Extract Representative Features Research Articles

Ratai: recurrent autoencoder with imputation units and temporal attention for multivariate time series imputation

Multivariate time series is ubiquitous in real-world applications, yet it often suffers from missing values that impede downstream analytical tasks. In this paper, we introduce the Long Short-Term Memory Network based Recurrent Autoencoder with Imputation Units and Temporal Attention Imputation Model (RATAI), tailored for multivariate time series. RATAI is designed to address certain limitations of traditional RNN-based imputation methods, which often focus on predictive modeling to estimate missing values, sometimes neglecting the contextual impact of observed data at and beyond the target time step. Drawing inspiration from Kalman smoothing, which effectively integrates past and future information to refine state estimations, RATAI aims to extract feature representations from time series data and use them to reconstruct a complete time series, thus overcoming the shortcomings of existing approaches. It employs a dual-stage imputation process: the encoder utilizes temporal information and attribute correlations to predict and impute missing values, and extract feature representation of imputed time series. Subsequently, the decoder reconstructs the series from the feature representation, and the reconstructed values are used as the final imputation values. Additionally, RATAI incorporates a temporal attention mechanism, allowing the decoder to focus on highly relevant inputs during reconstruction. This model can be trained directly using data that contains missing values, avoiding the misleading effects on model training that can arise from setting initial values for missing values. Our experiments demonstrate that RATAI outperforms benchmark models in multivariate time series imputation.

Fused Multi-Domains and Adaptive Variational Mode Decomposition ECG Feature Extraction for Lightweight Bio-Inspired Key Generation and Encryption.

Security is one of the increasingly significant issues given advancements in technology that harness data from multiple devices such as the internet of medical devices. While protecting data from unauthorized user access, several techniques are used including fingerprints, passwords, and others. One of the techniques that has attracted much attention is the use of human features, which has proven to be most effective because of the difficulties in impersonating human-related features. An example of a human-related attribute includes the electrical signal generated from the heart, mostly referred to as an Electrocardiogram (ECG) signal. The methods to extract features from ECG signals are time domain-based; however, the challenge with relying only on the time-domain or frequency-domain method is the inability to capture the intra-leading relationship of Variational Mode Decomposition signals. In this research, fusing multiple domains ECG feature and adaptive Variational Mode Decomposition approaches are utilized to mitigate the challenge of losing the intra-leading correlations of mode decompositions, which might reduce the robustness of encryption algorithms. The features extracted using the reconstructed signal have a mean (0.0004), standard deviation (0.0391), skewness (0.1562), and kurtosis (1.2205). Among the lightweight encryption methods considered, Chacha20 has a total execution time of 27µs. The study proposes a lightweight encryption technique based on the fused vector representation of extracted features to provide an encryption scheme in addition to a bio-inspired key generation technique for data encryption.

Fundus Vascular Segmentation Based on Data Enhancement and Invariant Feature Extraction

Deep neural networks have emerged as the predominant method for medical image segmentation, owing to their robust feature learning capabilities, enabling accurate automatic segmentation of target structures within intricate medical images. Fundus images, being crucial in diagnosing ophthalmic diseases, underscore the importance of effective segmentation techniques. However, fundus vascular images pose challenges due to their high complexity and subtle individual differences, necessitating improvement in existing segmentation methodologies for enhanced disease classification accuracy. This paper introduces a fundus blood vessel segmentation model, employing data augmentation and invariant feature extraction, to systematically tackle the core challenges in medical image processing, particularly in fundus blood vessel segmentation. These challenges include limited source domain samples and inadequate model domain generalization. The model adopts a dual-dimensional strategy. Firstly, it delves into data augmentation technology to enhance the diversity and representativeness of samples within the finite source domain. This is achieved through an image enhancement module based on Fourier transform, mitigating the impact of data scarcity on model training effectiveness. Secondly, the research focuses on interdomain invariant feature extraction, aiming to extract feature representations that consistently characterize fundus blood vessel structure and pathology across different data distributions, thereby enhancing model generalization performance in unfamiliar domains. Specifically, the paper designs a fundus image enhancement module based on Fourier transform in the data augmentation dimension. In the feature extraction dimension, it proposes a normalization module based on uncertainty theory, departing from traditional normalization methods. Experimental results demonstrate the efficacy of the proposed method, showcasing superior generalization performance compared to existing techniques in retinal blood vessel and OD/OC segmentation tasks. Experience validates the model-agnostic nature of the learned strategy, indicating its potential for seamless transferability to other models, thereby offering robust support for advancing medical image segmentation research and applications.

