Search Results (5,502)

The long-standing practice of document-based engineering has resulted in the accumulation of a large number of engineering documents across various industries. Engineering documents, such as 2D drawings, continue to play a significant role in exchanging information and sharing knowledge across multiple engineering processes. However, these documents are often stored in non-digitized formats, such as paper and portable document format (PDF) files, making automation difficult. As digital engineering transforms processes in many industries, digitizing engineering documents presents a crucial challenge that requires advanced methods. This research addresses the problem of automatically extracting textual content from non-digitized legacy engineering documents. We introduced an optical character recognition (OCR) system for text detection and recognition that leverages transformer-based generative deep learning models and transfer learning approaches to enhance text recognition accuracy in engineering documents. The proposed system was evaluated on a dataset collected from ships’ engineering drawings provided by a U.S. agency. Experimental results demonstrated that the proposed transformer-based OCR model significantly outperformed pretrained off-the-shelf OCR models. Full article

Background: The large language model (LLM) has the potential to be applied to clinical practice. However, there has been scarce study on this in the field of gastroenterology. Aim: This study explores the potential clinical utility of two LLMs in the field of gastroenterology: a customized GPT model and a conventional GPT-4o, an advanced LLM capable of retrieval-augmented generation (RAG). Method: We established a customized GPT with the BM25 algorithm using Open AI’s GPT-4o model, which allows it to produce responses in the context of specific documents including textbooks of internal medicine (in English) and gastroenterology (in Korean). Also, we prepared a conventional ChatGPT 4o (accessed on 16 October 2024) access. The benchmark (written in Korean) consisted of 15 clinical questions developed by four clinical experts, representing typical questions for medical students. The two LLMs, a gastroenterology fellow, and an expert gastroenterologist were tested to assess their performance. Results: While the customized LLM correctly answered 8 out of 15 questions, the fellow answered 10 correctly. When the standardized Korean medical terms were replaced with English terminology, the LLM’s performance improved, answering two additional knowledge-based questions correctly, matching the fellow’s score. However, judgment-based questions remained a challenge for the model. Even with the implementation of ‘Chain of Thought’ prompt engineering, the customized GPT did not achieve improved reasoning. Conventional GPT-4o achieved the highest score among the AI models (14/15). Although both models performed slightly below the expert gastroenterologist’s level (15/15), they show promising potential for clinical applications (scores comparable with or higher than that of the gastroenterology fellow). Conclusions: LLMs could be utilized to assist with specialized tasks such as patient counseling. However, RAG capabilities by enabling real-time retrieval of external data not included in the training dataset, appear essential for managing complex, specialized content, and clinician oversight will remain crucial to ensure safe and effective use in clinical practice. Full article

Ovarian cancer is one of the most aggressive gynecological cancers due to its high invasion and chemoresistance. It not only has a high incidence rate but also tops the list of mortality rates. Its subtle early symptoms make subsequent diagnosis difficult, significantly delaying timely treatment for patients. Once ovarian cancer reaches an advanced stage, the complexity and difficulty of treatment increase substantially, affecting patient survival rates. Therefore, it is crucial for both medical professionals and patients to remain highly vigilant about the early signs of ovarian cancer to ensure timely intervention. In recent years, ovarian cancer prediction research has advanced, allowing for the analysis of the likelihood and type of cancer based on patients’ genetic data. With the rapid development of machine learning, numerous efficient classification prediction models have emerged. These new technologies offer significant opportunities and potential for developing ovarian cancer diagnostic prediction methods. However, traditional approaches often struggle to achieve satisfactory classification accuracy in high-dimensional genetic datasets with small sample sizes. This research offers a prediction model utilizing genomic data to enhance the early diagnosis rate of ovarian cancer, incorporating feature selection, data augmentation through adversarial conditional generative adversarial networks (AC-GAN), and an extreme gradient boosting (XGBoost) classifier. First, we can simplify the original genetic dataset through feature selection methods, removing irrelevant variables and noise, thereby improving the model’s predictive accuracy. Following dimensionality reduction, AC-GAN enriches the data, producing more realistic genetic samples to enhance the model’s generalization capacity. Finally, the XGBoost classifier is applied to classify the augmented data, achieving efficient predictions for ovarian cancer. These research findings strongly demonstrate that the diagnostic method proposed in this paper has a significant advantage in the predictive diagnosis of ovarian cancer, with an accuracy of 99.01% that surpasses the current technologies in use. Additionally, the algorithm identifies twelve genes highly relevant to ovarian cancer, providing valuable insights for physicians during diagnosis. Full article

