Convolutional Network Research Articles

Visual Piezoresistive Dual‐Response Sensor Based on CaZnOS: Mn Mechanoluminescence Materials

AbstractThe ability to achieve real‐time movement visualization in piezoresistive sensors remains a challenge. A visual piezoresistive sensor to perceive the intensity of mechanical stimuli and visible spatial location information is designed based on the mechanoluminescence material CaZnOS: Mn. The linearity, detection range, sensitivity, and stability of the sensor are tested, and the sensing mechanism of the sensor is discussed, and the relationship between force, resistance, and light intensity is established. A 5 × 5 sensor array is prepared to realize the visual detection of dynamic force trajectory, and combined with a convolutional neural network and random forest algorithm, the human writing number and pressure characteristics are recognized, and the writing path and handwriting of the robot arm are controlled by multi‐feature input. The experimental results show that the machine learning algorithm is very reliable with an accuracy of 98.33% for digit recognition and 97.21% for identity recognition. The visual piezoresistive pressure sensor provides a new idea for the visualization of flexible pressure and promotes the development of flexible sensors towards integration and intelligence.

Using data-driven models to simulate the performance of surfactants in reducing heavy oil viscosity.

There is a substantial body of literature exploring the challenges associated with exploring and exploiting these underground resources. Unconventional resources, particularly heavy oil reservoirs, are critical for meeting ever-increasing global energy demand. By injecting surfactants into heavy oil, chemically enhanced oil recovery (EOR) may enable emulsification, which may reduce the viscosity of heavy oil and facilitate extraction and transportation. In this work, a large experimental dataset, containing 2020 data points, was extracted from the literature for modeling oil-in-water (O/W) emulsion viscosity using machine learning (ML) methods. The algorithms used pressure, temperature, salinity, surfactant concentration, type of surfactant, shear rate, and crude oil density as inputs. For this purpose, five ML algorithms were selected and optimized, including adaptive boosting (AB), convolutional neural network (CNN), ensemble learning (EL), artificial neural network (ANN), and decision tree (DT). A combined simulated annealing (CSA) method was utilized to optimize all algorithms. With AARE, R2, MAE, MSE, and RMSE values of 8.982, 0.996, 0.004, 0.0002, and 0.0132, respectively, the ANN predictor exhibited higher accuracy in predicting O/W emulsion viscosity for total data (train and test subsets combined). A Monte-Carlo sensitivity analysis was also performed to determine the impact of input features on the model output. By using the proposed ML predictor, expensive and time-consuming experiments can be eliminated and emulsion viscosity predictions can be expedited without the need for costly experiment.

Optimal Feature Selection and Classification for Parkinson’s Disease Using Deep Learning and Dynamic Bag of Features Optimization

Parkinson’s Disease (PD) is a neurological condition that worsens with time and is characterized bysymptoms such as cognitive impairment andbradykinesia, stiffness, and tremors. Parkinson’s is attributed to the interference of brain cells responsible for dopamine production, a substance regulating communication between brain cells. The brain cells involved in dopamine generation handle adaptation and control, and smooth movement. Convolutional Neural Networks are used to extract distinctive visual characteristics from numerous graphomotor sample representations generated by both PD and control participants. The proposed method presents an optimal feature selection technique based on Deep Learning (DL) and the Dynamic Bag of Features Optimization Technique (DBOFOT). Our method combines neural network-based feature extraction with a strong optimization technique to dynamically choose the most relevant characteristics from biological data. Advanced DL architectures are then used to classify the chosen features, guaranteeing excellent computational efficiency and accuracy. The framework’s adaptability to different datasets further highlights its versatility and potential for further medical applications. With a high accuracy of 0.93, the model accurately identifies 93% of the cases that are categorized as Parkinson’s. Additionally, it has a recall of 0.89, which means that 89% of real Parkinson’s patients are accurately identified. While the recall for Class 0 (Healthy) is 0.75, meaning that 75% of the real healthy cases are properly categorized, the precision decreases to 0.64 for this class, indicating a larger false positive rate.

Facial Image expression recognition and prediction system.

