While artificial intelligence(AI)shows promise in education,its real-world effectiveness in specific settings like blended English as a Foreign Language(EFL)learning needs closer examination.This study investigated th...While artificial intelligence(AI)shows promise in education,its real-world effectiveness in specific settings like blended English as a Foreign Language(EFL)learning needs closer examination.This study investigated the impact of a blended teaching model incorporating AI tools on the Superstar Learning Platform for Chinese university EFL students.Using a mixed-methods approach,60 first-year students were randomized into an experimental group(using the AI-enhanced model)and a control group(traditional instruction)for 16 weeks.Data included test scores,learning behaviors(duration,task completion),satisfaction surveys,and interviews.Results showed the experimental group significantly outperformed the control group on post-tests and achieved larger learning gains.These students also demonstrated greater engagement through longer study times and higher task completion rates,and reported significantly higher satisfaction.Interviews confirmed these findings,with students attributing benefits to the model’s personalized guidance,structured content presentation(knowledge graphs),immediate responses,flexibility,and varied interaction methods.However,limitations were noted,including areas where the platform’s AI could be improved(e.g.,for assessing speaking/translation)and ongoing challenges with student self-discipline.The study concludes that this AI-enhanced blended model significantly improved student performance,engagement,and satisfaction in this EFL context.The findings offer practical insights for educators and platform developers,suggesting AI integration holds significant potential while highlighting areas for refinement.展开更多
Deep learning algorithms have been rapidly incorporated into many different applications due to the increase in computational power and the availability of massive amounts of data.Recently,both deep learning and ensem...Deep learning algorithms have been rapidly incorporated into many different applications due to the increase in computational power and the availability of massive amounts of data.Recently,both deep learning and ensemble learning have been used to recognize underlying structures and patterns from high-level features to make predictions/decisions.With the growth in popularity of deep learning and ensemble learning algorithms,they have received significant attention from both scientists and the industrial community due to their superior ability to learn features from big data.Ensemble deep learning has exhibited significant performance in enhancing learning generalization through the use of multiple deep learning algorithms.Although ensemble deep learning has large quantities of training parameters,which results in time and space overheads,it performs much better than traditional ensemble learning.Ensemble deep learning has been successfully used in several areas,such as bioinformatics,finance,and health care.In this paper,we review and investigate recent ensemble deep learning algorithms and techniques in health care domains,medical imaging,health care data analytics,genomics,diagnosis,disease prevention,and drug discovery.We cover several widely used deep learning algorithms along with their architectures,including deep neural networks(DNNs),convolutional neural networks(CNNs),recurrent neural networks(RNNs),and generative adversarial networks(GANs).Common healthcare tasks,such as medical imaging,electronic health records,and genomics,are also demonstrated.Furthermore,in this review,the challenges inherent in reducing the burden on the healthcare system are discussed and explored.Finally,future directions and opportunities for enhancing healthcare model performance are discussed.展开更多
6G is desired to support more intelligence networks and this trend attaches importance to the self-healing capability if degradation emerges in the cellular networks.As a primary component of selfhealing networks,faul...6G is desired to support more intelligence networks and this trend attaches importance to the self-healing capability if degradation emerges in the cellular networks.As a primary component of selfhealing networks,fault detection is investigated in this paper.Considering the fast response and low timeand-computational consumption,it is the first time that the Online Broad Learning System(OBLS)is applied to identify outages in cellular networks.In addition,the Automatic-constructed Online Broad Learning System(AOBLS)is put forward to rationalize its structure and consequently avoid over-fitting and under-fitting.Furthermore,a multi-layer classification structure is proposed to further improve the classification performance.To face the challenges caused by imbalanced data in fault detection problems,a novel weighting strategy is derived to achieve the Multilayer Automatic-constructed Weighted Online Broad Learning System(MAWOBLS)and ensemble learning with retrained Support Vector Machine(SVM),denoted as EMAWOBLS,for superior treatment with this imbalance issue.Simulation results show that the proposed algorithm has excellent performance in detecting faults with satisfactory time usage.展开更多
In computer vision and artificial intelligence,automatic facial expression-based emotion identification of humans has become a popular research and industry problem.Recent demonstrations and applications in several fi...In computer vision and artificial intelligence,automatic facial expression-based emotion identification of humans has become a popular research and industry problem.Recent demonstrations and applications in several fields,including computer games,smart homes,expression analysis,gesture recognition,surveillance films,depression therapy,patientmonitoring,anxiety,and others,have brought attention to its significant academic and commercial importance.This study emphasizes research that has only employed facial images for face expression recognition(FER),because facial expressions are a basic way that people communicate meaning to each other.The immense achievement of deep learning has resulted in a growing use of its much architecture to enhance efficiency.This review is on machine learning,deep learning,and hybrid methods’use of preprocessing,augmentation techniques,and feature extraction for temporal properties of successive frames of data.The following section gives a brief summary of assessment criteria that are accessible to the public and then compares them with benchmark results the most trustworthy way to assess FER-related research topics statistically.In this review,a brief synopsis of the subject matter may be beneficial for novices in the field of FER as well as seasoned scholars seeking fruitful avenues for further investigation.The information conveys fundamental knowledge and provides a comprehensive understanding of the most recent state-of-the-art research.展开更多
