Search

Abstract Medical imaging is an indispensable and very important step in the diagnosis and treatment of illnesses. However, due to large amounts of resources necessary for training the model, training from scratch may not invariably emerge as the optimal recourse. Transfer learning has emerged as a viable solution, where pretrained weights from ImageNet are initially utilized and fine-tuninned afterwards. This paper presents a novel approach employing transfer learning to classify both respiratory diseases and radiological findings from chest X-rays. The dataset comprises 191 660 X-ray images gathered from public databases and 752 chest X-ray images obtained from a retrospective study at the University Clinical Center of Kragujevac, forming the foundation of Big data analysis. It includes various conditions such as atelectasis, cardiomegaly, infiltration, pleural thickening, non-viral pneumonia, pneumothorax, COVID-19 viral pneumonia, tuberculosis, etc. as well as masses and nodules indicative of tumors and images of healthy subjects. Although there are existing solutions with some diseases, this is the first paper that inlcludes differentiation between healthy and diseased cases, as well as in case of present disease, as much as 18 different classes are inlcuded in the analysis, which has not been done so far. The proposed methodology included transfer learning with DenseNet121 as the backbone and CheXNeXt weights as initialisation scheme, upon which additional layers were added for fine tuning. The results demonstrate the model’s capacity to distinguish between healthy and diseased, with an average area under curve (AUC) of 0.99. The AUC ranges from 0.86 for nodules to 0.99 for pneumonia and 0.99 for COVID-19. Our method outperforms the state-of-the-art in accuracy across all 18 classes, with the exception of classes consolidation, mass, and nodule. These findings are promising for a tested clinical site, though further validation in clinical environment accros multiple sites may be necessary before using the model as a standalone decision system, rather than a decision support system for disease diagnosis based on chest X-rays.

Satellite sea surface temperature (SST) images are valuable for various oceanic applications, including climate monitoring, ocean modeling, and marine ecology. However, cloud cover often obscures SST signals, creating gaps in the data that reduce resolution and hinder spatiotemporal analysis, particularly in the waters near Taiwan. Thus, gap-filling methods are crucial for reconstructing missing SST values to provide continuous and consistent data. This study introduces a gap-filling approach using the Double U-Net, a deep neural network model, pretrained on a diverse dataset of Level-4 SST images. These gap-free products are generated by blending satellite observations with numerical models and in situ measurements. The Double U-Net model excels in capturing SST dynamics and detailed spatial patterns, offering sharper representations of ocean current-induced SST patterns than the interpolated outputs of Data Interpolating Empirical Orthogonal Functions (DINEOFs). Comparative analysis with buoy observations shows the Double U-Net model’s enhanced accuracy, with better correlation results and lower error values across most study areas. By analyzing SST at five key locations near Taiwan, the research highlights the Double U-Net’s potential for high-resolution SST reconstruction, thus enhancing our understanding of ocean temperature dynamics. Based on this method, we can combine more high-resolution satellite data in the future to improve the data-filling model and apply it to marine geographic information science.

The rapid rise of social media has brought about new ways of digital communication, along with a worrying increase in online hate speech (HS), which, in turn, has led researchers to develop several Natural Language Processing methods for its detection. Although significant strides have been made in automating HS detection, research focusing on the European Portuguese language remains scarce (as it happens in several under-resourced languages). To address this gap, we explore the efficacy of various transfer learning models, which have been shown in the literature to have better performance for this task than other Deep Learning models. We employ BERT-like models pre-trained on Portuguese text, such as BERTimbau and mDeBERTa, as well as GPT, Gemini and Mistral generative models, for the detection of HS within Portuguese online discourse. Our study relies on two annotated corpora of YouTube comments and tweets, both annotated as HS and non-HS. Our findings show that the best model for the YouTube corpus was a variant of BERTimbau retrained with European Portuguese tweets and fine-tuned for the HS task, with an F-score of 87.1% for the positive class, outperforming the baseline models by more than 20% and with a 1.8% increase compared with base BERTimbau. The best model for the Twitter corpus was GPT-3.5, with an F-score of 50.2% for the positive class. We also assess the impact of using in-domain and mixed-domain training sets, as well as the impact of providing context in generative model prompts on their performance.

A complex web of intermolecular interactions defines and regulates biological processes. Understanding this web has been particularly challenging because of the sheer number of actors in biological systems: ∼10 4 proteins in a typical human cell offer a plausible 10 8 interactions. This number grows rapidly if we consider metabolites, drugs, nutrients, and other biological molecules. The relative strength of interactions also critically affects these biological processes. However, the small and often incomplete datasets (10 3 -10 4 protein-ligand interactions) traditionally used for binding affinity predictions limit the ability to capture the full complexity of these interactions. To overcome this challenge, we developed Yuel 2, a novel neural network-based approach that leverages transfer learning to address the limitations of small datasets. Yuel 2 is pre-trained on a large-scale dataset to learn intricate structural features and then fine-tuned on specialized datasets like PDBbind to enhance the predictive accuracy and robustness. We show that Yuel 2 predicts multiple binding affinity metrics - Kd, Ki, and IC50 - between proteins and small molecules, offering a comprehensive representation of molecular interactions crucial for drug design and development.