Aluminum Product Surface Defect Detection Method Based on Improved CenterNet

In order to realize real‐time detection of aluminum defects during aluminum production, the target detection algorithm needs to be able to run on locally deployed hardware. Convolutional neural networks can effectively extract representative features from high‐dimensional data such as images and videos, and capture spatial information in the data, making it easier to locate aluminum defects. Moreover, running CNN model inference on local hardware has high real‐time performance. Due to the advantages of convolutional neural network in anomaly detection, an improved CenterNet aluminum surface defect detection method was proposed. The algorithm combines common convolution and depthwise separable convolution to design a lightweight convolution module. Then, the Convolutional Block Attention Module is added to the feature extraction network to make the network better capture the rich input feature information of the image. Ultimately, the α‐DIoU loss function is implemented to enhance the precision of bounding box predictions. The experimental findings demonstrate that the proposed algorithm achieves an average detection accuracy (mAP) of 86.02%, which is 5.95% higher than the average detection accuracy of the traditional algorithm, and has a good detection effect on aluminum surface defects. Furthermore, there is an 11.9% reduction in model parameters and a 15.2% decrease in floating‐point computations, which helps to promote the deployment of embedded device platforms. © 2024 Institute of Electrical Engineers of Japan and Wiley Periodicals LLC.

CLHGNNMDA: Hypergraph Neural Network Model Enhanced by Contrastive Learning for miRNA-Disease Association Prediction.

Numerous biological experiments have demonstrated that microRNA (miRNA) is involved in gene regulation within cells, and mutations and abnormal expression of miRNA can cause a myriad of intricate diseases. Forecasting the association between miRNA and diseases can enhance disease prevention and treatment and accelerate drug research, which holds considerable importance for the development of clinical medicine and drug research. This investigation introduces a contrastive learning-augmented hypergraph neural network model, termed CLHGNNMDA, aimed at predicting associations between miRNAs and diseases. Initially, CLHGNNMDA constructs multiple hypergraphs by leveraging diverse similarity metrics related to miRNAs and diseases. Subsequently, hypergraph convolution is applied to each hypergraph to extract feature representations for nodes and hyperedges. Following this, autoencoders are employed to reconstruct information regarding the feature representations of nodes and hyperedges and to integrate various features of miRNAs and diseases extracted from each hypergraph. Finally, a joint contrastive loss function is utilized to refine the model and optimize its parameters. The CLHGNNMDA framework employs multi-hypergraph contrastive learning for the construction of a contrastive loss function. This approach takes into account inter-view interactions and upholds the principle of consistency, thereby augmenting the model's representational efficacy. The results obtained from fivefold cross-validation substantiate that the CLHGNNMDA algorithm achieves a mean area under the receiver operating characteristic curve of 0.9635 and a mean area under the precision-recall curve of 0.9656. These metrics are notably superior to those attained by contemporary state-of-the-art methodologies.