This study investigates the application of Learnable Memory Vision Transformers(LMViT)for detecting metal surface flaws,comparing their performance with traditional CNNs,specifically ResNet18 and ResNet50,as well as o...This study investigates the application of Learnable Memory Vision Transformers(LMViT)for detecting metal surface flaws,comparing their performance with traditional CNNs,specifically ResNet18 and ResNet50,as well as other transformer-based models including Token to Token ViT,ViT withoutmemory,and Parallel ViT.Leveraging awidely-used steel surface defect dataset,the research applies data augmentation and t-distributed stochastic neighbor embedding(t-SNE)to enhance feature extraction and understanding.These techniques mitigated overfitting,stabilized training,and improved generalization capabilities.The LMViT model achieved a test accuracy of 97.22%,significantly outperforming ResNet18(88.89%)and ResNet50(88.90%),aswell as the Token to TokenViT(88.46%),ViT without memory(87.18),and Parallel ViT(91.03%).Furthermore,LMViT exhibited superior training and validation performance,attaining a validation accuracy of 98.2%compared to 91.0%for ResNet 18,96.0%for ResNet50,and 89.12%,87.51%,and 91.21%for Token to Token ViT,ViT without memory,and Parallel ViT,respectively.The findings highlight the LMViT’s ability to capture long-range dependencies in images,an areawhere CNNs struggle due to their reliance on local receptive fields and hierarchical feature extraction.The additional transformer-based models also demonstrate improved performance in capturing complex features over CNNs,with LMViT excelling particularly at detecting subtle and complex defects,which is critical for maintaining product quality and operational efficiency in industrial applications.For instance,the LMViT model successfully identified fine scratches and minor surface irregularities that CNNs often misclassify.This study not only demonstrates LMViT’s potential for real-world defect detection but also underscores the promise of other transformer-based architectures like Token to Token ViT,ViT without memory,and Parallel ViT in industrial scenarios where complex spatial relationships are key.Future research may focus on enhancing LMViT’s computational efficiency for deployment in real-time quality control systems.展开更多
Ensemble learning,a pivotal branch of machine learning,amalgamates multiple base models to enhance the overarching performance of predictive models,capitalising on the diversity and collective wisdom of the ensemble t...Ensemble learning,a pivotal branch of machine learning,amalgamates multiple base models to enhance the overarching performance of predictive models,capitalising on the diversity and collective wisdom of the ensemble to surpass individual models and mitigate overfitting.In this review,a four-layer research framework is established for the research of ensemble learning,which can offer a comprehensive and structured review of ensemble learning from bottom to top.Firstly,this survey commences by introducing fundamental ensemble learning techniques,including bagging,boosting,and stacking,while also exploring the ensemble's diversity.Then,deep ensemble learning and semi-supervised ensemble learning are studied in detail.Furthermore,the utilisation of ensemble learning techniques to navigate challenging datasets,such as imbalanced and highdimensional data,is discussed.The application of ensemble learning techniques across various research domains,including healthcare,transportation,finance,manufacturing,and the Internet,is also examined.The survey concludes by discussing challenges intrinsic to ensemble learning.展开更多
The field of biometric identification has seen significant advancements over the years,with research focusing on enhancing the accuracy and security of these systems.One of the key developments is the integration of d...The field of biometric identification has seen significant advancements over the years,with research focusing on enhancing the accuracy and security of these systems.One of the key developments is the integration of deep learning techniques in biometric systems.However,despite these advancements,certain challenges persist.One of the most significant challenges is scalability over growing complexity.Traditional methods either require maintaining and securing a growing database,introducing serious security challenges,or relying on retraining the entiremodelwhen new data is introduced-a process that can be computationally expensive and complex.This challenge underscores the need for more efficient methods to scale securely.To this end,we introduce a novel approach that addresses these challenges by integrating multimodal biometrics,cancelable biometrics,and incremental learning techniques.This work is among the first attempts to seamlessly incorporate deep cancelable biometrics with dynamic architectural updates,applied incrementally to the deep learning model as new users are enrolled,achieving high performance with minimal catastrophic forgetting.By leveraging a One-Dimensional Convolutional Neural Network(1D-CNN)architecture combined with a hybrid incremental learning approach,our system achieves high recognition accuracy,averaging 98.98% over incrementing datasets,while ensuring user privacy through cancelable templates generated via a pre-trained CNN model and random projection.The approach demonstrates remarkable adaptability,utilizing the least intrusive biometric traits like facial features and fingerprints,ensuring not only robust performance but also long-term serviceability.展开更多
Healthcare networks are transitioning from manual records to electronic health records,but this shift introduces vulnerabilities such as secure communication issues,privacy concerns,and the presence of malicious nodes...Healthcare networks are transitioning from manual records to electronic health records,but this shift introduces vulnerabilities such as secure communication issues,privacy concerns,and the presence of malicious nodes.Existing machine and deep learning-based anomalies detection methods often rely on centralized training,leading to reduced accuracy and potential privacy breaches.Therefore,this study proposes a Blockchain-based-Federated Learning architecture for Malicious Node Detection(BFL-MND)model.It trains models locally within healthcare clusters,sharing only model updates instead of patient data,preserving privacy and improving accuracy.Cloud and edge computing enhance the model’s scalability,while blockchain ensures secure,tamper-proof access to health data.Using the PhysioNet dataset,the proposed model achieves an accuracy of 0.95,F1 score of 0.93,precision of 0.94,and recall of 0.96,outperforming baseline models like random forest(0.88),adaptive boosting(0.90),logistic regression(0.86),perceptron(0.83),and deep neural networks(0.92).展开更多
Glaucoma,a chronic eye disease affecting millions worldwide,poses a substantial threat to eyesight and can result in permanent vision loss if left untreated.Manual identification of glaucoma is a complicated and time-...Glaucoma,a chronic eye disease affecting millions worldwide,poses a substantial threat to eyesight and can result in permanent vision loss if left untreated.Manual identification of glaucoma is a complicated and time-consuming practice requiring specialized expertise and results may be subjective.To address these challenges,this research proposes a computer-aided diagnosis(CAD)approach using Artificial Intelligence(AI)techniques for binary and multiclass classification of glaucoma stages.An ensemble fusion mechanism that combines the outputs of three pre-trained convolutional neural network(ConvNet)models–ResNet-50,VGG-16,and InceptionV3 is utilized in this paper.This fusion technique enhances diagnostic accuracy and robustness by ensemble-averaging the predictions from individual models,leveraging their complementary strengths.The objective of this work is to assess the model’s capability for early-stage glaucoma diagnosis.Classification is performed on a dataset collected from the Harvard Dataverse repository.With the proposed technique,for Normal vs.Advanced glaucoma classification,a validation accuracy of 98.04%and testing accuracy of 98.03%is achieved,with a specificity of 100%which outperforms stateof-the-art methods.For multiclass classification,the suggested ensemble approach achieved a precision and sensitivity of 97%,specificity,and testing accuracy of 98.57%and 96.82%,respectively.The proposed E-GlauNet model has significant potential in assisting ophthalmologists in the screening and fast diagnosis of glaucoma,leading to more reliable,efficient,and timely diagnosis,particularly for early-stage detection and staging of the disease.While the proposed method demonstrates high accuracy and robustness,the study is limited by the evaluation of a single dataset.Future work will focus on external validation across diverse datasets and enhancing interpretability using explainable AI techniques.展开更多