Background: Medical imagesegmentation is an essential step in both clinical and research applications, and automated segmentation models—such as TotalSegmentator—have become ubiquitous. However, robust methods for validating the accuracy of these models remain limited, and manual inspection is often necessary before the segmentation masks produced by these models can be used. Methods: To address this gap, we have developed a novel validation framework for segmentation models, leveraging data augmentation to assess model consistency. We produced segmentation masks for both the original and augmented scans, and we calculated the alignment metrics between these segmentation masks. Results: Our results demonstrate strong correlation between the segmentation quality of the original scan and the average alignment between the masks of the original and augmented CT scans. These results were further validated by supporting metrics, including the coefficient of variance and the average symmetric surface distance, indicating that agreement with augmented-scan segmentation masks is a valid proxy for segmentation quality. Conclusions: Overall, our framework offers a pipeline for evaluating segmentation performance without relying on manually labeled ground truth data, establishing a foundation for future advancements in automated medical image analysis. Full article

As the performance of a convolutional neural network is logarithmically proportional to the amount of training data, data augmentation has attracted increasing attention in recent years. Although the current data augmentation methods are efficient because they force the network to learn multiple parts of a given training image through occlusion or re-editing, most of them can damage the internal structures of targets and ultimately affect the results of subsequent application tasks. To this end, region-focusing data augmentation via salient region activation and bitplane recombination for the target detection of optical satellite images is proposed in this paper to solve the problem of internal structure loss in data augmentation. More specifically, to boost the utilization of the positive regions and typical negative regions, a new surroundedness-based strategy for salient region activation is proposed, through which new samples with meaningful focusing regions can be generated. And to generate new samples of the focusing regions, a region-based strategy for bitplane recombination is also proposed, through which internal structures of the focusing regions can be reserved. Thus, a multiplied effect of data augmentation by the two strategies can be achieved. In addition, this is the first time that data augmentation has been examined from the perspective of meaningful focusing regions, rather than the whole sample image. Experiments on target detection with public datasets have demonstrated the effectiveness of this proposed method, especially for small targets. Full article

Porphyrin’s excellent biocompatibility and modifiability make it a widely studied photoactive material. However, its large π-bond conjugated structure leads to aggregation and precipitation in physiological solutions, limiting the biomedical applications of porphyrin-based photoactive materials. It has been demonstrated through research that fabricating porphyrin molecules into nanoscale covalent organic frameworks (COFs) structures can circumvent issues such as poor dispersibility resulting from hydrophobicity, thereby significantly augmenting the photoactivity of porphyrin materials. Porphyrin-based COF materials can exert combined photodynamic and photothermal effects, circumventing the limitations of photodynamic therapy (PDT) due to hypoxia and issues in photothermal therapy (PTT) from heat shock proteins or the adverse impact of excessive heat on the protein activity of normal tissue. Furthermore, the porous structure of porphyrin COFs facilitates the circulation of oxygen molecules and reactive oxygen species and promotes sufficient contact with the lesion site for therapeutic functions. This review covers recent progress regarding porphyrin-based COFs in treating malignant tumors and venous thrombosis and for antibacterial and anti-inflammatory uses via combined PDT and PTT. By summarizing relevant design strategies, ranging from molecular design to functional application, this review provides a reference basis for the enhanced phototherapy application of porphyrin-based COFs as photoactive materials. This review aims to offer valuable insights for more effective biomedical applications of porphyrin-based COFs through the synthesis of existing experimental data, thereby paving the way for their future preclinical utilization. Full article

Background: Obstetric lesions of the anal sphincter (OASIS) are tears intersecting the structure of the anus after vaginal delivery. Our aim is to provide data on the incidence of OASIS and investigate potentially connected risk factors. Methods: This is a retrospective analysis of 464 parturient patients admitted to the AOU Maggiore della Carità, Novara (Italy), in the last ten years (2013–2023), comparing 116 cases (with OASIS) versus 348 controls (with no OASIS). Results: The incidence of OASIS was 1.1%. Among the significant risk factors associated with the risk of severe perineal laceration in our sample, we observed nulliparity, previous caesarean sections, assisted reproduction technology, kilos gained during pregnancy, induced delivery, the use of oxytocin for augmentation, epidural analgesia, delivery after 40 weeks of gestation, position at delivery, the duration of labor, the application of a vacuum cup, newborn weight and head circumference. Conclusions: It was a challenge to find data on OASIS and on more preventable and modifiable risk factors. Beyond the improvement of the corresponding diagnostic and therapeutic tools, a new aim could be to stratify women giving birth based on possible risk factors. Full article

