Training Dataset Research Articles

Combining graph deep learning and London dispersion interatomic potentials: A case study on pnictogen chalcohalides.

Machine-learning interatomic potential models based on graph neural network architectures have the potential to make atomistic materials modeling widely accessible due to their computational efficiency, scalability, and broad applicability. The training datasets for many such models are derived from density-functional theory calculations, typically using a semilocal exchange-correlation functional. As a result, long-range interactions such as London dispersion are often missing in these models. We investigate whether this missing component can be addressed by combining a graph deep learning potential with semiempirical dispersion models. We assess this combination by deriving the equations of state for layered pnictogen chalcohalides BiTeBr and BiTeI and performing crystal structure optimizations for a broader set of V-VI-VII compounds with various stoichiometries, many of which possess van der Waals gaps. We characterize the optimized crystal structures by calculating their x-ray diffraction patterns and radial distribution function histograms, which are also used to compute Earth mover's distances to quantify the dissimilarity between the optimized and corresponding experimental structures. We find that dispersion-corrected graph deep learning potentials generally (though not universally) provide a more realistic description of these compounds due to the inclusion of van der Waals attractions. In particular, their use results in systematic improvements in predicting not only the van der Waals gap but also the layer thickness in layered V-VI-VII compounds. Our results demonstrate that the combined potentials studied here, derived from a straightforward approach that neither requires fine-tuning the training nor refitting the potential parameters, can significantly improve the description of layered polar crystals.

Integrated Deep Learning Model for the Detection, Segmentation, and Morphologic Analysis of Intracranial Aneurysms Using CT Angiography.

"Just Accepted" papers have undergone full peer review and have been accepted for publication in Radiology: Artificial Intelligence. This article will undergo copyediting, layout, and proof review before it is published in its final version. Please note that during production of the final copyedited article, errors may be discovered which could affect the content. Purpose To develop a deep learning model for the morphologic measurement of unruptured intracranial aneurysms (UIAs) based on CT angiography (CTA) data and validate its performance using a multicenter dataset. Materials and Methods In this retrospective study, patients with CTA examinations, including those with and without UIAs, in a tertiary referral hospital from February 2018 to February 2021 were included as the training dataset. Patients with UIAs who underwent CTA at multiple centers between April 2021 to December 2022 were included as the multicenter external testing set. An integrated deep-learning (IDL) model was developed for UIA detection, segmentation and morphologic measurement using an nnU-net algorithm. Model performance was evaluated using the Dice similarity coefficient (DSC) and intraclass correlation coefficient (ICC), with measurements by senior radiologists serving as the reference standard. The ability of the IDL model to improve performance of junior radiologists in measuring morphologic UIA features was assessed. Results The study included 1182 patients with UIAs and 578 controls without UIAs as the training dataset (55 years [IQR, 47-62], 1,012 [57.5%] females) and 535 patients with UIAs as the multicenter external testing set (57 years [IQR, 50-63], 353 [66.0%] females). The IDL model achieved 97% accuracy in detecting UIAs and achieved a DSC of 0.90 (95%CI, 0.88-0.92) for UIA segmentation. Model-based morphologic measurements showed good agreement with reference standard measurements (all ICCs > 0.85). Within the multicenter external testing set, the IDL model also showed agreement with reference standard measurements (all ICCs > 0.80). Junior radiologists assisted by the IDL model showed significantly improved performance in measuring UIA size (ICC improved from 0.88 [0.80-0.92] to 0.96 [0.92-0.97], P < .001). Conclusion The developed integrated deep learning model using CTA data showed good performance in UIA detection, segmentation and morphologic measurement and may be used to assist less experienced radiologists in morphologic analysis of UIAs. ©RSNA, 2024.

Development and validation of the prediction score for augmented renal clearance in critically Ill Japanese adults

