Search Results (871)

This paper proposes a knowledge graph (KG) construction method for a part machining process in response to the low degree of structuring of historical process data association relationships within the enterprise in the field of part machining, which makes it difficult to reuse effectively. The part types are mainly shafts, gears, boxes and other common parts. First, the schema layer of the process knowledge graph was constructed using a top-down approach. Second, deep learning techniques were employed for entity extraction, while knowledge fusion and ontology relationship establishment methods were combined to build the data layer of the process knowledge graph (PKG) from the bottom up. Third, the mapping between the schema layer and data layer was implemented in the Neo4j graph database. Based on the constructed process KG, process route recommendation and rapid retrieval of process information were thus accomplished. Finally, a shaft part was used as the target part to verify the effectiveness of the proposed method. In over 300 trials, the similarity-based recommendation model achieved a hit rate of 91.7% (the target part’s route appeared in the recommended list in 91.7% of cases). These results indicate that the proposed machining PKG construction is feasible and can assist in process planning, potentially improving the efficiency of retrieving and reusing machining knowledge. Full article

This study pioneers the integration of Sentinel-2 satellite imagery with Kolmogorov–Arnold networks (KAN) for the evaluation of chlorophyll-a (Chl-a) concentrations in inland lakes. Using Baiyangdian Lake in Hebei Province, China, as a case study, a specialized KAN architecture was designed to extract spectral features from Sentinel-2 data, and a robust algorithm was developed for Chl-a estimation. The results demonstrate that the KAN model outperformed traditional feature-engineering-based machine learning (ML) methods and standard multilayer perceptron (MLP) deep learning approaches, achieving an R² of 0.8451, with MAE and RMSE as low as 1.1920 μg/L and 1.6705 μg/L, respectively. Furthermore, attribution analysis was conducted to quantify the importance of individual features, highlighting the pivotal role of bands B3 and B5 in Chl-a retrieval. Furthermore, spatio-temporal distributions of Chl-a concentrations in Baiyangdian Lake from 2020 to 2024 were generated leveraging the KAN model, further elucidating the underlying causes of water quality changes and examining the driving factors. Compared to previous studies, the proposed approach leverages the high spatial resolution of Sentinel-2 imagery and the accuracy and interpretability of the KAN model, offering a novel framework for monitoring water quality parameters in inland lakes. These findings may guide similar research endeavors and provide valuable decision-making support for environmental agencies. Full article

Metacognitive monitoring plays a crucial role in self-regulated learning, as accurate monitoring enables effective control, which in turn impacts learning outcomes. Most studies on metacognitive monitoring have focused on learners’ monitoring abilities when they are explicitly prompted to monitor. However, in real-world educational settings, learners are more often prompted to control their learning, such as deciding whether to allocate additional time to a learning target. The primary goal of this study was to investigate whether retrieval is engaged when learners are explicitly prompted to control their learning processes by making study decisions. To address this, three experiments were conducted. In Experiment 1, participants (N = 39) studied 70 Swahili–English word pairs in a learning task. Each trial displayed a word pair for 8 s, followed by a distractor task (a two-digit mental addition) and a study decision intervention (choose “Study Again” or “Next”). After learning, participants provided a global judgment of learning (JOL), estimating their overall recall accuracy. Finally, they completed a cued recall test (Swahili cue). Responses were scored for accuracy and analyzed alongside study decisions, study decision reaction time (RT), and metacognitive judgments. Reaction times (RTs) for study decisions correlated positively with test accuracy, global judgments of learning (JOLs), and judgments of confidence (JOCs), suggesting retrieval likely underlies these decisions. Experiment 2 (N = 74, between-subjects) compared memory performance and intervention response time between single-study, restudy, retrieval (explicit recall prompt), and study decision (study decision prompt) groups to have better control over study time and cognitive processes. Although no significant group differences in test accuracy emerged, the retrieval group took longer to respond than the study decision group. Within-subject analyses revealed similar recall accuracy patterns: participants recalled successfully retrieved or “no restudy” items better than failed-retrieval or “restudy” items, implying shared cognitive processes underlying retrieval and study decision interventions. Experiment 3 (N = 74, within-subject, three learning conditions: single-study, retrieval, and study decision) replicated these findings, with no condition effects on test accuracy but longer RT for retrieval than study decisions. The similar recall accuracy patterns between retrieval and study decision interventions further supported shared cognitive processes underlying both tasks. Self-reports across experiments confirmed retrieval engagement in both retrieval and study decision interventions. Collectively, the results suggest that retrieval likely supports study decisions but may occur less frequently or less deeply than under explicit monitoring prompts. Additionally, this study explored objective, online measures to detect retrieval-based metacognitive monitoring. Full article