Multimodal feature integration network for lithology identification from point cloud data

Accurate lithology identification from outcrop surfaces is crucial for interpreting geological 3D data. However, challenges arise due to factors such as severe weathering and vegetation coverage, which hinder achieving ideal identification results with both accuracy and efficiency. The integration of 3D point cloud technology and deep learning methodologies presents a promising solution to address these challenges. In this study, we propose a novel multimodal feature integration network designed to distinguish various rock types from point clouds. Our network incorporates a multimodal feature integration block equipped with multiple attention mechanisms to extract representative deep features, along with a hierarchical feature separation block to leverage these features for precise segmentation of points corresponding to different lithologies. Furthermore, we introduce a specialized loss function tailored for rock type identification to enhance network training. Through experiments involving point cloud sampling strategies and loss function evaluation, we identify the optimal network configuration. Comparative analyses against baseline methods demonstrate the superiority of our proposed network across diverse study areas reconstructed from UAV images and laser scanner data, exhibiting improved visual appearance and metric values (Accuracy = 0.978, mean Accuracy = 0.895, mean IoU = 0.857). These findings underscore the efficacy of the multimodal feature integration network as a promising approach for lithology identification tasks in various digital outcrop models derived from heterogeneous data sources.

A Novel Image Feature Extraction Based Machine Learning approach for Disease Detection from Chest X-Ray Images

The limitation of feature selection is the biggest challenge for machine learning classifiers in disease classification. This research proposes a novel feature extraction method to extract representative features from medical images, combining extracted features with original image pixel features. Additionally, we propose a new method that uses data values from Andrews's curve function to transform chest x-ray images into spectrograms. The spectrogram images are believed to aid in distinguishing near-similar medical images, such as COVID and pneumonia. The study aims to build an efficient machine learning system that applies the proposed feature extraction method and utilizes spectrogram images for distinguishing near-similar medical images. For experimental analysis, we have used the award winning Kaggle Chest Radiography image dataset. The test results show that among all machine learning classifiers, the logistic regression classifier could correctly distinguish COVID and pneumonia images with a 97.18% test accuracy, a 98.34% detection rate, a 97.8% precision rate, and an AUC value of 0.99 on the test dataset. The machine learning model has learned to distinguish between medical images that appear similar using features found through the proposed feature extraction and spectrogram images. The results also proved that the proposed approach using XGBoost has outperformed state-of-the-art models in recent research studies when (i) binary classification is performed using COVID-19 and Normal Chest x-ray images and (ii) multiclass classification is performed using Normal, COVID and Pneumonia Chest x-ray images.

LoMAE: Simple Streamlined Low-Level Masked Autoencoders for Robust, Generalized, and Interpretable Low-Dose CT Denoising.

Low-dose computed tomography (LDCT) offers reduced X-ray radiation exposure but at the cost of compromised image quality, characterized by increased noise and artifacts. Recently, transformer models emerged as a promising avenue to enhance LDCT image quality. However, the success of such models relies on a large amount of paired noisy and clean images, which are often scarce in clinical settings. In computer vision and natural language processing, masked autoencoders (MAE) have been recognized as a powerful self-pretraining method for transformers, due to their exceptional capability to extract representative features. However, the original pretraining and fine-tuning design fails to work in low-level vision tasks like denoising. In response to this challenge, we redesign the classical encoder-decoder learning model and facilitate a simple yet effective streamlined low-level vision MAE, referred to as LoMAE, tailored to address the LDCT denoising problem. Moreover, we introduce an MAE-GradCAM method to shed light on the latent learning mechanisms of the MAE/LoMAE. Additionally, we explore the LoMAE's robustness and generability across a variety of noise levels. Experimental findings show that the proposed LoMAE enhances the denoising capabilities of the transformer and substantially reduce their dependency on high-quality, ground-truth data. It also demonstrates remarkable robustness and generalizability over a spectrum of noise levels. In summary, the proposed LoMAE provides promising solutions to the major issues in LDCT including interpretability, ground truth data dependency, and model robustness/generalizability.

