PeerJ Computer Science最新文献

{"title":"A novel facial expression recognition framework using deep learning based dynamic cross-domain dual attention network.","authors":"Ahmed Omar Alzahrani, Ahmed Mohammed Alghamdi, M Usman Ashraf, Iqra Ilyas, Nadeem Sarwar, Abdulrahman Alzahrani, Alaa Abdul Salam Alarood","doi":"10.7717/peerj-cs.2866","DOIUrl":"10.7717/peerj-cs.2866","url":null,"abstract":"<p><p>Variations in domain targets have recently posed significant challenges for facial expression recognition tasks, primarily due to domain shifts. Current methods focus largely on global feature adoption to achieve domain-invariant learning; however, transferring local features across diverse domains remains an ongoing challenge. Additionally, during training on target datasets, these methods often suffer from reduced feature representation in the target domain due to insufficient discriminative supervision. To tackle these challenges, we propose a dynamic cross-domain dual attention network for facial expression recognition. Our model is specifically designed to learn domain-invariant features through separate modules for global and local adversarial learning. We also introduce a semantic-aware module to generate pseudo-labels, which computes semantic labels from both global and local features. We assess our model's effectiveness through extensive experiments on the Real-world Affective Faces Database (RAF-DB), FER-PLUS, AffectNet, Expression in the Wild (ExpW), SFEW 2.0, and Japanese Female Facial Expression (JAFFE) datasets. The results demonstrate that our scheme outperforms the existing state-of-the-art methods by attaining recognition accuracies 93.18, 92.35, 82.13, 78.37, 72.47, 70.68 respectively.</p>","PeriodicalId":54224,"journal":{"name":"PeerJ Computer Science","volume":"11 ","pages":"e2866"},"PeriodicalIF":3.5,"publicationDate":"2025-05-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12192681/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144499157","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Machine learning for Internet of Things (IoT) device identification: a comparative study.","authors":"Hamid Tahaei, Anqi Liu, Hamid Forooghikian, Mehdi Gheisari, Faiz Zaki, Nor Badrul Anuar, Zhaoxi Fang, Longjun Huang","doi":"10.7717/peerj-cs.2873","DOIUrl":"10.7717/peerj-cs.2873","url":null,"abstract":"<p><p>The rapid deployment of millions of connected devices brings significant security challenges to the Internet of Things (IoT). IoT devices are typically resource-constrained and designed for specific tasks, from which new security challenges are introduced. As such, IoT device identification has garnered substantial attention and is regarded as an initial layer of cybersecurity. One of the major steps in distinguishing IoT devices involves leveraging machine learning (ML) techniques on device network flows known as device fingerprinting. Numerous studies have proposed various solutions that incorporate ML and feature selection (FS) algorithms with different degrees of accuracy. Yet, the domain needs a comparative analysis of the accuracy of different classifiers and FS algorithms to comprehend their true capabilities in various datasets. This article provides a comprehensive performance evaluation of several reputable classifiers being used in the literature. The study evaluates the efficacy of filter-and wrapper-based FS methods across various ML classifiers. Additionally, we implemented a Binary Green Wolf Optimizer (BGWO) and compared its performance with that of traditional ML classifiers to assess the potential of this binary meta-heuristic algorithm. To ensure the robustness of our findings, we evaluated the effectiveness of each classifier and FS method using two widely utilized datasets. Our experiments demonstrated that BGWO effectively reduced the feature set by 85.11% and 73.33% for datasets 1 and 2, respectively, while achieving classification accuracies of 98.51% and 99.8%, respectively. The findings of this study highlight the strong capabilities of BGWO in reducing both the feature dimensionality and accuracy gained through classification. Furthermore, it demonstrates the effectiveness of wrapper methods in the reduction of feature sets.