This paper introduces a damage diagnosis method based on the reassignment method and matching networks (MNs) to study the structural health monitoring of aerospace composite material components. This aims to facilitate the mapping of signal features to complex failure modes. We introduce a signal processing technique based on the reassignment method, employing a sliding analysis window to re‐estimate local instantaneous frequency and group delay. By utilizing the short‐time phase spectrum of the signal, we correct the nominal time and frequency coordinates of the spectrum data, aligning them more accurately with the true support region of the analyzed signal. Subsequently, this paper developed a deep matching network (DMN) damage diagnosis model based on MNs. This model utilizes a convolutional neural network (CNN) to extract damage‐related features from the signal and introduces the full context embedding (FCE) method to enhance the compatibility of sample embeddings. In this process, the embeddings of each sample in the training set should be mutually independent, while the embeddings of test samples should be regulated by the distribution of training set sample data. Ultimately, the damage category of test samples is determined based on cosine similarity. We validate our model using damage sample data collected from experiments and simulations conducted under varying components and operating conditions. Comparative assessments with five mainstream methods reveal an average accuracy exceeding 96%. This underscores the exceptional recognition accuracy and generalization performance of our proposed method in cross‐operating condition fault diagnosis experiments concerning aircraft composite material components. [ABSTRACT FROM AUTHOR]

Background: In recent years, numerous methods have been introduced to predict glucose levels using machine-learning techniques on patients' daily behavioral and continuous glucose data. Nevertheless, a definitive consensus remains elusive regarding modeling the combined effects of diet and exercise for optimal glucose prediction. A notable challenge is the propensity for observational patient datasets from uncontrolled environments to overfit due to skewed feature distributions of target behaviors; for instance, diabetic patients seldom engage in high-intensity exercise post-meal., Methods: In this study, we introduce a unique application of Bayesian transfer learning for postprandial glucose prediction using randomized controlled trial (RCT) data. The data comprises a time series of three key variables: continuous glucose levels, exercise expenditure, and carbohydrate intake. For building the optimal model to predict postprandial glucose levels we initially gathered balanced training data from RCTs on healthy participants by randomizing behavioral conditions. Subsequently, we pretrained the model's parameter distribution using RCT data from the healthy cohort. This pretrained distribution was then adjusted, transferred, and utilized to determine the model parameters for each patient., Results: The efficacy of the proposed method was appraised using data from 68 gestational diabetes mellitus (GDM) patients in uncontrolled settings. The evaluation underscored the enhanced performance attained through our method. Furthermore, when modeling the joint impact of diet and exercise, the synergetic model proved more precise than its additive counterpart., Conclusion: An innovative application of the transfer-learning utilizing randomized controlled trial data can improve the challenging modeling task of postprandial glucose prediction for GDM patients, integrating both dietary and exercise behaviors. For more accurate prediction, future research should focus on incorporating the long-term effects of exercise and other glycemic-related factors such as stress, sleep., Competing Interests: The authors have declared that no competing interests exist., (Copyright: © 2024 Hotta et al. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.)

BackgroundIn recent years, numerous methods have been introduced to predict glucose levels using machine-learning techniques on patients' daily behavioral and continuous glucose data. Nevertheless, a definitive consensus remains elusive regarding modeling the combined effects of diet and exercise for optimal glucose prediction. A notable challenge is the propensity for observational patient datasets from uncontrolled environments to overfit due to skewed feature distributions of target behaviors; for instance, diabetic patients seldom engage in high-intensity exercise post-meal.MethodsIn this study, we introduce a unique application of Bayesian transfer learning for postprandial glucose prediction using randomized controlled trial (RCT) data. The data comprises a time series of three key variables: continuous glucose levels, exercise expenditure, and carbohydrate intake. For building the optimal model to predict postprandial glucose levels we initially gathered balanced training data from RCTs on healthy participants by randomizing behavioral conditions. Subsequently, we pretrained the model's parameter distribution using RCT data from the healthy cohort. This pretrained distribution was then adjusted, transferred, and utilized to determine the model parameters for each patient.ResultsThe efficacy of the proposed method was appraised using data from 68 gestational diabetes mellitus (GDM) patients in uncontrolled settings. The evaluation underscored the enhanced performance attained through our method. Furthermore, when modeling the joint impact of diet and exercise, the synergetic model proved more precise than its additive counterpart.ConclusionAn innovative application of the transfer-learning utilizing randomized controlled trial data can improve the challenging modeling task of postprandial glucose prediction for GDM patients, integrating both dietary and exercise behaviors. For more accurate prediction, future research should focus on incorporating the long-term effects of exercise and other glycemic-related factors such as stress, sleep.