Vehicle re-identification (Re-ID) is a critical computer vision task that aims to match the same vehicle across spatially distributed cameras, especially in the context of remote sensing imagery. While prior research has primarily focused on Re-ID using remote sensing images captured from similar, typically elevated viewpoints, these settings do not fully reflect complex aerial-ground collaborative remote sensing scenarios. In this work, we introduce a novel and challenging task: aerial-ground cross-view vehicle Re-ID, which involves retrieving vehicles in ground-view image galleries using query images captured from aerial (top-down) perspectives. This task is increasingly relevant due to the integration of drone-based surveillance and ground-level monitoring in multi-source remote sensing systems, yet it poses substantial challenges due to significant appearance variations between aerial and ground views. To support this task, we present AGID (Aerial-Ground Vehicle Re-Identification), the first benchmark dataset specifically designed for aerial-ground cross-view vehicle Re-ID. AGID comprises 20,785 remote sensing images of 834 vehicle identities, collected using drones and fixed ground cameras. We further propose a novel method, Enhanced Self-Correlation Feature Computation (ESFC), which enhances spatial relationships between semantically similar regions and incorporates shape information to improve feature discrimination. Extensive experiments on the AGID dataset and three widely used vehicle Re-ID benchmarks validate the effectiveness of our method, which achieves a Rank-1 accuracy of 69.0% on AGID, surpassing state-of-the-art approaches by 2.1%. Full article

Background/Objectives: Melanoma is an aggressive type of skin cancer that poses serious health risks if not detected in its early stages. Although early diagnosis enables effective treatment, delays can result in life-threatening consequences. Traditional diagnostic processes predominantly rely on the subjective expertise of dermatologists, which can lead to variability and time inefficiencies. Consequently, there is an increasing demand for automated systems that can accurately classify melanoma lesions and retrieve visually similar cases to support clinical decision-making. Methods: This study proposes a transfer learning (TL)-based deep learning (DL) framework for the classification of melanoma images and the enhancement of content-based image retrieval (CBIR) systems. Pre-trained models including DenseNet121, InceptionV3, Vision Transformer (ViT), and Xception were employed to extract deep feature representations. These features were integrated using a weighted fusion strategy and classified through an Ensemble learning approach designed to capitalize on the complementary strengths of the individual models. The performance of the proposed system was evaluated using classification accuracy and mean Average Precision (mAP) metrics. Results: Experimental evaluations demonstrated that the proposed Ensemble model significantly outperformed each standalone model in both classification and retrieval tasks. The Ensemble approach achieved a classification accuracy of 95.25%. In the CBIR task, the system attained a mean Average Precision (mAP) score of 0.9538, indicating high retrieval effectiveness. The performance gains were attributed to the synergistic integration of features from diverse model architectures through the ensemble and fusion strategies. Conclusions: The findings underscore the effectiveness of TL-based DL models in automating melanoma image classification and enhancing CBIR systems. The integration of deep features from multiple pre-trained models using an Ensemble approach not only improved accuracy but also demonstrated robustness in feature generalization. This approach holds promise for integration into clinical workflows, offering improved diagnostic accuracy and efficiency in the early detection of melanoma. Full article

The increasing complexity and scale of electronic health records (EHRs) demand advanced tools for efficient data retrieval, summarization, and comparative analysis in clinical practice. MERA (Medical Electronic Records Assistant) is a Retrieval-Augmented Generation (RAG)-based AI system that addresses these needs by integrating domain-specific retrieval with large language models (LLMs) to deliver robust question answering, similarity search, and report summarization functionalities. MERA is designed to overcome key limitations of conventional LLMs in healthcare, such as hallucinations, outdated knowledge, and limited explainability. To ensure both privacy compliance and model robustness, we constructed a large synthetic dataset using state-of-the-art LLMs, including Mistral v0.3, Qwen 2.5, and Llama 3, and further validated MERA on de-identified real-world EHRs from the MIMIC-IV-Note dataset. Comprehensive evaluation demonstrates MERA’s high accuracy in medical question answering (correctness: 0.91; relevance: 0.98; groundedness: 0.89; retrieval relevance: 0.92), strong summarization performance (ROUGE-1 F1-score: 0.70; Jaccard similarity: 0.73), and effective similarity search (METEOR: 0.7–1.0 across diagnoses), with consistent results on real EHRs. The similarity search module empowers clinicians to efficiently identify and compare analogous patient cases, supporting differential diagnosis and personalized treatment planning. By generating concise, contextually relevant, and explainable insights, MERA reduces clinician workload and enhances decision-making. To our knowledge, this is the first system to integrate clinical question answering, summarization, and similarity search within a unified RAG-based framework. Full article