</p>","PeriodicalId":54224,"journal":{"name":"PeerJ Computer Science","volume":"11 ","pages":"e2873"},"PeriodicalIF":3.5,"publicationDate":"2025-05-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12192943/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144499282","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Enhancing healthcare data privacy and interoperability with federated learning.","authors":"Adil Akhmetov, Zohaib Latif, Benjamin Tyler, Adnan Yazici","doi":"10.7717/peerj-cs.2870","DOIUrl":"10.7717/peerj-cs.2870","url":null,"abstract":"<p><p>This article explores the application of federated learning (FL) with the Fast Healthcare Interoperability Resources (FHIR) protocol to address the underutilization of the huge volumes of healthcare data generated by the digital health revolution, especially those from wearable sensors, due to privacy concerns and interoperability challenges. Despite advances in electronic medical records, mobile health applications, and wearable sensors, current digital health cannot fully exploit these data due to the lack of data analysis and exchange between heterogeneous systems. To address this gap, we present a novel converged platform combining FL and FHIR, which enables collaborative model training that preserves the privacy of wearable sensor data while promoting data standardization and interoperability. Unlike traditional centralized learning (CL) solutions that require data centralization, our platform uses local model learning, which naturally improves data privacy. Our empirical evaluation demonstrates that federated learning models perform as well as, or even numerically better than, centralized learning models in terms of classification accuracy, while also performing equally well in regression, as indicated by metrics such as accuracy, area under the curve (AUC), recall, and precision, among others, for classification, and mean absolute error (MAE), mean squared error (MSE), and root mean square error (RMSE) for regression. In addition, we developed an intuitive AutoML-powered web application that is FL and CL compatible to illustrate the feasibility of our platform for predictive modeling of physical activity and energy expenditure, while complying with FHIR data reporting standards. These results highlight the immense potential of our FHIR-integrated federated learning platform as a practical framework for future interoperable and privacy-preserving digital health ecosystems to optimize the use of connected health data.</p>","PeriodicalId":54224,"journal":{"name":"PeerJ Computer Science","volume":"11 ","pages":"e2870"},"PeriodicalIF":3.5,"publicationDate":"2025-05-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12192955/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144499273","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A novel attention-based deep learning model for improving sentiment classification after the case of the 2023 Kahramanmaras/Turkey earthquake on Twitter.","authors":"Serpil Aslan, Muhammed Yildirim","doi":"10.7717/peerj-cs.2881","DOIUrl":"10.7717/peerj-cs.2881","url":null,"abstract":"<p><p>Twitter has emerged as one of the most widely used platforms for sharing information and updates. As users freely express their thoughts and emotions, a vast amount of data is generated, particularly in the aftermath of disasters, which can be collected quickly and directly from individuals. Traditionally, earthquake impact assessments have been conducted through field studies by non-governmental organizations (NGOs), a process that is often time-consuming and costly. Sentiment analysis (SA) on Twitter presents a valuable research area, enabling the extraction and interpretation of real-time public perceptions. In recent years, attention-based methods in deep learning networks have gained significant attention among researchers. This study proposes a novel sentiment classification model, MConv-BiLSTM-GAM, which leverages an attention mechanism to analyze public sentiment following the 7.8 and 7.5 Mw earthquakes that struck Kahramanmaraş, Turkey. The model employs the FastText word embedding technique to convert tweets into vector representations. These vectorized inputs are then processed by a hybrid model integrating convolutional neural networks (CNNs) and recurrent neural networks (RNNs) with a global attention mechanism. This ensures careful consideration of semantic dependencies in sentiment classification. The proposed model operates in three stages: (i) MConv-Local Contextual Feature Extraction, (ii) bidirectional long short-term memory (BiLSTM)-sequence learning, and (iii) Global Attention Mechanism (GAM)-Attention Mechanism. Experimental results demonstrate that the model achieves an accuracy of 93.32%, surpassing traditional deep learning models in the literature by approximately 3%. This research aims to provide objective insights to policymakers and decision-makers, facilitating adequate support for individuals and communities affected by disasters. Moreover, analyzing public sentiment during earthquakes contributes to understanding societal responses and emotional trends in disaster scenarios.