Unmanned aerial vehicle (UAV)-enabled vehicular communications in the sixth generation (6G) are characterized by line-of-sight (LoS) and dynamically varying channel conditions. However, the presence of obstacles in the LoS path leads to shadowed fading environments. In UAV-assisted cellular vehicle-to-everything (C-V2X) communication, vehicle and UAV mobility and shadowing adversely impact latency and throughput. Moreover, 6G vehicular communications comprise data-intensive applications such as augmented reality, mixed reality, virtual reality, intelligent transportation, and autonomous vehicles. Since vehicles’ sensors generate immense amount of data, the latency in processing these applications also increases, particularly when the data are not independently identically distributed (non-i.i.d.). Furthermore, when the sensors’ data are heterogeneous in size and distribution, the incoming packets demand substantial computing resources, energy efficiency at the UAV servers and intelligent mechanisms to queue the incoming packets. Due to the limited battery power and coverage range of UAV, the quality of service (QoS) requirements such as coverage rate, UAV flying time, and fairness of vehicle selection are adversely impacted. Controlling the UAV trajectory so that it serves a maximum number of vehicles while maximizing battery power usage is a potential solution to enhance QoS. This paper investigates the system performance and communication disruption between vehicles and UAV due to Doppler effect in the orthogonal time–frequency space (OTFS) modulated channel. Moreover, a low-complexity UAV trajectory prediction and vehicle selection method is proposed using federated learning, which exploits related information from past trajectories. The weighted total energy consumption of a UAV is minimized by jointly optimizing the transmission window ($L_w$), transmit power and UAV trajectory considering Doppler spread. The simulation results reveal that the weighted total energy consumption of the OTFS-based system decreases up to 10% when combined with federated learning to locally process the sensor data at the vehicles and communicate the processed local models to the UAV. The weighted total energy consumption of the proposed federated learning algorithm decreases by 10–15% compared with convex optimization, heuristic, and meta-heuristic algorithms. Full article

Building on a previously developed partially synthetic data generation algorithm utilizing data visualization techniques, this study extends the novel algorithm to generate fully synthetic tabular healthcare data. In this enhanced form, the algorithm serves as an alternative to conventional methods based on Generative Adversarial Networks (GANs) or Variational Autoencoders (VAEs). By iteratively applying the original methodology, the adapted algorithm employs UMAP (Uniform Manifold Approximation and Projection), a dimensionality reduction technique, to validate generated samples through low-dimensional clustering. This approach has been successfully applied to three healthcare domains: prostate cancer, breast cancer, and cardiovascular disease. The generated synthetic data have been rigorously evaluated for fidelity and utility. Results show that the UMAP-based algorithm outperforms GAN- and VAE-based generation methods across different scenarios. In fidelity assessments, it achieved smaller maximum distances between the cumulative distribution functions of real and synthetic data for different attributes. In utility evaluations, the UMAP-based synthetic datasets enhanced machine learning model performance, particularly in classification tasks. In conclusion, this method represents a robust solution for generating secure, high-quality synthetic healthcare data, effectively addressing data scarcity challenges. Full article

Classifying pictorial styles in artworks is a complex challenge due to the diversity and lack of available datasets, which often limit the performance of machine learning models. To address this issue, we propose a novel data augmentation approach using Diffusion models in contrast to traditional augmentation techniques. Our method generates new samples based on the existing data, expanding the available dataset and enhancing the generalization capability of classification models. We evaluate the effectiveness of this data augmentation technique by training deep learning models with varying proportions of augmented and real data and assessing their performance in pictorial style classification. Our results demonstrate that the proposed Diffusion model-based augmentation significantly improves classification accuracy, suggesting that it can be a viable solution for overcoming data limitations in similar applications. Full article

Historical maps are valuable sources of geospatial data for various geography-related applications, providing insightful information about historical land use, transportation infrastructure, and settlements. While transformer-based segmentation methods have been widely applied to image segmentation tasks, they have mostly focused on satellite images. There is a growing need to explore transformer-based approaches for geospatial object extraction from historical maps, given their superior performance over traditional convolutional neural network (CNN)-based architectures. In this research, we aim to automatically extract five different road types from historical maps, using a road dataset digitized from the scanned Deutsche Heereskarte 1:200,000 Türkei (DHK 200 Turkey) maps. We applied the variants of the transformer-based SegFormer model and evaluated the effects of different encoders, batch sizes, loss functions, optimizers, and augmentation techniques on road extraction performance. Our best results, with an intersection over union (IoU) of 0.5411 and an F1 score of 0.7017, were achieved using the SegFormer-B2 model, the Adam optimizer, and the focal loss function. All SegFormer-based experiments outperformed previously reported CNN-based segmentation models on the same dataset. In general, increasing the batch size and using larger SegFormer variants (from B0 to B2) resulted in improved accuracy metrics. Additionally, the choice of augmentation techniques significantly influenced the outcomes. Our results demonstrate that SegFormer models substantially enhance true positive predictions and resulted in higher precision metric values. These findings suggest that the output weights could be directly applied to transfer learning for similar historical maps and the inference of additional DHK maps, while offering a promising architecture for future road extraction studies. Full article