The COVID-19 pandemic,which was declared by the WHO,had created a global health crisis and disrupted people’s daily lives.A large number of people were affected by the COVID-19 pandemic.Therefore,a diagnostic model n...The COVID-19 pandemic,which was declared by the WHO,had created a global health crisis and disrupted people’s daily lives.A large number of people were affected by the COVID-19 pandemic.Therefore,a diagnostic model needs to be generated which can effectively classify the COVID and non-COVID cases.In this work,our aim is to develop a diagnostic model based on deep features using effectiveness of Chest X-ray(CXR)in distinguishing COVID from non-COVID cases.The proposed diagnostic framework utilizes CXR to diagnose COVID-19 and includes Grad-CAM visualizations for a visual interpretation of predicted images.The model’s performance was evaluated using various metrics,including accuracy,precision,recall,F1-score,and Gmean.Several machine learning models,such as random forest,dense neural network,SVM,twin SVM,extreme learning machine,random vector functional link,and kernel ridge regression,were selected to diagnose COVID-19 cases.Transfer learning was used to extract deep features.For feature extraction many CNN-based models such as Inception V3,MobileNet,ResNet50,VGG16 and Xception models are used.It was evident from the experiments that ResNet50 architecture outperformed all other CNN architectures based on AUC.The TWSVM classifier achieved the highest AUC score of 0.98 based on the ResNet50 feature vector.展开更多
Edge Machine Learning(EdgeML)and Tiny Machine Learning(TinyML)are fast-growing fields that bring machine learning to resource-constrained devices,allowing real-time data processing and decision-making at the network’...Edge Machine Learning(EdgeML)and Tiny Machine Learning(TinyML)are fast-growing fields that bring machine learning to resource-constrained devices,allowing real-time data processing and decision-making at the network’s edge.However,the complexity of model conversion techniques,diverse inference mechanisms,and varied learning strategies make designing and deploying these models challenging.Additionally,deploying TinyML models on resource-constrained hardware with specific software frameworks has broadened EdgeML’s applications across various sectors.These factors underscore the necessity for a comprehensive literature review,as current reviews do not systematically encompass the most recent findings on these topics.Consequently,it provides a comprehensive overview of state-of-the-art techniques in model conversion,inference mechanisms,learning strategies within EdgeML,and deploying these models on resource-constrained edge devices using TinyML.It identifies 90 research articles published between 2018 and 2025,categorizing them into two main areas:(1)model conversion,inference,and learning strategies in EdgeML and(2)deploying TinyML models on resource-constrained hardware using specific software frameworks.In the first category,the synthesis of selected research articles compares and critically reviews various model conversion techniques,inference mechanisms,and learning strategies.In the second category,the synthesis identifies and elaborates on major development boards,software frameworks,sensors,and algorithms used in various applications across six major sectors.As a result,this article provides valuable insights for researchers,practitioners,and developers.It assists them in choosing suitable model conversion techniques,inference mechanisms,learning strategies,hardware development boards,software frameworks,sensors,and algorithms tailored to their specific needs and applications across various sectors.展开更多
In the field of optoelectronics,certain types of data may be difficult to accurately annotate,such as high-resolution optoelectronic imaging or imaging in certain special spectral ranges.Weakly supervised learning can...In the field of optoelectronics,certain types of data may be difficult to accurately annotate,such as high-resolution optoelectronic imaging or imaging in certain special spectral ranges.Weakly supervised learning can provide a more reliable approach in these situations.Current popular approaches mainly adopt the classification-based class activation maps(CAM)as initial pseudo labels to solve the task.展开更多
The distributed fiber optic sensing system,known for its high sensitivity and wide-ranging measurement capabilities,has been widely used in monitoring underground gas pipelines.It primarily serves to perceive vibratio...The distributed fiber optic sensing system,known for its high sensitivity and wide-ranging measurement capabilities,has been widely used in monitoring underground gas pipelines.It primarily serves to perceive vibration signals induced by external events and to effectively provide early warnings of potential intrusion activities.Due to the complexity and diversity of external intrusion events,traditional deep learning methods can achieve event recognition with an average accuracy exceeding 90%.However,these methods rely on large-scale datasets,leading to significant time and labor costs during the data collection process.Additionally,traditional methods perform poorly when faced with the scarcity of low-frequency event samples,making it challenging to address these rare occurrences.To address this issue,this paper proposes a small-sample learning model based on triplet learning for intrusion event recognition.The model employs a 6-way 20-shot support set configuration and utilizes the KNN clustering algorithm to assess the model's performance.Experimental results indicate that the model achieves an average accuracy of 91.6%,further validating the superior performance of the triplet learning model in classifying external intrusion events.Compared to traditional methods,this approach not only effectively reduces the dependence on large-scale datasets but also better addresses the classification of low-frequency event samples,demonstrating significant application potential.展开更多
The rapid growth of machine learning(ML)across fields has intensified the challenge of selecting the right algorithm for specific tasks,known as the Algorithm Selection Problem(ASP).Traditional trial-and-error methods...The rapid growth of machine learning(ML)across fields has intensified the challenge of selecting the right algorithm for specific tasks,known as the Algorithm Selection Problem(ASP).Traditional trial-and-error methods have become impractical due to their resource demands.Automated Machine Learning(AutoML)systems automate this process,but often neglect the group structures and sparsity in meta-features,leading to inefficiencies in algorithm recommendations for classification tasks.This paper proposes a meta-learning approach using Multivariate Sparse Group Lasso(MSGL)to address these limitations.Our method models both within-group and across-group sparsity among meta-features to manage high-dimensional data and reduce multicollinearity across eight meta-feature groups.The Fast Iterative Shrinkage-Thresholding Algorithm(FISTA)with adaptive restart efficiently solves the non-smooth optimization problem.Empirical validation on 145 classification datasets with 17 classification algorithms shows that our meta-learning method outperforms four state-of-the-art approaches,achieving 77.18%classification accuracy,86.07%recommendation accuracy and 88.83%normalized discounted cumulative gain.展开更多