</p>","PeriodicalId":54224,"journal":{"name":"PeerJ Computer Science","volume":"11 ","pages":"e2881"},"PeriodicalIF":3.5,"publicationDate":"2025-05-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12192998/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144499145","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"GFADE: generalized feature adaptation and discrimination enhancement for deepfake detection.","authors":"ZhiYong Tian, Junkai Yi","doi":"10.7717/peerj-cs.2879","DOIUrl":"10.7717/peerj-cs.2879","url":null,"abstract":"<p><p>With the rapid advancement of deep generative techniques, such as generative adversarial networks (GANs), the creation of realistic fake images and videos has become increasingly accessible, raising significant security and privacy concerns. Although existing deepfake detection methods perform well within a single dataset, they often experience substantial performance degradation when applied across datasets or manipulation types. To address this challenge, we propose a novel deepfake detection framework that combines multiple loss functions and the MixStyle technique. By integrating Cross-Entropy Loss, ArcFace loss, and Focal Loss, our model enhances its discriminative power to better handle complex forgery characteristics and effectively mitigate data imbalance. Additionally, the MixStyle technique introduces diverse visual styles during training, further improving the model's generalization across different datasets and manipulation scenarios. Experimental results demonstrate that our method achieves superior detection accuracy across a range of cross-dataset and cross-manipulation tests, significantly improving model robustness and generalizability.</p>","PeriodicalId":54224,"journal":{"name":"PeerJ Computer Science","volume":"11 ","pages":"e2879"},"PeriodicalIF":3.5,"publicationDate":"2025-05-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12192638/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144499201","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Research on channel estimation based on joint perception and deep enhancement learning in complex communication scenarios.","authors":"Xin Liu, Shanghong Zhao, Yanxia Liang, Shahid Karim","doi":"10.7717/peerj-cs.2852","DOIUrl":"https://doi.org/10.7717/peerj-cs.2852","url":null,"abstract":"<p><p>In contemporary wireless communication systems, channel estimation and optimization have become increasingly pivotal with the growing number and complexity of devices. Communication systems frequently encounter multiple challenges, such as multipath propagation, signal fading, and interference, which may result in the degradation of communication quality, a reduction in data transmission rates, and even communication interruptions. Therefore, effective estimation and optimization of channels in complex communication environments are of paramount importance to ensure communication quality and enhance system performance. In this article, we address the intelligent, reflective surface (IRS)-assisted channel estimation problem and propose an intelligent channel estimation model based on the fusion of convolutional neural network (CNN) and gated recurrent unit (GRU) row features, utilizing the reinforcement learning Deep Deterministic Policy Gradient (DDPG) strategy for Channel Reconstruction Prediction and Generation Network (CRPG-Net). The framework initially acquires the received signal by converting the guide-frequency symbols at the transmitter into time-domain sequences to be transmitted, and after propagating through the direct channel and the IRS reflection channel, processes the data at the receiver. Subsequently, the spatial and temporal features in the received signal are extracted using the CRPG-Net model, with the adaptive optimization capability of the model enhanced by deep reinforcement learning. The introduction of reinforcement learning enables the model to continuously optimize decisions in dynamic channel environments, improve the robustness of channel estimation, and quickly adjust the IRS reflection parameters when the channel state changes to adapt to complex communication conditions. Experimental results demonstrate that the framework achieves significant channel estimation accuracy and robustness across several public datasets and real test scenarios, with the channel estimation error markedly smaller than that of traditional least squares (LS) and linear minimum mean square error (LMMSE) methods. This method introduces innovative techniques for channel estimation in intelligent communication systems, playing a crucial role in enhancing communication quality and overall system performance.