This study develops a domain-adaptive multimodal RAG (Retrieval-Augmented Generation) system to improve the accuracy and efficiency of technical question answering based on large-scale structured manuals. Using Hyundai Staria maintenance documents as a case study, we extracted text and images from PDF manuals and constructed QA, RAG, and Multi-Turn datasets to reflect realistic troubleshooting scenarios. To overcome limitations of baseline RAG models, we proposed an enhanced architecture that incorporates sentence-level similarity annotations and parameter-efficient fine-tuning via LoRA (Low-Rank Adaptation) using the bLLossom-8B language model and BAAI-bge-m3 embedding model. Experimental results show that the proposed system achieved improvements of 3.0%p in BERTScore, 3.0%p in cosine similarity, and 18.0%p in ROUGE-L compared to existing RAG systems, with notable gains in image-guided response accuracy. A qualitative evaluation by 20 domain experts yielded an average satisfaction score of 4.4 out of 5. This study presents a practical and extensible AI framework for multimodal document understanding, with broad applicability across automotive, industrial, and defense-related technical documentation. Full article

Magnetic nanoparticles (MNPs), especially iron oxide (Fe₃O₄), display distinctive superparamagnetic characteristics and elevated surface-area-to-volume ratios, facilitating improved physicochemical interactions with solutes and pollutants. These characteristics make MNPs strong contenders for use in water treatment applications. This research investigates the application of iron oxide MNPs synthesized via co-precipitation as innovative draw solutes in forward osmosis (FO) for treating synthetic produced water (SPW). The FO membrane underwent surface modification with sulfobetaine methacrylate (SBMA), a zwitterionic polymer, to increase hydrophilicity, minimize fouling, and elevate water flux. The SBMA functional groups aid in electrostatic repulsion of organic and inorganic contaminants, simultaneously encouraging robust hydration layers that improve water permeability. This adjustment is vital for sustaining consistent flux performance while functioning with MNP-based draw solutions. Material analysis through thermogravimetric analysis (TGA), scanning electron microscopy (SEM), and Fourier-transform infrared spectroscopy (FTIR) verified the MNPs’ thermal stability, consistent morphology, and modified surface chemistry. The FO experiments showed a distinct relationship between MNP concentration and osmotic efficiency. At an MNP dosage of 10 g/L, the peak real-time flux was observed at around 3.5–4.0 L/m²·h. After magnetic regeneration, 7.8 g of retrieved MNPs generated a steady flow of ~2.8 L/m²·h, whereas a subsequent regeneration (4.06 g) resulted in ~1.5 L/m²·h, demonstrating partial preservation of osmotic driving capability. Post-FO draw solutions, after filtration, exhibited total dissolved solids (TDS) measurements that varied from 2.5 mg/L (0 g/L MNP) to 227.1 mg/L (10 g/L MNP), further validating the effective dispersion and solute contribution of MNPs. The TDS of regenerated MNP solutions stayed similar to that of their fresh versions, indicating minimal loss of solute activity during the recycling process. The combined synergistic application of SBMA-modified FO membranes and regenerable MNP draw solutes showcases an effective and sustainable method for treating produced water, providing excellent water recovery, consistent operational stability, and opportunities for cyclic reuse. 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

Introduction: Limited access to pulmonary rehabilitation (PR) has contributed to the rise of telerehabilitation (TPR) for COPD patients. Positive comparable effects are observed in exercise tolerance, quality of life (QoL), and dyspnoea with TPR. However, patient adherence to TPR is an outcome that has not been sufficiently analysed. Objective: To analyse adherence, satisfaction, and quality-of-life improvements in COPD patients following the TPR program to determine whether telerehabilitation is comparable to conventional therapy or usual care. Methods: A systematic search was conducted using four electronic databases, retrieving 392 articles. Two independent researchers selected and evaluated these articles based on predefined eligibility criteria. A third researcher was consulted in the event of disagreements. Results: Primary outcomes: Adherence to PR and/or usual care showed a minimum reported value of 62% and a maximum reported value of 91%, while TPR adherence had the lowest reported value of 21% and the highest reported value of 93.5%. Five articles compared TPR to PR and/or usual care, showing that TPR adherence is higher or similar to other interventions, whereas only one article found lower TPR adherence compared to PR. Secondary outcomes: A higher number of dropouts were reported for PR and usual care compared to TPR. Three publications analysed satisfaction and demonstrated that patients are satisfied across groups. Tertiary outcomes: Comparable improvements in QoL were found for TPR and PR, both being superior to usual care. Conclusions: This systematic review reveals heterogeneity in classifying adherence for pulmonary rehabilitation and telerehabilitation. Adherence classification may be standardised in future studies for consistent analysis. Full article