HQNet: A hybrid quantum network for multi-class MRI brain classification via quantum computing

The complex and nonlinear nature of brain tumor morphology and texture pose significant challenges for representative feature extraction from magnetic resonance imaging (MRI) images, ultimately leading to inaccurate diagnoses of brain tumors. To tackle this problem, we propose a novel approach termed the hybrid quantum–classical convolutional network (HQNet) for detecting MRI brain tumors. Firstly, we use data augmentation techniques to deal with the issues of class imbalance and the sample scarcity within brain tumor MRI images. Secondly, we integrate channel attention and self-attention mechanisms to capture both channel and spatial dependencies from MRI images. This integration enables us to effectively fuse these dependencies and mitigate the discrepancies between them. However, the varying dependence of brain tumors at different scales can result in a decline in classification performance. To address this issue, we extract brain tumor features at various scales and combine them to alleviate this effect. Thirdly, a new parameterized quantum circuit is designed based on the principles of quantum computing to maximize the potential advantages of quantum computing and improve feature extraction. Finally, we compress the features and pass them through the fully connected layer to generate the final classification result. The effectiveness of our model is demonstrated through its superior performance when evaluated using three benchmark datasets.

Enhancing Clustering Performance of Failed Test Cases during HIL Simulation: A Study on Deep Auto-Encoder Structures and Hyperparameter Tuning

Over the last decade, hardware-in-the-loop (HIL) simulation has been established as a safe, efficient, reliable, and flexible method for performing real-time simulation. Furthermore, in the automotive sector, the HIL system has been recommended in the ISO 26262 standard as a powerful platform for performing realistic simulation during system integration testing. As a result of performing HIL black-box tests, the results of executing test cases (TCs) are reported as pass/fail without determining the nature and root causes of the underlying failures. The conventional analysis process of the failed TCs relies on expert knowledge. The higher the number of failed TCs, the higher the cost of manual analysis in terms of time and effort. In light of the shortcomings of existing methodologies, this study presents a novel intelligent framework capable of analyzing failed TCs without the need for expert knowledge or code access. To this end, a convolutional auto-encoder-based deep-learning approach is proposed to extract representative features from the textual description of the failed TCs. Furthermore, k-means-based clustering is used to categorize the extracted features according to their respective failure classes. To illustrate the effectiveness and validate the performance of the proposed method, a virtual test drive with real-time HIL simulation is presented as a case study. The proposed model exhibits superior clustering performance compared to other standalone k-means algorithms, as demonstrated by the David Bouldin Index (DBI) and accuracy values of 0.5184 and 94.33%, respectively. Furthermore, the proposed model shows a significant advantage in terms of feature extraction and clustering performance compared to the current state-of-the-art fault-analysis method. The proposed approach not only supports the validation process and improves the safety and reliability of the systems but also reduces the costs of manual analysis in terms of time and effort.

Multi-view graph convolutional networks based on multi-source information fusion for mechanical fault diagnosis

Data-driven intelligent diagnosis methods have demonstrated significant success within prognostics and health management systems due to their powerful feature representation and non-linear fitting capabilities. However, most existing methods employ simple fusion strategies and neglecting data structure considerations, which lead to incomplete feature representations for final diagnostic decisions. In this article, we address these limitations by proposing a multiview graph convolutional network [Formula: see text] framework based on multi-source information fusion for fault diagnosis of key components in mechanical equipment. This is achieved through joint research on sample graph and feature graph learning. First, convolution neural networks named the SharedNet module are leveraged to extract multi-source features, and then the deep features are concatenated in a fully connected layer. After that, we construct multi-view initial graphs to combine the correlations between samples and features to mine rich graph topology structure. Then, we redesign the graph learning strategy to further increase the robustness and generalizability of the proposed method. Finally, extensive experimental results on the multi-information datasets show that our proposed [Formula: see text] can not only outperform the state-of-the-art methods of comparison but also extract multi-view graph topology and feature representations for fault diagnosis.

A multi-task prediction method based on neighborhood structure embedding and signed graph representation learning to infer the relationship between circRNA, miRNA, and cancer.