Facial expression recognition system is an advanced technology that allows machines to recognize human emotions based on their facial expressions. In order to develop a robust prediction model, this research work proposes three distinct architectural models to produce a facial expression prediction system that looks like this: The first model is on using a support vector machine to carry out a classification task. As a follow-up to the second model, an attempt was made to create a Convolution Neural Network (CNN) using the VGG-NET (Visual Geometry Group Network). Following analysis of the results, an attempt was made to enhance the outcome using the third model, which used convolutional sequential layers linked to seven distinct expressions, and an inference was drawn based on loss and accuracy metric behavior. We will use a dataset of human picture facial images in this research, which has more than 35500 facial photographs and represents seven different types of facial expressions. We will analyze our data and make every effort to remove as much noise as we can before feeding that information to our model. We use the confusion matrix to assess the model's performance after it has been implemented effectively. To demonstrate the effectiveness of our model architecture, we will generate bar graphs and scatter plots for each model to display model loss and accuracy. The output of this model is visualized with actual class and predictive class and the result has a graphical representation for each and every output facial Images which makes our recognition system user-friendly.

ECG-based machine learning model for AF identification in patients with first ischemic stroke.

The recurrence rate of strokes associated with atrial fibrillation (AF) can be substantially reduced through the administration of oral anticoagulants. However, previous studies have not demonstrated a clear benefit from the universal application of oral anticoagulants in patients with embolic stroke of undetermined source. Timely detection of AF remains a challenge in patients with stroke. This study aims to develop a convolutional neural network (CNN) model to accurately identify patients with AF using a 12-lead sinus-rhythm electrocardiogram (ECG) recorded around the time of the first ischemic stroke. Additionally, this study also evaluates the model's ability to predict future occurrence of AF. A CNN model was trained with ECG data from patients at Taipei Veterans General Hospital. External validation was performed on ischemic stroke patients from National Taiwan University Hospital. The model's performance was assessed for detecting AF at the stroke event and predicting future AF occurrences. The model demonstrated an area under curve (AUC) of 0.91 for internal validation and 0.69 for external validation in identifying AF at the stroke event, with sensitivity and negative predictive value both achieving 97%. Kaplan-Meier survival analysis of patients without a prior diagnosis of AF revealed a significant increase in future AF incidence among the high-risk group identified by the model (adjusted hazard ratio: 4.06; 95% confidence interval: 2.74-6.00). The CNN model effectively identifies AF in stroke patients using 12-lead ECGs and predicts future AF events, facilitating early anticoagulation therapy and potentially reducing recurrent stroke risk. Further prospective studies are warranted to confirm these findings.

Abstract 4120990: Classification of Echocardiography Videos Using TimeSformer for Detecting Incipient Heart Failure in Asymptomatic Patients with Normal Ejection Fraction and Patients with Heart Failure

Background: Recent advancements have seen deep learning models help differentiate echocardiography images of patients with heart failure with preserved ejection fraction (HFpEF) from normal controls. Our aim was to develop a model capable of detecting early signs of heart failure in asymptomatic patients with a normal ejection fraction. Methods: We employed the TimeSformer, a video transformer model that classifies video data using a novel attention-based mechanism. This self-attention mechanism that diverges from traditional convolutional neural networks (CNNs). It focuses on relevant parts of the video across both space and time, split into spatial attention, which processes each frame individually, and temporal attention, which integrates information across different frames. The training and validation of the TimeSformer model were conducted on the same dataset of echocardiography videos from 50 normal controls and 50 patients diagnosed with HFpEF, employing 5-fold cross-validation to ensure robust performance evaluation. Results: The TimeSformer model effectively identified HFpEF in patients, as all diagnosed with HFpEF were flagged as abnormal. The echocardiography assessment, along with NT pro BNP levels, supported the diagnoses, with patients showing NT pro BNP levels of 1016±32 pg/ml. Conversely, 46 out of 50 normal controls were correctly identified, with their NT pro BNP levels averaging 52±12 pg/ml. These controls remained asymptomatic. Conclusions: The TimeSformer model demonstrated capability in identifying subtle deviations indicative of incipient heart failure in videos of normal controls, despite normal NT pro BNP levels. This suggests potential for early detection of heart failure in asymptomatic individuals. Further longitudinal studies are necessary to determine whether individuals identified as abnormal develop heart failure symptoms subsequently.