The interplay of academic atmosphere,learning motivation,and strategies inherently influences English learning.Effective vocabulary acquisition strategies significantly influence the achievements of English acquisitio...The interplay of academic atmosphere,learning motivation,and strategies inherently influences English learning.Effective vocabulary acquisition strategies significantly influence the achievements of English acquisition.Vocabulary mastery,a cornerstone of middle school English education,raises a critical question:How can vocabulary strategies optimize students’memory,understanding,and vocabulary application?This article elaborates on the importance and characteristics of vocabulary learning in Chinese junior high schools,analyzes definitions and theories of learning strategies,and proposes specific vocabulary approaches tailored to junior high school students in rural-urban fringe areas.展开更多
Emotion recognition plays a crucial role in various fields and is a key task in natural language processing (NLP). The objective is to identify and interpret emotional expressions in text. However, traditional emotion...Emotion recognition plays a crucial role in various fields and is a key task in natural language processing (NLP). The objective is to identify and interpret emotional expressions in text. However, traditional emotion recognition approaches often struggle in few-shot cross-domain scenarios due to their limited capacity to generalize semantic features across different domains. Additionally, these methods face challenges in accurately capturing complex emotional states, particularly those that are subtle or implicit. To overcome these limitations, we introduce a novel approach called Dual-Task Contrastive Meta-Learning (DTCML). This method combines meta-learning and contrastive learning to improve emotion recognition. Meta-learning enhances the model’s ability to generalize to new emotional tasks, while instance contrastive learning further refines the model by distinguishing unique features within each category, enabling it to better differentiate complex emotional expressions. Prototype contrastive learning, in turn, helps the model address the semantic complexity of emotions across different domains, enabling the model to learn fine-grained emotions expression. By leveraging dual tasks, DTCML learns from two domains simultaneously, the model is encouraged to learn more diverse and generalizable emotions features, thereby improving its cross-domain adaptability and robustness, and enhancing its generalization ability. We evaluated the performance of DTCML across four cross-domain settings, and the results show that our method outperforms the best baseline by 5.88%, 12.04%, 8.49%, and 8.40% in terms of accuracy.展开更多
In his speech,Han Zheng said that exchanges and mutual learning among civilisations are important driving forces for the advancement of human civilisation as well as world peace and development.President Xi Jinping po...In his speech,Han Zheng said that exchanges and mutual learning among civilisations are important driving forces for the advancement of human civilisation as well as world peace and development.President Xi Jinping pointed out that civilisations become richer and more colourful with exchanges and mutual learning.As the futures of all countries are closely interconnected,inclusiveness,coexistence,exchanges and mutual learning among different civilisations will contribute to the common progress of humanity and promote global prosperity and development.展开更多
Online interactive learning plays a crucial role in improving online education quality.This grounded theory study examines:(1)what key factors shape EFL learners’online interactive learning,(2)how these factors form ...Online interactive learning plays a crucial role in improving online education quality.This grounded theory study examines:(1)what key factors shape EFL learners’online interactive learning,(2)how these factors form an empirically validated model,and(3)how they interact within this model,through systematic analysis of 9,207 discussion forum posts from a Chinese University MOOC platform.Results demonstrate that learning drive,course structure,teaching competence,interaction behavior,expected outcomes,and online learning context significantly influence EFL online interactive learning.The analysis reveals two key mechanisms:expected outcomes mediate the effects of learning drive(β=0.45),course structure,teaching competence,and interaction behavior(β=0.35)on learning outcomes,while online learning context moderates these relationships(β=0.25).Specifically,learning drive provides intrinsic/extrinsic motivation,whereas course structure,teaching competence,interaction behavior,and expected outcomes collectively enhance interaction quality and sustainability.These findings,derived through rigorous grounded theory methodology involving open,axial,and selective coding of large-scale interaction data,yield three key contributions:(1)a comprehensive theoretical model of EFL online learning dynamics,(2)empirical validation of mediation/moderation mechanisms,and(3)practical strategies for designing scaffolded interaction protocols and adaptive feedback systems.The study establishes that its theoretically saturated model(achieved after analyzing 7,366 posts with 1,841 verification cases)offers educators evidence-based approaches to optimize collaborative interaction in digital EFL environments.展开更多
The isolation of healthcare data among worldwide hospitals and institutes forms barriers for fully realizing the data-hungry artificial intelligence(AI)models promises in renewing medical services.To overcome this,pri...The isolation of healthcare data among worldwide hospitals and institutes forms barriers for fully realizing the data-hungry artificial intelligence(AI)models promises in renewing medical services.To overcome this,privacy-preserving distributed learning frameworks,represented by swarm learning and federated learning,have been investigated recently with the sensitive healthcare data retaining in its local premises.However,existing frameworks use a one-size-fits-all mode that tunes one model for all healthcare situations,which could hardly fit the usually diverse disease prediction in practice.This work introduces the idea of ensemble learning into privacypreserving distributed learning and presents the En-split framework,where the predictions of multiple expert models with specialized diagnostic capabilities are jointly explored.Considering the exacerbation of communication and computation burdens with multiple models during learning,model split is used to partition targeted models into two parts,with hospitals focusing on building the feature-enriched shallow layers.Meanwhile,dedicated noises are implemented to the edge layers for differential privacy protection.Experiments on two public datasets demonstrate En-split’s superior performance on accuracy and efficiency,compared with existing distributed learning frameworks.展开更多
基金supported by the 2024“Special Research Project on the Application of Artificial Intelligence in Empowering Teaching and Education”of Zhejiang Province Association of Higher Education(KT2024165).