Abstract Background Augmented renal clearance (ARC) decreases the therapeutic concentration of drugs excreted by the kidneys in critically ill patients. Several ARC prediction models have been developed and validated; however, their usefulness in Japan has not been comprehensively investigated. Thus, we developed a unique ARC prediction model for a Japanese mixed intensive care unit (ICU) population and compared it with existing models. Methods This retrospective study enrolled a mixed ICU population in Japan from January 2019 and June 2022. The primary outcome was the development and validation of a model to predict ARC onset based on baseline information at ICU admission. Patients admitted until May 2021 were included in the training set, and external validation was performed on patients admitted thereafter. A multivariate logistic regression model was used to develop an integer-based predictive scoring system for ARC. The new model (the JPNARC score) was externally validated along with the ARC and Augmented Renal Clearance in Trauma Intensive Care (ARCTIC) scores. Results A total of 2,592 critically ill patients were enrolled initially, with 651 patients finally included after excluding 1,941 patients. The training and validation datasets comprised 456 and 195 patients, respectively. Multivariate analysis was performed to develop the JPNARC score, which incorporated age, sex, serum creatinine, and diagnosis upon ICU admission (trauma or central nervous system disease). The JPNARC score had a larger area under the receiver operating characteristic curve than the ARC and ARCTIC scores in the validation dataset (0.832, 0.633, and 0.740, respectively). Conclusions An integer-based scoring system was developed to predict ARC onset in a critically ill Japanese population and showed high predictive performance. New models designed to predict the often-unrecognized ARC phenomenon may aid in the decision-making process for upward drug dosage modifications, especially in resource- and labor-limited settings.

Model of Dynamic Mechanical Parameters and Vibration Analysis in Hot Rolling

As the core equipment of metal shaping processing, the vibration problem of rolling mill seriously affects the product quality and production efficiency. To address the problem of the limited prediction of mill vibration due to small sample data in non-steady states, we propose to predict dynamic mechanical parameters (rolling force and rolling torque) based on the TCN-LSTM step strategy transfer model. The prediction accuracies of the TCN-LSTM step strategy transfer model under 1000 sets of training data reach 95.8% and 93.2%, respectively, and at the same time, it saves the time of training and regulation of the deep learning model and can better meet the needs of online prediction. The horizontal-torsion hot rolling vibration model is further established to quantitatively analyze the relationship between process parameters and mill vibration. The experimental results show that with the vibration suppression measures of 10% reduction of the rolling speed and 10% reduction of the entrance thickness, the horizontal vibration displacement amplitude is reduced from 0.687 × 10−4 m to 0.229 × 10−4 m, and the rotational displacement amplitude is reduced from 0.0273 m to 0.0117 m, which effectively suppresses the vibration of the mill and improves the stability of the rolling process.

Automated acute skin toxicity scoring in a mouse model through deep learning.

This study presents a novel approach to skin toxicity assessment in preclinical radiotherapy trials through an advanced imaging setup and deep learning. Skin reactions, commonly associated with undesirable side effects in radiotherapy, were meticulously evaluated in 160 mice across four studies. A comprehensive dataset containing 7542 images was derived from proton/electron trials with matched manual scoring of the acute toxicity on the right hind leg, which was the target area irradiated in the trials. This dataset was the foundation for the subsequent model training. The two-step deep learning framework incorporated an object detection model for hind leg detection and a classification model for toxicity classification. An observer study involving five experts and the deep learning model, was conducted to analyze the retrospective capabilities and inter-observer variations. The results revealed that the hind leg object detection model exhibited a robust performance, achieving an accuracy of almost 99%. Subsequently, the classification model demonstrated an overall accuracy of about 85%, revealing nuanced challenges in specific toxicity grades. The observer study highlighted high inter-observer agreement and showcased the model's superiority in accuracy and misclassification distance. In conclusion, this study signifies an advancement in objective and reproducible skin toxicity assessment. The imaging and deep learning system not only allows for retrospective toxicity scoring, but also presents a potential for minimizing inter-observer variation and evaluation times, addressing critical gaps in manual scoring methodologies. Future recommendations include refining the system through an expanded training dataset, paving the way for its deployment in preclinical research and radiotherapy trials.

Development and validation of a risk predictive nomogram for colon cancer-specific mortality: a competing risk model based on the SEER database.