</p>","PeriodicalId":54224,"journal":{"name":"PeerJ Computer Science","volume":"11 ","pages":"e2852"},"PeriodicalIF":3.5,"publicationDate":"2025-05-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12192938/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144499322","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Improved salp swarm algorithm based optimization of mobile task offloading.","authors":"Aishwarya R, Mathivanan G","doi":"10.7717/peerj-cs.2818","DOIUrl":"https://doi.org/10.7717/peerj-cs.2818","url":null,"abstract":"<p><strong>Background: </strong>The realization of computation-intensive applications such as real-time video processing, virtual/augmented reality, and face recognition becomes possible for mobile devices with the latest advances in communication technologies. This application requires complex computation for better user experience and real-time decision-making. However, the Internet of Things (IoT) and mobile devices have computational power and limited energy. Executing these computational-intensive tasks on edge devices may result in high energy consumption or high computation latency. In recent times, mobile edge computing (MEC) has been used and modernized for offloading this complex task. In MEC, IoT devices transmit their tasks to edge servers, which consecutively carry out faster computation.</p><p><strong>Methods: </strong>However, several IoT devices and edge servers put an upper limit on executing concurrent tasks. Furthermore, implementing a smaller size task (1 KB) over an edge server leads to improved energy consumption. Thus, there is a need to have an optimum range for task offloading so that the energy consumption and response time will be minimal. The evolutionary algorithm is the best for resolving the multiobjective task. Energy, memory, and delay reduction together with the detection of the offloading task is the multiobjective to achieve. Therefore, this study presents an improved salp swarm algorithm-based Mobile Application Offloading Algorithm (ISSA-MAOA) technique for MEC.</p><p><strong>Results: </strong>This technique harnesses the optimization capabilities of the improved salp swarm algorithm (ISSA) to intelligently allocate computing tasks between mobile devices and the cloud, aiming to concurrently minimize energy consumption, and memory usage, and reduce task completion delays. Through the proposed ISSA-MAOA, the study endeavors to contribute to the enhancement of mobile cloud computing (MCC) frameworks, providing a more efficient and sustainable solution for offloading tasks in mobile applications. The results of this research contribute to better resource management, improved user interactions, and enhanced efficiency in MCC environments.</p>","PeriodicalId":54224,"journal":{"name":"PeerJ Computer Science","volume":"11 ","pages":"e2818"},"PeriodicalIF":3.5,"publicationDate":"2025-05-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12190771/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144499210","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Eternal-MAML: a meta-learning framework for cross-domain defect recognition.","authors":"Jipeng Feng, Haigang Zhang, Zhifeng Wang","doi":"10.7717/peerj-cs.2757","DOIUrl":"10.7717/peerj-cs.2757","url":null,"abstract":"<p><p>Defect recognition tasks for industrial product suffer from a serious lack of samples, greatly limiting the generalizability of deep learning models. Addressing the imbalance of defective samples often involves leveraging pre-trained models for transfer learning. However, when these models, pre-trained on natural image datasets, are transferred to pixel-level defect recognition tasks, they frequently suffer from overfitting due to data scarcity. Furthermore, significant variations in the morphology, texture, and underlying causes of defects across different industrial products often lead to a degradation in performance, or even complete failure, when directly transferring a defect classification model trained on one type of product to another. The Model-Agnostic Meta-Learning (MAML) framework can learn a general representation of defects from multiple industrial defect recognition tasks and build a foundational model. Despite lacking sufficient training data, the MAML framework can still achieve effective knowledge transfer among cross-domain tasks. We noticed there exists serious label arrangement issues in MAML because of the random selection of recognition tasks, which seriously affects the performance of MAML model during both training and testing phase. This article proposes a novel MAML framework, termed as Eternal-MAML, which guides the update of the classifier module by learning a meta-vector that shares commonality across batch tasks in the inner loop, and addresses the overfitting phenomenon caused by label arrangement issues in testing phase for vanilla MAML. Additionally, the feature extractor in this framework combines the advantages of the Squeeze-and-Excitation module and Residual block to enhance training stability and improve the generalization accuracy of model transfer with the learned initialization parameters. In the simulation experiments, several datasets are applied to verified the cross-domain meta-learning performance of the proposed Eternal-MAML framework. The experimental results show that the proposed framework outperforms the state-of-the-art baselines in terms of average normalized accuracy. Finally, the ablation studies are conducted to examine how the primary components of the framework affect its overall performance. Code is available at https://github.com/zhg-SZPT/Eternal-MAML.