文摘While artificial intelligence(AI)shows promise in education,its real-world effectiveness in specific settings like blended English as a Foreign Language(EFL)learning needs closer examination.This study investigated the impact of a blended teaching model incorporating AI tools on the Superstar Learning Platform for Chinese university EFL students.Using a mixed-methods approach,60 first-year students were randomized into an experimental group(using the AI-enhanced model)and a control group(traditional instruction)for 16 weeks.Data included test scores,learning behaviors(duration,task completion),satisfaction surveys,and interviews.Results showed the experimental group significantly outperformed the control group on post-tests and achieved larger learning gains.These students also demonstrated greater engagement through longer study times and higher task completion rates,and reported significantly higher satisfaction.Interviews confirmed these findings,with students attributing benefits to the model’s personalized guidance,structured content presentation(knowledge graphs),immediate responses,flexibility,and varied interaction methods.However,limitations were noted,including areas where the platform’s AI could be improved(e.g.,for assessing speaking/translation)and ongoing challenges with student self-discipline.The study concludes that this AI-enhanced blended model significantly improved student performance,engagement,and satisfaction in this EFL context.The findings offer practical insights for educators and platform developers,suggesting AI integration holds significant potential while highlighting areas for refinement.
基金funded by Taif University,Saudi Arabia,project No.(TU-DSPP-2024-263).
文摘Deep learning algorithms have been rapidly incorporated into many different applications due to the increase in computational power and the availability of massive amounts of data.Recently,both deep learning and ensemble learning have been used to recognize underlying structures and patterns from high-level features to make predictions/decisions.With the growth in popularity of deep learning and ensemble learning algorithms,they have received significant attention from both scientists and the industrial community due to their superior ability to learn features from big data.Ensemble deep learning has exhibited significant performance in enhancing learning generalization through the use of multiple deep learning algorithms.Although ensemble deep learning has large quantities of training parameters,which results in time and space overheads,it performs much better than traditional ensemble learning.Ensemble deep learning has been successfully used in several areas,such as bioinformatics,finance,and health care.In this paper,we review and investigate recent ensemble deep learning algorithms and techniques in health care domains,medical imaging,health care data analytics,genomics,diagnosis,disease prevention,and drug discovery.We cover several widely used deep learning algorithms along with their architectures,including deep neural networks(DNNs),convolutional neural networks(CNNs),recurrent neural networks(RNNs),and generative adversarial networks(GANs).Common healthcare tasks,such as medical imaging,electronic health records,and genomics,are also demonstrated.Furthermore,in this review,the challenges inherent in reducing the burden on the healthcare system are discussed and explored.Finally,future directions and opportunities for enhancing healthcare model performance are discussed.
基金supported in part by the National Key Research and Development Project under Grant 2020YFB1806805partially funded through a grant from Qualcomm。
文摘6G is desired to support more intelligence networks and this trend attaches importance to the self-healing capability if degradation emerges in the cellular networks.As a primary component of selfhealing networks,fault detection is investigated in this paper.Considering the fast response and low timeand-computational consumption,it is the first time that the Online Broad Learning System(OBLS)is applied to identify outages in cellular networks.In addition,the Automatic-constructed Online Broad Learning System(AOBLS)is put forward to rationalize its structure and consequently avoid over-fitting and under-fitting.Furthermore,a multi-layer classification structure is proposed to further improve the classification performance.To face the challenges caused by imbalanced data in fault detection problems,a novel weighting strategy is derived to achieve the Multilayer Automatic-constructed Weighted Online Broad Learning System(MAWOBLS)and ensemble learning with retrained Support Vector Machine(SVM),denoted as EMAWOBLS,for superior treatment with this imbalance issue.Simulation results show that the proposed algorithm has excellent performance in detecting faults with satisfactory time usage.
文摘In computer vision and artificial intelligence,automatic facial expression-based emotion identification of humans has become a popular research and industry problem.Recent demonstrations and applications in several fields,including computer games,smart homes,expression analysis,gesture recognition,surveillance films,depression therapy,patientmonitoring,anxiety,and others,have brought attention to its significant academic and commercial importance.This study emphasizes research that has only employed facial images for face expression recognition(FER),because facial expressions are a basic way that people communicate meaning to each other.The immense achievement of deep learning has resulted in a growing use of its much architecture to enhance efficiency.This review is on machine learning,deep learning,and hybrid methods’use of preprocessing,augmentation techniques,and feature extraction for temporal properties of successive frames of data.The following section gives a brief summary of assessment criteria that are accessible to the public and then compares them with benchmark results the most trustworthy way to assess FER-related research topics statistically.In this review,a brief synopsis of the subject matter may be beneficial for novices in the field of FER as well as seasoned scholars seeking fruitful avenues for further investigation.The information conveys fundamental knowledge and provides a comprehensive understanding of the most recent state-of-the-art research.
基金funded by Woosong University Academic Research 2024.