Utilizing the SEER database, we developed a competing risk model along with a nomogram designed for the early identification of colon cancer-specific mortality (CSM) risk. Clinical and pathological information, along with other significant data, were obtained from the SEER database. Patients were randomly divided into a training set and a validation set. We investigated the independent factors affecting CSM among colon cancer patients using univariate and multivariate analyses within a competing risk framework, ultimately developing a predictive tool for CSM in colon cancer. Involving 40,261 individuals diagnosed with colon cancer, our study included 10,397 deaths directly due to the disease and an additional 5,828 from other causes. We used a competing risk model to predict cancer-specific mortality (CSM) in these patients. For the training dataset, the model's area under the curve (AUC) for predicting 1-, 3-, and 5-year cancer-specific survival (CSS) was 0.835 (95% confidence interval [CI] 0.826 to 0.844), 0.849 (95% CI 0.843 to 0.855), and 0.843 (95% CI 0.836 to 0.850), respectively. In the validation group, the AUC values for the same time periods were 0.846 (95% CI 0.833 to 0.860), 0.853 (95% CI 0.843 to 0.862), and 0.846 (95% CI 0.835 to 0.856), respectively. In comparison, traditional survival analysis yielded higher cumulative CSM rates over time than those provided by our competing risk approach. We created a competitive risk assessment model along with a predictive tool designed to estimate CSM in patients with colon cancer. This nomogram demonstrates high accuracy and reliability, aiding medical professionals in making clinical decisions and developing patient follow-up plans.

Prediction of Dry Mouth Condition Using Radiomics Features from Tongue Diagnosis Image

Xerostomia, commonly known as dry mouth, is characterized by reduced salivary secretion, which can lead to various oral health issues and discomfort. In this paper, we propose a novel, non-invasive method for predicting xerostomia through the analysis of tongue images. To predict salivary gland secretion from tongue images, we collected images from patients who visited the hospital with complaints of dry mouth and measured their saliva secretion. Features were extracted from these tongue images, and correlation analysis was performed using machine learning techniques to assess the relationship between the extracted features and measured saliva secretion. We obtained tongue images and saliva secretion measurements from 176 patients. Images were cropped to 100 × 100 pixels, resulting in 462 features. The dataset was divided into training and test sets, consisting of 160 and 16 samples, respectively. The correlation coefficients for the training and test datasets were 0.9496 and 0.9415, respectively, while the correlation coefficient for the entire dataset was 0.9482. The estimated linear equation was y = 0.9244x + 2.1664. This study aimed to predict salivary gland secretion based on tongue images. By extracting features from color images and employing a neural network machine learning model, we estimated salivary gland secretion. With a sufficiently large dataset of tongue images, further advancements in regression analysis using deep learning techniques could enhance the accuracy of these predictions.

Discovery of Alloy Catalysts for Ammonia Decomposition by Machine Learning-Based Prediction of Adsorption Energies

Ammonia decomposition has gained significant attention as an eco-friendly method for hydrogen production because it creates no carbon dioxide emissions. While Ru catalysts are known for their high activity in ammonia decomposition, their high cost makes them uneconomical for commercial use. Therefore, it is essential to explore novel alloy catalysts composed of inexpensive elements with high catalytic performance. Nitrogen adsorption energies serve as key descriptors indicating the catalytic performance for ammonia decomposition, and first-principle calculations can compute these energies. However, the screening of numerous alloy catalyst candidates through extensive first-principle calculations and experimental validations remains time-consuming due to the vast number of potential candidates. To address this, artificial intelligence and machine learning models are being developed to quickly predict catalyst performance, efficiently searching for promising catalyst candidates. In this study, we developed a machine-learning-based method to rapidly predict nitrogen adsorption energies using a graph-based artificial neural network, thereby efficiently searching for novel catalysts for ammonia decomposition. Our training dataset included the nitrogen adsorption energies of 30 pure transition metal catalyst candidates, as well as binary alloy catalyst candidates, including core-shell and intermetallic compounds. As a result, we successfully identified 12 catalyst candidates composed of inexpensive elements that are likely to exhibit catalytic performance comparable to Ru catalysts.

Enhancing the Rainfall Forecasting Accuracy of Ensemble Numerical Prediction Systems via Convolutional Neural Networks

Abstract Ensemble prediction systems are commonly used to demonstrate the potential uncertainty of weather forecasts. These systems also help provide weather predictions to prepare for disasters. Specifically, a type of prediction called a quantitative precipitation forecast (QPF) is calculated from the average of multiple forecasts. The probability-matched mean (PMM) method is used to improve these QPF predictions when they underestimate rainfall. However, the PMM method can exhibit limitations when dealing with certain types of rain patterns. To address this issue, this study focuses on improving short-term heavy rainfall predictions using an artificial intelligence (AI) algorithm that combines deep neural networks (DNNs), including convolutional neural networks (CNNs), with a space-based attention mechanism (convolutional block attention module [CBAM]). Four experiments were conducted to evaluate the new method, including those performed to optimize the timing of a 24-hour QPF model, adjust the training dataset, and refine the training algorithm. Two specific weather events were assessed: rainfall influenced by southwest winds after typhoons and afternoon thunderstorm rainfall. A comparison of the results obtained via the root mean square error (RMSE) and structural similarity index measure (SSIM) reveals that the accuracy and distribution of the QPF predictions significantly improved over those of the PMM method. Compared with the PMM method, our approach can reduce the RMSE from 77.51 to 19.52 in the Mei-yu case, an improvement of approximately 74.82%. The SSIM also increased from 0.33 to 0.56, indicating a 70.9% enhancement. Overall, the new approach successfully enhances rainfall prediction accuracy via AI techniques and has the potential to be applied in disaster preparedness operations.