Analysis of Cardiovascular Disease Classification Through Deep Learning Approach

Multiple cardiovascular disease classification from Electrocardiogram (ECG) signal is necessary for efficient and fast remedial treatment of the patient. This paper presents a method to classify multiple heart diseases using one dimensional deep convolutional neural network (CNN) where a modified ECG signal is given as an input signal to the network. Each ECG signal is first decomposed through Empirical Mode Decomposition (EMD) and higher order Intrinsic Mode Functions (IMFs) is combined to form a modified ECG signal. It is believed that the use of EMD would provide a broader range of information and can provide denoising performance. This processed signal is fed into the CNN architecture that classifies the record according to cardiovascular diseases using soft max regress or at the end of the network. It is observed that the CNN architecture learns the inherent features of the modified ECG signal better in comparison with the raw ECG signal. The method is applied on three publicly available ECG databases and it is found to be superior to other approaches in terms of classification accuracy. In MIT-BIH, St. Petersburg, PTB databases the proposed method achieves maximum accuracy of 0.9770, 0.9971 and 0.9871 respectively.

Robust-DefReg: A Robust Coarse to Fine Non-rigid Point Cloud Registration Method based on Graph Convolutional Neural Networks

Abstract Point cloud registration is a critical process in computer vision and measurement science, aimed at determining transformations between corresponding sets of points for accurate spatial alignment. In particular, non-rigid registration involves estimating flexible transformations that map a source point cloud to a target point cloud, even under conditions of stretching, compression, or other complex deformations. This task becomes especially challenging when addressing measurement-specific issues like varying degrees of deformation, noise, and outliers, all of which can impact measurement accuracy and reliability.
This paper introduces Robust-DefReg, a novel method for non-rigid point cloud registration that applies graph convolutional networks (GCNNs) within a coarse-to-fine registration framework. This end-to-end pipeline harnesses global feature learning to establish robust correspondences and precise transformations, enabling high accuracy across different deformation scales and noise levels. A key contribution of Robust-DefReg is its demonstrated resilience to various challenges, such as substantial deformations, noise, and outliers, factors often underreported in existing registration literature.
In addition, we present SynBench, a comprehensive benchmark dataset specifically designed for evaluating non-rigid point cloud registration in realistic measurement scenarios. Unlike previous datasets, SynBench incorporates a range of challenges, making it a valuable tool for the fair assessment of registration methods in measurement applications. Experimental results on SynBench and additional datasets show that Robust-DefReg consistently outperforms state-of-the-art methods, offering higher registration accuracy and robustness, even with up to 45% outliers.
SynBench and the Robust-DefReg source code are publicly accessible for further research and development at https://doi.org/10.11588/data/R9IKCF and https://github.com/m-kinz/Robust-DefReg, respectively.

Dynamic Spatio-Temporal Hypergraph Convolutional Network for Traffic Flow Forecasting

Graph convolutional networks (GCN) are an important research method for intelligent transportation systems (ITS), but they also face the challenge of how to describe the complex spatio-temporal relationships between traffic objects (nodes) more effectively. Although most predictive models are designed based on graph convolutional structures and have achieved effective results, they have certain limitations in describing the high-order relationships between real data. The emergence of hypergraphs breaks this limitation. A dynamic spatio-temporal hypergraph convolutional network (DSTHGCN) model is proposed in this paper. It models the dynamic characteristics of traffic flow graph nodes and the hyperedge features of hypergraphs simultaneously, achieving collaborative convolution between graph convolution and hypergraph convolution (HGCN). On this basis, a hyperedge outlier removal mechanism (HOR) is introduced during the process of node information propagation to hyper-edges, effectively removing outliers and optimizing the hypergraph structure while reducing complexity. Through in-depth experimental analysis on real-world datasets, this method has better performance compared to other methods.

Abstract Su803: Sudden Cardiac Arrest Prediction via Deep Learning Electrocardiogram Analysis