</p>","PeriodicalId":54224,"journal":{"name":"PeerJ Computer Science","volume":"11 ","pages":"e2757"},"PeriodicalIF":3.5,"publicationDate":"2025-05-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12190434/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144499279","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"TASCI: transformers for aspect-based sentiment analysis with contextual intent integration.","authors":"Hassan Nazeer Chaudhry, Farzana Kulsoom, Zahid Ullah Khan, Muhammad Aman, Sajid Ullah Khan, Abdullah Albanyan","doi":"10.7717/peerj-cs.2760","DOIUrl":"10.7717/peerj-cs.2760","url":null,"abstract":"<p><p>In this article, we present a novel Transformer-Based Aspect-Level Sentiment Classification with Intent (TASCI) model, designed to enhance sentiment analysis by integrating aspect-level sentiment classification with intent analysis. Traditional sentiment analysis methods often overlook the nuanced relationship between the intent behind a statement and the sentiment expressed toward specific aspects of an entity. TASCI addresses this gap by first extracting aspects using a self-attention mechanism and then employing a Transformer-based model to infer the speaker's intent from preceding sentences. This dual approach allows TASCI to contextualize sentiment analysis, providing a more accurate reflection of user opinions. We validate TASCI's performance on three benchmark datasets: Restaurant, Laptop, and Twitter, achieving state-of-the-art results with an accuracy of 89.10% and a macro-F1 score of 83.38% on the Restaurant dataset, 84.81% accuracy and 78.63% macro-F1 score on the Laptop dataset, and 79.08% accuracy and 77.27% macro-F1 score on the Twitter dataset. These results demonstrate that incorporating intent analysis significantly enhances the model's ability to capture complex sentiment expressions across different domains, thereby setting a new standard for aspect-level sentiment classification.</p>","PeriodicalId":54224,"journal":{"name":"PeerJ Computer Science","volume":"11 ","pages":"e2760"},"PeriodicalIF":3.5,"publicationDate":"2025-05-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12190667/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144499366","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"HFSA: hybrid feature selection approach to improve medical diagnostic system.","authors":"Asmaa H Rabie, Mohammed Aldawsari, Ahmed I Saleh, M S Saraya, Metwally Rashad","doi":"10.7717/peerj-cs.2764","DOIUrl":"10.7717/peerj-cs.2764","url":null,"abstract":"<p><p>Thanks to the presence of artificial intelligence methods, the diagnosis of patients can be done quickly and accurately. This article introduces a new diagnostic system (DS) that includes three main layers called the rejection layer (RL), selection layer (SL), and diagnostic layer (DL) to accurately diagnose cases suffering from various diseases. In RL, outliers can be removed using the genetic algorithm (GA). At the same time, the best features can be selected by using a new feature selection method called the hybrid feature selection approach (HFSA) in SL. In the next step, the filtered data is passed to the naive Bayes (NB) classifier in DL to give accurate diagnoses. In this work, the main contribution is represented in introducing HFSA as a new selection approach that is composed of two main stages; fast stage (FS) and accurate stage (AS). In FS, chi-square, as a filtering methodology, is applied to quickly select the best features while Hybrid Optimization Algorithm (HOA), as a wrapper methodology, is applied in AS to accurately select features. It is concluded that HFSA is better than other selection methods based on experimental results because HFSA can enable three different classifiers called NB, K-nearest neighbors (KNN), and artificial neural network (ANN) to provide the maximum accuracy, precision, and recall values and the minimum error value. Additionally, experimental results proved that DS, including GA as an outlier rejection method, HFSA as feature selection, and NB as diagnostic mode, outperformed other diagnosis models.</p>","PeriodicalId":54224,"journal":{"name":"PeerJ Computer Science","volume":"11 ","pages":"e2764"},"PeriodicalIF":3.5,"publicationDate":"2025-05-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12190559/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144499203","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}