Using CT images to assist the segmentation of MR images via generalization: Segmentation of the renal parenchyma of renal carcinoma patients.

Developing deep learning models for segmenting medical images in multiple modalities with less data and annotation is an attractive and challenging task, which was previously discussed as being accomplished by complex external frameworks for bridging the gap between different modalities. Exploring the generalization ability of networks in medical images in different modalities could provide more simple and accessible methods, yet comprehensive testing could still be needed. To explore the feasibility and robustness of using computed tomography (CT) images to assist the segmentation of magnetic resonance (MR) images via the generalization, in the segmentation of renal parenchyma of renal cell carcinoma (RCC) patients. Nephrographic CT images and fat-suppressed T2-weighted (fs-T2W) images were retrospectively collected. The pure CT dataset included 116 CT images. Additionally, 240 MR images were randomly divided into subsets A and B. From subset A, three training datasets were constructed, each containing 40, 80, and 120 images, respectively. Similarly, three datasets were constructed from subset B. Subsequently, datasets with mixed modality were created by combining these pure MR datasets with the 116 CT images. The 3D-UNET models for segmenting the renal parenchyma in two steps were trained using these 13 datasets: segmenting kidneys and then the renal parenchyma. These models were evaluated in internal MR (n=120), CT (n=65) validation datasets, and an external validation dataset of CT (n=79), using the mean of the dice similarity coefficient (DSC). To demonstrate the robustness of generalization ability over different proportions of modalities, we compared the models trained with mixed modality in three different proportions and pure MR, using repeated measures analysis of variance (RM-ANOVA). We developed a renal parenchyma volume quantification tool by the trained models. The mean differences and Pearson correlation coefficients between the model segmentation volume and the ground truth segmentation volume were calculated for its evaluation. The mean DSCs of models trained with 116 data in CT in the validation of MR were 0.826, 0.842, and 0.953, respectively, for the predictions of kidney segmentation model on whole image, renal parenchymal segmentation model on kidneys with RCC and without RCC. For all models trained with mixed modality, the means of DSC were above 0.9, in all validations of CT and MR. According to the results of the comparison between models trained with mixed modality and pure MR, the means of DSC of the former were significantly greater or equal to the latter, at all three different proportions of modalities. The differences of volumes were all significantly lower than one-third of the volumetric quantification error of a previous method, and the Pearson correlation coefficients of volumes were all above 0.96 on kidneys with and without RCC of three validations. CT images could be used to assist the segmentation of MR images via the generalization, with or without the supervision of MR data. This ability showed acceptable robustness. A tool for accurately measuring renal parenchymal volume on CT and MR images was established.

Identification of novel markers for neuroblastoma immunoclustering using machine learning

BackgroundDue to the unique heterogeneity of neuroblastoma, its treatment and prognosis are closely related to the biological behavior of the tumor. However, the effect of the tumor immune microenvironment on neuroblastoma needs to be investigated, and there is a lack of biomarkers to reflect the condition of the tumor immune microenvironment.MethodsThe GEO Database was used to download transcriptome data (both training dataset and test dataset) on neuroblastoma. Immunity scores were calculated for each sample using ssGSEA, and hierarchical clustering was used to categorize the samples into high and low immunity groups. Subsequently, the differences in clinicopathological characteristics and treatment between the different groups were examined. Three machine learning algorithms (LASSO, SVM-RFE, and Random Forest) were used to screen biomarkers and synthesize their function in neuroblastoma.ResultsIn the training set, there were 362 samples in the immunity_L group and 136 samples in the immunity_H group, with differences in age, MYCN status, etc. Additionally, the tumor microenvironment can also affect the therapeutic response of neuroblastoma. Six characteristic genes (BATF, CXCR3, GIMAP5, GPR18, ISG20, and IGHM) were identified by machine learning, and these genes are associated with multiple immune-related pathways and immune cells in neuroblastoma.ConclusionsBATF, CXCR3, GIMAP5, GPR18, ISG20, and IGHM may serve as biomarkers that reflect the conditions of the immune microenvironment of neuroblastoma and hold promise in guiding neuroblastoma treatment.