Introduction: Radiomics is the extraction of non-invasive and reproducible quantitative imaging features, which may yield mineable information for clinical practice implementation. Quantification of lung function through radiomics could play a role in the management of patients with pulmonary lesions. The aim of this study is to test the capability of radiomic features to predict pulmonary function parameters, focusing on the diffusing capacity of lungs to carbon monoxide (DL_CO). Methods: Retrospective data were retrieved from electronical medical records of patients treated with Stereotactic Body Radiation Therapy (SBRT) at a single institution. Inclusion criteria were as follows: (1) SBRT treatment performed for primary early-stage non-small cell lung cancer (ES-NSCLC) or oligometastatic lung nodules, (2) availability of simulation four-dimensional computed tomography (4DCT) scan, (3) baseline spirometry data availability, (4) availability of baseline clinical data, and (5) written informed consent for the anonymized use of data. The gross tumor volume (GTV) was segmented on 4DCT reconstructed phases representing the moment of maximum inhalation and maximum exhalation (Phase 0 and Phase 50, respectively), and radiomic features were extracted from the lung parenchyma subtracting the lesion/s. An iterative algorithm was clustered based on correlation, while keeping only those most associated with baseline and post-treatment DL_CO. Three models were built to predict DL_CO abnormality: the clinical model—containing clinical information; the radiomic model—containing the radiomic score; the clinical-radiomic model—containing clinical information and the radiomic score. For the models just described, the following were constructed: Model 1 based on the features in Phase 0; Model 2 based on the features in Phase 50; Model 3 based on the difference between the two phases. The AUC was used to compare their performances. Results: A total of 98 patients met the inclusion criteria. The Charlson Comorbidity Index (CCI) scored as the clinical variable most associated with baseline DL_CO (p = 0.014), while the most associated features were mainly texture features and similar among the two phases. Clinical-radiomic models were the best at predicting both baseline and post-treatment abnormal DL_CO. In particular, the performances for the three clinical-radiomic models at predicting baseline abnormal DL_CO were AUC₁ = 0.72, AUC₂ = 0.72, and AUC₃ = 0.75, for Model 1, Model 2, and Model 3, respectively. Regarding the prediction of post-treatment abnormal DL_CO, the performances of the three clinical-radiomic models were AUC₁ = 0.91, AUC₂ = 0.91, and AUC₃ = 0.95, for Model 1, Model 2, and Model 3, respectively. Conclusions: This study demonstrates that radiomic features extracted from healthy lung parenchyma on a 4DCT scan are associated with baseline pulmonary function parameters, showing that radiomics can add a layer of information in surrogate models for lung function assessment. Preliminary results suggest the potential applicability of these models for predicting post-SBRT lung function, warranting validation in larger, prospective cohorts. Full article

The practice in agriculture of spreading polyethylene (PE) film over the soil surface as mulch is a common, global practice that aids in conserving water, increasing crop yields, suppressing weed growth, and decreasing growing time. However, these films are typically only used for a single growing season, and thus, their use and non-biodegradability come with some serious environmental consequences due to their persistence in the soil and potential for microplastic pollution, particularly when retrieval and disposal options are poor. On the microscale, particles < 5 mm from degraded films have been observed to disrupt soil structure, impede water and nutrient cycling, and affect soil organisms and plant health. On the macroscale, there are obvious and serious environmental consequences associated with the burning of plastic film and its leakage from poorly managed landfills. To maintain the crop productivity afforded by mulching with PE film while avoiding the environmental downsides, the development and use of biodegradable polymer technologies is being explored. Here, the efficacy of a newly developed, water-dispersible, sprayable, and biodegradable polyester–urethane–urea (PEUU)-based polymer was compared with two commercial PE mulches, non-degradable polyethylene (NPE) and OPE (ox-degradable polyethylene), in a greenhouse tomato growth trial. Water savings and the effects on plant growth and soil characteristics were studied. It was found that PEUU provided similar water savings to the commercial PE-based mulches, up to 30–35%, while showing no deleterious effects on plant growth. The results should be taken as preliminary indications that the sprayable, biodegradable PEUU shows promise as a replacement for PE mulch, with further studies under outside field conditions warranted to assess its cost effectiveness in improving crop yields and, importantly, its longer-term impacts on soil and terrestrial fauna. Full article