Farmer cooperatives are one of the types of important entities for agricultural production and rural community development in China. This study aims to examine the effects of farmer cooperatives on rural labor employment and explores the mechanisms from the perspective of institutional advantage, factor redistribution, and value chain. Leveraging two-waved panel data from the China Rural Development Survey, a multinomial Logit model and Tobit model with panel data are adopted. The results show that farmer cooperatives significantly boost rural labor employment, with a more pronounced effect on fully farming and part-time farming. These effects are primarily seen through three mechanisms: income augmentation stemming from institutional advantages, factor redistribution by land transferring and technology service/adoption, as well as industrial clusters. The limited value chain extension of farmer cooperatives hinders its role in improving fully non-agricultural employment. The findings suggest that the government should support the high-quality development of farmer cooperatives to facilitate rural labor employment. Full article

The efficacy of machine learning has increased exponentially over the past decade. The utilization of machine learning to predict and design materials has become a pivotal tool for accelerating materials development. High-entropy alloys are particularly intriguing candidates for exemplifying the potency of machine learning due to their superior mechanical properties, vast compositional space, and intricate chemical interactions. This review examines the general process of developing machine learning models. The advances and new algorithms of machine learning in the field of high-entropy alloys are presented in each part of the process. These advances are based on both improvements in computer algorithms and physical representations that focus on the unique ordering properties of high-entropy alloys. We also show the results of generative models, data augmentation, and transfer learning in high-entropy alloys and conclude with a summary of the challenges still faced in machine learning high-entropy alloys today. Full article

This study introduces a novel approach for predicting the decay levels of potato by integrating an electronic nose system combined with feature-optimized deep learning models. The electronic nose system was utilized to collect volatile gas data from potatoes at different decay stages, offering a non-invasive method to classify decay levels. To mitigate data scarcity and improve training model robustness, a Gaussian Mixture Embedded Generative Adversarial Network (GMEGAN) was used to generate synthetic data, resulting in augmented datasets that increased diversity and improved model performance. Several machine learning and deep learning models, including traditional classifiers (SVM, LR, RF, ANN) and advanced neural networks (CNN, ECA-CNN, CAM-CNN, Conditional CNN), were trained and evaluated. Models incorporating feature-optimized channel attention modules (f-CAM, f-ECA) achieved a classification accuracy of up to 90.28%, significantly outperforming traditional machine learning models (72–77%) and standard CNN models (83.33%). The inclusion of GMEGAN-generated datasets further enhanced classification performance, especially for feature-optimized Conditional CNN models, with an observed increase in accuracy of up to 5.55%. A comprehensive evaluation of the GMEGAN-generated data, including feature mapping consistency, data distribution similarity, and quality metrics, demonstrated that the generated data closely resembled real data, thereby effectively enhancing dataset diversity. The proposed approach shows significant potential in improving classification accuracy and robustness for agricultural quality assessment, particularly in predicting the decay levels of potatoes. Full article

Several approaches have been developed to generate synthetic object points using real LiDAR point cloud data for advanced driver-assistance system (ADAS) applications. The synthetic object points generated from a scene (both the near and distant objects) are essential for several ADAS tasks. However, generating points from distant objects using sparse LiDAR data with precision is still a challenging task. Although there are a few state-of-the-art techniques to generate points from synthetic objects using LiDAR point clouds, limitations such as the need for intense compute power still persist in most cases. This paper suggests a new framework to address these limitations in the existing literature. The proposed framework contains three major modules, namely position determination, object generation, and synthetic annotation. The proposed framework uses a spherical point-tracing method that augments 3D LiDAR distant objects using point cloud object projection with point-wall generation. Also, the pose determination module facilitates scenarios such as platooning carried out by the synthetic object points. Furthermore, the proposed framework improves the ability to describe distant points from synthetic object points using multiple LiDAR systems. The performance of the proposed framework is evaluated on various 3D detection models such as PointPillars, PV-RCNN, and Voxel R-CNN for the KITTI dataset. The results indicate an increase in mAP (mean average precision) by $1.97\%$, $1.3\%$, and $0.46\%$ from the original dataset values of $82.23\%$, $86.72\%$, and $87.05\%$, respectively. Full article