composite-disturbance benchmark. On a Jetson Orin NX 16 GB, batch-1 latency is 2.41 ms (FP16) and 1.66 ms (INT8), supporting Ampere-class edge-GPU deployment. Full article

One of the remaining challenges in deploying 3D CNN models in resource-constrained environments is the high computational demand. In this paper, we design three lightweight architectures that have distinct spatiotemporal topologies, namely, Lite-R21D, Lite-MC3, and Lite-LF, to reduce computational cost. However, these compact models have restricted representational capacity, which consequently limits their ability to capture complex spatiotemporal features. To overcome this, we employ Knowledge Distillation (KD) and further investigate hybrid combinations of response-based, spatiotemporal attention, and intermediate feature alignment paradigms. By analyzing knowledge transfer across these diverse architectures, our experiments on UCF101 and HMDB51 demonstrate that combining these distillation configurations consistently outperforms single KD methods, resulting in a substantial increase in accuracy across all Student models. Our optimal hybrid setup achieves 92.07% accuracy on UCF101 and 65.56% on HMDB51, compared to the Teacher’s 94.74% and 69.48%, reducing the accuracy gap to only 2.67% and 3.92%. These gains are achieved alongside significant efficiency improvements. The proposed models operate with up to 87% fewer parameters and an 89% reduction in Floating-Point Operations (FLOPs), achieving 6.7× faster inference. Our findings highlight that hybrid distillation is an effective approach for transferring and utilizing complex spatiotemporal knowledge in lightweight models. Full article

Drought stress significantly impacts barley (Hordeum vulgare L.) production, necessitating early and accurate detection systems for precision agriculture. Traditional monitoring approaches rely on manual inspection or single-modality sensing, which often fail to capture the complex physiological responses to water deficit. This study presents a novel multimodal deep learning framework that integrates RGB imaging with environmental sensor data (temperature and humidity) for real-time drought stress classification in barley plants. The proposed architecture employs EfficientNetV2-S for visual feature extraction, coupled with a dedicated sensor encoding branch, unified through a cross-modal attention mechanism and gated multimodal fusion strategy. To address the computational constraints of agricultural IoT systems, we implemented comprehensive CPU optimization techniques and model compression via TensorFlow Lite INT8 quantization, achieving a 68.5% reduction in training time and 90% reduction in model size. The system was validated on a custom greenhouse dataset (379 samples, 80/20 split) and the PlantVillage dataset (26,000 images, binary reformulation). A 10-seed evaluation protocol demonstrated that the full multimodal model achieves 98.3 ± 1.5% accuracy, outperforming both an image-only baseline (97.4 ± 1.8%) and a sensor-only MLP (73.8 ± 3.5%). Across seeds, the model also achieved an F1-score of 98.34 ± 1.48% and ROC-AUC of 99.93 ± 0.13%. Ablation analysis with ANOVA (F(4,36) = 4.44, p = 0.005) confirmed that multimodal fusion improves accuracy by 0.92% over image-only models, with the full gated cross-modal attention mechanism outperforming all simplified baselines, including AgriFusionNet (75.22%), Shallow CNN (92.54%), Logistic Regression multimodal (92.11%), and Random Forest multimodal (89.91%). These results further show that relying on environmental data alone is insufficient, reinforcing the benefit of multimodal fusion. External validation on PlantVillage achieved 99.97% accuracy, demonstrating strong generalization capabilities. The optimized model operates efficiently on CPU-only hardware (training time: 9.1 min/epoch), making it suitable for edge deployment in resource-constrained agricultural environments. This work demonstrates that a low-cost, CPU-compatible multimodal deep learning system can reliably detect drought stress in barley under real greenhouse conditions and provides a practical and scalable solution for early stress monitoring in precision agriculture. Full article

Resource-constrained edge processors deployed on unmanned aerial vehicles and wearable platforms require compact, drift-robust gas classification models for a range of environmental and security monitoring applications, including CBRN-motivated scenarios. Existing approaches rely on server-grade architectures incompatible with edge-board-scale deployment, or on classifiers that chemically degrade severely under long-term sensor drift. Each UCI gas class was mapped to a CBRN behavioral category based on physicochemical analogy (molecular functional group, vapor pressure, and metal-oxide semiconductor (MOS) cross-sensitivity pattern), following established precedent. Analyzed were Ammonia (NH₃), Acetaldehyde (CH₃CHO), Acetone ((CH₃)₂CO), Ethylene (C₂H₄), Ethanol (C₂H₅OH), Toluene (C₆H₅CH₃). We propose herein an end-to-end pipeline integrating a novel 1-D convolutional neural network with depth-wise separable convolutions (LiteSensor-Net), INT8 post-training quantization, structured magnitude pruning, and a knowledge-distillation domain-adaptation module (KD–DM) for sensor drift compensation. Using the UCI Gas Sensor Array Drift Dataset (13,910 measurements; 16 metal-oxide sensors; six analyte gases; a 36-month work span). LiteSensor-Net achieved accuracy = 92.63 ± 2.02%, macro-F1 = 0.898, model size = 5.99 kB INT8 pruned, inference latency = 6.3 ms, RAM footprint = 31.7 kB, and energy per inference = 0.04 mJ (all metrics on Raspberry Pi 4B, ARM Cortex-A72). Under chronological forward-chaining evaluation, KD–DM–20 achieved 47.91 ± 18.79% mean accuracy over Batches 2–10, representing a +9.25 pp improvement over uncompensated NC (38.66%). A six-metric benchmark framework—accuracy, macro-F1, model size, inference latency, RAM footprint, and energy per inference—is introduced to standardize edge-AI gas classifier evaluation. The proposed pipeline provides an open-source, deployable foundation for edge-class gas classification systems, with CBRN detection as a motivating application. Full operational validation on certified chemical simulants remains as future work. Full article