Handwritten Keyword Spotting (KWS) remains a challenging task, particularly in segmentation-free scenarios where word images must be retrieved and ranked based on their similarity to a query without relying on prior page-level segmentation. Traditional KWS methods primarily focus on visual similarity, often overlooking the underlying semantic relationships between words. In this work, we propose a novel NLP-driven re-ranking approach that refines the initial ranked lists produced by state-of-the-art KWS models. By leveraging semantic embeddings from pre-trained BERT-like Large Language Models (LLMs, e.g., RoBERTa, MPNet, and MiniLM), we introduce a relevance feedback mechanism that improves both verbatim and semantic keyword spotting. Our framework operates in two stages: (1) projecting retrieved word image transcriptions into a semantic space via LLMs and (2) re-ranking the retrieval list using a weighted combination of semantic and exact relevance scores based on pairwise similarities with the query. We evaluate our approach on the widely used George Washington (GW) and IAM collections using two cutting-edge segmentation-free KWS models, which are further integrated into our proposed pipeline. Our results show consistent gains in Mean Average Precision (mAP), with improvements of up to $2.3\%$ (from $94.3\%$ to $96.6\%$) on GW and $3\%$ (from $79.15\%$ to $82.12\%$) on IAM. Even when mAP gains are smaller, qualitative improvements emerge: semantically relevant but inexact matches are retrieved more frequently without compromising exact match recall. We further examine the effect of fine-tuning transformer-based OCR (TrOCR) models on historical GW data to align textual and visual features more effectively. Overall, our findings suggest that semantic feedback can enhance retrieval effectiveness in KWS pipelines, paving the way for lightweight hybrid vision-language approaches in handwritten document analysis. Full article

Non-remitting neutropenia in children and chronic idiopathic neutropenia (CIN) in adults have been described previously as peculiar subgroups of neutropenic patients carrying similar clinical and immunological features. The present collection comprising 25 subjects (16 adults and 9 children) mostly affected with mild (84%) and moderate (16%) neutropenia aimed to identify the underlying (possibly common) genetic background. The phenotype of these patients resemble the one described previously: no severe infections, presence of rheumathological signs, leukopenia in almost all patients and lymphocytopenia in one-third of the cohort. The pediatric patients did not share common genes with the adults, based on the results of the multisample test, while some singular variants in neutropenia potentially associated with immune dysregulation likely consistent with the phenotype were found. SPINK5, RELA and CARD11 were retrieved and seem to be consistent with the clinical picture characterized by neutropenia associated to immune dysregulation. The enrichment and burden tests performed in comparison with a control group underline that the products of expression by the variants involved belong to the autoimmunity and immune regulation pathways (i.e., SPINK5, PTPN22 and PSMB9). Even with the limitation of this study’s low number of patients, these results may suggest that non-remitting neutropenia and CIN in adults deserve deep genetic study and enlarged consideration in comparison with classical neutropenia. Full article

In cybersecurity, constructing an accurate knowledge graph is vital for discovering key entities and relationships in security incidents buried in vast unstructured threat reports. Traditional knowledge-graph construction pipelines based on handcrafted rules or conventional machine learning models falter when the data scale and linguistic variety grow. GraphRAG, a retrieval-augmented generation (RAG) framework that splits documents into fixed-length chunks and then retrieves the most relevant ones for generation, offers a scalable alternative yet still suffers from fragmentation and semantic gaps that erode graph integrity. To resolve these issues, this paper proposes SC-LKM, a cybersecurity knowledge-graph construction method that couples the GraphRAG backbone with hierarchical semantic chunking. SC-LKM applies semantic chunking to build a cybersecurity knowledge graph that avoids the fragmentation and inconsistency seen in prior work. The semantic chunking method first respects the native document hierarchy and then refines boundaries with topic similarity and named-entity continuity, maintaining logical coherence while limiting information loss during the fine-grained processing of unstructured text. SC-LKM further integrates the semantic comprehension capacity of Qwen2.5-14B-Instruct, markedly boosting extraction accuracy and reasoning quality. Experimental results show that SC-LKM surpasses baseline systems in entity-recognition coverage, topology density, and semantic consistency. Full article