Background: Sudden cardiac arrest (SCA) is a potentially fatal event that often occurs without prior indications. Hypothesis: It was hypothesized that electrocardiogram (ECG) data could be used in conjunction with Deep Learning (DL) algorithms to predict the occurrence of SCA’s. Aims: To improve SCA outcomes and enable preventative strategies, the ECG data from the Nightingale Open Science - Subtyping Cardiac Arrest dataset were utilized to create a DL model to serve as a screening tool for sudden cardiac arrest. Methods: A publicly-available dataset containing ten seconds of 12-lead ECGs from individuals who had a SCA and persons who did not have a SCA, and information about time from ECG to arrest, and age and sex were utilized for individualized prediction of SCA. Subsets of the initial data were used to train, validate, and test deep convolution neural network models that processed cardiac cycles from single-lead ECG voltage waveforms. Results: The cohort comprised 221 (mean age: 68.5 and #females: 75) patients who experienced SCA and 1046 controls (mean age: 69.7 and #females: 497) who did not have a cardiac arrest. The SCA ECG-DL base model, with ECGs within one day and with age and sex data, had an area under the receiver operating curve (AUROC) of 0.774 during hold-out testing for discrimination of subsequent SCA. With sensitivity set at 95%, the base model specificity of the SCA ECG-DL model was 31%. Gradient-weighted class activation mapping showed that the SCA ECG-DL model relied most heavily on the QRS complex to make predictions. The performance of the SCA ECG-DL model was similar removing age and sex data (AUROC 0.775) and less reliable when predicting SCA within one month (AUROC 0.734) or between one month and one year (AUROC 0.574). Conclusion: DL interpretation of ECG data is a promising means of screening for SCA, and this method explains differences in SCA’s due to age and sex. Model performance improved when ECGs were obtained at shorter intervals to the incident SCA event, and SCA prediction was more dependent upon QRS complex data than other temporal segments of the ECG.

Quantum machine learning enhanced laser speckle analysis for precise speed prediction.

Laser speckle contrast imaging (LSCI) is an optical technique used to assess blood flow perfusion by modeling changes in speckle intensity, but it is generally limited to qualitative analysis due to difficulties in absolute quantification. Three-dimensional convolutional neural networks (3D CNNs) enhance the quantitative performance of LSCI by excelling at extracting spatiotemporal features from speckle data. However, excessive downsampling techniques can lead to significant information loss. To address this, we propose a hybrid quantum-classical 3D CNN framework that leverages variational quantum algorithms (VQAs) to enhance the performance of classical models. The proposed framework employs variational quantum circuits (VQCs) to replace the 3D global pooling layer, enabling the model to utilize the complete 3D information extracted by the convolutional layers for feature integration, thereby enhancing velocity prediction performance. We perform cross-validation on experimental LSCI speckle data and demonstrate the superiority of the hybrid models over their classical counterparts in terms of prediction accuracy and learning stability. Furthermore, we evaluate the models on an unseen test set and observe that the hybrid models outperform the classical models with up to 14.8% improvement in mean squared error (MSE) and up to 26.1% improvement in mean absolute percentage error (MAPE) evaluation metrics. Finally, our qualitative analysis shows that the hybrid models offer substantial improvements over classical models in predicting blood flow at both low and high velocities. These results indicate that the hybrid models possess more powerful learning and generalization capabilities.

Abstract 4131622: Opportunistic Screening of Chronic Liver Disease With Deep Learning Enhanced Echocardiography

Introduction: Chronic liver disease affects more than 1.5 billion adults worldwide, but the majority of cases are asymptomatic and undiagnosed. Echocardiography is broadly performed and visualizes the liver; however, this information is not diagnostically leveraged. Hypothesis and Aims: We hypothesized that a deep-learning algorithm can detect chronic liver diseases using subcostal echocardiography images that contains hepatic tissue. To develop and evaluate a deep learning algorithm on subcostal echocardiography videos to enable opportunistic screening for chronic liver disease. Methods: We identified adult patients who received echocardiography and abdominal imaging (either abdominal ultrasound or abdominal magnetic resonance imaging) with ≤30 days between tests. A convolutional neural network pipeline was developed to predict the presence of cirrhosis or steatotic liver disease (SLD) using echocardiogram images. The model performance was evaluated in a held-out test dataset, dataset in which diagnosis was made by magnetic resonance imaging, and external dataset. Results: A total of 2,083,932 echocardiography videos (51,608 studies) from Cedars-Sinai Medical Center (CSMC) were used to develop EchoNet-Liver, an automated pipeline that identifies high quality subcostal images from echocardiogram studies and detects presence of cirrhosis or SLD. In a total of 11,419 quality-controlled subcostal videos from 4,849 patients, a chronic liver disease detection model was able to detect the presence of cirrhosis with an AUC of 0.837 (0.789 - 0.880) and SLD with an AUC of 0.799 (0.758 - 0.837). In a separate test cohort with paired abdominal MRIs, cirrhosis was detected with an AUC of 0.726 (0.659-0.790) compared to MR elastography and SLD was detected with an AUC of 0.704 (0.689-0.718). In the external test cohort of 66 patients (n = 130 videos), the model detected cirrhosis with an AUC of 0.830 (0.738 - 0.909) and SLD with an AUC of 0.768 (0.652 – 0.875). Conclusions: Deep learning assessment of clinically indicated echocardiography enables opportunistic screening of SLD and cirrhosis. Application of this algorithm may identify patients who may benefit from further diagnostic testing and treatment for hepatic disease.