Coherence and Intensity Statistical Mapping of Earthquake Affected Areas using Sentinel-1 Images

Abstract. The January 1, 2024, Noto Peninsula earthquake left many devastated areas. Right after the event, aerial photography provided the initial assessment but covered only specific areas. Satellite images with optical sensors that are freely available are limited by spatial resolution and oftentimes covered by cloud. The Sentinel-1 Synthetic Aperture Radar (SAR) due to its all-weather sensing capability proved to be useful in mapping the extent of the affected areas. This study mapped Wajima City where earthquake aftereffects were severe as reported using coherence and intensity mapping. Pre- and post-event images were used to rapidly identify affected areas. Based on the result, taking the coherence of one pre- and one post-event images can give an impression of wide earthquake damage. The coherence of two post-event images compared with two pre-event images provides a better estimate of affected areas. Taking multiple pre- and post- event images improved the map because the large variation of the intensity is minimized through time-series averaging. Using a simple RGB composite, the affected areas were mapped. Threshold mapping was also used to extract collapsed buildings/houses using a training dataset. The mean coherence difference and mean intensity difference between pre- and post-event images were the two variables used. The computed minimum threshold for the mean coherence difference was 0.35. However, the average not the minimum of the mean intensity difference of 3.0 was used as initial value. Using mean coherence difference&gt;=0.35 gave a high accurate prediction of collapsed buildings at 73.47% but also has false identification of 30.95%. To negate the overprediction, the mean intensity difference&lt;=4.0 was integrated. The result lowered the overprediction to 20.75% but also lowered the accuracy to 64.97%. This assessment was only conducted in the fire-razed morning market in Wajima City.

A review of artificial intelligence in wound care

Our aging population, diabetes, and obesity have fueled the growth of chronic wounds seen throughout the world. Often, wounds are a marker of poor health that leads to increased mortality rates. However, the diagnosis and treatment of these wounds are challenging. Incorrectly differentiating between chronic wounds and other complex conditions can lead to adverse events. Artificial intelligence (AI) has been shown to offer some early benefits, and we hypothesized that it may enhance wound care but also carry some notable risks. We performed a detailed search using PubMed, Scopus, Cumulated Index in Nursing and Allied Health Literature, and Web of Science for AI applications in wound care. AI was found to be applied to wound diagnosis and characterization, wound monitoring for tissue change, daily therapy, and prevention and prognostics. AI made for more efficient and accurate wound assessments, less painful assessments of chronic wounds, more personalized treatment, and improved prognostic prediction capabilities. AI also allowed for more precise at-home observation and care, facilitating earlier wound treatment as needed. Challenges associated with AI included how to best allocate AI-assisted technologies equitably, how to safely maintain patient data, and how to diversify datasets for algorithm training. Because the algorithms are not transparent, validating findings may be challenging. AI presents a powerful tool in several aspects of advanced wound care and has the potential to improve diagnoses, accelerate healing, reduce pain, and improve the cost-effectiveness of wound care. More research needs to be done into how to best incorporate AI into daily clinical practice while keeping clinicians aware of the potential risks of using these evolving technologies.

CAD-PsorNet: deep transfer learning for computer-assisted diagnosis of skin psoriasis

Psoriasis, being a chronic, inflammatory, lifelong skin disorder, has become a major threat to the human population. The precise and effective diagnosis of psoriasis continues to be difficult for clinicians due to its varied nature. In northern India, the prevalence of psoriasis among adult population ranges from 0.44 to 2.8%. Chronic plaque psoriasis accounts for over 90% of cases. This study utilized a dataset of 325 raw images collected from a reputable local hospital using a digital camera under uniform lighting conditions. These images were processed to generate 496 image patches (both diseased and normal), which were then normalized and resized for model training. An automated psoriasis image recognition framework was developed using four state-of-the-art deep transfer learning models: VGG16, VGG19, MobileNetV1, and ResNet-50. The convolutional layers adopted various edge, shape, and color filters to generate the feature map for psoriasis detection. Each pre-trained model was adapted with two dense layers, one dropout layer, and one output layer to classify input images. Among these models, MobileNetV1 achieved the best performance, with 94.84% sensitivity, 89.37% specificity, and 97.24% overall accuracy. Hyper-parameter tuning was performed using grid search to optimize learning rates, batch sizes, and dropout rates. The AdaGrad (Adaptive gradient)) optimizer was chosen for its adaptive learning rate capabilities, facilitating quicker convergence in model performance. Consequently, the methodology’s performance improved to 94.25% sensitivity, 96.42% specificity, and 99.13% overall accuracy. The model’s performance was also compared with non-machine learning-based diagnostic methods, yielding a Dice coefficient of 0.98. However, the model’s effectiveness is dependent upon high-quality input images, as poor image conditions may affect accuracy, and it may not generalize well across diverse demographics or psoriasis variations, highlighting the need for varied training datasets for robustness.