Research shows that competing endogenous RNA is widely involved in gene regulation in cells, and identifying the association between circular RNA (circRNA), microRNA (miRNA), and cancer can provide new hope for disease diagnosis, treatment, and prognosis. However, affected by reductionism, previous studies regarded the prediction of circRNA-miRNA interaction, circRNA-cancer association, and miRNA-cancer association as separate studies. Currently, few models are capable of simultaneously predicting these three associations. Inspired by holism, we propose a multi-task prediction method based on neighborhood structure embedding and signed graph representation learning, CMCSG, to infer the relationship between circRNA, miRNA, and cancer. Our method aims to extract feature descriptors of all molecules from the circRNA-miRNA-cancer regulatory network using known types of association information to predict unknown types of molecular associations. Specifically, we first constructed the circRNA-miRNA-cancer association network (CMCN), which is constructed based on the experimentally verified biomedical entity regulatory network; next, we combine topological structure embedding methods to extract feature representations in CMCN from local and global perspectives, and use denoising autoencoder for enhancement; then, combined with balance theory and state theory, molecular features are extracted from the point of social relations through the propagation and aggregation of signed graph attention network; finally, the GBDT classifier is used to predict the association of molecules. The results show that CMCSG can effectively predict the relationship between circRNA, miRNA, and cancer. Additionally, the case studies also demonstrate that CMCSG is capable of accurately identifying biomarkers across various types of cancer. The data and source code can be found at https://github.com/1axin/CMCSG.

Learning Heterogeneous Spatial-Temporal Context for Skeleton-Based Action Recognition.

Graph convolution networks (GCNs) have been widely used and achieved fruitful progress in the skeleton-based action recognition task. In GCNs, node interaction modeling dominates the context aggregation and, therefore, is crucial for a graph-based convolution kernel to extract representative features. In this article, we introduce a closer look at a powerful graph convolution formulation to capture rich movement patterns from these skeleton-based graphs. Specifically, we propose a novel heterogeneous graph convolution (HetGCN) that can be considered as the middle ground between the extremes of (2 + 1)-D and 3-D graph convolution. The core observation of HetGCN is that multiple information flows are jointly intertwined in a 3-D convolution kernel, including spatial, temporal, and spatial-temporal cues. Since spatial and temporal information flows characterize different cues for action recognition, HetGCN first dynamically analyzes pairwise interactions between each node and its cross-space-time neighbors and then encourages heterogeneous context aggregation among them. Considering the HetGCN as a generic convolution formulation, we further develop it into two specific instantiations (i.e., intra-scale and inter-scale HetGCN) that significantly facilitate cross-space-time and cross-scale learning on skeleton graphs. By integrating these modules, we propose a strong human action recognition system that outperforms state-of-the-art methods with the accuracy of 93.1% on NTU-60 cross-subject (X-Sub) benchmark, 88.9% on NTU-120 X-Sub benchmark, and 38.4% on kinetics skeleton.

ESMformer: Error-aware self-supervised transformer for multi-view 3D human pose estimation

Multi-view 3D human pose estimation (HPE) currently faces several key challenges. Information from different viewpoints exhibits high variability due to complex environmental factors, posing difficulties in cross-view feature extraction and fusion. Additionally, multi-view 3D labeled pose data is rather scarce, and the impact of input 2D poses on 3D HPE accuracy has received little attention. To address these issues, we propose an Error-aware Self-supervised transformer framework for Multi-view 3D HPE (ESMformer). Firstly, we introduce a single-view multi-level feature extraction module to enhance pose features in individual viewpoints, which incorporates a novel relative attention mechanism for representative feature extraction at different levels. Subsequently, we develop multi-view intra-level and cross-level fusion modules to exploit spatio-temporal feature dependencies among human joints, and progressively fuse pose information from all views and levels. Furthermore, we explore an error-aware self-supervised learning strategy to reduce the model’s reliance on 3D pose annotations and mitigate the impact of incorrect 2D poses. This strategy adaptively selects reliable input 2D poses based on 3D pose prediction errors. Experiments on three popular benchmarks show that ESMformer achieves state-of-the-art results and maintains cost-effective computational complexity. Notably, ESMformer does not rely on any 3D pose annotations or prior human body knowledge, making it highly versatile and adaptable in practical applications.11The code and models are available at https://github.com/z0911k/ESMformer.