Spatiotemporal feature extraction method combining common spatial pattern and hybrid spatial‐temporal attention‐Net in motor imagery–brain‐computer interface system

AbstractIn recent years, motor imagery (MI) based on brain‐computer interface (BCI) has gained the attention of researchers and been widely used in many fields, such as medical rehabilitation and entertainment. The temporal and spatial features of electroencephalography (EEG) are very important for MI‐BCI classification. This study proposed a better spatiotemporal feature extraction method by combining the common spatial pattern (CSP) with a hybrid spatiotemporal attention convolutional neural network (HSTA‐Net) model. The method first intercepts the MI‐EEG into multiple time windows and projects them into the feature space and feeds into the HSTA‐Net in parallel. Subsequently, the scaled dot product attention module and multi‐head attention module are used to extract spatial feature attention. Finally, the features in multiple time windows obtained through HSTA‐Net are integrated and used for classification. The proposed method achieves a classification accuracy of 77.3% on the BCI Competition IV2a dataset. The experimental results show that the proposed model has better classification performance. The CSP‐HSTA‐Net model can quickly adapt to the distribution of MI‐EEG data during the training process, which increases the interclass distance of the extracted features and decreases its intraclass distance; it can better accomplish the MI‐BCI classification task.

Abstract 4135928: Externally Validated Deep Learning Model for Patent Ductus Arteriosus Detection by Echocardiography in Preterm Infants

Introduction: Patent ductus arteriosus (PDA) is a common form of congenital heart disease in premature infants and a source of significant morbidity. Echocardiography is the mainstay modality for diagnosis and monitoring but is resource-intensive and requires expertise for interpretation. Aims: To develop and externally validate a deep learning model to identify PDA in preterm infants by echocardiography. Methods: We trained, validated, and tested a convolutional neural network to detect PDA in raw echocardiogram clips from infants (gestational age <37 weeks) with and without PDAs and no significant additional congenital heart disease at the Medical University of South Carolina (MUSC). For training and validation, we employed a 12-fold cross-validation procedure. Experienced cardiologists defined the ground truth labels. We assessed classification performance on an internal model naïve dataset using the area under the receiver operator curve (AUROC), sensitivity, specificity, positive predictive value, and negative predictive value. For external multicenter testing, we used studies from Children’s Hospital of Orange County (CHOC) and Boston Children’s Hospital (BCH), both of which utilize a different ultrasound system vendor. Results: Training and validation were completed using 1,145 color/color-compare clips (661 clips with PDA and 484 no PDA) from 66 patients. The internal test dataset consisted of 142 clips from 16 patients. The external CHOC and BCH cohorts consisted of 146 clips from 50 patients and 294 clips from 68 patients, respectively. Model performance was similar for internal and external testing (Table 1). Conclusions: Our deep learning model detected the presence of PDA with acceptable performance. This performance generalized well across multiple institutions and ultrasound vendors. This work shows promise for the future development of an automated tool for PDA diagnosis enabling the democratization of pediatric cardiology resources.

An Enhanced Detection Method of Hardware Trojan Based on CNN- Attention-LSTM

The security issues caused by the insertion of hardware Trojans seriously threaten the security and reliability of the entire hardware device. This article constructs a detection model that combines convolutional neural networks (CNN) and long short-term memory networks (LSTM), and introduces attention mechanism to enhance the model's ability to recognize complex circuits. This method can automatically learn and optimize feature extraction and classification models, reduce reliance on manual experience through training on large amounts of data, and improve the intelligence level of detection. Especially, by combining attention mechanisms and LSTM models, it is possible to more effectively capture small anomalies in circuit design and improve the accuracy and efficiency of hardware Trojan detection. The experimental results show that the proposed CNN-Attention-LSTM model exhibits superior Trojan detection performance and good generalization ability on different datasets, with an precision of 96.3%, a recall rate of 94.7%, and an F1 score of 95.5%.