Crime remains a crucial concern regarding ensuring a safe and secure environment for the public. Numerous efforts have been made to predict crime, emphasizing the importance of employing deep learning approaches for precise predictions. However, sufficient crime data and resources for training state-of-the-art deep learning-based crime prediction systems pose a challenge. To address this issue, this study adopts the transfer learning paradigm. Moreover, this study fine-tunes state-of-the-art statistical and deep learning methods, including Simple Moving Averages (SMA), Weighted Moving Averages (WMA), Exponential Moving Averages (EMA), Long Short Term Memory (LSTM), Bi-directional Long Short Term Memory (BiLSTMs), and Convolutional Neural Networks and Long Short Term Memory (CNN-LSTM) for crime prediction. Primarily, this study proposed a BiLSTM based transfer learning architecture due to its high accuracy in predicting weekly and monthly crime trends. The transfer learning paradigm leverages the fine-tuned BiLSTM model to transfer crime knowledge from one neighbourhood to another. The proposed method is evaluated on Chicago, New York, and Lahore crime datasets. Experimental results demonstrate the superiority of transfer learning with BiLSTM, achieving low error values and reduced execution time. These prediction results can significantly enhance the efficiency of law enforcement agencies in controlling and preventing crime.

Abstract COVID-19, a global pandemic, has killed thousands in the last three years. Pathogenic laboratory testing is the gold standard but has a high false-negative rate, making alternate diagnostic procedures necessary to fight against it. Computer Tomography (CT) scans help diagnose and monitor COVID-19, especially in severe cases. But, visual inspection of CT images takes time and effort. In this study, we employ Convolution Neural Network (CNN) to detect coronavirus infection from CT images. The proposed study utilized transfer learning on the three pre-trained deep CNN models, namely VGG-16, ResNet, and wide ResNet, to diagnose and detect COVID-19 infection from the CT images. However, when the pre-trained models are retrained, the model suffers the generalization capability to categorize the data in the original datasets. The novel aspect of this work is the integration of deep CNN architectures with Learning without Forgetting (LwF) to enhance the model’s generalization capabilities on both trained and new data samples. The LwF makes the network use its learning capabilities in training on the new dataset while preserving the original competencies. The deep CNN models with the LwF model are evaluated on original images and CT scans of individuals infected with Delta-variant of the SARS-CoV-2 virus. The experimental results show that of the three fine-tuned CNN models with the LwF method, the wide ResNet model’s performance is superior and effective in classifying original and delta-variant datasets with an accuracy of 93.08% and 92.32%, respectively.

Crime remains a crucial concern regarding ensuring a safe and secure environment for the public. Numerous efforts have been made to predict crime, emphasizing the importance of employing deep learning approaches for precise predictions. However, sufficient crime data and resources for training state-of-the-art deep learning-based crime prediction systems pose a challenge. To address this issue, this study adopts the transfer learning paradigm. Moreover, this study fine-tunes state-of-the-art statistical and deep learning methods, including Simple Moving Averages (SMA), Weighted Moving Averages (WMA), Exponential Moving Averages (EMA), Long Short Term Memory (LSTM), Bi-directional Long Short Term Memory (BiLSTMs), and Convolutional Neural Networks and Long Short Term Memory (CNN-LSTM) for crime prediction. Primarily, this study proposed a BiLSTM based transfer learning architecture due to its high accuracy in predicting weekly and monthly crime trends. The transfer learning paradigm leverages the fine-tuned BiLSTM model to transfer crime knowledge from one neighbourhood to another. The proposed method is evaluated on Chicago, New York, and Lahore crime datasets. Experimental results demonstrate the superiority of transfer learning with BiLSTM, achieving low error values and reduced execution time. These prediction results can significantly enhance the efficiency of law enforcement agencies in controlling and preventing crime., Competing Interests: The authors have declared that no competing interests exist., (Copyright: © 2024 Butt et al. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.)

Satellite sea surface temperature (SST) images are valuable for various oceanic applications, including climate monitoring, ocean modeling, and marine ecology. However, cloud cover often obscures SST signals, creating gaps in the data that reduce resolution and hinder spatiotemporal analysis, particularly in the waters near Taiwan. Thus, gap-filling methods are crucial for reconstructing missing SST values to provide continuous and consistent data. This study introduces a gap-filling approach using the Double U-Net, a deep neural network model, pretrained on a diverse dataset of Level-4 SST images. These gap-free products are generated by blending satellite observations with numerical models and in situ measurements. The Double U-Net model excels in capturing SST dynamics and detailed spatial patterns, offering sharper representations of ocean current-induced SST patterns than the interpolated outputs of Data Interpolating Empirical Orthogonal Functions (DINEOFs). Comparative analysis with buoy observations shows the Double U-Net model's enhanced accuracy, with better correlation results and lower error values across most study areas. By analyzing SST at five key locations near Taiwan, the research highlights the Double U-Net's potential for high-resolution SST reconstruction, thus enhancing our understanding of ocean temperature dynamics. Based on this method, we can combine more high-resolution satellite data in the future to improve the data-filling model and apply it to marine geographic information science. [ABSTRACT FROM AUTHOR]