Impact of Adverse Weather and Image Distortions on Vision-Based UAV Detection: A Performance Evaluation of Deep Learning Models

Unmanned aerial vehicle (UAV) detection in real-time is a challenging task despite the advances in computer vision and deep learning techniques. The increasing use of UAVs in numerous applications has generated worries about possible risks and misuse. Although vision-based UAV detection methods have been proposed in recent years, a standing open challenge and overlooked issue is that of adverse weather. This work is the first, to the best of our knowledge, to investigate the impact of adverse weather conditions and image distortions on vision-based UAV detection methods. To achieve this, a custom training dataset was curated with images containing a variety of UAVs in diverse complex backgrounds. In addition, this work develops a first-of-its-kind dataset, to the best of our knowledge, with UAV-containing images affected by adverse conditions. Based on the proposed datasets, a comprehensive benchmarking study is conducted to evaluate the impact of adverse weather and image distortions on the performance of popular object detection methods such as YOLOv5, YOLOv8, Faster-RCNN, RetinaNet, and YOLO-NAS. The experimental results reveal the weaknesses of the studied models and the performance degradation due to adverse weather, highlighting avenues for future improvement. The results show that even the best UAV detection model’s performance degrades in mean average precision (mAP) by −50.62 points in torrential rain conditions, by −52.40 points in high noise conditions, and by −77.0 points in high motion blur conditions. To increase the selected models’ resilience, we propose and evaluate a strategy to enhance the training of the selected models by introducing weather effects in the training images. For example, the YOLOv5 model with the proposed enhancement strategy gained +35.4, +39.3, and +44.9 points higher mAP in severe rain, noise, and motion blur conditions respectively. The findings presented in this work highlight the advantages of considering adverse weather conditions during model training and underscore the significance of data enrichment for improving model generalization. The work also accentuates the need for further research into advanced techniques and architectures to ensure more reliable UAV detection under extreme weather conditions and image distortions.

Tra ined Wi thout My C onsent: Detecting Code Inclusion In Language Models Trained on Code

Code auditing ensures that the developed code adheres to standards, regulations, and copyright protection by verifying that it does not contain code from protected sources. The recent advent of Large Language Models (LLMs) as coding assistants in the software development process poses new challenges for code auditing. The dataset for training these models is mainly collected from publicly available sources. This raises the issue of intellectual property infringement as developers’ codes are already included in the dataset. Therefore, auditing code developed using LLMs is challenging, as it is difficult to reliably assert if an LLM used during development has been trained on specific copyrighted codes, given that we do not have access to the training datasets of these models. Given the non-disclosure of the training datasets, traditional approaches such as code clone detection are insufficient for asserting copyright infringement. To address this challenge, we propose a new approach, TraWiC; a model-agnostic and interpretable method based on membership inference for detecting code inclusion in an LLM’s training dataset. We extract syntactic and semantic identifiers unique to each program to train a classifier for detecting code inclusion. In our experiments, we observe that TraWiC is capable of detecting 83.87% of codes that were used to train an LLM. In comparison, the prevalent clone detection tool NiCad is only capable of detecting 47.64%. In addition to its remarkable performance, TraWiC has low resource overhead in contrast to pair-wise clone detection that is conducted during the auditing process of tools like CodeWhisperer reference tracker, across thousands of code snippets.