An Improved Transformer Model for Sap Flow Prediction that Efficiently Utilizes Environmental Information

AbstractAs an important reference for assessing plant water consumption and estimating plant transpiration, it is of great significance to achieve accurate prediction of plant sap flow. A number of deep learning models were established and compared using approximately 3 years of continuous eucalyptus flow time series data collected from the SAPFLUXNET open dataset and 6 environmental factors, including shortwave solar incident radiation, air temperature, air relative humidity, net radiation, vapor pressure deficit, and photosynthetic photon flux density. The experimental results show that the improved Transformer model, with the introduction of a two-step self-attention mechanism and simplified design, maintains significant predictive performance advantages compared to the original Transformer model, long short-term memory, gated recurrent unit, and temporal convolutional neural network models. In the shorter 1-h forecast, the mean squared error and coefficient of determination (R2) of the improved Transformer model are 0.0191 and 0.965, respectively. Compared to the suboptimal typical Transformer model, the MSE is reduced by 22.9%, and R2 is increased by 1.0%. Additionally, the improved model maintains stable predictive performance advantages in long-term plant flow prediction. In the longest 8-h advance prediction, the MSE is reduced by 14.9% compared to the suboptimal Transformer model, and R2 increases by 3.0% compared to the Transformer model. The comprehensive experimental results show that the improved Transformer model makes more effective use of environmental information to achieve more accurate and long-term plant flow prediction. This study emphasizes the basic principle and validity of the two-step self-attention network structure and provides a valuable basis for developing more effective methods for predicting plant sap flow.

Abstract 4138272: CMR Quantification of Myocardial Oxygenation Extraction Fraction Maps Using a Model-based Self-supervised Learning Network: Initial Experience in Patients with Cardiomyopathies

Background: Measurements of myocardial oxygenation extraction fraction (mOEF) maps with cardiovascular magnetic resonance (CMR) has been recently developed to assess myocardial oxygen metabolism in healthy. Recent studies focus on developing supervised machine learning methods to improve the quantification of mOEF. However, these supervised learning methods may be limited by the lack of ground-truth mOEF maps because MRI cannot directly measure mOEF with the same precision as PET. Hypothesis: Model-based self-supervised learning neural networks maybe feasible to generate mOEF maps accurately. Aims: To develop a physical model-based self-supervised learning neural network to accurately estimate mOEF for the patients with a variety of cardiomyopathies. Methods: An ECG triggered, two-dimensional asymmetric spin-echo (ASE) prepared sequence was employed to scan 71 patients with dilated, hypertrophic, or ischemic cardiomyopathies. At least 3 slices were scanned for each patient and each ASE scan was performed free-breathing with a spatial resolution of 1.7 × 1.7 × 8 mm 3 and scan time of 18 RR-interval. Acquisition of late gadolinium enhancement (LGE) was performed in each patient after the administration of 0.15 mmol/kg gadolinium agent for the visualization of myocardial infarction regions. A fully convolutional neural network with U-Net architecture was optimized with a physical model-based signal loss function (see Figure 1) on the ASE training dataset from 67 patients to generate mOEF maps. To evaluate if the method can accurately quantify abnormal mOEF, four patients with myocardial infarction were selected as the test set. Results: A previous publication reported normal mOEF levels at approximately 0.6-0.7 in healthy subjects. Figure 2 shows our proposed method generated mOEF maps from two representative patients and their LGE images for comparisons. In comparison with the remote region (mOEF = 0.70±0.10), the mOEF of myocardial regions with infarction was significantly lower (mOEF = 0.36±0.12, p < 0.001). The infarction areas predicted by the network overlapped well with the LGE. Conclusion: Quantification of mOEF using the proposed model-based self-supervised U-Net is feasible to detect abnormalities in regional myocardial oxygenation. Current study is ongoing to evaluate the proposed technique in a large cardiac patient dataset.

Understanding Polymers Through Transfer Learning and Explainable AI

In this work we study the use of artificial intelligence models, particularly focusing on transfer learning and interpretability, to predict polymer properties. Given the challenges imposed by data scarcity in polymer science, transfer learning offers a promising solution by using learnt features of models pre-trained on other datasets. We conducted a comparative analysis of direct modelling and transfer learning-based approaches using a polyacrylates’ glass transitions dataset as a proof-of-concept study. The AI models utilized tokenized SMILES strings to represent polymer structures, with convolutional neural networks processing these representations to predict Tg. To enhance model interpretability, Shapley value analysis was employed to assess the contribution of specific chemical groups to the predictions. The results indicate that while transfer learning provides robust predictive capabilities, direct modelling on polymer-specific data offers superior performance, particularly in capturing the complex interactions influencing Tg. This work highlights the importance of model interpretability and the limitations of applying molecular-level models to polymer systems.