文摘This study investigates the application of Learnable Memory Vision Transformers(LMViT)for detecting metal surface flaws,comparing their performance with traditional CNNs,specifically ResNet18 and ResNet50,as well as other transformer-based models including Token to Token ViT,ViT withoutmemory,and Parallel ViT.Leveraging awidely-used steel surface defect dataset,the research applies data augmentation and t-distributed stochastic neighbor embedding(t-SNE)to enhance feature extraction and understanding.These techniques mitigated overfitting,stabilized training,and improved generalization capabilities.The LMViT model achieved a test accuracy of 97.22%,significantly outperforming ResNet18(88.89%)and ResNet50(88.90%),aswell as the Token to TokenViT(88.46%),ViT without memory(87.18),and Parallel ViT(91.03%).Furthermore,LMViT exhibited superior training and validation performance,attaining a validation accuracy of 98.2%compared to 91.0%for ResNet 18,96.0%for ResNet50,and 89.12%,87.51%,and 91.21%for Token to Token ViT,ViT without memory,and Parallel ViT,respectively.The findings highlight the LMViT’s ability to capture long-range dependencies in images,an areawhere CNNs struggle due to their reliance on local receptive fields and hierarchical feature extraction.The additional transformer-based models also demonstrate improved performance in capturing complex features over CNNs,with LMViT excelling particularly at detecting subtle and complex defects,which is critical for maintaining product quality and operational efficiency in industrial applications.For instance,the LMViT model successfully identified fine scratches and minor surface irregularities that CNNs often misclassify.This study not only demonstrates LMViT’s potential for real-world defect detection but also underscores the promise of other transformer-based architectures like Token to Token ViT,ViT without memory,and Parallel ViT in industrial scenarios where complex spatial relationships are key.Future research may focus on enhancing LMViT’s computational efficiency for deployment in real-time quality control systems.
基金supported in part by National Natural Science Foundation of China No.92467109,U21A20478National Key R&D Program of China 2023YFA1011601the Major Key Project of PCL(Grant PCL2024A05).
文摘Ensemble learning,a pivotal branch of machine learning,amalgamates multiple base models to enhance the overarching performance of predictive models,capitalising on the diversity and collective wisdom of the ensemble to surpass individual models and mitigate overfitting.In this review,a four-layer research framework is established for the research of ensemble learning,which can offer a comprehensive and structured review of ensemble learning from bottom to top.Firstly,this survey commences by introducing fundamental ensemble learning techniques,including bagging,boosting,and stacking,while also exploring the ensemble's diversity.Then,deep ensemble learning and semi-supervised ensemble learning are studied in detail.Furthermore,the utilisation of ensemble learning techniques to navigate challenging datasets,such as imbalanced and highdimensional data,is discussed.The application of ensemble learning techniques across various research domains,including healthcare,transportation,finance,manufacturing,and the Internet,is also examined.The survey concludes by discussing challenges intrinsic to ensemble learning.
基金the Deputyship for Research&Innovation,Ministry of Education in Saudi Arabia for funding this research work through project number RI-44-0833.
文摘The field of biometric identification has seen significant advancements over the years,with research focusing on enhancing the accuracy and security of these systems.One of the key developments is the integration of deep learning techniques in biometric systems.However,despite these advancements,certain challenges persist.One of the most significant challenges is scalability over growing complexity.Traditional methods either require maintaining and securing a growing database,introducing serious security challenges,or relying on retraining the entiremodelwhen new data is introduced-a process that can be computationally expensive and complex.This challenge underscores the need for more efficient methods to scale securely.To this end,we introduce a novel approach that addresses these challenges by integrating multimodal biometrics,cancelable biometrics,and incremental learning techniques.This work is among the first attempts to seamlessly incorporate deep cancelable biometrics with dynamic architectural updates,applied incrementally to the deep learning model as new users are enrolled,achieving high performance with minimal catastrophic forgetting.By leveraging a One-Dimensional Convolutional Neural Network(1D-CNN)architecture combined with a hybrid incremental learning approach,our system achieves high recognition accuracy,averaging 98.98% over incrementing datasets,while ensuring user privacy through cancelable templates generated via a pre-trained CNN model and random projection.The approach demonstrates remarkable adaptability,utilizing the least intrusive biometric traits like facial features and fingerprints,ensuring not only robust performance but also long-term serviceability.
基金funded by the Northern Border University,Arar,KSA,under the project number“NBU-FFR-2025-3555-07”.
文摘Healthcare networks are transitioning from manual records to electronic health records,but this shift introduces vulnerabilities such as secure communication issues,privacy concerns,and the presence of malicious nodes.Existing machine and deep learning-based anomalies detection methods often rely on centralized training,leading to reduced accuracy and potential privacy breaches.Therefore,this study proposes a Blockchain-based-Federated Learning architecture for Malicious Node Detection(BFL-MND)model.It trains models locally within healthcare clusters,sharing only model updates instead of patient data,preserving privacy and improving accuracy.Cloud and edge computing enhance the model’s scalability,while blockchain ensures secure,tamper-proof access to health data.Using the PhysioNet dataset,the proposed model achieves an accuracy of 0.95,F1 score of 0.93,precision of 0.94,and recall of 0.96,outperforming baseline models like random forest(0.88),adaptive boosting(0.90),logistic regression(0.86),perceptron(0.83),and deep neural networks(0.92).
基金funded by Department of Robotics and Mechatronics Engineering,Kennesaw State University,Marietta,GA 30060,USA.