Transformer and cross-attention-based multi-sensor in-situ monitoring of molten pool stability and part quality in laser powder bed fusion

The fluctuations in process parameters, as a random phenomenon in the laser powder bed fusion (LPBF) process, is occasional. These subtle variations can lead to defects such as porosity if not monitored and corrected promptly. Therefore, monitoring the stability of the molten pool and small changes in process parameters is significant. For process monitoring, the commonly used Transformer architectures have demonstrated remarkable performance in single-sensor signal processing. However, as the core component of the Transformer, the self-attention mechanism has limitations in data fusion of multi-sensor signals. To this end, a novel Transformer-based deep learning method associated with the cross-attention mechanism (Trans-Cross) is proposed. Trans-Cross leverages the collected photodiode and acoustic signals to monitor the fluctuation of process parameters as well as the quality of parts. Specifically, the cross-attention mechanism is introduced to enhance representative feature extraction from photodiode and acoustic signals, exploiting their complementary information. To better characterize the raw signals, an improved adaptive variational mode decomposition (VMD) algorithm is proposed for data preprocessing. The proposed Trans-Cross achieves impressive prediction accuracies of 97.41 % for identifying the fluctuations in the process parameters and 99.73 % for part quality classification. Trans-Cross exhibits superior performance and strong robustness when dealing with constraints such as limited input signal length and training data ratio. These results validate the feasibility of the proposed method in accurately identifying the fluctuations in process parameters as well as the part quality. This work provided data guidance to enhance the stability of the LPBF process.

Enhanced domain transfer deep fuzzy echo state network for rotating machinery fault diagnosis based on current signal

Although vibration-based fault diagnosis methods have achieved remarkable results in rotating machinery, they are still limited by various factors, such as environment noise and additional sensor installation. Meanwhile, due to inevitable distribution differences in practical engineering, deep transfer learning models are commonly used in fault diagnostic fields. Although deep architectures can extract representative domain-invariant features, they typically result in substantial computational burdens and training time. Therefore, to address the above problems, an enhanced domain transfer deep fuzzy echo state network (EDFESN) is proposed for rotating machinery fault diagnosis based on current signals. Firstly, current signals derived from the driving motor are directly collected without additional sensors. Secondly, an enhanced domain mapping method is raised to solve the problem of data distribution discrepancies between cross domain. Furthermore, a deep fuzzy echo state network (DFESN) integrated with fuzzy clustering is constructed, which utilizes layer-wise fuzzy-tuning learning paradigm instead of backpropagation step to reduce training time. Two datasets from gearbox and bearing both verify the effectiveness of the proposed method. Compared with other popular transfer methods, EDFESN not only achieves highest accuracy, but also has fastest training speed.

MH2AFormer: An Efficient Multiscale Hierarchical Hybrid Attention With a Transformer for Bladder Wall and Tumor Segmentation.

Achieving accurate bladder wall and tumor segmentation from MRI is critical for diagnosing and treating bladder cancer. However, automated segmentation remains challenging due to factors such as comparable density distributions, intricate tumor morphologies, and unclear boundaries. Considering the attributes of bladder MRI images, we propose an efficient multiscale hierarchical hybrid attention with a transformer (MH2AFormer) for bladder cancer and wall segmentation. Specifically, a multiscale hybrid attention and transformer (MHAT) module in the encoder is designed to adaptively extract and aggregate multiscale hybrid feature representations from the input image. In the decoder stage, we devise a multiscale hybrid attention (MHA) module to generate high-quality segmentation results from multiscale hybrid features. Combining these modules enhances the feature representation and guides the model to focus on tumor and wall regions, which helps to solve bladder image segmentation challenges. Moreover, MHAT utilizes the Fast Fourier Transformer with a large kernel (e.g., 224 × 224) to model global feature relationships while reducing computational complexity in the encoding stage. The model performance was evaluated on two datasets. As a result, the model achieves relatively best results regarding the intersection over union (IoU) and dice similarity coefficient (DSC) on both datasets (Dataset A: IoU = 80.26%, DSC = 88.20%; Dataset B: IoU = 89.74%, DSC = 94.48%). These advantageous outcomes substantiate the practical utility of our approach, highlighting its potential to alleviate the workload of radiologists when applied in clinical settings.