Abstract 4119992: 12-lead electrocardiograms predict adverse cardiovascular outcomes of emergency department patients

Introduction: Chest pain is a common cause for presentation to the emergency department (ED). Identifying patients at increased risk of adverse cardiovascular outcomes may help guide testing. Aims: We sought to determine if deep learning enabled 12-lead electrocardiogram (ECG) analysis may improve prediction of adverse cardiovascular outcomes of ED patients presenting with chest pain compared to conventional approaches. Methods: A pretrained convolutional neural network was applied to derive numerical representations of the index ECG waveforms from patients presenting to the Brigham and Women’s Hospital (BWH) ED with chest pain. We trained a neural network model (‘CP-AI’) to predict 30-day major adverse cardiovascular events (MACE) defined as myocardial infarction (MI), pulmonary embolism (PE), aortic dissection (AD), or mortality using age, sex, cardiac biomarkers (troponin and d-dimer), and the numerical ECG representations as inputs ( Figure 1 ). In a holdout sample of Massachusetts General Hospital (MGH) ED patients, we compared the performance of the CP-AI model to alternative models fit on (1) demographics (‘Age and Sex’) (2) demographics + cardiac biomarkers (‘Biomarker Model’), and (3) demographics + numerical ECG representations (‘ECG Model’). Results: The BWH derivation sample included 18,811 individuals (51% female, mean age 65 ± 16 years). The MGH validation sample included 14,476 individuals (45% female, mean age 65 ± 15 years). The CP-AI model significantly outperformed the comparison models for prediction of 30-day MACE with an area under the receiver operating characteristic curve (AUROC) of 0.82 [95% CI 0.81-0.83] ( Figure 1 ). CP-AI also significantly outperformed the comparison models for classification of the 30-day MACE components including MI (AUROC 0.91 [95% CI 0.90-0.92]), PE (AUROC 0.74 [95% CI 0.72-0.76]), and mortality (AUROC 0.86 [95% CI 0.85-0.87]), but not aortic dissection (0.71 [95% CI 0.68-0.75]). Conclusions: The integration of deep learning ECG analysis with conventional assessment improved prediction of adverse cardiovascular of ED patients presenting with chest pain.

Trading Community Analysis of Countries’ Roll-On/Roll-Off Shipping Networks Using Fine-Grained Vessel Trajectory Data

Roll-on/roll-off vessels (RO/RO vessels) are playing an increasingly critical role in international automobile transport, facilitating the efficient movement of vehicles and heavy machinery across continents. Despite this growing significance, there is still limited research specifically focused on the RO/RO shipping network and its impact on global trade. This paper studies the global RO/RO shipping network using AIS data on RO/RO vessels collected from 2020 to 2023. We construct a method based on the complex network theory and the graph feature extraction method to quantitatively assess the features of the RO/RO shipping network. This method assesses the complexity, sparsity, homogeneity, modularity, and hierarchy of the RO/RO shipping network across various ports and countries and employs the graph convolutional neural network (GCN) model to extract network features for community detection. This process enables the identification of port clusters that are frequently linked to RO/RO vessels, as well as regional transport modes. The paper’s findings support these conclusions: (1) From 2020 to 2023, the number of nodes in the RO/RO shipping network increased by 22%, primarily concentrated in African countries. The RO/RO shipping network underwent restructuring after the pandemic, with major complex network parameters showing an upward trend. (2) The RO/RO shipping network is complex, with a stable graph density of 0.106 from 2020 to 2023. The average degree increased by 7% to 4.224. Modularity decreased by 6.5% from 0.431 in 2022 to 0.403, while the hierarchy coefficient rose to 0.575, suggesting that post-pandemic, community routes have become more diverse, reflecting the reconstruction and maturation of the overall network. (3) The model yielded a silhouette coefficient of 0.548 and a Davies–Bouldin index of 0.559 using an improved automatic feature extraction method. In comparison between 2020 and 2023, the changes in the two indicators are small. This shows that GINs can effectively extract network features and give us results that we can understand for community detection. (4) In 2023, key communities divide the RO/RO shipping network, with one community handling 39% of global routes (primarily Europe–Asia), another community handling 23% (serving Asia–Pacific, Africa, and the Middle East), and a third community managing 38% (linking Asia, Europe, and South America).