文摘Glaucoma,a chronic eye disease affecting millions worldwide,poses a substantial threat to eyesight and can result in permanent vision loss if left untreated.Manual identification of glaucoma is a complicated and time-consuming practice requiring specialized expertise and results may be subjective.To address these challenges,this research proposes a computer-aided diagnosis(CAD)approach using Artificial Intelligence(AI)techniques for binary and multiclass classification of glaucoma stages.An ensemble fusion mechanism that combines the outputs of three pre-trained convolutional neural network(ConvNet)models–ResNet-50,VGG-16,and InceptionV3 is utilized in this paper.This fusion technique enhances diagnostic accuracy and robustness by ensemble-averaging the predictions from individual models,leveraging their complementary strengths.The objective of this work is to assess the model’s capability for early-stage glaucoma diagnosis.Classification is performed on a dataset collected from the Harvard Dataverse repository.With the proposed technique,for Normal vs.Advanced glaucoma classification,a validation accuracy of 98.04%and testing accuracy of 98.03%is achieved,with a specificity of 100%which outperforms stateof-the-art methods.For multiclass classification,the suggested ensemble approach achieved a precision and sensitivity of 97%,specificity,and testing accuracy of 98.57%and 96.82%,respectively.The proposed E-GlauNet model has significant potential in assisting ophthalmologists in the screening and fast diagnosis of glaucoma,leading to more reliable,efficient,and timely diagnosis,particularly for early-stage detection and staging of the disease.While the proposed method demonstrates high accuracy and robustness,the study is limited by the evaluation of a single dataset.Future work will focus on external validation across diverse datasets and enhancing interpretability using explainable AI techniques.
文摘The COVID-19 pandemic,which was declared by the WHO,had created a global health crisis and disrupted people’s daily lives.A large number of people were affected by the COVID-19 pandemic.Therefore,a diagnostic model needs to be generated which can effectively classify the COVID and non-COVID cases.In this work,our aim is to develop a diagnostic model based on deep features using effectiveness of Chest X-ray(CXR)in distinguishing COVID from non-COVID cases.The proposed diagnostic framework utilizes CXR to diagnose COVID-19 and includes Grad-CAM visualizations for a visual interpretation of predicted images.The model’s performance was evaluated using various metrics,including accuracy,precision,recall,F1-score,and Gmean.Several machine learning models,such as random forest,dense neural network,SVM,twin SVM,extreme learning machine,random vector functional link,and kernel ridge regression,were selected to diagnose COVID-19 cases.Transfer learning was used to extract deep features.For feature extraction many CNN-based models such as Inception V3,MobileNet,ResNet50,VGG16 and Xception models are used.It was evident from the experiments that ResNet50 architecture outperformed all other CNN architectures based on AUC.The TWSVM classifier achieved the highest AUC score of 0.98 based on the ResNet50 feature vector.
文摘Edge Machine Learning(EdgeML)and Tiny Machine Learning(TinyML)are fast-growing fields that bring machine learning to resource-constrained devices,allowing real-time data processing and decision-making at the network’s edge.However,the complexity of model conversion techniques,diverse inference mechanisms,and varied learning strategies make designing and deploying these models challenging.Additionally,deploying TinyML models on resource-constrained hardware with specific software frameworks has broadened EdgeML’s applications across various sectors.These factors underscore the necessity for a comprehensive literature review,as current reviews do not systematically encompass the most recent findings on these topics.Consequently,it provides a comprehensive overview of state-of-the-art techniques in model conversion,inference mechanisms,learning strategies within EdgeML,and deploying these models on resource-constrained edge devices using TinyML.It identifies 90 research articles published between 2018 and 2025,categorizing them into two main areas:(1)model conversion,inference,and learning strategies in EdgeML and(2)deploying TinyML models on resource-constrained hardware using specific software frameworks.In the first category,the synthesis of selected research articles compares and critically reviews various model conversion techniques,inference mechanisms,and learning strategies.In the second category,the synthesis identifies and elaborates on major development boards,software frameworks,sensors,and algorithms used in various applications across six major sectors.As a result,this article provides valuable insights for researchers,practitioners,and developers.It assists them in choosing suitable model conversion techniques,inference mechanisms,learning strategies,hardware development boards,software frameworks,sensors,and algorithms tailored to their specific needs and applications across various sectors.
文摘In the field of optoelectronics,certain types of data may be difficult to accurately annotate,such as high-resolution optoelectronic imaging or imaging in certain special spectral ranges.Weakly supervised learning can provide a more reliable approach in these situations.Current popular approaches mainly adopt the classification-based class activation maps(CAM)as initial pseudo labels to solve the task.
基金Supported by the Scientific Research and Technology Development Project of Petrochina Southwest Oil and Gas Field Company(20230307-02)。
文摘The distributed fiber optic sensing system,known for its high sensitivity and wide-ranging measurement capabilities,has been widely used in monitoring underground gas pipelines.It primarily serves to perceive vibration signals induced by external events and to effectively provide early warnings of potential intrusion activities.Due to the complexity and diversity of external intrusion events,traditional deep learning methods can achieve event recognition with an average accuracy exceeding 90%.However,these methods rely on large-scale datasets,leading to significant time and labor costs during the data collection process.Additionally,traditional methods perform poorly when faced with the scarcity of low-frequency event samples,making it challenging to address these rare occurrences.To address this issue,this paper proposes a small-sample learning model based on triplet learning for intrusion event recognition.The model employs a 6-way 20-shot support set configuration and utilizes the KNN clustering algorithm to assess the model's performance.Experimental results indicate that the model achieves an average accuracy of 91.6%,further validating the superior performance of the triplet learning model in classifying external intrusion events.Compared to traditional methods,this approach not only effectively reduces the dependence on large-scale datasets but also better addresses the classification of low-frequency event samples,demonstrating significant application potential.