Distribution-based detection of radiographic changes in pneumonia patterns: A COVID-19 case study

Although the classification of chest radiographs has long been an extensively researched topic, interest increased significantly with the onset of the COVID-19 pandemic. Existing results are promising; however, the radiological similarities between COVID-19 and other types of respiratory diseases limit the success of conventional image classification approaches that focus on single instances. This study proposes a novel perspective that conceptualizes COVID-19 pneumonia as a deviation from a normative distribution of typical pneumonia patterns. Using a population-based approach, our approach utilizes distributional anomaly detection. This method diverges from traditional instance-wise approaches by focusing on sets of scans instead of individual images. Using an autoencoder to extract feature representations, we present instance-based and distribution-based assessments of the separability between COVID-positive and COVID-negative pneumonia radiographs. The results demonstrate that the proposed distribution-based methodology outperforms conventional instance-based techniques in identifying radiographic changes associated with COVID-positive cases. This underscores its potential as an early warning system capable of detecting significant distributional shifts in radiographic data. By continuously monitoring these changes, this approach offers a mechanism for early identification of emerging health trends, potentially signaling the onset of new pandemics and enabling prompt public health responses.

Attentive Review Semantics-Aware Recommendation Model for Rating Prediction

Online reviews are crucial when building a recommendation model because they contain the specific and rich preferences of users related to different aspects of a particular item. Incorporating these online reviews into the recommendation model mitigates the data sparsity issue to some extent and contributes to better recommendation performance. Despite this success, review-based recommender systems have the limitation that they do not fully consider the relevance of the review text to the target item. Specifically, the review text should reflect the user’s detailed opinion about the target item to extract detailed preference information. Meanwhile, the review content must be directly related to the target item to extract the customer’s specific preferences for the item. However, previous studies have overlooked both of these aspects. Therefore, it is necessary to build a recommendation model that considers the relevance of the review content to the target item. To address this issue, this study proposes a novel recommendation model that accurately estimates users’ preferences by carefully considering the relevance of the review content to the items. The proposed model effectively extracts feature representations from the text using bidirectional encoder representations from a transformer and obtains fused features by considering the importance of features through the attention mechanism. To evaluate the performance of the model, we used a publicly accessible dataset of reviews from Amazon.com and compared it to various baseline models. The experimental results demonstrated better recommendation performance of the proposed model compared to other baseline models.

Porous-DeepONet: Learning the Solution Operators of Parametric Reactive Transport Equations in Porous Media

Reactive transport equations in porous media are critical in various scientific and engineering disciplines, but solving these equations can be computationally expensive when exploring different scenarios, such as varying porous structures and initial or boundary conditions. The deep operator network (DeepONet) has emerged as a popular deep learning framework for solving parametric partial differential equations. However, applying the DeepONet to porous media presents significant challenges due to its limited capability to extract representative features from intricate structures. To address this issue, we propose the Porous-DeepONet, a simple yet highly effective extension of the DeepONet framework that leverages convolutional neural networks (CNNs) to learn the solution operators of parametric reactive transport equations in porous media. By incorporating CNNs, we can effectively capture the intricate features of porous media, enabling accurate and efficient learning of the solution operators. We demonstrate the effectiveness of the Porous-DeepONet in accurately and rapidly learning the solution operators of parametric reactive transport equations with various boundary conditions, multiple phases, and multi-physical fields through five examples. This approach offers significant computational savings, potentially reducing the computation time by 50–1000 times compared with the finite-element method. Our work may provide a robust alternative for solving parametric reactive transport equations in porous media, paving the way for exploring complex phenomena in porous media.