Employing Transfer Learning in Land-use Land-cover for Risk Management

Abstract. In disaster management, land-use land-cover (LULC) maps are vital for real-time situational awareness and coordinated responses. These maps aid in coordinating field operations, guiding rescue teams, and identifying high vulnerability areas. They ensure accurate spatial information sharing and management during disaster response efforts. Deep transfer learning models have emerged as powerful tools for LULC classification, addressing challenges like insufficient training data and complex classification tasks. In this research instead of building networks from scratch, pre-trained networks that used EuroSAT benchmark dataset are employed. Several deep learning models including 1-layer CNN, 4-layers CNN, VGG16 and an improved ResNet-50 network as proposed method are considered and compared in this study. The results were analyzed in both quantitative and qualitative ways. In the quantitative mode, the measurement criteria such as Overall Accuracy (OA), F1Score, Precision and Recall were calculated, and in the qualitative mode, the class diagram was drawn in the feature space to check the separability of the classes. Finally, the results show high overall accuracy score of 95.9% indicating the high potential of our proposed network for ResNet-50. The proposed method has resolved insufficient training dataset by implementing data augmentation that it can be solved the problem of lack dataset.

LEAVES: An Expandable Light-curve Data Set for Automatic Classification of Variable Stars

With the increasing amount of astronomical observation data, it is an inevitable trend to use artificial intelligence methods for automatic analysis and identification of light curves for full samples. However, data sets covering all known classes of variable stars that meet all research needs are not yet available. There is still a lack of standard training data sets specifically designed for any type of light-curve classification, but existing light-curve training sets or data sets cannot be directly merged into a large collection. Based on the open data sets of the All-Sky Automated Survey for SuperNovae, Gaia, and Zwicky Transient Facility, we construct a compatible light-curve data set named LEAVES for automated recognition of variable stars, which can be used for training and testing new classification algorithms. The data set contains a total of 977,953 variable and 134,592 nonvariable light curves, in which the supported variables are divided into six superclasses and nine subclasses. We validate the compatibility of the data set through experiments and employ it to train a hierarchical random forest classifier, which achieves a weighted average F1-score of 0.95 for seven-class classification and 0.93 for 10-class classification. Experimental results prove that the classifier is more compatible than the classifier established based on a single band and a single survey, and has wider applicability while ensuring classification accuracy, which means it can be directly applied to different data types with only a relatively small loss in performance compared to a dedicated model.

Hybrid real-time wave forecasting model combining Gaussian process regression and neural networks

To safely and effectively conduct offshore operations, a real-time wave forecast model that can accurately and rapidly forecast waves hours or days in advance is highly valuable. Recent studies have investigated models with neural networks (NNs) and have demonstrated their advantages in terms of forecasting speed and accuracy. However, NNs are limited by their requirement for a large training dataset, which can hinder the construction of the model if sufficient training data are unavailable. Therefore, this study constructed a hybrid real-time wave forecast model by combining an NN model and Gaussian process regression (GPR) model. The objective was to obtain reasonably accurate forecasts that were more accurate than those from individual NN models even when sufficient training data for the NN model was unavailable. To derive an optimal prediction, the values predicted by the NN and GPR models were combined by utilizing the standard deviation of the latter and considering the accuracy of each model. Consequently, predictions that were more accurate compared to those of the individual models for an entire year were obtained. This improvement was particularly significant for predicting relatively large wave heights, as indicated by the daily maximum wave heights. Additionally, various accuracy evaluation metrics demonstrated that despite using a small training dataset, the optimal prediction of the hybrid model was still superior to those of the individual models for predicting the daily maximum wave heights.

VTSIM: Attention‐Based Recurrent Neural Network for Intersection Vehicle Trajectory Simulation

ABSTRACTSimulating vehicle trajectories at intersections is one of the challenging tasks in traffic simulation. Existing methods are often ineffective due to the complexity and diversity of lane topologies at intersections, as well as the numerous interactions affecting vehicle motion. To address this issue, we propose a deep learning based vehicle trajectory simulation method. First, we employ a vectorized representation to uniformly extract features from traffic elements such as pedestrians, vehicles, and lanes. By fusing all factors that influence vehicle motion, this representation makes our method suitable for a variety of intersections. Second, we propose a deep learning model, which has an attention network to dynamically extract features from the surrounding environment of the vehicles. To address the issue of vehicles continuously entering and exiting the simulation scene, we employ an asynchronous recurrent neural network for the extraction of temporal features. Comparative evaluations against existing rule‐based and deep learning‐based methods demonstrate our model's superior simulation accuracy. Furthermore, experimental validation on public datasets demonstrates that our model can simulate vehicle trajectories among the urban intersections with different topologies including those not present in the training dataset.