文摘The rapid growth of machine learning(ML)across fields has intensified the challenge of selecting the right algorithm for specific tasks,known as the Algorithm Selection Problem(ASP).Traditional trial-and-error methods have become impractical due to their resource demands.Automated Machine Learning(AutoML)systems automate this process,but often neglect the group structures and sparsity in meta-features,leading to inefficiencies in algorithm recommendations for classification tasks.This paper proposes a meta-learning approach using Multivariate Sparse Group Lasso(MSGL)to address these limitations.Our method models both within-group and across-group sparsity among meta-features to manage high-dimensional data and reduce multicollinearity across eight meta-feature groups.The Fast Iterative Shrinkage-Thresholding Algorithm(FISTA)with adaptive restart efficiently solves the non-smooth optimization problem.Empirical validation on 145 classification datasets with 17 classification algorithms shows that our meta-learning method outperforms four state-of-the-art approaches,achieving 77.18%classification accuracy,86.07%recommendation accuracy and 88.83%normalized discounted cumulative gain.
文摘The interplay of academic atmosphere,learning motivation,and strategies inherently influences English learning.Effective vocabulary acquisition strategies significantly influence the achievements of English acquisition.Vocabulary mastery,a cornerstone of middle school English education,raises a critical question:How can vocabulary strategies optimize students’memory,understanding,and vocabulary application?This article elaborates on the importance and characteristics of vocabulary learning in Chinese junior high schools,analyzes definitions and theories of learning strategies,and proposes specific vocabulary approaches tailored to junior high school students in rural-urban fringe areas.
基金supported by the ScientificResearch and Innovation Team Program of Sichuan University of Science and Technology(No.SUSE652A006)Sichuan Key Provincial Research Base of Intelligent Tourism(ZHYJ22-03)In addition,it is also listed as a project of Sichuan Provincial Science and Technology Programme(2022YFG0028).
文摘Emotion recognition plays a crucial role in various fields and is a key task in natural language processing (NLP). The objective is to identify and interpret emotional expressions in text. However, traditional emotion recognition approaches often struggle in few-shot cross-domain scenarios due to their limited capacity to generalize semantic features across different domains. Additionally, these methods face challenges in accurately capturing complex emotional states, particularly those that are subtle or implicit. To overcome these limitations, we introduce a novel approach called Dual-Task Contrastive Meta-Learning (DTCML). This method combines meta-learning and contrastive learning to improve emotion recognition. Meta-learning enhances the model’s ability to generalize to new emotional tasks, while instance contrastive learning further refines the model by distinguishing unique features within each category, enabling it to better differentiate complex emotional expressions. Prototype contrastive learning, in turn, helps the model address the semantic complexity of emotions across different domains, enabling the model to learn fine-grained emotions expression. By leveraging dual tasks, DTCML learns from two domains simultaneously, the model is encouraged to learn more diverse and generalizable emotions features, thereby improving its cross-domain adaptability and robustness, and enhancing its generalization ability. We evaluated the performance of DTCML across four cross-domain settings, and the results show that our method outperforms the best baseline by 5.88%, 12.04%, 8.49%, and 8.40% in terms of accuracy.
文摘In his speech,Han Zheng said that exchanges and mutual learning among civilisations are important driving forces for the advancement of human civilisation as well as world peace and development.President Xi Jinping pointed out that civilisations become richer and more colourful with exchanges and mutual learning.As the futures of all countries are closely interconnected,inclusiveness,coexistence,exchanges and mutual learning among different civilisations will contribute to the common progress of humanity and promote global prosperity and development.
文摘Online interactive learning plays a crucial role in improving online education quality.This grounded theory study examines:(1)what key factors shape EFL learners’online interactive learning,(2)how these factors form an empirically validated model,and(3)how they interact within this model,through systematic analysis of 9,207 discussion forum posts from a Chinese University MOOC platform.Results demonstrate that learning drive,course structure,teaching competence,interaction behavior,expected outcomes,and online learning context significantly influence EFL online interactive learning.The analysis reveals two key mechanisms:expected outcomes mediate the effects of learning drive(β=0.45),course structure,teaching competence,and interaction behavior(β=0.35)on learning outcomes,while online learning context moderates these relationships(β=0.25).Specifically,learning drive provides intrinsic/extrinsic motivation,whereas course structure,teaching competence,interaction behavior,and expected outcomes collectively enhance interaction quality and sustainability.These findings,derived through rigorous grounded theory methodology involving open,axial,and selective coding of large-scale interaction data,yield three key contributions:(1)a comprehensive theoretical model of EFL online learning dynamics,(2)empirical validation of mediation/moderation mechanisms,and(3)practical strategies for designing scaffolded interaction protocols and adaptive feedback systems.The study establishes that its theoretically saturated model(achieved after analyzing 7,366 posts with 1,841 verification cases)offers educators evidence-based approaches to optimize collaborative interaction in digital EFL environments.
基金supported by the National Natural Science Foundation of China(62172155)the NationalKey Research andDevelopment Programof China(2022YFF1203001)+2 种基金the Science and Technology Innovation Program of Hunan Province(Nos.2022RC3061,2023RC3027)the Graduate Research Innovation Project of Hunan Province(XJCX2023157)NUDT Scientific Project“Research on Privacy-Enhancing Computing Technologies for Activity Trajectory Data”.
文摘The isolation of healthcare data among worldwide hospitals and institutes forms barriers for fully realizing the data-hungry artificial intelligence(AI)models promises in renewing medical services.To overcome this,privacy-preserving distributed learning frameworks,represented by swarm learning and federated learning,have been investigated recently with the sensitive healthcare data retaining in its local premises.However,existing frameworks use a one-size-fits-all mode that tunes one model for all healthcare situations,which could hardly fit the usually diverse disease prediction in practice.This work introduces the idea of ensemble learning into privacypreserving distributed learning and presents the En-split framework,where the predictions of multiple expert models with specialized diagnostic capabilities are jointly explored.Considering the exacerbation of communication and computation burdens with multiple models during learning,model split is used to partition targeted models into two parts,with hospitals focusing on building the feature-enriched shallow layers.Meanwhile,dedicated noises are implemented to the edge layers for differential privacy protection.Experiments on two public datasets demonstrate En-split’s superior performance on accuracy and efficiency,compared with existing distributed learning frameworks.
